add package @google/gemini-cli-devtools to devDependencies

Co-authored-by: gemini-cli-robot <224641728+gemini-cli-robot@users.noreply.github.com>
Co-authored-by: Sam Roberts <158088236+g-samroberts@users.noreply.github.com>

.gemini/commands/strict-development-rules.md

@@ -1,64 +1,142 @@
 # Gemini CLI Strict Development Rules
 
-These rules apply strictly to all code modifications and additions within the Gemini CLI project.
+These rules apply strictly to all code modifications and additions within the
+Gemini CLI project.
 
 ## Testing Guidelines
 
-*   **Async/Await**: Always use `waitFor` from `packages/cli/src/test-utils/async.ts` instead of `vi.waitFor` for all `waitFor` calls within `packages/cli`. NEVER use fixed waits (e.g., `await delay(100)`). Always use `waitFor` with a predicate to ensure tests are stable and fast. Using the wrong `waitFor` can result in flaky tests and `act` warnings.
-*   **React Testing**: Use `act` to wrap all blocks in tests that change component state. Use `render` or `renderWithProviders` from `packages/cli/src/test-utils/render.tsx` instead of `render` from `ink-testing-library` directly. This prevents spurious `act` warnings. If test cases specify providers directly, consider whether the existing `renderWithProviders` should be modified.
-*   **Snapshots**: Use `toMatchSnapshot` to verify that rendering works as expected rather than matching against the raw content of the output. When modifying snapshots, verify the changes are intentional and do not hide underlying bugs.
-*   **Parameterized Tests**: Use parameterized tests where it reduces duplicated lines. Give the parameters explicit types to ensure the tests are type-safe.
-*   **Mocks Management**:
-    *   Mock critical dependencies (`fs`, `os`, `child_process`) ONLY at the top of the file. Ideally, avoid mocking these dependencies altogether.
-    *   Reuse existing mocks and fakes rather than creating new ones.
-    *   Avoid mocking the file system whenever possible. If using the real file system is too difficult, consider writing an integration test instead.
-    *   Always call `vi.restoreAllMocks()` in `afterEach` to prevent test pollution.
-    *   Use `vi.useFakeTimers()` for tests involving time-based logic to avoid flakiness.
-*   **Typing in Tests**: Avoid using `any` in tests; prefer proper types or `unknown` with narrowing.
+- **Async/Await**: Always use `waitFor` from
+  `packages/cli/src/test-utils/async.ts` instead of `vi.waitFor` for all
+  `waitFor` calls within `packages/cli`. NEVER use fixed waits (e.g.,
+  `await delay(100)`). Always use `waitFor` with a predicate to ensure tests are
+  stable and fast. Using the wrong `waitFor` can result in flaky tests and `act`
+  warnings.
+- **React Testing**: Use `act` to wrap all blocks in tests that change component
+  state. Use `render` or `renderWithProviders` from
+  `packages/cli/src/test-utils/render.tsx` instead of `render` from
+  `ink-testing-library` directly. This prevents spurious `act` warnings. If test
+  cases specify providers directly, consider whether the existing
+  `renderWithProviders` should be modified.
+- **Snapshots**: Use `toMatchSnapshot` to verify that rendering works as
+  expected rather than matching against the raw content of the output. When
+  modifying snapshots, verify the changes are intentional and do not hide
+  underlying bugs.
+- **Parameterized Tests**: Use parameterized tests where it reduces duplicated
+  lines. Give the parameters explicit types to ensure the tests are type-safe.
+- **Mocks Management**:
+  - Mock critical dependencies (`fs`, `os`, `child_process`) ONLY at the top of
+    the file. Ideally, avoid mocking these dependencies altogether.
+  - Reuse existing mocks and fakes rather than creating new ones.
+  - Avoid mocking the file system whenever possible. If using the real file
+    system is too difficult, consider writing an integration test instead.
+  - Always call `vi.restoreAllMocks()` in `afterEach` to prevent test pollution.
+  - Use `vi.useFakeTimers()` for tests involving time-based logic to avoid
+    flakiness.
+- **Typing in Tests**: Avoid using `any` in tests; prefer proper types or
+  `unknown` with narrowing.
 
 ## React Guidelines (`packages/cli`)
 
-*   **`setState` and Side Effects**: NEVER trigger side effects from within the body of a `setState` callback. Use a reducer or `useRef` if necessary. These cases have historically introduced multiple bugs; typically, they should be resolved using a reducer.
-*   **Rendering**: Do not introduce infinite rendering loops. Avoid synchronous file I/O in React components as it will hang the UI. Do not implement new logic for custom string measurement or string truncation. Use Ink layout instead, leveraging `ResizeObserver` as needed.
-*   **Keyboard Handling**: Keyboard handling MUST go through `useKeyPress.ts` from the Gemini CLI package rather than the standard ink library. This library supports reporting multiple keyboard events sequentially in the same React frame (critical for slow terminals). Handling this correctly often requires reducers to ensure multiple state updates are handled gracefully without overriding values. Refer to `text-buffer.ts` for a canonical example.
-*   **Logging**: Do not leave `console.log`, `console.warn`, or `console.error` in the code.
-*   **State & Effects**: Ensure state initialization is explicit (e.g., use `undefined` rather than `true` as a default if the state is truly unknown). Carefully manage `useEffect` dependencies. Prefer a reducer whenever practical. NEVER disable `react-hooks/exhaustive-deps`; fix the code to correctly declare dependencies instead.
-*   **Context & Props**: Avoid excessive property drilling. Leverage existing providers, extend them, or propose a new one if necessary. Only use providers for properties that are consistent across the entire application.
-*   **Code Structure**: Avoid complex `if` statements where `switch` statements could be used. Keep `AppContainer` minimal; refactor complex logic into React hooks. Evaluate whether business logic should be added to `hookSystem.ts` or integrated into `packages/core` rather than `packages/cli`.
+- **`setState` and Side Effects**: NEVER trigger side effects from within the
+  body of a `setState` callback. Use a reducer or `useRef` if necessary. These
+  cases have historically introduced multiple bugs; typically, they should be
+  resolved using a reducer.
+- **Rendering**: Do not introduce infinite rendering loops. Avoid synchronous
+  file I/O in React components as it will hang the UI. Do not implement new
+  logic for custom string measurement or string truncation. Use Ink layout
+  instead, leveraging `ResizeObserver` as needed.
+- **Keyboard Handling**: Keyboard handling MUST go through `useKeyPress.ts` from
+  the Gemini CLI package rather than the standard ink library. This library
+  supports reporting multiple keyboard events sequentially in the same React
+  frame (critical for slow terminals). Handling this correctly often requires
+  reducers to ensure multiple state updates are handled gracefully without
+  overriding values. Refer to `text-buffer.ts` for a canonical example.
+- **Logging**: Do not leave `console.log`, `console.warn`, or `console.error` in
+  the code.
+- **State & Effects**: Ensure state initialization is explicit (e.g., use
+  `undefined` rather than `true` as a default if the state is truly unknown).
+  Carefully manage `useEffect` dependencies. Prefer a reducer whenever
+  practical. NEVER disable `react-hooks/exhaustive-deps`; fix the code to
+  correctly declare dependencies instead.
+- **Context & Props**: Avoid excessive property drilling. Leverage existing
+  providers, extend them, or propose a new one if necessary. Only use providers
+  for properties that are consistent across the entire application.
+- **Code Structure**: Avoid complex `if` statements where `switch` statements
+  could be used. Keep `AppContainer` minimal; refactor complex logic into React
+  hooks. Evaluate whether business logic should be added to `hookSystem.ts` or
+  integrated into `packages/core` rather than `packages/cli`.
 
 ## Core Guidelines (`packages/core`)
 
-*   **Services**: Implement services as classes with clear lifecycle management (e.g., `initialize()` methods). Services should be stateless where possible, or use the centralized `Storage` service for persistence.
-*   **Cross-Service Communication**: Prefer using the `coreEvents` bus (from `packages/core/src/utils/events.ts`) for asynchronous communication between services or to notify the UI of state changes. Avoid tight coupling between services.
-*   **Utilities**: Use `debugLogger` from `packages/core/src/utils/debugLogger.ts` for internal logging instead of `console`. Ensure all shell operations use `spawnAsync` from `packages/core/src/utils/shell-utils.ts` for consistent error handling and promise management. Handle filesystem errors gracefully using `isNodeError` from `packages/core/src/utils/errors.ts`.
-*   **Exports & Tooling**: Add new tools to `packages/core/src/tools/` and register them in `packages/core/src/tools/tool-registry.ts`. Export all new public services, utilities, and types from `packages/core/src/index.ts`.
+- **Services**: Implement services as classes with clear lifecycle management
+  (e.g., `initialize()` methods). Services should be stateless where possible,
+  or use the centralized `Storage` service for persistence.
+- **Cross-Service Communication**: Prefer using the `coreEvents` bus (from
+  `packages/core/src/utils/events.ts`) for asynchronous communication between
+  services or to notify the UI of state changes. Avoid tight coupling between
+  services.
+- **Utilities**: Use `debugLogger` from `packages/core/src/utils/debugLogger.ts`
+  for internal logging instead of `console`. Ensure all shell operations use
+  `spawnAsync` from `packages/core/src/utils/shell-utils.ts` for consistent
+  error handling and promise management. Handle filesystem errors gracefully
+  using `isNodeError` from `packages/core/src/utils/errors.ts`.
+- **Exports & Tooling**: Add new tools to `packages/core/src/tools/` and
+  register them in `packages/core/src/tools/tool-registry.ts`. Export all new
+  public services, utilities, and types from `packages/core/src/index.ts`.
 
 ## Architectural Audit (Package Boundaries)
 
-*   **Logic Placement**: Non-UI logic (e.g., model orchestration, tool implementation, git/filesystem operations) MUST reside in `packages/core`. `packages/cli` should ONLY contain UI/Ink components, command-line argument parsing, and user interaction logic.
-*   **Environment Isolation**: Core logic must not assume a TUI environment. Use the `ConfirmationBus` or `Output` abstractions for communicating with the user from Core.
-*   **Decoupling**: Actively look for opportunities to decouple services using `coreEvents`. If a service imports another just to notify it of a change, use an event instead.
+- **Logic Placement**: Non-UI logic (e.g., model orchestration, tool
+  implementation, git/filesystem operations) MUST reside in `packages/core`.
+  `packages/cli` should ONLY contain UI/Ink components, command-line argument
+  parsing, and user interaction logic.
+- **Environment Isolation**: Core logic must not assume a TUI environment. Use
+  the `ConfirmationBus` or `Output` abstractions for communicating with the user
+  from Core.
+- **Decoupling**: Actively look for opportunities to decouple services using
+  `coreEvents`. If a service imports another just to notify it of a change, use
+  an event instead.
 
 ## General Gemini CLI Design Principles
 
-*   **Settings**: Use settings for user-configurable options rather than adding new command line arguments. Add new settings to `packages/cli/src/config/settingsSchema.ts`. If a setting has `showInDialog: true`, it MUST be documented in `docs/get-started/configuration.md`. Ensure `requiresRestart` is correctly set.
-*   **Logging**: Use `debugLogger` for rethrown errors to avoid duplicate logging.
-*   **Keyboard Shortcuts**: Define all new keyboard shortcuts in `packages/cli/src/config/keyBindings.ts` and document them in `docs/cli/keyboard-shortcuts.md`. Be careful of keybindings that require the `Meta` key, as only certain meta key shortcuts are supported on Mac. Avoid function keys and shortcuts commonly bound in VSCode.
+- **Settings**: Use settings for user-configurable options rather than adding
+  new command line arguments. Add new settings to
+  `packages/cli/src/config/settingsSchema.ts`. If a setting has
+  `showInDialog: true`, it MUST be documented in
+  `docs/get-started/configuration.md`. Ensure `requiresRestart` is correctly
+  set.
+- **Logging**: Use `debugLogger` for rethrown errors to avoid duplicate logging.
+- **Keyboard Shortcuts**: Define all new keyboard shortcuts in
+  `packages/cli/src/config/keyBindings.ts` and document them in
+  `docs/cli/keyboard-shortcuts.md`. Be careful of keybindings that require the
+  `Meta` key, as only certain meta key shortcuts are supported on Mac. Avoid
+  function keys and shortcuts commonly bound in VSCode.
 
 ## TypeScript Best Practices
 
-*   Use `checkExhaustive` in the `default` clause of `switch` statements to ensure all cases are handled.
-*   Avoid using the non-null assertion operator (`!`) unless absolutely necessary.
-*   **STRICT TYPING**: Strictly forbid `any` and `unknown` in both CLI and Core packages. `unknown` is only allowed if it is immediately narrowed using type guards or Zod validation.
-*   NEVER disable `@typescript-eslint/no-floating-promises`.
-*   Avoid making types nullable unless strictly necessary, as it hurts readability.
+- Use `checkExhaustive` in the `default` clause of `switch` statements to ensure
+  all cases are handled.
+- Avoid using the non-null assertion operator (`!`) unless absolutely necessary.
+- **STRICT TYPING**: Strictly forbid `any` and `unknown` in both CLI and Core
+  packages. `unknown` is only allowed if it is immediately narrowed using type
+  guards or Zod validation.
+- NEVER disable `@typescript-eslint/no-floating-promises`.
+- Avoid making types nullable unless strictly necessary, as it hurts
+  readability.
 
 ## TUI Best Practices
 
-*   **Terminal Compatibility**: Consider how changes might behave differently across terminals (e.g., VSCode terminal, SSH, Kitty, default Mac terminal, iTerm2, Windows terminal). If modifying keyboard handling, integrate deeply with existing files like `KeypressContext.tsx` and `terminalCapabilityManager.ts`.
-*   **iTerm**: Be aware that `ITERM_SESSION_ID` may be present when users run VSCode from within iTerm, even if the terminal is not iTerm.
+- **Terminal Compatibility**: Consider how changes might behave differently
+  across terminals (e.g., VSCode terminal, SSH, Kitty, default Mac terminal,
+  iTerm2, Windows terminal). If modifying keyboard handling, integrate deeply
+  with existing files like `KeypressContext.tsx` and
+  `terminalCapabilityManager.ts`.
+- **iTerm**: Be aware that `ITERM_SESSION_ID` may be present when users run
+  VSCode from within iTerm, even if the terminal is not iTerm.
 
 ## Code Cleanup
 
-*   **Refactoring**: Actively clean up code duplication, technical debt, and boilerplate ("AI Slop") when working in the codebase.
-*   **Prompts**: Be aware that changes can impact the prompts sent to Gemini CLI and affect overall quality.
+- **Refactoring**: Actively clean up code duplication, technical debt, and
+  boilerplate ("AI Slop") when working in the codebase.
+- **Prompts**: Be aware that changes can impact the prompts sent to Gemini CLI
+  and affect overall quality.

.gemini/skills/docs-changelog/SKILL.md

@@ -23,6 +23,8 @@ To standardize the process of updating changelog files (`latest.md`,
 ## Guidelines for `latest.md` and `preview.md` Highlights
 
 - Aim for **3-5 key highlight points**.
+- Each highlight point must start with a bold-typed title that summarizes the
+  change (e.g., `**New Feature:** A brief description...`).
 - **Prioritize** summarizing new features over other changes like bug fixes or
   chores.
 - **Avoid** mentioning features that are "experimental" or "in preview" in
@@ -65,6 +67,8 @@ detailed **highlights** section for the release-specific page.
 
 1.  **Create the Announcement for `index.md`**:
     -   Generate a concise announcement summarizing the most important changes.
+        Each announcement entry must start with a bold-typed title that
+        summarizes the change.
     -   **Important**: The format for this announcement is unique. You **must**
         use the existing announcements in `docs/changelogs/index.md` and the
         example within

.github/workflows/release-notes.yml

@@ -32,6 +32,7 @@ jobs:
         with:
           # The user-level skills need to be available to the workflow
           fetch-depth: 0
+          ref: 'main'
 
       - name: 'Set up Node.js'
         uses: 'actions/setup-node@v4'
@@ -42,7 +43,6 @@ jobs:
         id: 'release_info'
         run: |
           VERSION="${{ github.event.inputs.version || github.event.release.tag_name }}"
-          BODY="${{ github.event.inputs.body || github.event.release.body }}"
           TIME="${{ github.event.inputs.time || github.event.release.created_at }}"
 
           echo "VERSION=${VERSION}" >> "$GITHUB_OUTPUT"
@@ -50,10 +50,11 @@ jobs:
 
           # Use a heredoc to preserve multiline release body
           echo 'RAW_CHANGELOG<<EOF' >> "$GITHUB_OUTPUT"
-          printf "%s\n" "${BODY}" >> "$GITHUB_OUTPUT"
+          printf "%s\n" "$BODY" >> "$GITHUB_OUTPUT"
           echo 'EOF' >> "$GITHUB_OUTPUT"
         env:
           GH_TOKEN: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
+          BODY: '${{ github.event.inputs.body || github.event.release.body }}'
 
       - name: 'Generate Changelog with Gemini'
         uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0

.gitignore

@@ -46,6 +46,7 @@ packages/*/coverage/
 # Generated files
 packages/cli/src/generated/
 packages/core/src/generated/
+packages/devtools/src/_client-assets.ts
 .integration-tests/
 packages/vscode-ide-companion/*.vsix
 packages/cli/download-ripgrep*/

GEMINI.md

@@ -47,7 +47,13 @@ powerful tool for developers.
     be relative to the workspace root, e.g.,
     `-w @google/gemini-cli-core -- src/routing/modelRouterService.test.ts`)
 - **Full Validation:** `npm run preflight` (Heaviest check; runs clean, install,
-  build, lint, type check, and tests. Recommended before submitting PRs.)
+  build, lint, type check, and tests. Recommended before submitting PRs. Due to
+  its long runtime, only run this at the very end of a code implementation task.
+  If it fails, use faster, targeted commands (e.g., `npm run test`,
+  `npm run lint`, or workspace-specific tests) to iterate on fixes before
+  re-running `preflight`. For simple, non-code changes like documentation or
+  prompting updates, skip `preflight` at the end of the task and wait for PR
+  validation.)
 - **Individual Checks:** `npm run lint` / `npm run format` / `npm run typecheck`
 
 ## Development Conventions

docs/architecture.md

@@ -1,80 +0,0 @@
-# Gemini CLI Architecture Overview
-
-This document provides a high-level overview of the Gemini CLI's architecture.
-
-## Core components
-
-The Gemini CLI is primarily composed of two main packages, along with a suite of
-tools that can be used by the system in the course of handling command-line
-input:
-
-1.  **CLI package (`packages/cli`):**
-    - **Purpose:** This contains the user-facing portion of the Gemini CLI, such
-      as handling the initial user input, presenting the final output, and
-      managing the overall user experience.
-    - **Key functions contained in the package:**
-      - [Input processing](/docs/cli/commands)
-      - History management
-      - Display rendering
-      - [Theme and UI customization](/docs/cli/themes)
-      - [CLI configuration settings](/docs/get-started/configuration)
-
-2.  **Core package (`packages/core`):**
-    - **Purpose:** This acts as the backend for the Gemini CLI. It receives
-      requests sent from `packages/cli`, orchestrates interactions with the
-      Gemini API, and manages the execution of available tools.
-    - **Key functions contained in the package:**
-      - API client for communicating with the Google Gemini API
-      - Prompt construction and management
-      - Tool registration and execution logic
-      - State management for conversations or sessions
-      - Server-side configuration
-
-3.  **Tools (`packages/core/src/tools/`):**
-    - **Purpose:** These are individual modules that extend the capabilities of
-      the Gemini model, allowing it to interact with the local environment
-      (e.g., file system, shell commands, web fetching).
-    - **Interaction:** `packages/core` invokes these tools based on requests
-      from the Gemini model.
-
-## Interaction flow
-
-A typical interaction with the Gemini CLI follows this flow:
-
-1.  **User input:** The user types a prompt or command into the terminal, which
-    is managed by `packages/cli`.
-2.  **Request to core:** `packages/cli` sends the user's input to
-    `packages/core`.
-3.  **Request processed:** The core package:
-    - Constructs an appropriate prompt for the Gemini API, possibly including
-      conversation history and available tool definitions.
-    - Sends the prompt to the Gemini API.
-4.  **Gemini API response:** The Gemini API processes the prompt and returns a
-    response. This response might be a direct answer or a request to use one of
-    the available tools.
-5.  **Tool execution (if applicable):**
-    - When the Gemini API requests a tool, the core package prepares to execute
-      it.
-    - If the requested tool can modify the file system or execute shell
-      commands, the user is first given details of the tool and its arguments,
-      and the user must approve the execution.
-    - Read-only operations, such as reading files, might not require explicit
-      user confirmation to proceed.
-    - Once confirmed, or if confirmation is not required, the core package
-      executes the relevant action within the relevant tool, and the result is
-      sent back to the Gemini API by the core package.
-    - The Gemini API processes the tool result and generates a final response.
-6.  **Response to CLI:** The core package sends the final response back to the
-    CLI package.
-7.  **Display to user:** The CLI package formats and displays the response to
-    the user in the terminal.
-
-## Key design principles
-
-- **Modularity:** Separating the CLI (frontend) from the Core (backend) allows
-  for independent development and potential future extensions (e.g., different
-  frontends for the same backend).
-- **Extensibility:** The tool system is designed to be extensible, allowing new
-  capabilities to be added.
-- **User experience:** The CLI focuses on providing a rich and interactive
-  terminal experience.

docs/changelogs/index.md

@@ -18,7 +18,26 @@ on GitHub.
 | [Preview](preview.md) | Experimental features ready for early feedback. |
 | [Stable](latest.md)   | Stable, recommended for general use.            |
 
-## Announcements: v0.28.0 - 2026-02-03
+## Announcements: v0.29.0 - 2026-02-17
+
+- **Plan Mode:** A new comprehensive planning capability with `/plan`,
+  `enter_plan_mode` tool, and dedicated documentation
+  ([#17698](https://github.com/google-gemini/gemini-cli/pull/17698) by @Adib234,
+  [#18324](https://github.com/google-gemini/gemini-cli/pull/18324) by @jerop).
+- **Gemini 3 Default:** We've removed the preview flag and enabled Gemini 3 by
+  default for all users
+  ([#18414](https://github.com/google-gemini/gemini-cli/pull/18414) by
+  @sehoon38).
+- **Extension Exploration:** New UI and settings to explore and manage
+  extensions more easily
+  ([#18686](https://github.com/google-gemini/gemini-cli/pull/18686) by
+  @sripasg).
+- **Admin Control:** Administrators can now allowlist specific MCP server
+  configurations
+  ([#18311](https://github.com/google-gemini/gemini-cli/pull/18311) by
+  @skeshive).
+
+## Announcements: v0.28.0 - 2026-02-10
 
 - **Slash Command:** We've added a new `/prompt-suggest` slash command to help
   you generate prompt suggestions

docs/changelogs/latest.md

@@ -1,6 +1,6 @@
-# Latest stable release: v0.28.0
+# Latest stable release: v0.29.0
 
-Released: February 10, 2026
+Released: February 17, 2026
 
 For most users, our latest stable release is the recommended release. Install
 the latest stable version with:
@@ -11,305 +11,371 @@ npm install -g @google/gemini-cli
 
 ## Highlights
 
-- **Commands & UX Enhancements:** Introduced `/prompt-suggest` command,
-  alongside updated undo/redo keybindings and automatic theme switching.
-- **Expanded IDE Support:** Now offering compatibility with Positron IDE,
-  expanding integration options for developers.
-- **Enhanced Security & Authentication:** Implemented interactive and
-  non-interactive OAuth consent, improving both security and diagnostic
-  capabilities for bug reports.
-- **Advanced Planning & Agent Tools:** Integrated a generic Checklist component
-  for structured task management and evolved subagent capabilities with dynamic
-  policy registration.
-- **Improved Core Stability & Reliability:** Resolved critical environment
-  loading, authentication, and session management issues, ensuring a more robust
-  experience.
-- **Background Shell Commands:** Enabled the execution of shell commands in the
-  background for increased workflow efficiency.
+- **Plan Mode:** Introduce a dedicated "Plan Mode" to help you architect complex
+  changes before implementation. Use `/plan` to get started.
+- **Gemini 3 by Default:** Gemini 3 is now the default model family, bringing
+  improved performance and reasoning capabilities to all users without needing a
+  feature flag.
+- **Extension Discovery:** Easily discover and install extensions with the new
+  exploration features and registry client.
+- **Enhanced Admin Controls:** New administrative capabilities allow for
+  allowlisting MCP server configurations, giving organizations more control over
+  available tools.
+- **Sub-agent Improvements:** Sub-agents have been transitioned to a new format
+  with improved definitions and system prompts for better reliability.
 
 ## What's Changed
 
-- feat(commands): add /prompt-suggest slash command by @NTaylorMullen in
-  [#17264](https://github.com/google-gemini/gemini-cli/pull/17264)
-- feat(cli): align hooks enable/disable with skills and improve completion by
-  @sehoon38 in [#16822](https://github.com/google-gemini/gemini-cli/pull/16822)
-- docs: add CLI reference documentation by @leochiu-a in
-  [#17504](https://github.com/google-gemini/gemini-cli/pull/17504)
-- chore(release): bump version to 0.28.0-nightly.20260128.adc8e11bb by
+- fix: remove `ask_user` tool from non-interactive modes by @jackwotherspoon in
+  [#18154](https://github.com/google-gemini/gemini-cli/pull/18154)
+- fix(cli): allow restricted .env loading in untrusted sandboxed folders by
+  @galz10 in [#17806](https://github.com/google-gemini/gemini-cli/pull/17806)
+- Encourage agent to utilize ecosystem tools to perform work by @gundermanc in
+  [#17881](https://github.com/google-gemini/gemini-cli/pull/17881)
+- feat(plan): unify workflow location in system prompt to optimize caching by
+  @jerop in [#18258](https://github.com/google-gemini/gemini-cli/pull/18258)
+- feat(core): enable getUserTierName in config by @sehoon38 in
+  [#18265](https://github.com/google-gemini/gemini-cli/pull/18265)
+- feat(core): add default execution limits for subagents by @abhipatel12 in
+  [#18274](https://github.com/google-gemini/gemini-cli/pull/18274)
+- Fix issue where agent gets stuck at interactive commands. by @gundermanc in
+  [#18272](https://github.com/google-gemini/gemini-cli/pull/18272)
+- chore(release): bump version to 0.29.0-nightly.20260203.71f46f116 by
   @gemini-cli-robot in
-  [#17725](https://github.com/google-gemini/gemini-cli/pull/17725)
-- feat(skills): final stable promotion cleanup by @abhipatel12 in
-  [#17726](https://github.com/google-gemini/gemini-cli/pull/17726)
-- test(core): mock fetch in OAuth transport fallback tests by @jw409 in
-  [#17059](https://github.com/google-gemini/gemini-cli/pull/17059)
-- feat(cli): include auth method in /bug by @erikus in
-  [#17569](https://github.com/google-gemini/gemini-cli/pull/17569)
-- Add a email privacy note to bug_report template by @nemyung in
-  [#17474](https://github.com/google-gemini/gemini-cli/pull/17474)
-- Rewind documentation by @Adib234 in
-  [#17446](https://github.com/google-gemini/gemini-cli/pull/17446)
-- fix: verify audio/video MIME types with content check by @maru0804 in
-  [#16907](https://github.com/google-gemini/gemini-cli/pull/16907)
-- feat(core): add support for positron ide
-  ([#15045](https://github.com/google-gemini/gemini-cli/pull/15045)) by @kapsner
-  in [#15047](https://github.com/google-gemini/gemini-cli/pull/15047)
-- /oncall dedup - wrap texts to nextlines by @sehoon38 in
-  [#17782](https://github.com/google-gemini/gemini-cli/pull/17782)
-- fix(admin): rename advanced features admin setting by @skeshive in
-  [#17786](https://github.com/google-gemini/gemini-cli/pull/17786)
-- [extension config] Make breaking optional value non-optional by @chrstnb in
-  [#17785](https://github.com/google-gemini/gemini-cli/pull/17785)
-- Fix docs-writer skill issues by @g-samroberts in
-  [#17734](https://github.com/google-gemini/gemini-cli/pull/17734)
-- fix(core): suppress duplicate hook failure warnings during streaming by
+  [#18243](https://github.com/google-gemini/gemini-cli/pull/18243)
+- feat(core): remove hardcoded policy bypass for local subagents by @abhipatel12
+  in [#18153](https://github.com/google-gemini/gemini-cli/pull/18153)
+- feat(plan): implement `plan` slash command by @Adib234 in
+  [#17698](https://github.com/google-gemini/gemini-cli/pull/17698)
+- feat: increase `ask_user` label limit to 16 characters by @jackwotherspoon in
+  [#18320](https://github.com/google-gemini/gemini-cli/pull/18320)
+- Add information about the agent skills lifecycle and clarify docs-writer skill
+  metadata. by @g-samroberts in
+  [#18234](https://github.com/google-gemini/gemini-cli/pull/18234)
+- feat(core): add `enter_plan_mode` tool by @jerop in
+  [#18324](https://github.com/google-gemini/gemini-cli/pull/18324)
+- Stop showing an error message in `/plan` by @Adib234 in
+  [#18333](https://github.com/google-gemini/gemini-cli/pull/18333)
+- fix(hooks): remove unnecessary logging for hook registration by @abhipatel12
+  in [#18332](https://github.com/google-gemini/gemini-cli/pull/18332)
+- fix(mcp): ensure MCP transport is closed to prevent memory leaks by
+  @cbcoutinho in
+  [#18054](https://github.com/google-gemini/gemini-cli/pull/18054)
+- feat(skills): implement linking for agent skills by @MushuEE in
+  [#18295](https://github.com/google-gemini/gemini-cli/pull/18295)
+- Changelogs for 0.27.0 and 0.28.0-preview0 by @g-samroberts in
+  [#18336](https://github.com/google-gemini/gemini-cli/pull/18336)
+- chore: correct docs as skills and hooks are stable by @jackwotherspoon in
+  [#18358](https://github.com/google-gemini/gemini-cli/pull/18358)
+- feat(admin): Implement admin allowlist for MCP server configurations by
+  @skeshive in [#18311](https://github.com/google-gemini/gemini-cli/pull/18311)
+- fix(core): add retry logic for transient SSL/TLS errors (#17318) by @ppgranger
+  in [#18310](https://github.com/google-gemini/gemini-cli/pull/18310)
+- Add support for /extensions config command by @chrstnb in
+  [#17895](https://github.com/google-gemini/gemini-cli/pull/17895)
+- fix(core): handle non-compliant mcpbridge responses from Xcode 26.3 by
+  @peterfriese in
+  [#18376](https://github.com/google-gemini/gemini-cli/pull/18376)
+- feat(cli): Add W, B, E Vim motions and operator support by @ademuri in
+  [#16209](https://github.com/google-gemini/gemini-cli/pull/16209)
+- fix: Windows Specific Agent Quality & System Prompt by @scidomino in
+  [#18351](https://github.com/google-gemini/gemini-cli/pull/18351)
+- feat(plan): support `replace` tool in plan mode to edit plans by @jerop in
+  [#18379](https://github.com/google-gemini/gemini-cli/pull/18379)
+- Improving memory tool instructions and eval testing by @alisa-alisa in
+  [#18091](https://github.com/google-gemini/gemini-cli/pull/18091)
+- fix(cli): color extension link success message green by @MushuEE in
+  [#18386](https://github.com/google-gemini/gemini-cli/pull/18386)
+- undo by @jacob314 in
+  [#18147](https://github.com/google-gemini/gemini-cli/pull/18147)
+- feat(plan): add guidance on iterating on approved plans vs creating new plans
+  by @jerop in [#18346](https://github.com/google-gemini/gemini-cli/pull/18346)
+- feat(plan): fix invalid tool calls in plan mode by @Adib234 in
+  [#18352](https://github.com/google-gemini/gemini-cli/pull/18352)
+- feat(plan): integrate planning artifacts and tools into primary workflows by
+  @jerop in [#18375](https://github.com/google-gemini/gemini-cli/pull/18375)
+- Fix permission check by @scidomino in
+  [#18395](https://github.com/google-gemini/gemini-cli/pull/18395)
+- ux(polish) autocomplete in the input prompt by @jacob314 in
+  [#18181](https://github.com/google-gemini/gemini-cli/pull/18181)
+- fix: resolve infinite loop when using 'Modify with external editor' by
+  @ppgranger in [#17453](https://github.com/google-gemini/gemini-cli/pull/17453)
+- feat: expand verify-release to macOS and Windows by @yunaseoul in
+  [#18145](https://github.com/google-gemini/gemini-cli/pull/18145)
+- feat(plan): implement support for MCP servers in Plan mode by @Adib234 in
+  [#18229](https://github.com/google-gemini/gemini-cli/pull/18229)
+- chore: update folder trust error messaging by @galz10 in
+  [#18402](https://github.com/google-gemini/gemini-cli/pull/18402)
+- feat(plan): create a metric for execution of plans generated in plan mode by
+  @Adib234 in [#18236](https://github.com/google-gemini/gemini-cli/pull/18236)
+- perf(ui): optimize stripUnsafeCharacters with regex by @gsquared94 in
+  [#18413](https://github.com/google-gemini/gemini-cli/pull/18413)
+- feat(context): implement observation masking for tool outputs by @abhipatel12
+  in [#18389](https://github.com/google-gemini/gemini-cli/pull/18389)
+- feat(core,cli): implement session-linked tool output storage and cleanup by
   @abhipatel12 in
-  [#17727](https://github.com/google-gemini/gemini-cli/pull/17727)
-- test: add more tests for AskUser by @jackwotherspoon in
-  [#17720](https://github.com/google-gemini/gemini-cli/pull/17720)
-- feat(cli): enable activity logging for non-interactive mode and evals by
-  @SandyTao520 in
-  [#17703](https://github.com/google-gemini/gemini-cli/pull/17703)
-- feat(core): add support for custom deny messages in policy rules by
-  @allenhutchison in
-  [#17427](https://github.com/google-gemini/gemini-cli/pull/17427)
-- Fix unintended credential exposure to MCP Servers by @Adib234 in
-  [#17311](https://github.com/google-gemini/gemini-cli/pull/17311)
-- feat(extensions): add support for custom themes in extensions by @spencer426
-  in [#17327](https://github.com/google-gemini/gemini-cli/pull/17327)
-- fix: persist and restore workspace directories on session resume by
-  @korade-krushna in
-  [#17454](https://github.com/google-gemini/gemini-cli/pull/17454)
-- Update release notes pages for 0.26.0 and 0.27.0-preview. by @g-samroberts in
-  [#17744](https://github.com/google-gemini/gemini-cli/pull/17744)
-- feat(ux): update cell border color and created test file for table rendering
-  by @devr0306 in
-  [#17798](https://github.com/google-gemini/gemini-cli/pull/17798)
-- Change height for the ToolConfirmationQueue. by @jacob314 in
-  [#17799](https://github.com/google-gemini/gemini-cli/pull/17799)
-- feat(cli): add user identity info to stats command by @sehoon38 in
-  [#17612](https://github.com/google-gemini/gemini-cli/pull/17612)
-- fix(ux): fixed off-by-some wrapping caused by fixed-width characters by
-  @devr0306 in [#17816](https://github.com/google-gemini/gemini-cli/pull/17816)
-- feat(cli): update undo/redo keybindings to Cmd+Z/Alt+Z and
-  Shift+Cmd+Z/Shift+Alt+Z by @scidomino in
-  [#17800](https://github.com/google-gemini/gemini-cli/pull/17800)
-- fix(evals): use absolute path for activity log directory by @SandyTao520 in
-  [#17830](https://github.com/google-gemini/gemini-cli/pull/17830)
-- test: add integration test to verify stdout/stderr routing by @ved015 in
-  [#17280](https://github.com/google-gemini/gemini-cli/pull/17280)
-- fix(cli): list installed extensions when update target missing by @tt-a1i in
-  [#17082](https://github.com/google-gemini/gemini-cli/pull/17082)
-- fix(cli): handle PAT tokens and credentials in git remote URL parsing by
-  @afarber in [#14650](https://github.com/google-gemini/gemini-cli/pull/14650)
-- fix(core): use returnDisplay for error result display by @Nubebuster in
-  [#14994](https://github.com/google-gemini/gemini-cli/pull/14994)
-- Fix detection of bun as package manager by @Randomblock1 in
-  [#17462](https://github.com/google-gemini/gemini-cli/pull/17462)
-- feat(cli): show hooksConfig.enabled in settings dialog by @abhipatel12 in
-  [#17810](https://github.com/google-gemini/gemini-cli/pull/17810)
-- feat(cli): Display user identity (auth, email, tier) on startup by @yunaseoul
-  in [#17591](https://github.com/google-gemini/gemini-cli/pull/17591)
-- fix: prevent ghost border for AskUserDialog by @jackwotherspoon in
-  [#17788](https://github.com/google-gemini/gemini-cli/pull/17788)
-- docs: mark A2A subagents as experimental in subagents.md by @adamfweidman in
-  [#17863](https://github.com/google-gemini/gemini-cli/pull/17863)
-- Resolve error thrown for sensitive values by @chrstnb in
-  [#17826](https://github.com/google-gemini/gemini-cli/pull/17826)
-- fix(admin): Rename secureModeEnabled to strictModeDisabled by @skeshive in
-  [#17789](https://github.com/google-gemini/gemini-cli/pull/17789)
-- feat(ux): update truncate dots to be shorter in tables by @devr0306 in
-  [#17825](https://github.com/google-gemini/gemini-cli/pull/17825)
-- fix(core): resolve DEP0040 punycode deprecation via patch-package by
-  @ATHARVA262005 in
-  [#17692](https://github.com/google-gemini/gemini-cli/pull/17692)
-- feat(plan): create generic Checklist component and refactor Todo by @Adib234
-  in [#17741](https://github.com/google-gemini/gemini-cli/pull/17741)
-- Cleanup post delegate_to_agent removal by @gundermanc in
-  [#17875](https://github.com/google-gemini/gemini-cli/pull/17875)
-- fix(core): use GIT_CONFIG_GLOBAL to isolate shadow git repo configuration -
-  Fixes [#17877](https://github.com/google-gemini/gemini-cli/pull/17877) by
-  @cocosheng-g in
-  [#17803](https://github.com/google-gemini/gemini-cli/pull/17803)
-- Disable mouse tracking e2e by @alisa-alisa in
-  [#17880](https://github.com/google-gemini/gemini-cli/pull/17880)
-- fix(cli): use correct setting key for Cloud Shell auth by @sehoon38 in
-  [#17884](https://github.com/google-gemini/gemini-cli/pull/17884)
-- chore: revert IDE specific ASCII logo by @jackwotherspoon in
-  [#17887](https://github.com/google-gemini/gemini-cli/pull/17887)
-- Revert "fix(core): resolve DEP0040 punycode deprecation via patch-package" by
-  @sehoon38 in [#17898](https://github.com/google-gemini/gemini-cli/pull/17898)
-- Refactoring of disabling of mouse tracking in e2e tests by @alisa-alisa in
-  [#17902](https://github.com/google-gemini/gemini-cli/pull/17902)
-- feat(core): Add GOOGLE_GENAI_API_VERSION environment variable support by
-  @deyim in [#16177](https://github.com/google-gemini/gemini-cli/pull/16177)
-- feat(core): Isolate and cleanup truncated tool outputs by @SandyTao520 in
-  [#17594](https://github.com/google-gemini/gemini-cli/pull/17594)
-- Create skills page, update commands, refine docs by @g-samroberts in
-  [#17842](https://github.com/google-gemini/gemini-cli/pull/17842)
-- feat: preserve EOL in files by @Thomas-Shephard in
-  [#16087](https://github.com/google-gemini/gemini-cli/pull/16087)
-- Fix HalfLinePaddedBox in screenreader mode. by @jacob314 in
-  [#17914](https://github.com/google-gemini/gemini-cli/pull/17914)
-- bug(ux) vim mode fixes. Start in insert mode. Fix bug blocking F12 and ctrl-X
-  in vim mode. by @jacob314 in
-  [#17938](https://github.com/google-gemini/gemini-cli/pull/17938)
-- feat(core): implement interactive and non-interactive consent for OAuth by
-  @ehedlund in [#17699](https://github.com/google-gemini/gemini-cli/pull/17699)
-- perf(core): optimize token calculation and add support for multimodal tool
-  responses by @abhipatel12 in
-  [#17835](https://github.com/google-gemini/gemini-cli/pull/17835)
-- refactor(hooks): remove legacy tools.enableHooks setting by @abhipatel12 in
-  [#17867](https://github.com/google-gemini/gemini-cli/pull/17867)
-- feat(ci): add npx smoke test to verify installability by @bdmorgan in
-  [#17927](https://github.com/google-gemini/gemini-cli/pull/17927)
-- feat(core): implement dynamic policy registration for subagents by
+  [#18416](https://github.com/google-gemini/gemini-cli/pull/18416)
+- Shorten temp directory by @joshualitt in
+  [#17901](https://github.com/google-gemini/gemini-cli/pull/17901)
+- feat(plan): add behavioral evals for plan mode by @jerop in
+  [#18437](https://github.com/google-gemini/gemini-cli/pull/18437)
+- Add extension registry client by @chrstnb in
+  [#18396](https://github.com/google-gemini/gemini-cli/pull/18396)
+- Enable extension config by default by @chrstnb in
+  [#18447](https://github.com/google-gemini/gemini-cli/pull/18447)
+- Automatically generate change logs on release by @g-samroberts in
+  [#18401](https://github.com/google-gemini/gemini-cli/pull/18401)
+- Remove previewFeatures and default to Gemini 3 by @sehoon38 in
+  [#18414](https://github.com/google-gemini/gemini-cli/pull/18414)
+- feat(admin): apply MCP allowlist to extensions & gemini mcp list command by
+  @skeshive in [#18442](https://github.com/google-gemini/gemini-cli/pull/18442)
+- fix(cli): improve focus navigation for interactive and background shells by
+  @galz10 in [#18343](https://github.com/google-gemini/gemini-cli/pull/18343)
+- Add shortcuts hint and panel for discoverability by @LyalinDotCom in
+  [#18035](https://github.com/google-gemini/gemini-cli/pull/18035)
+- fix(config): treat system settings as read-only during migration and warn user
+  by @spencer426 in
+  [#18277](https://github.com/google-gemini/gemini-cli/pull/18277)
+- feat(plan): add positive test case and update eval stability policy by @jerop
+  in [#18457](https://github.com/google-gemini/gemini-cli/pull/18457)
+- fix- windows: add shell: true for spawnSync to fix EINVAL with .cmd editors by
+  @zackoch in [#18408](https://github.com/google-gemini/gemini-cli/pull/18408)
+- bug(core): Fix bug when saving plans. by @joshualitt in
+  [#18465](https://github.com/google-gemini/gemini-cli/pull/18465)
+- Refactor atCommandProcessor by @scidomino in
+  [#18461](https://github.com/google-gemini/gemini-cli/pull/18461)
+- feat(core): implement persistence and resumption for masked tool outputs by
   @abhipatel12 in
-  [#17838](https://github.com/google-gemini/gemini-cli/pull/17838)
-- feat: Implement background shell commands by @galz10 in
-  [#14849](https://github.com/google-gemini/gemini-cli/pull/14849)
-- feat(admin): provide actionable error messages for disabled features by
-  @skeshive in [#17815](https://github.com/google-gemini/gemini-cli/pull/17815)
-- Fix bugs where Rewind and Resume showed Ugly and 100X too verbose content. by
-  @jacob314 in [#17940](https://github.com/google-gemini/gemini-cli/pull/17940)
-- Fix broken link in docs by @chrstnb in
-  [#17959](https://github.com/google-gemini/gemini-cli/pull/17959)
-- feat(plan): reuse standard tool confirmation for AskUser tool by @jerop in
-  [#17864](https://github.com/google-gemini/gemini-cli/pull/17864)
-- feat(core): enable overriding CODE_ASSIST_API_VERSION with env var by
-  @lottielin in [#17942](https://github.com/google-gemini/gemini-cli/pull/17942)
-- run npx pointing to the specific commit SHA by @sehoon38 in
-  [#17970](https://github.com/google-gemini/gemini-cli/pull/17970)
-- Add allowedExtensions setting by @kevinjwang1 in
-  [#17695](https://github.com/google-gemini/gemini-cli/pull/17695)
-- feat(plan): refactor ToolConfirmationPayload to union type by @jerop in
-  [#17980](https://github.com/google-gemini/gemini-cli/pull/17980)
-- lower the default max retries to reduce contention by @sehoon38 in
-  [#17975](https://github.com/google-gemini/gemini-cli/pull/17975)
-- fix(core): ensure YOLO mode auto-approves complex shell commands when parsing
-  fails by @abhipatel12 in
-  [#17920](https://github.com/google-gemini/gemini-cli/pull/17920)
-- Fix broken link. by @g-samroberts in
-  [#17972](https://github.com/google-gemini/gemini-cli/pull/17972)
-- Support ctrl-C and Ctrl-D correctly Refactor so InputPrompt has priority over
-  AppContainer for input handling. by @jacob314 in
-  [#17993](https://github.com/google-gemini/gemini-cli/pull/17993)
-- Fix truncation for AskQuestion by @jacob314 in
-  [#18001](https://github.com/google-gemini/gemini-cli/pull/18001)
-- fix(workflow): update maintainer check logic to be inclusive and
-  case-insensitive by @bdmorgan in
-  [#18009](https://github.com/google-gemini/gemini-cli/pull/18009)
-- Fix Esc cancel during streaming by @LyalinDotCom in
-  [#18039](https://github.com/google-gemini/gemini-cli/pull/18039)
-- feat(acp): add session resume support by @bdmorgan in
-  [#18043](https://github.com/google-gemini/gemini-cli/pull/18043)
-- fix(ci): prevent stale PR closer from incorrectly closing new PRs by @bdmorgan
-  in [#18069](https://github.com/google-gemini/gemini-cli/pull/18069)
-- chore: delete autoAccept setting unused in production by @victorvianna in
-  [#17862](https://github.com/google-gemini/gemini-cli/pull/17862)
-- feat(plan): use placeholder for choice question "Other" option by @jerop in
-  [#18101](https://github.com/google-gemini/gemini-cli/pull/18101)
-- docs: update clearContext to hookSpecificOutput by @jackwotherspoon in
-  [#18024](https://github.com/google-gemini/gemini-cli/pull/18024)
-- docs-writer skill: Update docs writer skill by @jkcinouye in
-  [#17928](https://github.com/google-gemini/gemini-cli/pull/17928)
-- Sehoon/oncall filter by @sehoon38 in
-  [#18105](https://github.com/google-gemini/gemini-cli/pull/18105)
-- feat(core): add setting to disable loop detection by @SandyTao520 in
-  [#18008](https://github.com/google-gemini/gemini-cli/pull/18008)
-- Docs: Revise docs/index.md by @jkcinouye in
-  [#17879](https://github.com/google-gemini/gemini-cli/pull/17879)
-- Fix up/down arrow regression and add test. by @jacob314 in
-  [#18108](https://github.com/google-gemini/gemini-cli/pull/18108)
-- fix(ui): prevent content leak in MaxSizedBox bottom overflow by @jerop in
-  [#17991](https://github.com/google-gemini/gemini-cli/pull/17991)
-- refactor: migrate checks.ts utility to core and deduplicate by @jerop in
-  [#18139](https://github.com/google-gemini/gemini-cli/pull/18139)
-- feat(core): implement tool name aliasing for backward compatibility by
-  @SandyTao520 in
-  [#17974](https://github.com/google-gemini/gemini-cli/pull/17974)
-- docs: fix help-wanted label spelling by @pavan-sh in
-  [#18114](https://github.com/google-gemini/gemini-cli/pull/18114)
-- feat(cli): implement automatic theme switching based on terminal background by
+  [#18451](https://github.com/google-gemini/gemini-cli/pull/18451)
+- refactor: simplify tool output truncation to single config by @SandyTao520 in
+  [#18446](https://github.com/google-gemini/gemini-cli/pull/18446)
+- bug(core): Ensure storage is initialized early, even if config is not. by
+  @joshualitt in
+  [#18471](https://github.com/google-gemini/gemini-cli/pull/18471)
+- chore: Update build-and-start script to support argument forwarding by
   @Abhijit-2592 in
-  [#17976](https://github.com/google-gemini/gemini-cli/pull/17976)
-- fix(ide): no-op refactoring that moves the connection logic to helper
-  functions by @skeshive in
-  [#18118](https://github.com/google-gemini/gemini-cli/pull/18118)
-- feat: update review-frontend-and-fix slash command to review-and-fix by
-  @galz10 in [#18146](https://github.com/google-gemini/gemini-cli/pull/18146)
-- fix: improve Ctrl+R reverse search by @jackwotherspoon in
-  [#18075](https://github.com/google-gemini/gemini-cli/pull/18075)
-- feat(plan): handle inconsistency in schedulers by @Adib234 in
-  [#17813](https://github.com/google-gemini/gemini-cli/pull/17813)
-- feat(plan): add core logic and exit_plan_mode tool definition by @jerop in
-  [#18110](https://github.com/google-gemini/gemini-cli/pull/18110)
-- feat(core): rename search_file_content tool to grep_search and add legacy
-  alias by @SandyTao520 in
-  [#18003](https://github.com/google-gemini/gemini-cli/pull/18003)
-- fix(core): prioritize detailed error messages for code assist setup by
-  @gsquared94 in
-  [#17852](https://github.com/google-gemini/gemini-cli/pull/17852)
-- fix(cli): resolve environment loading and auth validation issues in ACP mode
-  by @bdmorgan in
-  [#18025](https://github.com/google-gemini/gemini-cli/pull/18025)
-- feat(core): add .agents/skills directory alias for skill discovery by
+  [#18241](https://github.com/google-gemini/gemini-cli/pull/18241)
+- fix(core): prevent subagent bypass in plan mode by @jerop in
+  [#18484](https://github.com/google-gemini/gemini-cli/pull/18484)
+- feat(cli): add WebSocket-based network logging and streaming chunk support by
+  @SandyTao520 in
+  [#18383](https://github.com/google-gemini/gemini-cli/pull/18383)
+- feat(cli): update approval modes UI by @jerop in
+  [#18476](https://github.com/google-gemini/gemini-cli/pull/18476)
+- fix(cli): reload skills and agents on extension restart by @NTaylorMullen in
+  [#18411](https://github.com/google-gemini/gemini-cli/pull/18411)
+- fix(core): expand excludeTools with legacy aliases for renamed tools by
+  @SandyTao520 in
+  [#18498](https://github.com/google-gemini/gemini-cli/pull/18498)
+- feat(core): overhaul system prompt for rigor, integrity, and intent alignment
+  by @NTaylorMullen in
+  [#17263](https://github.com/google-gemini/gemini-cli/pull/17263)
+- Patch for generate changelog docs yaml file by @g-samroberts in
+  [#18496](https://github.com/google-gemini/gemini-cli/pull/18496)
+- Code review fixes for show question mark pr. by @jacob314 in
+  [#18480](https://github.com/google-gemini/gemini-cli/pull/18480)
+- fix(cli): add SS3 Shift+Tab support for Windows terminals by @ThanhNguyxn in
+  [#18187](https://github.com/google-gemini/gemini-cli/pull/18187)
+- chore: remove redundant planning prompt from final shell by @jerop in
+  [#18528](https://github.com/google-gemini/gemini-cli/pull/18528)
+- docs: require pr-creator skill for PR generation by @NTaylorMullen in
+  [#18536](https://github.com/google-gemini/gemini-cli/pull/18536)
+- chore: update colors for ask_user dialog by @jackwotherspoon in
+  [#18543](https://github.com/google-gemini/gemini-cli/pull/18543)
+- feat(core): exempt high-signal tools from output masking by @abhipatel12 in
+  [#18545](https://github.com/google-gemini/gemini-cli/pull/18545)
+- refactor(core): remove memory tool instructions from Gemini 3 prompt by
   @NTaylorMullen in
-  [#18151](https://github.com/google-gemini/gemini-cli/pull/18151)
-- chore(core): reassign telemetry keys to avoid server conflict by @mattKorwel
-  in [#18161](https://github.com/google-gemini/gemini-cli/pull/18161)
-- Add link to rewind doc in commands.md by @Adib234 in
-  [#17961](https://github.com/google-gemini/gemini-cli/pull/17961)
-- feat(core): add draft-2020-12 JSON Schema support with lenient fallback by
-  @afarber in [#15060](https://github.com/google-gemini/gemini-cli/pull/15060)
-- refactor(core): robust trimPreservingTrailingNewline and regression test by
+  [#18559](https://github.com/google-gemini/gemini-cli/pull/18559)
+- chore: remove feedback instruction from system prompt by @NTaylorMullen in
+  [#18560](https://github.com/google-gemini/gemini-cli/pull/18560)
+- feat(context): add remote configuration for tool output masking thresholds by
+  @abhipatel12 in
+  [#18553](https://github.com/google-gemini/gemini-cli/pull/18553)
+- feat(core): pause agent timeout budget while waiting for tool confirmation by
+  @abhipatel12 in
+  [#18415](https://github.com/google-gemini/gemini-cli/pull/18415)
+- refactor(config): remove experimental.enableEventDrivenScheduler setting by
+  @abhipatel12 in
+  [#17924](https://github.com/google-gemini/gemini-cli/pull/17924)
+- feat(cli): truncate shell output in UI history and improve active shell
+  display by @jwhelangoog in
+  [#17438](https://github.com/google-gemini/gemini-cli/pull/17438)
+- refactor(cli): switch useToolScheduler to event-driven engine by @abhipatel12
+  in [#18565](https://github.com/google-gemini/gemini-cli/pull/18565)
+- fix(core): correct escaped interpolation in system prompt by @NTaylorMullen in
+  [#18557](https://github.com/google-gemini/gemini-cli/pull/18557)
+- propagate abortSignal by @scidomino in
+  [#18477](https://github.com/google-gemini/gemini-cli/pull/18477)
+- feat(core): conditionally include ctrl+f prompt based on interactive shell
+  setting by @NTaylorMullen in
+  [#18561](https://github.com/google-gemini/gemini-cli/pull/18561)
+- fix(core): ensure `enter_plan_mode` tool registration respects
+  `experimental.plan` by @jerop in
+  [#18587](https://github.com/google-gemini/gemini-cli/pull/18587)
+- feat(core): transition sub-agents to XML format and improve definitions by
+  @NTaylorMullen in
+  [#18555](https://github.com/google-gemini/gemini-cli/pull/18555)
+- docs: Add Plan Mode documentation by @jerop in
+  [#18582](https://github.com/google-gemini/gemini-cli/pull/18582)
+- chore: strengthen validation guidance in system prompt by @NTaylorMullen in
+  [#18544](https://github.com/google-gemini/gemini-cli/pull/18544)
+- Fix newline insertion bug in replace tool by @werdnum in
+  [#18595](https://github.com/google-gemini/gemini-cli/pull/18595)
+- fix(evals): update save_memory evals and simplify tool description by
+  @NTaylorMullen in
+  [#18610](https://github.com/google-gemini/gemini-cli/pull/18610)
+- chore(evals): update validation_fidelity_pre_existing_errors to USUALLY_PASSES
+  by @NTaylorMullen in
+  [#18617](https://github.com/google-gemini/gemini-cli/pull/18617)
+- fix: shorten tool call IDs and fix duplicate tool name in truncated output
+  filenames by @SandyTao520 in
+  [#18600](https://github.com/google-gemini/gemini-cli/pull/18600)
+- feat(cli): implement atomic writes and safety checks for trusted folders by
+  @galz10 in [#18406](https://github.com/google-gemini/gemini-cli/pull/18406)
+- Remove relative docs links by @chrstnb in
+  [#18650](https://github.com/google-gemini/gemini-cli/pull/18650)
+- docs: add legacy snippets convention to GEMINI.md by @NTaylorMullen in
+  [#18597](https://github.com/google-gemini/gemini-cli/pull/18597)
+- fix(chore): Support linting for cjs by @aswinashok44 in
+  [#18639](https://github.com/google-gemini/gemini-cli/pull/18639)
+- feat: move shell efficiency guidelines to tool description by @NTaylorMullen
+  in [#18614](https://github.com/google-gemini/gemini-cli/pull/18614)
+- Added "" as default value, since getText() used to expect a string only and
+  thus crashed when undefined... Fixes #18076 by @019-Abhi in
+  [#18099](https://github.com/google-gemini/gemini-cli/pull/18099)
+- Allow @-includes outside of workspaces (with permission) by @scidomino in
+  [#18470](https://github.com/google-gemini/gemini-cli/pull/18470)
+- chore: make `ask_user` header description more clear by @jackwotherspoon in
+  [#18657](https://github.com/google-gemini/gemini-cli/pull/18657)
+- refactor(core): model-dependent tool definitions by @aishaneeshah in
+  [#18563](https://github.com/google-gemini/gemini-cli/pull/18563)
+- Harded code assist converter. by @jacob314 in
+  [#18656](https://github.com/google-gemini/gemini-cli/pull/18656)
+- bug(core): Fix minor bug in migration logic. by @joshualitt in
+  [#18661](https://github.com/google-gemini/gemini-cli/pull/18661)
+- feat: enable plan mode experiment in settings by @jerop in
+  [#18636](https://github.com/google-gemini/gemini-cli/pull/18636)
+- refactor: push isValidPath() into parsePastedPaths() by @scidomino in
+  [#18664](https://github.com/google-gemini/gemini-cli/pull/18664)
+- fix(cli): correct 'esc to cancel' position and restore duration display by
+  @NTaylorMullen in
+  [#18534](https://github.com/google-gemini/gemini-cli/pull/18534)
+- feat(cli): add DevTools integration with gemini-cli-devtools by @SandyTao520
+  in [#18648](https://github.com/google-gemini/gemini-cli/pull/18648)
+- chore: remove unused exports and redundant hook files by @SandyTao520 in
+  [#18681](https://github.com/google-gemini/gemini-cli/pull/18681)
+- Fix number of lines being reported in rewind confirmation dialog by @Adib234
+  in [#18675](https://github.com/google-gemini/gemini-cli/pull/18675)
+- feat(cli): disable folder trust in headless mode by @galz10 in
+  [#18407](https://github.com/google-gemini/gemini-cli/pull/18407)
+- Disallow unsafe type assertions by @gundermanc in
+  [#18688](https://github.com/google-gemini/gemini-cli/pull/18688)
+- Change event type for release by @g-samroberts in
+  [#18693](https://github.com/google-gemini/gemini-cli/pull/18693)
+- feat: handle multiple dynamic context filenames in system prompt by
+  @NTaylorMullen in
+  [#18598](https://github.com/google-gemini/gemini-cli/pull/18598)
+- Properly parse at-commands with narrow non-breaking spaces by @scidomino in
+  [#18677](https://github.com/google-gemini/gemini-cli/pull/18677)
+- refactor(core): centralize core tool definitions and support model-specific
+  schemas by @aishaneeshah in
+  [#18662](https://github.com/google-gemini/gemini-cli/pull/18662)
+- feat(core): Render memory hierarchically in context. by @joshualitt in
+  [#18350](https://github.com/google-gemini/gemini-cli/pull/18350)
+- feat: Ctrl+O to expand paste placeholder by @jackwotherspoon in
+  [#18103](https://github.com/google-gemini/gemini-cli/pull/18103)
+- fix(cli): Improve header spacing by @NTaylorMullen in
+  [#18531](https://github.com/google-gemini/gemini-cli/pull/18531)
+- Feature/quota visibility 16795 by @spencer426 in
+  [#18203](https://github.com/google-gemini/gemini-cli/pull/18203)
+- Inline thinking bubbles with summary/full modes by @LyalinDotCom in
+  [#18033](https://github.com/google-gemini/gemini-cli/pull/18033)
+- docs: remove TOC marker from Plan Mode header by @jerop in
+  [#18678](https://github.com/google-gemini/gemini-cli/pull/18678)
+- fix(ui): remove redundant newlines in Gemini messages by @NTaylorMullen in
+  [#18538](https://github.com/google-gemini/gemini-cli/pull/18538)
+- test(cli): fix AppContainer act() warnings and improve waitFor resilience by
+  @NTaylorMullen in
+  [#18676](https://github.com/google-gemini/gemini-cli/pull/18676)
+- refactor(core): refine Security & System Integrity section in system prompt by
+  @NTaylorMullen in
+  [#18601](https://github.com/google-gemini/gemini-cli/pull/18601)
+- Fix layout rounding. by @gundermanc in
+  [#18667](https://github.com/google-gemini/gemini-cli/pull/18667)
+- docs(skills): enhance pr-creator safety and interactivity by @NTaylorMullen in
+  [#18616](https://github.com/google-gemini/gemini-cli/pull/18616)
+- test(core): remove hardcoded model from TestRig by @NTaylorMullen in
+  [#18710](https://github.com/google-gemini/gemini-cli/pull/18710)
+- feat(core): optimize sub-agents system prompt intro by @NTaylorMullen in
+  [#18608](https://github.com/google-gemini/gemini-cli/pull/18608)
+- feat(cli): update approval mode labels and shortcuts per latest UX spec by
+  @jerop in [#18698](https://github.com/google-gemini/gemini-cli/pull/18698)
+- fix(plan): update persistent approval mode setting by @Adib234 in
+  [#18638](https://github.com/google-gemini/gemini-cli/pull/18638)
+- fix: move toasts location to left side by @jackwotherspoon in
+  [#18705](https://github.com/google-gemini/gemini-cli/pull/18705)
+- feat(routing): restrict numerical routing to Gemini 3 family by @mattKorwel in
+  [#18478](https://github.com/google-gemini/gemini-cli/pull/18478)
+- fix(ide): fix ide nudge setting by @skeshive in
+  [#18733](https://github.com/google-gemini/gemini-cli/pull/18733)
+- fix(core): standardize tool formatting in system prompts by @NTaylorMullen in
+  [#18615](https://github.com/google-gemini/gemini-cli/pull/18615)
+- chore: consolidate to green in ask user dialog by @jackwotherspoon in
+  [#18734](https://github.com/google-gemini/gemini-cli/pull/18734)
+- feat: add `extensionsExplore` setting to enable extensions explore UI. by
+  @sripasg in [#18686](https://github.com/google-gemini/gemini-cli/pull/18686)
+- feat(cli): defer devtools startup and integrate with F12 by @SandyTao520 in
+  [#18695](https://github.com/google-gemini/gemini-cli/pull/18695)
+- ui: update & subdue footer colors and animate progress indicator by
+  @keithguerin in
+  [#18570](https://github.com/google-gemini/gemini-cli/pull/18570)
+- test: add model-specific snapshots for coreTools by @aishaneeshah in
+  [#18707](https://github.com/google-gemini/gemini-cli/pull/18707)
+- ci: shard windows tests and fix event listener leaks by @NTaylorMullen in
+  [#18670](https://github.com/google-gemini/gemini-cli/pull/18670)
+- fix: allow `ask_user` tool in yolo mode by @jackwotherspoon in
+  [#18541](https://github.com/google-gemini/gemini-cli/pull/18541)
+- feat: redact disabled tools from system prompt (#13597) by @NTaylorMullen in
+  [#18613](https://github.com/google-gemini/gemini-cli/pull/18613)
+- Update Gemini.md to use the curent year on creating new files by @sehoon38 in
+  [#18460](https://github.com/google-gemini/gemini-cli/pull/18460)
+- Code review cleanup for thinking display by @jacob314 in
+  [#18720](https://github.com/google-gemini/gemini-cli/pull/18720)
+- fix(cli): hide scrollbars when in alternate buffer copy mode by @werdnum in
+  [#18354](https://github.com/google-gemini/gemini-cli/pull/18354)
+- Fix issues with rip grep by @gundermanc in
+  [#18756](https://github.com/google-gemini/gemini-cli/pull/18756)
+- fix(cli): fix history navigation regression after prompt autocomplete by
+  @sehoon38 in [#18752](https://github.com/google-gemini/gemini-cli/pull/18752)
+- chore: cleanup unused and add unlisted dependencies in packages/cli by
   @adamfweidman in
-  [#18196](https://github.com/google-gemini/gemini-cli/pull/18196)
-- Remove MCP servers on extension uninstall by @chrstnb in
-  [#18121](https://github.com/google-gemini/gemini-cli/pull/18121)
-- refactor: localize ACP error parsing logic to cli package by @bdmorgan in
-  [#18193](https://github.com/google-gemini/gemini-cli/pull/18193)
-- feat(core): Add A2A auth config types by @adamfweidman in
-  [#18205](https://github.com/google-gemini/gemini-cli/pull/18205)
-- Set default max attempts to 3 and use the common variable by @sehoon38 in
-  [#18209](https://github.com/google-gemini/gemini-cli/pull/18209)
-- feat(plan): add exit_plan_mode ui and prompt by @jerop in
-  [#18162](https://github.com/google-gemini/gemini-cli/pull/18162)
-- fix(test): improve test isolation and enable subagent evaluations by
-  @cocosheng-g in
-  [#18138](https://github.com/google-gemini/gemini-cli/pull/18138)
-- feat(plan): use custom deny messages in plan mode policies by @Adib234 in
-  [#18195](https://github.com/google-gemini/gemini-cli/pull/18195)
-- Match on extension ID when stopping extensions by @chrstnb in
-  [#18218](https://github.com/google-gemini/gemini-cli/pull/18218)
-- fix(core): Respect user's .gitignore preference by @xyrolle in
-  [#15482](https://github.com/google-gemini/gemini-cli/pull/15482)
-- docs: document GEMINI_CLI_HOME environment variable by @adamfweidman in
-  [#18219](https://github.com/google-gemini/gemini-cli/pull/18219)
-- chore(core): explicitly state plan storage path in prompt by @jerop in
-  [#18222](https://github.com/google-gemini/gemini-cli/pull/18222)
-- A2a admin setting by @DavidAPierce in
-  [#17868](https://github.com/google-gemini/gemini-cli/pull/17868)
-- feat(a2a): Add pluggable auth provider infrastructure by @adamfweidman in
-  [#17934](https://github.com/google-gemini/gemini-cli/pull/17934)
-- Fix handling of empty settings by @chrstnb in
-  [#18131](https://github.com/google-gemini/gemini-cli/pull/18131)
-- Reload skills when extensions change by @chrstnb in
-  [#18225](https://github.com/google-gemini/gemini-cli/pull/18225)
-- feat: Add markdown rendering to ask_user tool by @jackwotherspoon in
-  [#18211](https://github.com/google-gemini/gemini-cli/pull/18211)
-- Add telemetry to rewind by @Adib234 in
-  [#18122](https://github.com/google-gemini/gemini-cli/pull/18122)
-- feat(admin): add support for MCP configuration via admin controls (pt1) by
-  @skeshive in [#18223](https://github.com/google-gemini/gemini-cli/pull/18223)
-- feat(core): require user consent before MCP server OAuth by @ehedlund in
-  [#18132](https://github.com/google-gemini/gemini-cli/pull/18132)
-- fix(sandbox): propagate GOOGLE_GEMINI_BASE_URL&GOOGLE_VERTEX_BASE_URL env vars
-  by @skeshive in
-  [#18231](https://github.com/google-gemini/gemini-cli/pull/18231)
-- feat(ui): move user identity display to header by @sehoon38 in
-  [#18216](https://github.com/google-gemini/gemini-cli/pull/18216)
-- fix: enforce folder trust for workspace settings, skills, and context by
-  @galz10 in [#17596](https://github.com/google-gemini/gemini-cli/pull/17596)
+  [#18749](https://github.com/google-gemini/gemini-cli/pull/18749)
+- Fix issue where Gemini CLI creates tests in a new file by @gundermanc in
+  [#18409](https://github.com/google-gemini/gemini-cli/pull/18409)
+- feat(telemetry): Ensure experiment IDs are included in OpenTelemetry logs by
+  @kevin-ramdass in
+  [#18747](https://github.com/google-gemini/gemini-cli/pull/18747)
+- fix(patch): cherry-pick e9a9474 to release/v0.29.0-preview.0-pr-18840 to patch
+  version v0.29.0-preview.0 and create version 0.29.0-preview.1 by
+  @gemini-cli-robot in
+  [#18841](https://github.com/google-gemini/gemini-cli/pull/18841)
+- fix(patch): cherry-pick 08e8eea to release/v0.29.0-preview.1-pr-18855 to patch
+  version v0.29.0-preview.1 and create version 0.29.0-preview.2 by
+  @gemini-cli-robot in
+  [#18905](https://github.com/google-gemini/gemini-cli/pull/18905)
+- fix(patch): cherry-pick d0c6a56 to release/v0.29.0-preview.2-pr-18976 to patch
+  version v0.29.0-preview.2 and create version 0.29.0-preview.3 by
+  @gemini-cli-robot in
+  [#19023](https://github.com/google-gemini/gemini-cli/pull/19023)
+- fix(patch): cherry-pick e5ff202 to release/v0.29.0-preview.3-pr-19254 to patch
+  version v0.29.0-preview.3 and create version 0.29.0-preview.4 by
+  @gemini-cli-robot in
+  [#19264](https://github.com/google-gemini/gemini-cli/pull/19264)
+- fix(patch): cherry-pick 9590a09 to release/v0.29.0-preview.4-pr-18771 to patch
+  version v0.29.0-preview.4 and create version 0.29.0-preview.5 by
+  @gemini-cli-robot in
+  [#19274](https://github.com/google-gemini/gemini-cli/pull/19274)
 
 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.27.0...v0.28.0
+https://github.com/google-gemini/gemini-cli/compare/v0.28.2...v0.29.0

docs/changelogs/preview.md

@@ -1,6 +1,6 @@
-# Preview release: Release v0.29.0-preview.0
+# Preview release: v0.30.0-preview.1
 
-Released: February 10, 2026
+Released: February 19, 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).
@@ -13,355 +13,302 @@ npm install -g @google/gemini-cli@preview
 
 ## Highlights
 
-- **Plan Mode Enhancements**: Significant updates to Plan Mode, including new
-  commands, support for MCP servers, integration of planning artifacts, and
-  improved iteration guidance.
-- **Core Agent Improvements**: Enhancements to the core agent, including better
-  system prompt rigor, improved subagent definitions, and enhanced tool
-  execution limits.
-- **CLI UX/UI Updates**: Various UI and UX improvements, such as autocomplete in
-  the input prompt, updated approval mode labels, DevTools integration, and
-  improved header spacing.
-- **Tooling & Extension Updates**: Improvements to existing tools like
-  `ask_user` and `grep_search`, and new features for extension management.
-- **Bug Fixes**: Numerous bug fixes across the CLI and core, addressing issues
-  with interactive commands, memory leaks, permission checks, and more.
-- **Context and Tool Output Management**: Features for observation masking for
-  tool outputs, session-linked tool output storage, and persistence for masked
-  tool outputs.
+- **Initial SDK Package:** Introduced the initial SDK package with support for
+  custom skills and dynamic system instructions.
+- **Refined Plan Mode:** Refined Plan Mode with support for enabling skills,
+  improved agentic execution, and project exploration without planning.
+- **Enhanced CLI UI:** Enhanced CLI UI with a new clean UI toggle, minimal-mode
+  bleed-through, and support for Ctrl-Z suspension.
+- **`--policy` flag:** Added the `--policy` flag to support user-defined
+  policies.
+- **New Themes:** Added Solarized Dark and Solarized Light themes.
 
 ## What's Changed
 
-- fix: remove ask_user tool from non-interactive modes by jackwotherspoon in
-  [#18154](https://github.com/google-gemini/gemini-cli/pull/18154)
-- fix(cli): allow restricted .env loading in untrusted sandboxed folders by
-  galz10 in [#17806](https://github.com/google-gemini/gemini-cli/pull/17806)
-- Encourage agent to utilize ecosystem tools to perform work by gundermanc in
-  [#17881](https://github.com/google-gemini/gemini-cli/pull/17881)
-- feat(plan): unify workflow location in system prompt to optimize caching by
-  jerop in [#18258](https://github.com/google-gemini/gemini-cli/pull/18258)
-- feat(core): enable getUserTierName in config by sehoon38 in
-  [#18265](https://github.com/google-gemini/gemini-cli/pull/18265)
-- feat(core): add default execution limits for subagents by abhipatel12 in
-  [#18274](https://github.com/google-gemini/gemini-cli/pull/18274)
-- Fix issue where agent gets stuck at interactive commands. by gundermanc in
-  [#18272](https://github.com/google-gemini/gemini-cli/pull/18272)
-- chore(release): bump version to 0.29.0-nightly.20260203.71f46f116 by
-  gemini-cli-robot in
-  [#18243](https://github.com/google-gemini/gemini-cli/pull/18243)
-- feat(core): remove hardcoded policy bypass for local subagents by abhipatel12
-  in [#18153](https://github.com/google-gemini/gemini-cli/pull/18153)
-- feat(plan): implement plan slash command by Adib234 in
-  [#17698](https://github.com/google-gemini/gemini-cli/pull/17698)
-- feat: increase ask_user label limit to 16 characters by jackwotherspoon in
-  [#18320](https://github.com/google-gemini/gemini-cli/pull/18320)
-- Add information about the agent skills lifecycle and clarify docs-writer skill
-  metadata. by g-samroberts in
-  [#18234](https://github.com/google-gemini/gemini-cli/pull/18234)
-- feat(core): add enter_plan_mode tool by jerop in
-  [#18324](https://github.com/google-gemini/gemini-cli/pull/18324)
-- Stop showing an error message in /plan by Adib234 in
-  [#18333](https://github.com/google-gemini/gemini-cli/pull/18333)
-- fix(hooks): remove unnecessary logging for hook registration by abhipatel12 in
-  [#18332](https://github.com/google-gemini/gemini-cli/pull/18332)
-- fix(mcp): ensure MCP transport is closed to prevent memory leaks by cbcoutinho
-  in [#18054](https://github.com/google-gemini/gemini-cli/pull/18054)
-- feat(skills): implement linking for agent skills by MushuEE in
-  [#18295](https://github.com/google-gemini/gemini-cli/pull/18295)
-- Changelogs for 0.27.0 and 0.28.0-preview0 by g-samroberts in
-  [#18336](https://github.com/google-gemini/gemini-cli/pull/18336)
-- chore: correct docs as skills and hooks are stable by jackwotherspoon in
-  [#18358](https://github.com/google-gemini/gemini-cli/pull/18358)
-- feat(admin): Implement admin allowlist for MCP server configurations by
-  skeshive in [#18311](https://github.com/google-gemini/gemini-cli/pull/18311)
-- fix(core): add retry logic for transient SSL/TLS errors
-  ([#17318](https://github.com/google-gemini/gemini-cli/pull/17318)) by
-  ppgranger in [#18310](https://github.com/google-gemini/gemini-cli/pull/18310)
-- Add support for /extensions config command by chrstnb in
-  [#17895](https://github.com/google-gemini/gemini-cli/pull/17895)
-- fix(core): handle non-compliant mcpbridge responses from Xcode 26.3 by
-  peterfriese in
-  [#18376](https://github.com/google-gemini/gemini-cli/pull/18376)
-- feat(cli): Add W, B, E Vim motions and operator support by ademuri in
-  [#16209](https://github.com/google-gemini/gemini-cli/pull/16209)
-- fix: Windows Specific Agent Quality & System Prompt by scidomino in
-  [#18351](https://github.com/google-gemini/gemini-cli/pull/18351)
-- feat(plan): support replace tool in plan mode to edit plans by jerop in
-  [#18379](https://github.com/google-gemini/gemini-cli/pull/18379)
-- Improving memory tool instructions and eval testing by alisa-alisa in
-  [#18091](https://github.com/google-gemini/gemini-cli/pull/18091)
-- fix(cli): color extension link success message green by MushuEE in
-  [#18386](https://github.com/google-gemini/gemini-cli/pull/18386)
-- undo by jacob314 in
-  [#18147](https://github.com/google-gemini/gemini-cli/pull/18147)
-- feat(plan): add guidance on iterating on approved plans vs creating new plans
-  by jerop in [#18346](https://github.com/google-gemini/gemini-cli/pull/18346)
-- feat(plan): fix invalid tool calls in plan mode by Adib234 in
-  [#18352](https://github.com/google-gemini/gemini-cli/pull/18352)
-- feat(plan): integrate planning artifacts and tools into primary workflows by
-  jerop in [#18375](https://github.com/google-gemini/gemini-cli/pull/18375)
-- Fix permission check by scidomino in
-  [#18395](https://github.com/google-gemini/gemini-cli/pull/18395)
-- ux(polish) autocomplete in the input prompt by jacob314 in
-  [#18181](https://github.com/google-gemini/gemini-cli/pull/18181)
-- fix: resolve infinite loop when using 'Modify with external editor' by
-  ppgranger in [#17453](https://github.com/google-gemini/gemini-cli/pull/17453)
-- feat: expand verify-release to macOS and Windows by yunaseoul in
-  [#18145](https://github.com/google-gemini/gemini-cli/pull/18145)
-- feat(plan): implement support for MCP servers in Plan mode by Adib234 in
-  [#18229](https://github.com/google-gemini/gemini-cli/pull/18229)
-- chore: update folder trust error messaging by galz10 in
-  [#18402](https://github.com/google-gemini/gemini-cli/pull/18402)
-- feat(plan): create a metric for execution of plans generated in plan mode by
-  Adib234 in [#18236](https://github.com/google-gemini/gemini-cli/pull/18236)
-- perf(ui): optimize stripUnsafeCharacters with regex by gsquared94 in
-  [#18413](https://github.com/google-gemini/gemini-cli/pull/18413)
-- feat(context): implement observation masking for tool outputs by abhipatel12
-  in [#18389](https://github.com/google-gemini/gemini-cli/pull/18389)
-- feat(core,cli): implement session-linked tool output storage and cleanup by
-  abhipatel12 in
-  [#18416](https://github.com/google-gemini/gemini-cli/pull/18416)
-- Shorten temp directory by joshualitt in
-  [#17901](https://github.com/google-gemini/gemini-cli/pull/17901)
-- feat(plan): add behavioral evals for plan mode by jerop in
-  [#18437](https://github.com/google-gemini/gemini-cli/pull/18437)
-- Add extension registry client by chrstnb in
-  [#18396](https://github.com/google-gemini/gemini-cli/pull/18396)
-- Enable extension config by default by chrstnb in
-  [#18447](https://github.com/google-gemini/gemini-cli/pull/18447)
-- Automatically generate change logs on release by g-samroberts in
-  [#18401](https://github.com/google-gemini/gemini-cli/pull/18401)
-- Remove previewFeatures and default to Gemini 3 by sehoon38 in
-  [#18414](https://github.com/google-gemini/gemini-cli/pull/18414)
-- feat(admin): apply MCP allowlist to extensions & gemini mcp list command by
-  skeshive in [#18442](https://github.com/google-gemini/gemini-cli/pull/18442)
-- fix(cli): improve focus navigation for interactive and background shells by
-  galz10 in [#18343](https://github.com/google-gemini/gemini-cli/pull/18343)
-- Add shortcuts hint and panel for discoverability by LyalinDotCom in
-  [#18035](https://github.com/google-gemini/gemini-cli/pull/18035)
-- fix(config): treat system settings as read-only during migration and warn user
-  by spencer426 in
-  [#18277](https://github.com/google-gemini/gemini-cli/pull/18277)
-- feat(plan): add positive test case and update eval stability policy by jerop
-  in [#18457](https://github.com/google-gemini/gemini-cli/pull/18457)
-- fix- windows: add shell: true for spawnSync to fix EINVAL with .cmd editors by
-  zackoch in [#18408](https://github.com/google-gemini/gemini-cli/pull/18408)
-- bug(core): Fix bug when saving plans. by joshualitt in
-  [#18465](https://github.com/google-gemini/gemini-cli/pull/18465)
-- Refactor atCommandProcessor by scidomino in
-  [#18461](https://github.com/google-gemini/gemini-cli/pull/18461)
-- feat(core): implement persistence and resumption for masked tool outputs by
-  abhipatel12 in
-  [#18451](https://github.com/google-gemini/gemini-cli/pull/18451)
-- refactor: simplify tool output truncation to single config by SandyTao520 in
-  [#18446](https://github.com/google-gemini/gemini-cli/pull/18446)
-- bug(core): Ensure storage is initialized early, even if config is not. by
-  joshualitt in [#18471](https://github.com/google-gemini/gemini-cli/pull/18471)
-- chore: Update build-and-start script to support argument forwarding by
-  Abhijit-2592 in
-  [#18241](https://github.com/google-gemini/gemini-cli/pull/18241)
-- fix(core): prevent subagent bypass in plan mode by jerop in
-  [#18484](https://github.com/google-gemini/gemini-cli/pull/18484)
-- feat(cli): add WebSocket-based network logging and streaming chunk support by
-  SandyTao520 in
-  [#18383](https://github.com/google-gemini/gemini-cli/pull/18383)
-- feat(cli): update approval modes UI by jerop in
-  [#18476](https://github.com/google-gemini/gemini-cli/pull/18476)
-- fix(cli): reload skills and agents on extension restart by NTaylorMullen in
-  [#18411](https://github.com/google-gemini/gemini-cli/pull/18411)
-- fix(core): expand excludeTools with legacy aliases for renamed tools by
-  SandyTao520 in
-  [#18498](https://github.com/google-gemini/gemini-cli/pull/18498)
-- feat(core): overhaul system prompt for rigor, integrity, and intent alignment
-  by NTaylorMullen in
-  [#17263](https://github.com/google-gemini/gemini-cli/pull/17263)
-- Patch for generate changelog docs yaml file by g-samroberts in
-  [#18496](https://github.com/google-gemini/gemini-cli/pull/18496)
-- Code review fixes for show question mark pr. by jacob314 in
-  [#18480](https://github.com/google-gemini/gemini-cli/pull/18480)
-- fix(cli): add SS3 Shift+Tab support for Windows terminals by ThanhNguyxn in
-  [#18187](https://github.com/google-gemini/gemini-cli/pull/18187)
-- chore: remove redundant planning prompt from final shell by jerop in
-  [#18528](https://github.com/google-gemini/gemini-cli/pull/18528)
-- docs: require pr-creator skill for PR generation by NTaylorMullen in
-  [#18536](https://github.com/google-gemini/gemini-cli/pull/18536)
-- chore: update colors for ask_user dialog by jackwotherspoon in
-  [#18543](https://github.com/google-gemini/gemini-cli/pull/18543)
-- feat(core): exempt high-signal tools from output masking by abhipatel12 in
-  [#18545](https://github.com/google-gemini/gemini-cli/pull/18545)
-- refactor(core): remove memory tool instructions from Gemini 3 prompt by
-  NTaylorMullen in
-  [#18559](https://github.com/google-gemini/gemini-cli/pull/18559)
-- chore: remove feedback instruction from system prompt by NTaylorMullen in
-  [#18560](https://github.com/google-gemini/gemini-cli/pull/18560)
-- feat(context): add remote configuration for tool output masking thresholds by
-  abhipatel12 in
-  [#18553](https://github.com/google-gemini/gemini-cli/pull/18553)
-- feat(core): pause agent timeout budget while waiting for tool confirmation by
-  abhipatel12 in
-  [#18415](https://github.com/google-gemini/gemini-cli/pull/18415)
-- refactor(config): remove experimental.enableEventDrivenScheduler setting by
-  abhipatel12 in
-  [#17924](https://github.com/google-gemini/gemini-cli/pull/17924)
-- feat(cli): truncate shell output in UI history and improve active shell
-  display by jwhelangoog in
-  [#17438](https://github.com/google-gemini/gemini-cli/pull/17438)
-- refactor(cli): switch useToolScheduler to event-driven engine by abhipatel12
-  in [#18565](https://github.com/google-gemini/gemini-cli/pull/18565)
-- fix(core): correct escaped interpolation in system prompt by NTaylorMullen in
-  [#18557](https://github.com/google-gemini/gemini-cli/pull/18557)
-- propagate abortSignal by scidomino in
-  [#18477](https://github.com/google-gemini/gemini-cli/pull/18477)
-- feat(core): conditionally include ctrl+f prompt based on interactive shell
-  setting by NTaylorMullen in
-  [#18561](https://github.com/google-gemini/gemini-cli/pull/18561)
-- fix(core): ensure enter_plan_mode tool registration respects experimental.plan
-  by jerop in [#18587](https://github.com/google-gemini/gemini-cli/pull/18587)
-- feat(core): transition sub-agents to XML format and improve definitions by
-  NTaylorMullen in
-  [#18555](https://github.com/google-gemini/gemini-cli/pull/18555)
-- docs: Add Plan Mode documentation by jerop in
-  [#18582](https://github.com/google-gemini/gemini-cli/pull/18582)
-- chore: strengthen validation guidance in system prompt by NTaylorMullen in
-  [#18544](https://github.com/google-gemini/gemini-cli/pull/18544)
-- Fix newline insertion bug in replace tool by werdnum in
-  [#18595](https://github.com/google-gemini/gemini-cli/pull/18595)
-- fix(evals): update save_memory evals and simplify tool description by
-  NTaylorMullen in
-  [#18610](https://github.com/google-gemini/gemini-cli/pull/18610)
-- chore(evals): update validation_fidelity_pre_existing_errors to USUALLY_PASSES
-  by NTaylorMullen in
-  [#18617](https://github.com/google-gemini/gemini-cli/pull/18617)
-- fix: shorten tool call IDs and fix duplicate tool name in truncated output
-  filenames by SandyTao520 in
-  [#18600](https://github.com/google-gemini/gemini-cli/pull/18600)
-- feat(cli): implement atomic writes and safety checks for trusted folders by
-  galz10 in [#18406](https://github.com/google-gemini/gemini-cli/pull/18406)
-- Remove relative docs links by chrstnb in
-  [#18650](https://github.com/google-gemini/gemini-cli/pull/18650)
-- docs: add legacy snippets convention to GEMINI.md by NTaylorMullen in
-  [#18597](https://github.com/google-gemini/gemini-cli/pull/18597)
-- fix(chore): Support linting for cjs by aswinashok44 in
-  [#18639](https://github.com/google-gemini/gemini-cli/pull/18639)
-- feat: move shell efficiency guidelines to tool description by NTaylorMullen in
-  [#18614](https://github.com/google-gemini/gemini-cli/pull/18614)
-- Added "" as default value, since getText() used to expect a string only and
-  thus crashed when undefined... Fixes #18076 by 019-Abhi in
-  [#18099](https://github.com/google-gemini/gemini-cli/pull/18099)
-- Allow @-includes outside of workspaces (with permission) by scidomino in
-  [#18470](https://github.com/google-gemini/gemini-cli/pull/18470)
-- chore: make ask_user header description more clear by jackwotherspoon in
-  [#18657](https://github.com/google-gemini/gemini-cli/pull/18657)
-- refactor(core): model-dependent tool definitions by aishaneeshah in
-  [#18563](https://github.com/google-gemini/gemini-cli/pull/18563)
-- Harded code assist converter. by jacob314 in
-  [#18656](https://github.com/google-gemini/gemini-cli/pull/18656)
-- bug(core): Fix minor bug in migration logic. by joshualitt in
-  [#18661](https://github.com/google-gemini/gemini-cli/pull/18661)
-- feat: enable plan mode experiment in settings by jerop in
-  [#18636](https://github.com/google-gemini/gemini-cli/pull/18636)
-- refactor: push isValidPath() into parsePastedPaths() by scidomino in
-  [#18664](https://github.com/google-gemini/gemini-cli/pull/18664)
-- fix(cli): correct 'esc to cancel' position and restore duration display by
-  NTaylorMullen in
-  [#18534](https://github.com/google-gemini/gemini-cli/pull/18534)
-- feat(cli): add DevTools integration with gemini-cli-devtools by SandyTao520 in
-  [#18648](https://github.com/google-gemini/gemini-cli/pull/18648)
-- chore: remove unused exports and redundant hook files by SandyTao520 in
-  [#18681](https://github.com/google-gemini/gemini-cli/pull/18681)
-- Fix number of lines being reported in rewind confirmation dialog by Adib234 in
-  [#18675](https://github.com/google-gemini/gemini-cli/pull/18675)
-- feat(cli): disable folder trust in headless mode by galz10 in
-  [#18407](https://github.com/google-gemini/gemini-cli/pull/18407)
-- Disallow unsafe type assertions by gundermanc in
-  [#18688](https://github.com/google-gemini/gemini-cli/pull/18688)
-- Change event type for release by g-samroberts in
-  [#18693](https://github.com/google-gemini/gemini-cli/pull/18693)
-- feat: handle multiple dynamic context filenames in system prompt by
-  NTaylorMullen in
-  [#18598](https://github.com/google-gemini/gemini-cli/pull/18598)
-- Properly parse at-commands with narrow non-breaking spaces by scidomino in
-  [#18677](https://github.com/google-gemini/gemini-cli/pull/18677)
-- refactor(core): centralize core tool definitions and support model-specific
-  schemas by aishaneeshah in
-  [#18662](https://github.com/google-gemini/gemini-cli/pull/18662)
-- feat(core): Render memory hierarchically in context. by joshualitt in
-  [#18350](https://github.com/google-gemini/gemini-cli/pull/18350)
-- feat: Ctrl+O to expand paste placeholder by jackwotherspoon in
-  [#18103](https://github.com/google-gemini/gemini-cli/pull/18103)
-- fix(cli): Improve header spacing by NTaylorMullen in
-  [#18531](https://github.com/google-gemini/gemini-cli/pull/18531)
-- Feature/quota visibility 16795 by spencer426 in
-  [#18203](https://github.com/google-gemini/gemini-cli/pull/18203)
-- Inline thinking bubbles with summary/full modes by LyalinDotCom in
-  [#18033](https://github.com/google-gemini/gemini-cli/pull/18033)
-- docs: remove TOC marker from Plan Mode header by jerop in
-  [#18678](https://github.com/google-gemini/gemini-cli/pull/18678)
-- fix(ui): remove redundant newlines in Gemini messages by NTaylorMullen in
-  [#18538](https://github.com/google-gemini/gemini-cli/pull/18538)
-- test(cli): fix AppContainer act() warnings and improve waitFor resilience by
-  NTaylorMullen in
-  [#18676](https://github.com/google-gemini/gemini-cli/pull/18676)
-- refactor(core): refine Security & System Integrity section in system prompt by
-  NTaylorMullen in
-  [#18601](https://github.com/google-gemini/gemini-cli/pull/18601)
-- Fix layout rounding. by gundermanc in
-  [#18667](https://github.com/google-gemini/gemini-cli/pull/18667)
-- docs(skills): enhance pr-creator safety and interactivity by NTaylorMullen in
-  [#18616](https://github.com/google-gemini/gemini-cli/pull/18616)
-- test(core): remove hardcoded model from TestRig by NTaylorMullen in
-  [#18710](https://github.com/google-gemini/gemini-cli/pull/18710)
-- feat(core): optimize sub-agents system prompt intro by NTaylorMullen in
-  [#18608](https://github.com/google-gemini/gemini-cli/pull/18608)
-- feat(cli): update approval mode labels and shortcuts per latest UX spec by
-  jerop in [#18698](https://github.com/google-gemini/gemini-cli/pull/18698)
-- fix(plan): update persistent approval mode setting by Adib234 in
-  [#18638](https://github.com/google-gemini/gemini-cli/pull/18638)
-- fix: move toasts location to left side by jackwotherspoon in
-  [#18705](https://github.com/google-gemini/gemini-cli/pull/18705)
-- feat(routing): restrict numerical routing to Gemini 3 family by mattKorwel in
-  [#18478](https://github.com/google-gemini/gemini-cli/pull/18478)
-- fix(ide): fix ide nudge setting by skeshive in
-  [#18733](https://github.com/google-gemini/gemini-cli/pull/18733)
-- fix(core): standardize tool formatting in system prompts by NTaylorMullen in
-  [#18615](https://github.com/google-gemini/gemini-cli/pull/18615)
-- chore: consolidate to green in ask user dialog by jackwotherspoon in
-  [#18734](https://github.com/google-gemini/gemini-cli/pull/18734)
-- feat: add extensionsExplore setting to enable extensions explore UI. by
-  sripasg in [#18686](https://github.com/google-gemini/gemini-cli/pull/18686)
-- feat(cli): defer devtools startup and integrate with F12 by SandyTao520 in
-  [#18695](https://github.com/google-gemini/gemini-cli/pull/18695)
-- ui: update & subdue footer colors and animate progress indicator by
-  keithguerin in
-  [#18570](https://github.com/google-gemini/gemini-cli/pull/18570)
-- test: add model-specific snapshots for coreTools by aishaneeshah in
-  [#18707](https://github.com/google-gemini/gemini-cli/pull/18707)
-- ci: shard windows tests and fix event listener leaks by NTaylorMullen in
-  [#18670](https://github.com/google-gemini/gemini-cli/pull/18670)
-- fix: allow ask_user tool in yolo mode by jackwotherspoon in
-  [#18541](https://github.com/google-gemini/gemini-cli/pull/18541)
-- feat: redact disabled tools from system prompt
-  ([#13597](https://github.com/google-gemini/gemini-cli/pull/13597)) by
-  NTaylorMullen in
-  [#18613](https://github.com/google-gemini/gemini-cli/pull/18613)
-- Update Gemini.md to use the curent year on creating new files by sehoon38 in
-  [#18460](https://github.com/google-gemini/gemini-cli/pull/18460)
-- Code review cleanup for thinking display by jacob314 in
-  [#18720](https://github.com/google-gemini/gemini-cli/pull/18720)
-- fix(cli): hide scrollbars when in alternate buffer copy mode by werdnum in
-  [#18354](https://github.com/google-gemini/gemini-cli/pull/18354)
-- Fix issues with rip grep by gundermanc in
-  [#18756](https://github.com/google-gemini/gemini-cli/pull/18756)
-- fix(cli): fix history navigation regression after prompt autocomplete by
-  sehoon38 in [#18752](https://github.com/google-gemini/gemini-cli/pull/18752)
-- chore: cleanup unused and add unlisted dependencies in packages/cli by
-  adamfweidman in
-  [#18749](https://github.com/google-gemini/gemini-cli/pull/18749)
-- Fix issue where Gemini CLI creates tests in a new file by gundermanc in
-  [#18409](https://github.com/google-gemini/gemini-cli/pull/18409)
-- feat(telemetry): Ensure experiment IDs are included in OpenTelemetry logs by
-  kevin-ramdass in
-  [#18747](https://github.com/google-gemini/gemini-cli/pull/18747)
+- fix(patch): cherry-pick 261788c to release/v0.30.0-preview.0-pr-19453 to patch
+  version v0.30.0-preview.0 and create version 0.30.0-preview.1 by
+  @gemini-cli-robot in
+  [#19490](https://github.com/google-gemini/gemini-cli/pull/19490)
+- feat(ux): added text wrapping capabilities to markdown tables by @devr0306 in
+  [#18240](https://github.com/google-gemini/gemini-cli/pull/18240)
+- Revert "fix(mcp): ensure MCP transport is closed to prevent memory leaks" by
+  @skeshive in [#18771](https://github.com/google-gemini/gemini-cli/pull/18771)
+- chore(release): bump version to 0.30.0-nightly.20260210.a2174751d by
+  @gemini-cli-robot in
+  [#18772](https://github.com/google-gemini/gemini-cli/pull/18772)
+- chore: cleanup unused and add unlisted dependencies in packages/core by
+  @adamfweidman in
+  [#18762](https://github.com/google-gemini/gemini-cli/pull/18762)
+- chore(core): update activate_skill prompt verbiage to be more direct by
+  @NTaylorMullen in
+  [#18605](https://github.com/google-gemini/gemini-cli/pull/18605)
+- Add autoconfigure memory usage setting to the dialog by @jacob314 in
+  [#18510](https://github.com/google-gemini/gemini-cli/pull/18510)
+- fix(core): prevent race condition in policy persistence by @braddux in
+  [#18506](https://github.com/google-gemini/gemini-cli/pull/18506)
+- fix(evals): prevent false positive in hierarchical memory test by
+  @Abhijit-2592 in
+  [#18777](https://github.com/google-gemini/gemini-cli/pull/18777)
+- test(evals): mark all `save_memory` evals as `USUALLY_PASSES` due to
+  unreliability by @jerop in
+  [#18786](https://github.com/google-gemini/gemini-cli/pull/18786)
+- feat(cli): add setting to hide shortcuts hint UI by @LyalinDotCom in
+  [#18562](https://github.com/google-gemini/gemini-cli/pull/18562)
+- feat(core): formalize 5-phase sequential planning workflow by @jerop in
+  [#18759](https://github.com/google-gemini/gemini-cli/pull/18759)
+- Introduce limits for search results. by @gundermanc in
+  [#18767](https://github.com/google-gemini/gemini-cli/pull/18767)
+- fix(cli): allow closing debug console after auto-open via flicker by
+  @SandyTao520 in
+  [#18795](https://github.com/google-gemini/gemini-cli/pull/18795)
+- feat(masking): enable tool output masking by default by @abhipatel12 in
+  [#18564](https://github.com/google-gemini/gemini-cli/pull/18564)
+- perf(ui): optimize table rendering by memoizing styled characters by @devr0306
+  in [#18770](https://github.com/google-gemini/gemini-cli/pull/18770)
+- feat: multi-line text answers in ask-user tool by @jackwotherspoon in
+  [#18741](https://github.com/google-gemini/gemini-cli/pull/18741)
+- perf(cli): truncate large debug logs and limit message history by @mattKorwel
+  in [#18663](https://github.com/google-gemini/gemini-cli/pull/18663)
+- fix(core): complete MCP discovery when configured servers are skipped by
+  @LyalinDotCom in
+  [#18586](https://github.com/google-gemini/gemini-cli/pull/18586)
+- fix(core): cache CLI version to ensure consistency during sessions by
+  @sehoon38 in [#18793](https://github.com/google-gemini/gemini-cli/pull/18793)
+- fix(cli): resolve double rendering in shpool and address vscode lint warnings
+  by @braddux in
+  [#18704](https://github.com/google-gemini/gemini-cli/pull/18704)
+- feat(plan): document and validate Plan Mode policy overrides by @jerop in
+  [#18825](https://github.com/google-gemini/gemini-cli/pull/18825)
+- Fix pressing any key to exit select mode. by @jacob314 in
+  [#18421](https://github.com/google-gemini/gemini-cli/pull/18421)
+- fix(cli): update F12 behavior to only open drawer if browser fails by
+  @SandyTao520 in
+  [#18829](https://github.com/google-gemini/gemini-cli/pull/18829)
+- feat(plan): allow skills to be enabled in plan mode by @Adib234 in
+  [#18817](https://github.com/google-gemini/gemini-cli/pull/18817)
+- docs(plan): add documentation for plan mode tools by @jerop in
+  [#18827](https://github.com/google-gemini/gemini-cli/pull/18827)
+- Remove experimental note in extension settings docs by @chrstnb in
+  [#18822](https://github.com/google-gemini/gemini-cli/pull/18822)
+- Update prompt and grep tool definition to limit context size by @gundermanc in
+  [#18780](https://github.com/google-gemini/gemini-cli/pull/18780)
+- docs(plan): add `ask_user` tool documentation by @jerop in
+  [#18830](https://github.com/google-gemini/gemini-cli/pull/18830)
+- Revert unintended credentials exposure by @Adib234 in
+  [#18840](https://github.com/google-gemini/gemini-cli/pull/18840)
+- feat(core): update internal utility models to Gemini 3 by @SandyTao520 in
+  [#18773](https://github.com/google-gemini/gemini-cli/pull/18773)
+- feat(a2a): add value-resolver for auth credential resolution by @adamfweidman
+  in [#18653](https://github.com/google-gemini/gemini-cli/pull/18653)
+- Removed getPlainTextLength by @devr0306 in
+  [#18848](https://github.com/google-gemini/gemini-cli/pull/18848)
+- More grep prompt tweaks by @gundermanc in
+  [#18846](https://github.com/google-gemini/gemini-cli/pull/18846)
+- refactor(cli): Reactive useSettingsStore hook by @psinha40898 in
+  [#14915](https://github.com/google-gemini/gemini-cli/pull/14915)
+- fix(mcp): Ensure that stdio MCP server execution has the `GEMINI_CLI=1` env
+  variable populated. by @richieforeman in
+  [#18832](https://github.com/google-gemini/gemini-cli/pull/18832)
+- fix(core): improve headless mode detection for flags and query args by @galz10
+  in [#18855](https://github.com/google-gemini/gemini-cli/pull/18855)
+- refactor(cli): simplify UI and remove legacy inline tool confirmation logic by
+  @abhipatel12 in
+  [#18566](https://github.com/google-gemini/gemini-cli/pull/18566)
+- feat(cli): deprecate --allowed-tools and excludeTools in favor of policy
+  engine by @Abhijit-2592 in
+  [#18508](https://github.com/google-gemini/gemini-cli/pull/18508)
+- fix(workflows): improve maintainer detection for automated PR actions by
+  @bdmorgan in [#18869](https://github.com/google-gemini/gemini-cli/pull/18869)
+- refactor(cli): consolidate useToolScheduler and delete legacy implementation
+  by @abhipatel12 in
+  [#18567](https://github.com/google-gemini/gemini-cli/pull/18567)
+- Update changelog for v0.28.0 and v0.29.0-preview0 by @g-samroberts in
+  [#18819](https://github.com/google-gemini/gemini-cli/pull/18819)
+- fix(core): ensure sub-agents are registered regardless of tools.allowed by
+  @mattKorwel in
+  [#18870](https://github.com/google-gemini/gemini-cli/pull/18870)
+- Show notification when there's a conflict with an extensions command by
+  @chrstnb in [#17890](https://github.com/google-gemini/gemini-cli/pull/17890)
+- fix(cli): dismiss '?' shortcuts help on hotkeys and active states by
+  @LyalinDotCom in
+  [#18583](https://github.com/google-gemini/gemini-cli/pull/18583)
+- fix(core): prioritize conditional policy rules and harden Plan Mode by
+  @Abhijit-2592 in
+  [#18882](https://github.com/google-gemini/gemini-cli/pull/18882)
+- feat(core): refine Plan Mode system prompt for agentic execution by
+  @NTaylorMullen in
+  [#18799](https://github.com/google-gemini/gemini-cli/pull/18799)
+- feat(plan): create metrics for usage of `AskUser` tool by @Adib234 in
+  [#18820](https://github.com/google-gemini/gemini-cli/pull/18820)
+- feat(cli): support Ctrl-Z suspension by @scidomino in
+  [#18931](https://github.com/google-gemini/gemini-cli/pull/18931)
+- fix(github-actions): use robot PAT for release creation to trigger release
+  notes by @SandyTao520 in
+  [#18794](https://github.com/google-gemini/gemini-cli/pull/18794)
+- feat: add strict seatbelt profiles and remove unusable closed profiles by
+  @SandyTao520 in
+  [#18876](https://github.com/google-gemini/gemini-cli/pull/18876)
+- chore: cleanup unused and add unlisted dependencies in packages/a2a-server by
+  @adamfweidman in
+  [#18916](https://github.com/google-gemini/gemini-cli/pull/18916)
+- fix(plan): isolate plan files per session by @Adib234 in
+  [#18757](https://github.com/google-gemini/gemini-cli/pull/18757)
+- fix: character truncation in raw markdown mode by @jackwotherspoon in
+  [#18938](https://github.com/google-gemini/gemini-cli/pull/18938)
+- feat(cli): prototype clean UI toggle and minimal-mode bleed-through by
+  @LyalinDotCom in
+  [#18683](https://github.com/google-gemini/gemini-cli/pull/18683)
+- ui(polish) blend background color with theme by @jacob314 in
+  [#18802](https://github.com/google-gemini/gemini-cli/pull/18802)
+- Add generic searchable list to back settings and extensions by @chrstnb in
+  [#18838](https://github.com/google-gemini/gemini-cli/pull/18838)
+- feat(ui): align `AskUser` color scheme with UX spec by @jerop in
+  [#18943](https://github.com/google-gemini/gemini-cli/pull/18943)
+- Hide AskUser tool validation errors from UI (agent self-corrects) by @jerop in
+  [#18954](https://github.com/google-gemini/gemini-cli/pull/18954)
+- bug(cli) fix flicker due to AppContainer continuous initialization by
+  @jacob314 in [#18958](https://github.com/google-gemini/gemini-cli/pull/18958)
+- feat(admin): Add admin controls documentation by @skeshive in
+  [#18644](https://github.com/google-gemini/gemini-cli/pull/18644)
+- feat(cli): disable ctrl-s shortcut outside of alternate buffer mode by
+  @jacob314 in [#18887](https://github.com/google-gemini/gemini-cli/pull/18887)
+- fix(vim): vim support that feels (more) complete by @ppgranger in
+  [#18755](https://github.com/google-gemini/gemini-cli/pull/18755)
+- feat(policy): add --policy flag for user defined policies by @allenhutchison
+  in [#18500](https://github.com/google-gemini/gemini-cli/pull/18500)
+- Update installation guide by @g-samroberts in
+  [#18823](https://github.com/google-gemini/gemini-cli/pull/18823)
+- refactor(core): centralize tool definitions (Group 1: replace, search, grep)
+  by @aishaneeshah in
+  [#18944](https://github.com/google-gemini/gemini-cli/pull/18944)
+- refactor(cli): finalize event-driven transition and remove interaction bridge
+  by @abhipatel12 in
+  [#18569](https://github.com/google-gemini/gemini-cli/pull/18569)
+- Fix drag and drop escaping by @scidomino in
+  [#18965](https://github.com/google-gemini/gemini-cli/pull/18965)
+- feat(sdk): initial package bootstrap for SDK by @mbleigh in
+  [#18861](https://github.com/google-gemini/gemini-cli/pull/18861)
+- feat(sdk): implements SessionContext for SDK tool calls by @mbleigh in
+  [#18862](https://github.com/google-gemini/gemini-cli/pull/18862)
+- fix(plan): make question type required in AskUser tool by @Adib234 in
+  [#18959](https://github.com/google-gemini/gemini-cli/pull/18959)
+- fix(core): ensure --yolo does not force headless mode by @NTaylorMullen in
+  [#18976](https://github.com/google-gemini/gemini-cli/pull/18976)
+- refactor(core): adopt `CoreToolCallStatus` enum for type safety by @jerop in
+  [#18998](https://github.com/google-gemini/gemini-cli/pull/18998)
+- Enable in-CLI extension management commands for team by @chrstnb in
+  [#18957](https://github.com/google-gemini/gemini-cli/pull/18957)
+- Adjust lint rules to avoid unnecessary warning. by @scidomino in
+  [#18970](https://github.com/google-gemini/gemini-cli/pull/18970)
+- fix(vscode): resolve unsafe type assertion lint errors by @ehedlund in
+  [#19006](https://github.com/google-gemini/gemini-cli/pull/19006)
+- Remove unnecessary eslint config file by @scidomino in
+  [#19015](https://github.com/google-gemini/gemini-cli/pull/19015)
+- fix(core): Prevent loop detection false positives on lists with long shared
+  prefixes by @SandyTao520 in
+  [#18975](https://github.com/google-gemini/gemini-cli/pull/18975)
+- feat(core): fallback to chat-base when using unrecognized models for chat by
+  @SandyTao520 in
+  [#19016](https://github.com/google-gemini/gemini-cli/pull/19016)
+- docs: fix inconsistent commandRegex example in policy engine by @NTaylorMullen
+  in [#19027](https://github.com/google-gemini/gemini-cli/pull/19027)
+- fix(plan): persist the approval mode in UI even when agent is thinking by
+  @Adib234 in [#18955](https://github.com/google-gemini/gemini-cli/pull/18955)
+- feat(sdk): Implement dynamic system instructions by @mbleigh in
+  [#18863](https://github.com/google-gemini/gemini-cli/pull/18863)
+- Docs: Refresh docs to organize and standardize reference materials. by
+  @jkcinouye in [#18403](https://github.com/google-gemini/gemini-cli/pull/18403)
+- fix windows escaping (and broken tests) by @scidomino in
+  [#19011](https://github.com/google-gemini/gemini-cli/pull/19011)
+- refactor: use `CoreToolCallStatus` in the the history data model by @jerop in
+  [#19033](https://github.com/google-gemini/gemini-cli/pull/19033)
+- feat(cleanup): enable 30-day session retention by default by @skeshive in
+  [#18854](https://github.com/google-gemini/gemini-cli/pull/18854)
+- feat(plan): hide plan write and edit operations on plans in Plan Mode by
+  @jerop in [#19012](https://github.com/google-gemini/gemini-cli/pull/19012)
+- bug(ui) fix flicker refreshing background color by @jacob314 in
+  [#19041](https://github.com/google-gemini/gemini-cli/pull/19041)
+- chore: fix dep vulnerabilities by @scidomino in
+  [#19036](https://github.com/google-gemini/gemini-cli/pull/19036)
+- Revamp automated changelog skill by @g-samroberts in
+  [#18974](https://github.com/google-gemini/gemini-cli/pull/18974)
+- feat(sdk): implement support for custom skills by @mbleigh in
+  [#19031](https://github.com/google-gemini/gemini-cli/pull/19031)
+- refactor(core): complete centralization of core tool definitions by
+  @aishaneeshah in
+  [#18991](https://github.com/google-gemini/gemini-cli/pull/18991)
+- feat: add /commands reload to refresh custom TOML commands by @korade-krushna
+  in [#19078](https://github.com/google-gemini/gemini-cli/pull/19078)
+- fix(cli): wrap terminal capability queries in hidden sequence by @srithreepo
+  in [#19080](https://github.com/google-gemini/gemini-cli/pull/19080)
+- fix(workflows): fix GitHub App token permissions for maintainer detection by
+  @bdmorgan in [#19139](https://github.com/google-gemini/gemini-cli/pull/19139)
+- test: fix hook integration test flakiness on Windows CI by @NTaylorMullen in
+  [#18665](https://github.com/google-gemini/gemini-cli/pull/18665)
+- fix(core): Encourage non-interactive flags for scaffolding commands by
+  @NTaylorMullen in
+  [#18804](https://github.com/google-gemini/gemini-cli/pull/18804)
+- fix(core): propagate User-Agent header to setup-phase CodeAssist API calls by
+  @gsquared94 in
+  [#19182](https://github.com/google-gemini/gemini-cli/pull/19182)
+- docs: document .agents/skills alias and discovery precedence by @kevmoo in
+  [#19166](https://github.com/google-gemini/gemini-cli/pull/19166)
+- feat(cli): add loading state to new agents notification by @sehoon38 in
+  [#19190](https://github.com/google-gemini/gemini-cli/pull/19190)
+- Add base branch to workflow. by @g-samroberts in
+  [#19189](https://github.com/google-gemini/gemini-cli/pull/19189)
+- feat(cli): handle invalid model names in useQuotaAndFallback by @sehoon38 in
+  [#19222](https://github.com/google-gemini/gemini-cli/pull/19222)
+- docs: custom themes in extensions by @jackwotherspoon in
+  [#19219](https://github.com/google-gemini/gemini-cli/pull/19219)
+- Disable workspace settings when starting GCLI in the home directory. by
+  @kevinjwang1 in
+  [#19034](https://github.com/google-gemini/gemini-cli/pull/19034)
+- feat(cli): refactor model command to support set and manage subcommands by
+  @sehoon38 in [#19221](https://github.com/google-gemini/gemini-cli/pull/19221)
+- Add refresh/reload aliases to slash command subcommands by @korade-krushna in
+  [#19218](https://github.com/google-gemini/gemini-cli/pull/19218)
+- refactor: consolidate development rules and add cli guidelines by @jacob314 in
+  [#19214](https://github.com/google-gemini/gemini-cli/pull/19214)
+- chore(ui): remove outdated tip about model routing by @sehoon38 in
+  [#19226](https://github.com/google-gemini/gemini-cli/pull/19226)
+- feat(core): support custom reasoning models by default by @NTaylorMullen in
+  [#19227](https://github.com/google-gemini/gemini-cli/pull/19227)
+- Add Solarized Dark and Solarized Light themes by @rmedranollamas in
+  [#19064](https://github.com/google-gemini/gemini-cli/pull/19064)
+- fix(telemetry): replace JSON.stringify with safeJsonStringify in file
+  exporters by @gsquared94 in
+  [#19244](https://github.com/google-gemini/gemini-cli/pull/19244)
+- feat(telemetry): add keychain availability and token storage metrics by
+  @abhipatel12 in
+  [#18971](https://github.com/google-gemini/gemini-cli/pull/18971)
+- feat(cli): update approval mode cycle order by @jerop in
+  [#19254](https://github.com/google-gemini/gemini-cli/pull/19254)
+- refactor(cli): code review cleanup fix for tab+tab by @jacob314 in
+  [#18967](https://github.com/google-gemini/gemini-cli/pull/18967)
+- feat(plan): support project exploration without planning when in plan mode by
+  @Adib234 in [#18992](https://github.com/google-gemini/gemini-cli/pull/18992)
+- feat: add role-specific statistics to telemetry and UI (cont. #15234) by
+  @yunaseoul in [#18824](https://github.com/google-gemini/gemini-cli/pull/18824)
+- feat(cli): remove Plan Mode from rotation when actively working by @jerop in
+  [#19262](https://github.com/google-gemini/gemini-cli/pull/19262)
+- Fix side breakage where anchors don't work in slugs. by @g-samroberts in
+  [#19261](https://github.com/google-gemini/gemini-cli/pull/19261)
+- feat(config): add setting to make directory tree context configurable by
+  @kevin-ramdass in
+  [#19053](https://github.com/google-gemini/gemini-cli/pull/19053)
+- fix(acp): Wait for mcp initialization in acp (#18893) by @Mervap in
+  [#18894](https://github.com/google-gemini/gemini-cli/pull/18894)
+- docs: format UTC times in releases doc by @pavan-sh in
+  [#18169](https://github.com/google-gemini/gemini-cli/pull/18169)
+- Docs: Clarify extensions documentation. by @jkcinouye in
+  [#19277](https://github.com/google-gemini/gemini-cli/pull/19277)
+- refactor(core): modularize tool definitions by model family by @aishaneeshah
+  in [#19269](https://github.com/google-gemini/gemini-cli/pull/19269)
+- fix(paths): Add cross-platform path normalization by @spencer426 in
+  [#18939](https://github.com/google-gemini/gemini-cli/pull/18939)
+- feat(core): experimental in-progress steering hints (1 of 3) by @joshualitt in
+  [#19008](https://github.com/google-gemini/gemini-cli/pull/19008)
 
 **Full changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.28.0-preview.0...v0.29.0-preview.0
+https://github.com/google-gemini/gemini-cli/compare/v0.29.0-preview.5...v0.30.0-preview.1

docs/cli/commands.md

@@ -223,6 +223,13 @@ Slash commands provide meta-level control over the CLI itself.
 
 - **Description:** Opens a dialog to choose your Gemini model.
 
+### `/plan`
+
+- **Description:** Switch to Plan Mode (read-only) and view the current plan if
+  one has been generated.
+  - **Note:** This feature requires the `experimental.plan` setting to be
+    enabled in your configuration.
+
 ### `/policies`
 
 - **Description:** Manage policies.

docs/cli/enterprise.md

@@ -483,7 +483,7 @@ avoid collecting potentially sensitive information from user prompts.
 You can enforce a specific authentication method for all users by setting the
 `enforcedAuthType` in the system-level `settings.json` file. This prevents users
 from choosing a different authentication method. See the
-[Authentication docs](./authentication.md) for more details.
+[Authentication docs](../get-started/authentication.md) for more details.
 
 **Example:** Enforce the use of Google login for all users.
 

docs/cli/index.md

@@ -1,123 +0,0 @@
-# Using Gemini CLI
-
-Gemini CLI is a terminal-first interface that brings the power of Gemini AI
-models directly into your development workflow. It lets you interact with AI
-using your local files, shell environment, and project context, creating a
-bridge between generative AI and your system tools.
-
-## User guides
-
-These guides provide step-by-step instructions and practical examples for using
-Gemini CLI in your daily development workflow.
-
-- **[Quickstart](../get-started/index.md):** Get up and running with Gemini CLI
-  in minutes.
-- **[Examples](../get-started/examples.md):** See practical examples of Gemini
-  CLI in action.
-- **[Get started with skills](./tutorials/skills-getting-started.md):** Learn
-  how to use and manage specialized expertise.
-- **[File management](./tutorials/file-management.md):** How to include, search,
-  and modify local files.
-- **[Set up an MCP server](./tutorials/mcp-setup.md):** Configure Model Context
-  Protocol servers for custom tools.
-- **[Manage context and memory](./tutorials/memory-management.md):** Manage
-  persistent instructions and individual facts.
-- **[Manage sessions and history](./tutorials/session-management.md):** Resume,
-  manage, and rewind your conversations.
-- **[Execute shell commands](./tutorials/shell-commands.md):** Execute system
-  commands safely directly from your prompt.
-- **[Plan tasks with todos](./tutorials/task-planning.md):** Using todos for
-  complex, multi-step agent requests.
-- **[Web search and fetch](./tutorials/web-tools.md):** Searching and fetching
-  content from the web.
-
-## Features
-
-Technical reference documentation for each capability of Gemini CLI.
-
-- **[/about](../cli/commands.md#about):** Show version info.
-- **[/auth](../cli/commands.md#auth):** Change authentication method.
-- **[/bug](../cli/commands.md#bug):** File an issue about Gemini CLI.
-- **[/chat](../cli/commands.md#chat):** Save and resume conversation history.
-- **[/clear](../cli/commands.md#clear):** Clear the terminal screen.
-- **[/compress](../cli/commands.md#compress):** Replace context with a summary.
-- **[/copy](../cli/commands.md#copy):** Copy output to clipboard.
-- **[/directory](../cli/commands.md#directory-or-dir):** Manage workspace
-  directories.
-- **[/docs](../cli/commands.md#docs):** Open documentation in browser.
-- **[/editor](../cli/commands.md#editor):** Select preferred editor.
-- **[/extensions](../cli/commands.md#extensions):** List active extensions.
-- **[/help](../cli/commands.md#help-or):** Display help information.
-- **[/hooks](../hooks/index.md):** Manage hooks for lifecycle events.
-- **[/ide](../ide-integration/index.md):** Manage IDE integration.
-- **[/init](../cli/commands.md#init):** Create a GEMINI.md context file.
-- **[/mcp](../tools/mcp-server.md):** Manage Model Context Protocol servers.
-- **[/memory](../cli/commands.md#memory):** Manage instructional context.
-- **[/model](./model.md):** Choose Gemini model.
-- **[/policies](../cli/commands.md#policies):** Manage security policies.
-- **[/privacy](../cli/commands.md#privacy):** Display privacy notice.
-- **[/quit](../cli/commands.md#quit-or-exit):** Exit Gemini CLI.
-- **[/restore](../cli/commands.md#restore):** Restore file state.
-- **[/resume](../cli/commands.md#resume):** Browse and resume sessions.
-- **[/rewind](./rewind.md):** Navigate backward through history.
-- **[/settings](./settings.md):** Open settings editor.
-- **[/setup-github](../cli/commands.md#setup-github):** Set up GitHub Actions.
-- **[/shells](../cli/commands.md#shells-or-bashes):** Toggle background shells
-  view.
-- **[/skills](./skills.md):** Manage Agent Skills.
-- **[/stats](../cli/commands.md#stats):** Display session statistics.
-- **[/terminal-setup](../cli/commands.md#terminal-setup):** Configure
-  keybindings.
-- **[/theme](./themes.md):** Change visual theme.
-- **[/tools](../cli/commands.md#tools):** Display list of available tools.
-- **[/vim](../cli/commands.md#vim):** Toggle vim mode.
-- **[Activate skill (tool)](../tools/activate-skill.md):** Internal mechanism
-  for loading expert procedures.
-- **[Ask user (tool)](../tools/ask-user.md):** Internal dialog system for
-  clarification.
-- **[Checkpointing](./checkpointing.md):** Automatic session snapshots.
-- **[File system (tool)](../tools/file-system.md):** Technical details for local
-  file operations.
-- **[Headless mode](./headless.md):** Programmatic and scripting interface.
-- **[Internal documentation (tool)](../tools/internal-docs.md):** Technical
-  lookup for CLI features.
-- **[Memory (tool)](../tools/memory.md):** Storage details for persistent facts.
-- **[Model routing](./model-routing.md):** Automatic fallback resilience.
-- **[Plan mode (experimental)](./plan-mode.md):** Use a safe, read-only mode for
-  planning complex changes.
-- **[Sandboxing](./sandbox.md):** Isolate tool execution.
-- **[Shell (tool)](../tools/shell.md):** Detailed system execution parameters.
-- **[Telemetry](./telemetry.md):** Usage and performance metric details.
-- **[Todo (tool)](../tools/todos.md):** Progress tracking specification.
-- **[Token caching](./token-caching.md):** Performance optimization.
-- **[Web fetch (tool)](../tools/web-fetch.md):** URL retrieval and extraction
-  details.
-- **[Web search (tool)](../tools/web-search.md):** Google Search integration
-  technicals.
-
-## Configuration
-
-Settings and customization options for Gemini CLI.
-
-- **[Custom commands](./custom-commands.md):** Personalized shortcuts.
-- **[Enterprise configuration](./enterprise.md):** Professional environment
-  controls.
-- **[Ignore files (.geminiignore)](./gemini-ignore.md):** Exclusion pattern
-  reference.
-- **[Model configuration](./generation-settings.md):** Fine-tune generation
-  parameters like temperature and thinking budget.
-- **[Project context (GEMINI.md)](./gemini-md.md):** Technical hierarchy of
-  context files.
-- **[Settings](./settings.md):** Full `settings.json` schema.
-- **[System prompt override](./system-prompt.md):** Instruction replacement
-  logic.
-- **[Themes](./themes.md):** UI personalization technical guide.
-- **[Trusted folders](./trusted-folders.md):** Security permission logic.
-
-## Next steps
-
-- Explore the [Command reference](./commands.md) to learn about all available
-  slash commands.
-- Read about [Project context](./gemini-md.md) to understand how to provide
-  persistent instructions to the model.
-- See the [CLI reference](./cli-reference.md) for a quick cheatsheet of flags.

docs/cli/keyboard-shortcuts.md

@@ -36,7 +36,7 @@ available combinations.
 | Delete from the cursor to the start of the line. | `Ctrl + U`                                                       |
 | Clear all text in the input field.               | `Ctrl + C`                                                       |
 | Delete the previous word.                        | `Ctrl + Backspace`<br />`Alt + Backspace`<br />`Ctrl + W`        |
-| Delete the next word.                            | `Ctrl + Delete`<br />`Alt + Delete`                              |
+| Delete the next word.                            | `Ctrl + Delete`<br />`Alt + Delete`<br />`Alt + D`               |
 | Delete the character to the left.                | `Backspace`<br />`Ctrl + H`                                      |
 | Delete the character to the right.               | `Delete`<br />`Ctrl + D`                                         |
 | Undo the most recent text edit.                  | `Cmd + Z (no Shift)`<br />`Alt + Z (no Shift)`                   |
@@ -61,7 +61,7 @@ available combinations.
 | Show the next entry in history.              | `Ctrl + N (no Shift)` |
 | Start reverse search through history.        | `Ctrl + R`            |
 | Submit the selected reverse-search match.    | `Enter (no Ctrl)`     |
-| Accept a suggestion while reverse searching. | `Tab`                 |
+| Accept a suggestion while reverse searching. | `Tab (no Shift)`      |
 | Browse and rewind previous interactions.     | `Double Esc`          |
 
 #### Navigation
@@ -79,7 +79,7 @@ available combinations.
 
 | Action                                  | Keys                                               |
 | --------------------------------------- | -------------------------------------------------- |
-| Accept the inline suggestion.           | `Tab`<br />`Enter (no Ctrl)`                       |
+| Accept the inline suggestion.           | `Tab (no Shift)`<br />`Enter (no Ctrl)`            |
 | Move to the previous completion option. | `Up Arrow (no Shift)`<br />`Ctrl + P (no Shift)`   |
 | Move to the next completion option.     | `Down Arrow (no Shift)`<br />`Ctrl + N (no Shift)` |
 | Expand an inline suggestion.            | `Right Arrow`                                      |
@@ -96,31 +96,31 @@ available combinations.
 
 #### App Controls
 
-| Action                                                                                                | Keys             |
-| ----------------------------------------------------------------------------------------------------- | ---------------- |
-| Toggle detailed error information.                                                                    | `F12`            |
-| Toggle the full TODO list.                                                                            | `Ctrl + T`       |
-| Show IDE context details.                                                                             | `Ctrl + G`       |
-| Toggle Markdown rendering.                                                                            | `Alt + M`        |
-| Toggle copy mode when in alternate buffer mode.                                                       | `Ctrl + S`       |
-| Toggle YOLO (auto-approval) mode for tool calls.                                                      | `Ctrl + Y`       |
-| Cycle through approval modes: default (prompt), auto_edit (auto-approve edits), and plan (read-only). | `Shift + Tab`    |
-| Expand and collapse blocks of content when not in alternate buffer mode.                              | `Ctrl + O`       |
-| Expand or collapse a paste placeholder when cursor is over placeholder.                               | `Ctrl + O`       |
-| Toggle current background shell visibility.                                                           | `Ctrl + B`       |
-| Toggle background shell list.                                                                         | `Ctrl + L`       |
-| Kill the active background shell.                                                                     | `Ctrl + K`       |
-| Confirm selection in background shell list.                                                           | `Enter`          |
-| Dismiss background shell list.                                                                        | `Esc`            |
-| Move focus from background shell to Gemini.                                                           | `Shift + Tab`    |
-| Move focus from background shell list to Gemini.                                                      | `Tab (no Shift)` |
-| Show warning when trying to move focus away from background shell.                                    | `Tab (no Shift)` |
-| Show warning when trying to move focus away from shell input.                                         | `Tab (no Shift)` |
-| Move focus from Gemini to the active shell.                                                           | `Tab (no Shift)` |
-| Move focus from the shell back to Gemini.                                                             | `Shift + Tab`    |
-| Clear the terminal screen and redraw the UI.                                                          | `Ctrl + L`       |
-| Restart the application.                                                                              | `R`              |
-| Suspend the CLI and move it to the background.                                                        | `Ctrl + Z`       |
+| Action                                                                                                                                             | Keys             |
+| -------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------- |
+| Toggle detailed error information.                                                                                                                 | `F12`            |
+| Toggle the full TODO list.                                                                                                                         | `Ctrl + T`       |
+| Show IDE context details.                                                                                                                          | `Ctrl + G`       |
+| Toggle Markdown rendering.                                                                                                                         | `Alt + M`        |
+| Toggle copy mode when in alternate buffer mode.                                                                                                    | `Ctrl + S`       |
+| Toggle YOLO (auto-approval) mode for tool calls.                                                                                                   | `Ctrl + Y`       |
+| Cycle through approval modes: default (prompt), auto_edit (auto-approve edits), and plan (read-only). Plan mode is skipped when the agent is busy. | `Shift + Tab`    |
+| Expand and collapse blocks of content when not in alternate buffer mode.                                                                           | `Ctrl + O`       |
+| Expand or collapse a paste placeholder when cursor is over placeholder.                                                                            | `Ctrl + O`       |
+| Toggle current background shell visibility.                                                                                                        | `Ctrl + B`       |
+| Toggle background shell list.                                                                                                                      | `Ctrl + L`       |
+| Kill the active background shell.                                                                                                                  | `Ctrl + K`       |
+| Confirm selection in background shell list.                                                                                                        | `Enter`          |
+| Dismiss background shell list.                                                                                                                     | `Esc`            |
+| Move focus from background shell to Gemini.                                                                                                        | `Shift + Tab`    |
+| Move focus from background shell list to Gemini.                                                                                                   | `Tab (no Shift)` |
+| Show warning when trying to move focus away from background shell.                                                                                 | `Tab (no Shift)` |
+| Show warning when trying to move focus away from shell input.                                                                                      | `Tab (no Shift)` |
+| Move focus from Gemini to the active shell.                                                                                                        | `Tab (no Shift)` |
+| Move focus from the shell back to Gemini.                                                                                                          | `Shift + Tab`    |
+| Clear the terminal screen and redraw the UI.                                                                                                       | `Ctrl + L`       |
+| Restart the application.                                                                                                                           | `R`              |
+| Suspend the CLI and move it to the background.                                                                                                     | `Ctrl + Z`       |
 
 <!-- KEYBINDINGS-AUTOGEN:END -->
 
@@ -138,7 +138,8 @@ available combinations.
   details when no completion/search interaction is active. The selected mode is
   remembered for future sessions. Full UI remains the default on first run, and
   single `Tab` keeps its existing completion/focus behavior.
-- `Shift + Tab` (while typing in the prompt): Cycle approval modes.
+- `Shift + Tab` (while typing in the prompt): Cycle approval modes: default,
+  auto-edit, and plan (skipped when agent is busy).
 - `\` (at end of a line) + `Enter`: Insert a newline without leaving single-line
   mode.
 - `Esc` pressed twice quickly: Clear the input prompt if it is not empty,

docs/cli/plan-mode.md

@@ -62,6 +62,10 @@ You can enter Plan Mode in three ways:
 
 1.  **Keyboard Shortcut:** Press `Shift+Tab` to cycle through approval modes
     (`Default` -> `Auto-Edit` -> `Plan`).
+
+    > **Note:** Plan Mode is automatically removed from the rotation when the
+    > agent is actively processing or showing confirmation dialogs.
+
 2.  **Command:** Type `/plan` in the input box.
 3.  **Natural Language:** Ask the agent to "start a plan for...". The agent will
     then call the [`enter_plan_mode`] tool to switch modes.

docs/cli/settings.md

@@ -27,6 +27,7 @@ they appear in the UI.
 | Vim Mode                 | `general.vimMode`                  | Enable Vim keybindings                                                                                                                                                         | `false`     |
 | 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' is not supported yet. | `"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. Currently macOS only.                                                                       | `false`     |
 | Enable Prompt Completion | `general.enablePromptCompletion`   | Enable AI-powered prompt completion suggestions while typing.                                                                                                                  | `false`     |
 | Debug Keystroke Logging  | `general.debugKeystrokeLogging`    | Enable debug logging of keystrokes to the console.                                                                                                                             | `false`     |
 | Enable Session Cleanup   | `general.sessionRetention.enabled` | Enable automatic session cleanup                                                                                                                                               | `false`     |
@@ -49,6 +50,7 @@ they appear in the UI.
 | 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` |
 | Show Shortcuts Hint                  | `ui.showShortcutsHint`                  | Show the "? for shortcuts" hint above the input.                                                                                                                  | `true`  |
 | Hide Banner                          | `ui.hideBanner`                         | Hide the application banner                                                                                                                                       | `false` |
@@ -131,6 +133,7 @@ they appear in the UI.
 | Enable Tool Output Masking | `experimental.toolOutputMasking.enabled` | Enables tool output masking to save tokens.                                         | `true`  |
 | Use OSC 52 Paste           | `experimental.useOSC52Paste`             | Use OSC 52 sequence for pasting instead of clipboardy (useful for remote sessions). | `false` |
 | Plan                       | `experimental.plan`                      | Enable planning features (Plan Mode and tools).                                     | `false` |
+| Model Steering             | `experimental.modelSteering`             | Enable model steering (user hints) to guide the model during tool execution.        | `false` |
 
 ### Skills
 

docs/core/concepts.md

@@ -1,137 +0,0 @@
-# Core concepts
-
-This guide explains the fundamental concepts and terminology used throughout the
-Gemini CLI ecosystem. Understanding these terms will help you make the most of
-the tool's capabilities.
-
-## Approval mode
-
-**Approval mode** determines the level of autonomy you grant to the agent when
-executing tools.
-
-- **Default:** The agent asks for confirmation before performing any potentially
-  impactful action (like writing files or running shell commands).
-- **Auto-edit:** File modifications are applied automatically, but shell
-  commands still require confirmation.
-- **YOLO (You Only Look Once):** The agent runs all tools without asking for
-  permission. High risk, high speed.
-
-## Checkpointing
-
-**Checkpointing** is a safety feature that automatically snapshots your
-project's file state before the agent performs any destructive action (like
-writing a file).
-
-- **Snapshots:** Stored in a hidden Git repository (separate from your project's
-  Git history).
-- **Restore:** Allows you to instantly revert changes if the agent makes a
-  mistake, using the `/restore` command.
-
-## Context
-
-**Context** refers to the information the agent has about your current task and
-environment. Gemini CLI provides context through several mechanisms:
-
-- **Conversation history:** The chat log of the current session.
-- **Project context (`GEMINI.md`):** Persistent instructions and rules defined
-  in your project's root or subdirectories.
-- **File content:** Files you explicitly reference (e.g., `@src/app.ts`) or that
-  the agent reads using tools.
-- **Environment:** Information about your operating system, shell, and working
-  directory.
-
-Effective context management is key to getting accurate and relevant responses.
-
-## Extension
-
-An **Extension** is a pluggable package that adds new capabilities to Gemini
-CLI. Extensions can bundle:
-
-- **Skills:** Specialized procedural knowledge.
-- **MCP Servers:** Connections to external tools and data.
-- **Commands:** Custom slash commands.
-
-## Headless mode
-
-**Headless mode** refers to running Gemini CLI without the interactive terminal
-UI (TUI). This is used for scripting, automation, and piping data into or out of
-the agent.
-
-- **Interactive:** `gemini` (starts the REPL).
-- **Headless:** `gemini "Fix this file"` (runs once and exits).
-
-## Hook
-
-A **Hook** is a script or function that intercepts specific lifecycle events in
-the CLI.
-
-- **Use cases:** Logging tool usage, validating user input, or modifying the
-  agent's system prompt dynamically.
-- **Lifecycle:** Hooks can run before or after the agent starts, before tools
-  are executed, or after the session ends.
-
-## Model Context Protocol (MCP)
-
-The **Model Context Protocol (MCP)** is an open standard that allows Gemini CLI
-to connect to external data sources and tools.
-
-- **MCP Server:** A lightweight application that exposes resources (data) and
-  tools (functions) to the CLI.
-- **Use case:** Connecting Gemini to a PostgreSQL database, a GitHub repository,
-  or a Slack workspace without building custom integration logic into the CLI
-  core.
-
-## Policy engine
-
-The **Policy Engine** is the security subsystem that enforces rules on tool
-execution. It evaluates every tool call against your configuration (e.g.,
-[Trusted folders](#trusted-folders), allowed commands) to decide whether to:
-
-- Allow the action immediately.
-- Require user confirmation.
-- Block the action entirely.
-
-## Sandboxing
-
-**Sandboxing** is an optional security mode that isolates the agent's execution
-environment. When enabled, the agent runs inside a secure container (e.g.,
-Docker), preventing it from accessing sensitive files or system resources
-outside of the designated workspace.
-
-## Session
-
-A **Session** is a single continuous interaction thread with the agent.
-
-- **State:** Sessions maintain conversation history and short-term memory.
-- **Persistence:** Sessions are automatically saved, allowing you to pause,
-  resume, or rewind them later.
-
-## Skill
-
-A **Skill** (or **Agent Skill**) is a package of specialized expertise that the
-agent can load on demand. Unlike general context, a skill provides specific
-procedural knowledge for a distinct task.
-
-- **Example:** A "Code Reviewer" skill might contain a checklist of security
-  vulnerabilities to look for and a specific format for reporting findings.
-- **Activation:** Skills are typically activated dynamically when the agent
-  recognizes a matching request.
-
-## Tool
-
-A **Tool** is a specific function or capability that the agent can execute.
-Tools allow the AI to interact with the outside world.
-
-- **Built-in tools:** Core capabilities like `read_file`, `run_shell_command`,
-  and `google_web_search`.
-- **MCP tools:** External tools provided by
-  [MCP servers](#model-context-protocol-mcp).
-
-When the agent uses a tool, it pauses generation, executes the code, and feeds
-the output back into its context window.
-
-## Trusted folders
-
-**Trusted folders** are specific directories you have explicitly authorized the
-agent to access without repeated confirmation prompts. This is a key component
-of the [Policy engine](#policy-engine) to balance security and usability.

docs/core/subagents.md

@@ -1,13 +1,13 @@
-# Sub-agents (experimental)
+# Subagents (experimental)
 
-Sub-agents are specialized agents that operate within your main Gemini CLI
+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.
 
-> **Note: Sub-agents are currently an experimental feature.**
+> **Note: Subagents are currently an experimental feature.**
 >
-> To use custom sub-agents, you must explicitly enable them in your
+> To use custom subagents, you must explicitly enable them in your
 > `settings.json`:
 >
 > ```json
@@ -16,31 +16,31 @@ the main agent's context or toolset.
 > }
 > ```
 >
-> **Warning:** Sub-agents currently operate in
+> **Warning:** Subagents currently operate in
 > ["YOLO mode"](../get-started/configuration.md#command-line-arguments), meaning
 > they may execute tools without individual user confirmation for each step.
 > Proceed with caution when defining agents with powerful tools like
 > `run_shell_command` or `write_file`.
 
-## What are sub-agents?
+## What are subagents?
 
-Sub-agents are "specialists" that the main Gemini agent can hire for a specific
+Subagents are "specialists" that the main Gemini agent can hire for a specific
 job.
 
-- **Focused context:** Each sub-agent has its own system prompt and persona.
-- **Specialized tools:** Sub-agents can have a restricted or specialized set of
+- **Focused context:** Each subagent has its own system prompt and persona.
+- **Specialized tools:** Subagents can have a restricted or specialized set of
   tools.
-- **Independent context window:** Interactions with a sub-agent happen in a
+- **Independent context window:** Interactions with a subagent happen in a
   separate context loop, which saves tokens in your main conversation history.
 
-Sub-agents are exposed to the main agent as a tool of the same name. When the
-main agent calls the tool, it delegates the task to the sub-agent. Once the
-sub-agent completes its task, it reports back to the main agent with its
+Subagents are exposed to the main agent as a tool of the same name. When the
+main agent calls the tool, it delegates the task to the subagent. Once the
+subagent completes its task, it reports back to the main agent with its
 findings.
 
-## Built-in sub-agents
+## Built-in subagents
 
-Gemini CLI comes with the following built-in sub-agents:
+Gemini CLI comes with the following built-in subagents:
 
 ### Codebase Investigator
 
@@ -75,15 +75,15 @@ Gemini CLI comes with the following built-in sub-agents:
 ### Generalist Agent
 
 - **Name:** `generalist_agent`
-- **Purpose:** Route tasks to the appropriate specialized sub-agent.
+- **Purpose:** Route tasks to the appropriate specialized subagent.
 - **When to use:** Implicitly used by the main agent for routing. Not directly
   invoked by the user.
 - **Configuration:** Enabled by default. No specific configuration options.
 
-## Creating custom sub-agents
+## Creating custom subagents
 
-You can create your own sub-agents to automate specific workflows or enforce
-specific personas. To use custom sub-agents, you must enable them in your
+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
@@ -138,20 +138,20 @@ it yourself; just report it.
 
 ### Configuration schema
 
-| Field          | Type   | Required | Description                                                                                                                |
-| :------------- | :----- | :------- | :------------------------------------------------------------------------------------------------------------------------- |
-| `name`         | string | Yes      | Unique identifier (slug) used as the tool name for the agent. Only lowercase letters, numbers, hyphens, and underscores.   |
-| `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 sub-agent. |
-| `kind`         | string | No       | `local` (default) or `remote`.                                                                                             |
-| `tools`        | array  | No       | List of tool names this agent can use. If omitted, it may have access to a default set.                                    |
-| `model`        | string | No       | Specific model to use (e.g., `gemini-2.5-pro`). Defaults to `inherit` (uses the main session model).                       |
-| `temperature`  | number | No       | Model temperature (0.0 - 2.0).                                                                                             |
-| `max_turns`    | number | No       | Maximum number of conversation turns allowed for this agent before it must return. Defaults to `15`.                       |
-| `timeout_mins` | number | No       | Maximum execution time in minutes. Defaults to `5`.                                                                        |
+| Field          | Type   | Required | Description                                                                                                               |
+| :------------- | :----- | :------- | :------------------------------------------------------------------------------------------------------------------------ |
+| `name`         | string | Yes      | Unique identifier (slug) used as the tool name for the agent. Only lowercase letters, numbers, hyphens, and underscores.  |
+| `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. If omitted, it may have access to a default set.                                   |
+| `model`        | string | No       | Specific model to use (e.g., `gemini-2.5-pro`). Defaults to `inherit` (uses the main session model).                      |
+| `temperature`  | number | No       | Model temperature (0.0 - 2.0).                                                                                            |
+| `max_turns`    | number | No       | Maximum number of conversation turns allowed for this agent before it must return. Defaults to `15`.                      |
+| `timeout_mins` | number | No       | Maximum execution time in minutes. Defaults to `5`.                                                                       |
 
-### Optimizing your sub-agent
+### Optimizing your subagent
 
-The main agent's system prompt encourages it to use an expert sub-agent when one
+The main agent's system prompt encourages it to use an expert subagent when one
 is available. It decides whether an agent is a relevant expert based on the
 agent's description. You can improve the reliability with which an agent is used
 by updating the description to more clearly indicate:
@@ -160,7 +160,7 @@ by updating the description to more clearly indicate:
 - When it should be used.
 - Some example scenarios.
 
-For example, the following sub-agent description should be called fairly
+For example, the following subagent description should be called fairly
 consistently for Git operations.
 
 > Git expert agent which should be used for all local and remote git operations.
@@ -170,13 +170,13 @@ consistently for Git operations.
 > - Searching for regressions with bisect
 > - Interacting with source control and issues providers such as GitHub.
 
-If you need to further tune your sub-agent, you can do so by selecting the model
+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 sub-agent was called with a specific prompt and the given description.
+that your subagent was called with a specific prompt and the given description.
 
 ## Remote subagents (Agent2Agent) (experimental)
 
-Gemini CLI can also delegate tasks to remote sub-agents using the Agent-to-Agent
+Gemini CLI can also delegate tasks to remote subagents using the Agent-to-Agent
 (A2A) protocol.
 
 > **Note: Remote subagents are currently an experimental feature.**
@@ -184,8 +184,8 @@ Gemini CLI can also delegate tasks to remote sub-agents using the Agent-to-Agent
 See the [Remote Subagents documentation](/docs/core/remote-agents) for detailed
 configuration and usage instructions.
 
-## Extension sub-agents
+## Extension subagents
 
-Extensions can bundle and distribute sub-agents. See the
-[Extensions documentation](../extensions/index.md#sub-agents) for details on how
+Extensions can bundle and distribute subagents. See the
+[Extensions documentation](../extensions/index.md#subagents) for details on how
 to package agents within an extension.

docs/extensions/best-practices.md

@@ -1,19 +1,19 @@
-# Extensions on Gemini CLI: Best practices
+# Gemini CLI extension best practices
 
 This guide covers best practices for developing, securing, and maintaining
 Gemini CLI extensions.
 
 ## Development
 
-Developing extensions for Gemini CLI is intended to be a lightweight, iterative
-process.
+Developing extensions for Gemini CLI is a lightweight, iterative process. Use
+these strategies to build robust and efficient extensions.
 
 ### Structure your extension
 
-While simple extensions can just be a few files, we recommend a robust structure
-for complex extensions:
+While simple extensions may contain only a few files, we recommend a organized
+structure for complex projects.
 
-```
+```text
 my-extension/
 ├── package.json
 ├── tsconfig.json
@@ -24,47 +24,50 @@ my-extension/
 └── dist/
 ```
 
-- **Use TypeScript**: We strongly recommend using TypeScript for type safety and
-  better tooling.
-- **Separate source and build**: Keep your source code in `src` and build to
-  `dist`.
-- **Bundle dependencies**: If your extension has many dependencies, consider
-  bundling them (e.g., with `esbuild` or `webpack`) to reduce install time and
-  potential conflicts.
+- **Use TypeScript:** We strongly recommend using TypeScript for type safety and
+  improved developer experience.
+- **Separate source and build:** Keep your source code in `src/` and output
+  build artifacts to `dist/`.
+- **Bundle dependencies:** If your extension has many dependencies, bundle them
+  using a tool like `esbuild` to reduce installation time and avoid conflicts.
 
 ### Iterate with `link`
 
-Use `gemini extensions link` to develop locally without constantly reinstalling:
+Use the `gemini extensions link` command to develop locally without reinstalling
+your extension after every change.
 
 ```bash
 cd my-extension
 gemini extensions link .
 ```
 
-Changes to your code (after rebuilding) will be immediately available in the CLI
-on restart.
+Changes to your code are immediately available in the CLI after you rebuild the
+project and restart the session.
 
 ### Use `GEMINI.md` effectively
 
-Your `GEMINI.md` file provides context to the model. Keep it focused:
+Your `GEMINI.md` file provides essential context to the model.
 
-- **Do:** Explain high-level goals and how to use the provided tools.
-- **Don't:** Dump your entire documentation.
-- **Do:** Use clear, concise language.
+- **Focus on goals:** Explain the high-level purpose of the extension and how to
+  interact with its tools.
+- **Be concise:** Avoid dumping exhaustive documentation into the file. Use
+  clear, direct language.
+- **Provide examples:** Include brief examples of how the model should use
+  specific tools or commands.
 
 ## Security
 
-When building a Gemini CLI extension, follow general security best practices
-(such as least privilege and input validation) to reduce risk.
+Follow the principle of least privilege and rigorous input validation when
+building extensions.
 
 ### Minimal permissions
 
-When defining tools in your MCP server, only request the permissions necessary.
-Avoid giving the model broad access (like full shell access) if a more
-restricted set of tools will suffice.
+Only request the permissions your MCP server needs to function. Avoid giving the
+model broad access (such as full shell access) if restricted tools are
+sufficient.
 
-If you must use powerful tools like `run_shell_command`, consider restricting
-them to specific commands in your `gemini-extension.json`:
+If your extension uses powerful tools like `run_shell_command`, restrict them in
+your `gemini-extension.json` file:
 
 ```json
 {
@@ -73,27 +76,26 @@ them to specific commands in your `gemini-extension.json`:
 }
 ```
 
-This ensures that even if the model tries to execute a dangerous command, it
-will be blocked at the CLI level.
+This ensures the CLI blocks dangerous commands even if the model attempts to
+execute them.
 
 ### Validate inputs
 
-Your MCP server is running on the user's machine. Always validate inputs to your
-tools to prevent arbitrary code execution or filesystem access outside the
-intended scope.
+Your MCP server runs on the user's machine. Always validate tool inputs to
+prevent arbitrary code execution or unauthorized filesystem access.
 
 ```typescript
-// Good: Validating paths
+// Example: Validating paths
 if (!path.resolve(inputPath).startsWith(path.resolve(allowedDir) + path.sep)) {
   throw new Error('Access denied');
 }
 ```
 
-### Sensitive settings
+### Secure sensitive settings
 
-If your extension requires API keys, use the `sensitive: true` option in
-`gemini-extension.json`. This ensures keys are stored securely in the system
-keychain and obfuscated in the UI.
+If your extension requires API keys or other secrets, use the `sensitive: true`
+option in your manifest. This ensures keys are stored in the system keychain and
+obfuscated in the CLI output.
 
 ```json
 "settings": [
@@ -105,35 +107,82 @@ keychain and obfuscated in the UI.
 ]
 ```
 
-## Releasing
+## Release
 
-You can upload your extension directly to GitHub to list it in the gallery.
-Gemini CLI extensions also offers support for more complicated
-[releases](releasing.md).
+Follow standard versioning and release practices to ensure a smooth experience
+for your users.
 
 ### Semantic versioning
 
-Follow [Semantic Versioning](https://semver.org/).
+Follow [Semantic Versioning (SemVer)](https://semver.org/) to communicate
+changes clearly.
 
-- **Major**: Breaking changes (renaming tools, changing arguments).
-- **Minor**: New features (new tools, commands).
-- **Patch**: Bug fixes.
+- **Major:** Breaking changes (e.g., renaming tools or changing arguments).
+- **Minor:** New features (e.g., adding new tools or commands).
+- **Patch:** Bug fixes and performance improvements.
 
-### Release Channels
+### Release channels
 
-Use git branches to manage release channels (e.g., `main` for stable, `dev` for
-bleeding edge). This allows users to choose their stability level:
+Use Git branches to manage release channels. This lets users choose between
+stability and the latest features.
 
 ```bash
-# Stable
+# Install the stable version (default branch)
 gemini extensions install github.com/user/repo
 
-# Dev
+# Install the development version
 gemini extensions install github.com/user/repo --ref dev
 ```
 
 ### Clean artifacts
 
-If you are using GitHub Releases, ensure your release artifacts only contain the
-necessary files (`dist/`, `gemini-extension.json`, `package.json`). Exclude
-`node_modules` (users will install them) and `src/` to keep downloads small.
+When using GitHub Releases, ensure your archives only contain necessary files
+(such as `dist/`, `gemini-extension.json`, and `package.json`). Exclude
+`node_modules/` and `src/` to minimize download size.
+
+## Test and verify
+
+Test your extension thoroughly before releasing it to users.
+
+- **Manual verification:** Use `gemini extensions link` to test your extension
+  in a live CLI session. Verify that tools appear in the debug console (F12) and
+  that custom commands resolve correctly.
+- **Automated testing:** If your extension includes an MCP server, write unit
+  tests for your tool logic using a framework like Vitest or Jest. You can test
+  MCP tools in isolation by mocking the transport layer.
+
+## Troubleshooting
+
+Use these tips to diagnose and fix common extension issues.
+
+### Extension not loading
+
+If your extension doesn't appear in `/extensions list`:
+
+- **Check the manifest:** Ensure `gemini-extension.json` is in the root
+  directory and contains valid JSON.
+- **Verify the name:** The `name` field in the manifest must match the extension
+  directory name exactly.
+- **Restart the CLI:** Extensions are loaded at the start of a session. Restart
+  Gemini CLI after making changes to the manifest or linking a new extension.
+
+### MCP server failures
+
+If your tools aren't working as expected:
+
+- **Check the logs:** View the CLI logs to see if the MCP server failed to
+  start.
+- **Test the command:** Run the server's `command` and `args` directly in your
+  terminal to ensure it starts correctly outside of Gemini CLI.
+- **Debug console:** In interactive mode, press **F12** to open the debug
+  console and inspect tool calls and responses.
+
+### Command conflicts
+
+If a custom command isn't responding:
+
+- **Check precedence:** Remember that user and project commands take precedence
+  over extension commands. Use the prefixed name (e.g., `/extension.command`) to
+  verify the extension's version.
+- **Help command:** Run `/help` to see a list of all available commands and
+  their sources.

docs/extensions/index.md

@@ -6,19 +6,44 @@ With extensions, you can expand the capabilities of Gemini CLI and share those
 capabilities with others. They are designed to be easily installable and
 shareable.
 
-To see examples of extensions, you can browse a gallery of
-[Gemini CLI extensions](https://geminicli.com/extensions/browse/).
+To see what's possible, browse the
+[Gemini CLI extension gallery](https://geminicli.com/extensions/browse/).
 
-## Managing extensions
+## Choose your path
 
-You can verify your installed extensions and their status using the interactive
-command:
+Choose the guide that best fits your needs.
+
+### I want to use extensions
+
+Learn how to discover, install, and manage extensions to enhance your Gemini CLI
+experience.
+
+- **[Manage extensions](#manage-extensions):** List and verify your installed
+  extensions.
+- **[Install extensions](#installation):** Add new capabilities from GitHub or
+  local paths.
+
+### I want to build extensions
+
+Learn how to create, test, and share your own extensions with the community.
+
+- **[Build extensions](writing-extensions.md):** Create your first extension
+  from a template.
+- **[Best practices](best-practices.md):** Learn how to build secure and
+  reliable extensions.
+- **[Publish to the gallery](releasing.md):** Share your work with the world.
+
+## Manage extensions
+
+Use the interactive `/extensions` command to verify your installed extensions
+and their status:
 
 ```bash
 /extensions list
 ```
 
-or in noninteractive mode:
+You can also manage extensions from your terminal using the `gemini extensions`
+command group:
 
 ```bash
 gemini extensions list
@@ -26,20 +51,11 @@ gemini extensions list
 
 ## Installation
 
-To install a real extension, you can use the `extensions install` command with a
-GitHub repository URL in noninteractive mode. For example:
+Install an extension by providing its GitHub repository URL. For example:
 
 ```bash
 gemini extensions install https://github.com/gemini-cli-extensions/workspace
 ```
 
-## Next steps
-
-- [Writing extensions](writing-extensions.md): Learn how to create your first
-  extension.
-- [Extensions reference](reference.md): Deeply understand the extension format,
-  commands, and configuration.
-- [Best practices](best-practices.md): Learn strategies for building great
-  extensions.
-- [Extensions releasing](releasing.md): Learn how to share your extensions with
-  the world.
+For more advanced installation options, see the
+[Extension reference](reference.md#install-an-extension).

docs/extensions/reference.md

@@ -1,134 +1,113 @@
-# Extensions reference
+# Extension reference
 
 This guide covers the `gemini extensions` commands and the structure of the
 `gemini-extension.json` configuration file.
 
-## Extension management
+## Manage extensions
 
-We offer a suite of extension management tools using `gemini extensions`
-commands.
+Use the `gemini extensions` command group to manage your extensions from the
+terminal.
 
-Note that these commands (e.g. `gemini extensions install`) are not supported
-from within the CLI's **interactive mode**, although you can list installed
-extensions using the `/extensions list` slash command.
+Note that commands like `gemini extensions install` are not supported within the
+CLI's interactive mode. However, you can use the `/extensions list` command to
+view installed extensions. All management operations, including updates to slash
+commands, take effect only after you restart the CLI session.
 
-Note that all of these management operations (including updates to slash
-commands) will only be reflected in active CLI sessions on **restart**.
+### Install an extension
 
-### Installing an extension
+Install an extension by providing its GitHub repository URL or a local file
+path.
 
-You can install an extension using `gemini extensions install` with either a
-GitHub URL or a local path.
+Gemini CLI creates a copy of the extension during installation. You must run
+`gemini extensions update` to pull changes from the source. To install from
+GitHub, you must have `git` installed on your machine.
 
-Note that we create a copy of the installed extension, so you will need to run
-`gemini extensions update` to pull in changes from both locally-defined
-extensions and those on GitHub.
-
-NOTE: If you are installing an extension from GitHub, you'll need to have `git`
-installed on your machine. See
-[git installation instructions](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git)
-for help.
-
-```
+```bash
 gemini extensions install <source> [--ref <ref>] [--auto-update] [--pre-release] [--consent]
 ```
 
-- `<source>`: The github URL or local path of the extension to install.
-- `--ref`: The git ref to install from.
-- `--auto-update`: Enable auto-update for this extension.
-- `--pre-release`: Enable pre-release versions for this extension.
-- `--consent`: Acknowledge the security risks of installing an extension and
-  skip the confirmation prompt.
+- `<source>`: The GitHub URL or local path of the extension.
+- `--ref`: The git ref (branch, tag, or commit) to install.
+- `--auto-update`: Enable automatic updates for this extension.
+- `--pre-release`: Enable installation of pre-release versions.
+- `--consent`: Acknowledge security risks and skip the confirmation prompt.
 
-### Uninstalling an extension
+### Uninstall an extension
 
-To uninstall one or more extensions, run
-`gemini extensions uninstall <name...>`:
+To uninstall one or more extensions, use the `uninstall` command:
 
-```
-gemini extensions uninstall gemini-cli-security gemini-cli-another-extension
+```bash
+gemini extensions uninstall <name...>
 ```
 
-### Disabling an extension
+### Disable an extension
 
-Extensions are, by default, enabled across all workspaces. You can disable an
-extension entirely or for specific workspace.
+Extensions are enabled globally by default. You can disable an extension
+entirely or for a specific workspace.
 
-```
+```bash
 gemini extensions disable <name> [--scope <scope>]
 ```
 
 - `<name>`: The name of the extension to disable.
 - `--scope`: The scope to disable the extension in (`user` or `workspace`).
 
-### Enabling an extension
+### Enable an extension
 
-You can enable extensions using `gemini extensions enable <name>`. You can also
-enable an extension for a specific workspace using
-`gemini extensions enable <name> --scope=workspace` from within that workspace.
+Re-enable a disabled extension using the `enable` command:
 
-```
+```bash
 gemini extensions enable <name> [--scope <scope>]
 ```
 
 - `<name>`: The name of the extension to enable.
 - `--scope`: The scope to enable the extension in (`user` or `workspace`).
 
-### Updating an extension
+### Update an extension
 
-For extensions installed from a local path or a git repository, you can
-explicitly update to the latest version (as reflected in the
-`gemini-extension.json` `version` field) with `gemini extensions update <name>`.
-
-You can update all extensions with:
+Update an extension to the version specified in its `gemini-extension.json`
+file.
 
+```bash
+gemini extensions update <name>
 ```
+
+To update all installed extensions at once:
+
+```bash
 gemini extensions update --all
 ```
 
-### Create a boilerplate extension
+### Create an extension from a template
 
-We offer several example extensions `context`, `custom-commands`,
-`exclude-tools` and `mcp-server`. You can view these examples
-[here](https://github.com/google-gemini/gemini-cli/tree/main/packages/cli/src/commands/extensions/examples).
+Create a new extension directory using a built-in template.
 
-To copy one of these examples into a development directory using the type of
-your choosing, run:
-
-```
+```bash
 gemini extensions new <path> [template]
 ```
 
-- `<path>`: The path to create the extension in.
-- `[template]`: The boilerplate template to use.
+- `<path>`: The directory to create.
+- `[template]`: The template to use (e.g., `mcp-server`, `context`,
+  `custom-commands`).
 
 ### Link a local extension
 
-The `gemini extensions link` command will create a symbolic link from the
-extension installation directory to the development path.
+Create a symbolic link between your development directory and the Gemini CLI
+extensions directory. This lets you test changes immediately without
+reinstalling.
 
-This is useful so you don't have to run `gemini extensions update` every time
-you make changes you'd like to test.
-
-```
+```bash
 gemini extensions link <path>
 ```
 
-- `<path>`: The path of the extension to link.
-
 ## Extension format
 
-On startup, Gemini CLI looks for extensions in `<home>/.gemini/extensions`
-
-Extensions exist as a directory that contains a `gemini-extension.json` file.
-For example:
-
-`<home>/.gemini/extensions/my-extension/gemini-extension.json`
+Gemini CLI loads extensions from `<home>/.gemini/extensions`. Each extension
+must have a `gemini-extension.json` file in its root directory.
 
 ### `gemini-extension.json`
 
-The `gemini-extension.json` file contains the configuration for the extension.
-The file has the following structure:
+The manifest file defines the extension's behavior and configuration.
 
 ```json
 {
@@ -145,56 +124,27 @@ The file has the following structure:
 }
 ```
 
-- `name`: The name of the extension. This is used to uniquely identify the
-  extension and for conflict resolution when extension commands have the same
-  name as user or project commands. The name should be lowercase or numbers and
-  use dashes instead of underscores or spaces. This is how users will refer to
-  your extension in the CLI. Note that we expect this name to match the
-  extension directory name.
-- `version`: The version of the extension.
-- `description`: A short description of the extension. This will be displayed on
-  [geminicli.com/extensions](https://geminicli.com/extensions).
-- `mcpServers`: A map of MCP servers to settings. The key is the name of the
-  server, and the value is the server configuration. These servers will be
-  loaded on startup just like MCP servers settingsd in a
-  [`settings.json` file](../get-started/configuration.md). If both an extension
-  and a `settings.json` file settings an MCP server with the same name, the
-  server defined in the `settings.json` file takes precedence.
-  - Note that all MCP server configuration options are supported except for
-    `trust`.
-- `contextFileName`: The name of the file that contains the context for the
-  extension. This will be used to load the context from the extension directory.
-  If this property is not used but a `GEMINI.md` file is present in your
-  extension directory, then that file will be loaded.
-- `excludeTools`: An array of tool names to exclude from the model. You can also
-  specify command-specific restrictions for tools that support it, like the
-  `run_shell_command` tool. For example,
-  `"excludeTools": ["run_shell_command(rm -rf)"]` will block the `rm -rf`
-  command. Note that this differs from the MCP server `excludeTools`
-  functionality, which can be listed in the MCP server config.
-- `themes`: An array of custom themes provided by the extension. Each theme is
-  an object that defines the color scheme for the CLI UI. See the
-  [Themes guide](../cli/themes.md) for more details on the theme format.
+- `name`: A unique identifier for the extension. Use lowercase letters, numbers,
+  and dashes. This name must match the extension's directory name.
+- `version`: The current version of the extension.
+- `description`: A short summary shown in the extension gallery.
+- <a id="mcp-servers"></a>`mcpServers`: A map of Model Context Protocol (MCP)
+  servers. Extension servers follow the same format as standard
+  [CLI configuration](../get-started/configuration.md).
+- `contextFileName`: The name of the context file (defaults to `GEMINI.md`). Can
+  also be an array of strings to load multiple context files.
+- `excludeTools`: An array of tools to block from the model. You can restrict
+  specific arguments, such as `run_shell_command(rm -rf)`.
+- `themes`: An optional list of themes provided by the extension. See
+  [Themes](../cli/themes.md) for more information.
 
-When Gemini CLI starts, it loads all the extensions and merges their
-configurations. If there are any conflicts, the workspace configuration takes
-precedence.
+### Extension settings
 
-### Settings
+Extensions can define settings that users provide during installation, such as
+API keys or URLs. These values are stored in a `.env` file within the extension
+directory.
 
-Extensions can define settings that the user will be prompted to provide upon
-installation. This is useful for things like API keys, URLs, or other
-configuration that the extension needs to function.
-
-To define settings, add a `settings` array to your `gemini-extension.json` file.
-Each object in the array should have the following properties:
-
-- `name`: A user-friendly name for the setting.
-- `description`: A description of the setting and what it's used for.
-- `envVar`: The name of the environment variable that the setting will be stored
-  as.
-- `sensitive`: Optional boolean. If true, obfuscates the input the user provides
-  and stores the secret in keychain storage. **Example**
+To define settings, add a `settings` array to your manifest:
 
 ```json
 {
@@ -204,106 +154,54 @@ Each object in the array should have the following properties:
     {
       "name": "API Key",
       "description": "Your API key for the service.",
-      "envVar": "MY_API_KEY"
+      "envVar": "MY_API_KEY",
+      "sensitive": true
     }
   ]
 }
 ```
 
-When a user installs this extension, they will be prompted to enter their API
-key. The value will be saved to a `.env` file in the extension's directory
-(e.g., `<home>/.gemini/extensions/my-api-extension/.env`).
+- `name`: The setting's display name.
+- `description`: A clear explanation of the setting.
+- `envVar`: The environment variable name where the value is stored.
+- `sensitive`: If `true`, the value is stored in the system keychain and
+  obfuscated in the UI.
 
-You can view a list of an extension's settings by running:
+To update an extension's settings:
 
+```bash
+gemini extensions config <name> [setting] [--scope <scope>]
 ```
-gemini extensions list
-```
-
-and you can update a given setting using:
-
-```
-gemini extensions config <extension name> [setting name] [--scope <scope>]
-```
-
-- `--scope`: The scope to set the setting in (`user` or `workspace`). This is
-  optional and will default to `user`.
 
 ### Custom commands
 
-Extensions can provide [custom commands](../cli/custom-commands.md) by placing
-TOML files in a `commands/` subdirectory within the extension directory. These
-commands follow the same format as user and project custom commands and use
-standard naming conventions.
+Provide [custom commands](../cli/custom-commands.md) by placing TOML files in a
+`commands/` subdirectory. Gemini CLI uses the directory structure to determine
+the command name.
 
-**Example**
+For an extension named `gcp`:
 
-An extension named `gcp` with the following structure:
-
-```
-.gemini/extensions/gcp/
-├── gemini-extension.json
-└── commands/
-    ├── deploy.toml
-    └── gcs/
-        └── sync.toml
-```
-
-Would provide these commands:
-
-- `/deploy` - Shows as `[gcp] Custom command from deploy.toml` in help
-- `/gcs:sync` - Shows as `[gcp] Custom command from sync.toml` in help
+- `commands/deploy.toml` becomes `/deploy`
+- `commands/gcs/sync.toml` becomes `/gcs:sync` (namespaced with a colon)
 
 ### Hooks
 
-Extensions can provide [hooks](../hooks/index.md) to intercept and customize
-Gemini CLI behavior at specific lifecycle events. Hooks provided by an extension
-must be defined in a `hooks/hooks.json` file within the extension directory.
+Intercept and customize CLI behavior using [hooks](../hooks/index.md). Define
+hooks in a `hooks/hooks.json` file within your extension directory. Note that
+hooks are not defined in the `gemini-extension.json` manifest.
 
-> [!IMPORTANT] Hooks are not defined directly in `gemini-extension.json`. The
-> CLI specifically looks for the `hooks/hooks.json` file.
+### Agent skills
 
-### Agent Skills
-
-Extensions can bundle [Agent Skills](../cli/skills.md) to provide specialized
-workflows. Skills must be placed in a `skills/` directory within the extension.
-
-**Example**
-
-An extension with the following structure:
-
-```
-.gemini/extensions/my-extension/
-├── gemini-extension.json
-└── skills/
-    └── security-audit/
-        └── SKILL.md
-```
-
-Will expose a `security-audit` skill that the model can activate.
+Bundle [agent skills](../cli/skills.md) to provide specialized workflows. Place
+skill definitions in a `skills/` directory. For example,
+`skills/security-audit/SKILL.md` exposes a `security-audit` skill.
 
 ### Sub-agents
 
-> **Note: Sub-agents are currently an experimental feature.**
+> **Note:** Sub-agents are a preview feature currently under active development.
 
-Extensions can provide [sub-agents](../core/subagents.md) that users can
-delegate tasks to.
-
-To bundle sub-agents with your extension, create an `agents/` directory in your
-extension's root folder and add your agent definition files (`.md`) there.
-
-**Example**
-
-```
-.gemini/extensions/my-extension/
-├── gemini-extension.json
-└── agents/
-    ├── security-auditor.md
-    └── database-expert.md
-```
-
-Gemini CLI will automatically discover and load these agents when the extension
-is installed and enabled.
+Provide [sub-agents](../core/subagents.md) that users can delegate tasks to. Add
+agent definition files (`.md`) to an `agents/` directory in your extension root.
 
 ### Themes
 
@@ -351,30 +249,17 @@ the theme name in parentheses, e.g., `shades-of-green (my-green-extension)`.
 
 ### Conflict resolution
 
-Extension commands have the lowest precedence. When a conflict occurs with user
-or project commands:
-
-1. **No conflict**: Extension command uses its natural name (e.g., `/deploy`)
-2. **With conflict**: Extension command is renamed with the extension prefix
-   (e.g., `/gcp.deploy`)
-
-For example, if both a user and the `gcp` extension define a `deploy` command:
-
-- `/deploy` - Executes the user's deploy command
-- `/gcp.deploy` - Executes the extension's deploy command (marked with `[gcp]`
-  tag)
+Extension commands have the lowest precedence. If an extension command name
+conflicts with a user or project command, the extension command is prefixed with
+the extension name (e.g., `/gcp.deploy`) using a dot separator.
 
 ## Variables
 
-Gemini CLI extensions allow variable substitution in both
-`gemini-extension.json` and `hooks/hooks.json`. This can be useful if e.g., you
-need the current directory to run an MCP server using an argument like
-`"args": ["${extensionPath}${/}dist${/}server.js"]`.
+Gemini CLI supports variable substitution in `gemini-extension.json` and
+`hooks/hooks.json`.
 
-**Supported variables:**
-
-| variable                   | description                                                                                                                                                     |
-| -------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `${extensionPath}`         | The fully-qualified path of the extension in the user's filesystem e.g., '/Users/username/.gemini/extensions/example-extension'. This will not unwrap symlinks. |
-| `${workspacePath}`         | The fully-qualified path of the current workspace.                                                                                                              |
-| `${/} or ${pathSeparator}` | The path separator (differs per OS).                                                                                                                            |
+| Variable           | Description                                     |
+| :----------------- | :---------------------------------------------- |
+| `${extensionPath}` | The absolute path to the extension's directory. |
+| `${workspacePath}` | The absolute path to the current workspace.     |
+| `${/}`             | The platform-specific path separator.           |

docs/extensions/releasing.md

@@ -1,146 +1,117 @@
-# Extension releasing
+# Release extensions
 
-There are two primary ways of releasing extensions to users:
+Release Gemini CLI extensions to your users through a Git repository or GitHub
+Releases.
 
-- [Git repository](#releasing-through-a-git-repository)
-- [Github Releases](#releasing-through-github-releases)
+Git repository releases are the simplest approach and offer the most flexibility
+for managing development branches. GitHub Releases are more efficient for
+initial installations because they ship as single archives rather than requiring
+a full `git clone`. Use GitHub Releases if you need to include platform-specific
+binary files.
 
-Git repository releases tend to be the simplest and most flexible approach,
-while GitHub releases can be more efficient on initial install as they are
-shipped as single archives instead of requiring a git clone which downloads each
-file individually. Github releases may also contain platform specific archives
-if you need to ship platform specific binary files.
+## List your extension in the gallery
 
-## Releasing through a git repository
+The [Gemini CLI extension gallery](https://geminicli.com/extensions/browse/)
+automatically indexes public extensions to help users discover your work. You
+don't need to submit an issue or email us to list your extension.
 
-This is the most flexible and simple option. All you need to do is create a
-publicly accessible git repo (such as a public github repository) and then users
-can install your extension using `gemini extensions install <your-repo-uri>`.
-They can optionally depend on a specific ref (branch/tag/commit) using the
-`--ref=<some-ref>` argument, this defaults to the default branch.
+To have your extension automatically discovered and listed:
 
-Whenever commits are pushed to the ref that a user depends on, they will be
-prompted to update the extension. Note that this also allows for easy rollbacks,
-the HEAD commit is always treated as the latest version regardless of the actual
-version in the `gemini-extension.json` file.
+1.  **Use a public repository:** Ensure your extension is hosted in a public
+    GitHub repository.
+2.  **Add the GitHub topic:** Add the `gemini-cli-extension` topic to your
+    repository's **About** section. Our crawler uses this topic to find new
+    extensions.
+3.  **Place the manifest at the root:** Ensure your `gemini-extension.json` file
+    is in the absolute root of the repository or the release archive.
 
-### Managing release channels using a git repository
+Our system crawls tagged repositories daily. Once you tag your repository, your
+extension will appear in the gallery if it passes validation.
 
-Users can depend on any ref from your git repo, such as a branch or tag, which
-allows you to manage multiple release channels.
+## Release through a Git repository
 
-For instance, you can maintain a `stable` branch, which users can install this
-way `gemini extensions install <your-repo-uri> --ref=stable`. Or, you could make
-this the default by treating your default branch as your stable release branch,
-and doing development in a different branch (for instance called `dev`). You can
-maintain as many branches or tags as you like, providing maximum flexibility for
-you and your users.
+Releasing through Git is the most flexible option. Create a public Git
+repository and provide the URL to your users. They can then install your
+extension using `gemini extensions install <your-repo-uri>`.
 
-Note that these `ref` arguments can be tags, branches, or even specific commits,
-which allows users to depend on a specific version of your extension. It is up
-to you how you want to manage your tags and branches.
+Users can optionally depend on a specific branch, tag, or commit using the
+`--ref` argument. For example:
 
-### Example releasing flow using a git repo
+```bash
+gemini extensions install <your-repo-uri> --ref=stable
+```
 
-While there are many options for how you want to manage releases using a git
-flow, we recommend treating your default branch as your "stable" release branch.
-This means that the default behavior for
-`gemini extensions install <your-repo-uri>` is to be on the stable release
-branch.
+Whenever you push commits to the referenced branch, the CLI prompts users to
+update their installation. The `HEAD` commit is always treated as the latest
+version.
 
-Lets say you want to maintain three standard release channels, `stable`,
-`preview`, and `dev`. You would do all your standard development in the `dev`
-branch. When you are ready to do a preview release, you merge that branch into
-your `preview` branch. When you are ready to promote your preview branch to
-stable, you merge `preview` into your stable branch (which might be your default
-branch or a different branch).
+### Manage release channels
 
-You can also cherry pick changes from one branch into another using
-`git cherry-pick`, but do note that this will result in your branches having a
-slightly divergent history from each other, unless you force push changes to
-your branches on each release to restore the history to a clean slate (which may
-not be possible for the default branch depending on your repository settings).
-If you plan on doing cherry picks, you may want to avoid having your default
-branch be the stable branch to avoid force-pushing to the default branch which
-should generally be avoided.
+You can use branches or tags to manage different release channels, such as
+`stable`, `preview`, or `dev`.
 
-## Releasing through GitHub releases
+We recommend using your default branch as the stable release channel. This
+ensures that the default installation command always provides the most reliable
+version of your extension. You can then use a `dev` branch for active
+development and merge it into the default branch when you are ready for a
+release.
 
-Gemini CLI extensions can be distributed through
-[GitHub Releases](https://docs.github.com/en/repositories/releasing-projects-on-github/about-releases).
-This provides a faster and more reliable initial installation experience for
-users, as it avoids the need to clone the repository.
+## Release through GitHub Releases
 
-Each release includes at least one archive file, which contains the full
-contents of the repo at the tag that it was linked to. Releases may also include
-[pre-built archives](#custom-pre-built-archives) if your extension requires some
-build step or has platform specific binaries attached to it.
+Distributing extensions through
+[GitHub Releases](https://docs.github.com/en/repositories/releasing-projects-on-github/about-releases)
+provides a faster installation experience by avoiding a repository clone.
 
-When checking for updates, gemini will just look for the "latest" release on
-github (you must mark it as such when creating the release), unless the user
-installed a specific release by passing `--ref=<some-release-tag>`.
-
-You may also install extensions with the `--pre-release` flag in order to get
-the latest release regardless of whether it has been marked as "latest". This
-allows you to test that your release works before actually pushing it to all
-users.
+Gemini CLI checks for updates by looking for the **Latest** release on GitHub.
+Users can also install specific versions using the `--ref` argument with a
+release tag. Use the `--pre-release` flag to install the latest version even if
+it isn't marked as **Latest**.
 
 ### Custom pre-built archives
 
-Custom archives must be attached directly to the github release as assets and
-must be fully self-contained. This means they should include the entire
-extension, see [archive structure](#archive-structure).
+You can attach custom archives directly to your GitHub Release as assets. This
+is useful if your extension requires a build step or includes platform-specific
+binaries.
 
-If your extension is platform-independent, you can provide a single generic
-asset. In this case, there should be only one asset attached to the release.
+Custom archives must be fully self-contained and follow the required
+[archive structure](#archive-structure). If your extension is
+platform-independent, provide a single generic asset.
 
-Custom archives may also be used if you want to develop your extension within a
-larger repository, you can build an archive which has a different layout from
-the repo itself (for instance it might just be an archive of a subdirectory
-containing the extension).
+#### Platform-specific archives
 
-#### Platform specific archives
+To let Gemini CLI find the correct asset for a user's platform, use the
+following naming convention:
 
-To ensure Gemini CLI can automatically find the correct release asset for each
-platform, you must follow this naming convention. The CLI will search for assets
-in the following order:
-
-1.  **Platform and architecture-Specific:**
+1.  **Platform and architecture-specific:**
     `{platform}.{arch}.{name}.{extension}`
 2.  **Platform-specific:** `{platform}.{name}.{extension}`
-3.  **Generic:** If only one asset is provided, it will be used as a generic
-    fallback.
+3.  **Generic:** A single asset will be used as a fallback if no specific match
+    is found.
 
-- `{name}`: The name of your extension.
-- `{platform}`: The operating system. Supported values are:
-  - `darwin` (macOS)
-  - `linux`
-  - `win32` (Windows)
-- `{arch}`: The architecture. Supported values are:
-  - `x64`
-  - `arm64`
-- `{extension}`: The file extension of the archive (e.g., `.tar.gz` or `.zip`).
+Use these values for the placeholders:
+
+- `{name}`: Your extension name.
+- `{platform}`: Use `darwin` (macOS), `linux`, or `win32` (Windows).
+- `{arch}`: Use `x64` or `arm64`.
+- `{extension}`: Use `.tar.gz` or `.zip`.
 
 **Examples:**
 
 - `darwin.arm64.my-tool.tar.gz` (specific to Apple Silicon Macs)
-- `darwin.my-tool.tar.gz` (for all Macs)
+- `darwin.my-tool.tar.gz` (fallback for all Macs, e.g. Intel)
 - `linux.x64.my-tool.tar.gz`
 - `win32.my-tool.zip`
 
 #### Archive structure
 
-Archives must be fully contained extensions and have all the standard
-requirements - specifically the `gemini-extension.json` file must be at the root
-of the archive.
-
-The rest of the layout should look exactly the same as a typical extension, see
-[extensions.md](./index.md).
+Archives must be fully contained extensions. The `gemini-extension.json` file
+must be at the root of the archive. The rest of the layout should match a
+standard extension structure.
 
 #### Example GitHub Actions workflow
 
-Here is an example of a GitHub Actions workflow that builds and releases a
-Gemini CLI extension for multiple platforms:
+Use this example workflow to build and release your extension for multiple
+platforms:
 
 ```yaml
 name: Release Extension

docs/extensions/writing-extensions.md

@@ -1,18 +1,19 @@
-# Getting started with Gemini CLI extensions
+# Build Gemini CLI extensions
 
-This guide will walk you through creating your first Gemini CLI extension.
-You'll learn how to set up a new extension, add a custom tool via an MCP server,
-create a custom command, and provide context to the model with a `GEMINI.md`
-file.
+Gemini CLI extensions let you expand the capabilities of Gemini CLI by adding
+custom tools, commands, and context. This guide walks you through creating your
+first extension, from setting up a template to adding custom functionality and
+linking it for local development.
 
 ## Prerequisites
 
-Before you start, make sure you have the Gemini CLI installed and a basic
+Before you start, ensure you have the Gemini CLI installed and a basic
 understanding of Node.js.
 
-## When to use what
+## Extension features
 
-Extensions offer a variety of ways to customize Gemini CLI.
+Extensions offer several ways to customize Gemini CLI. Use this table to decide
+which features your extension needs.
 
 | Feature                                                        | What it is                                                                                                         | When to use it                                                                                                                                                                                                                                                                                 | Invoked by            |
 | :------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------- |
@@ -25,8 +26,8 @@ Extensions offer a variety of ways to customize Gemini CLI.
 
 ## Step 1: Create a new extension
 
-The easiest way to start is by using one of the built-in templates. We'll use
-the `mcp-server` example as our foundation.
+The easiest way to start is by using a built-in template. We'll use the
+`mcp-server` example as our foundation.
 
 Run the following command to create a new directory called `my-first-extension`
 with the template files:
@@ -35,7 +36,7 @@ with the template files:
 gemini extensions new my-first-extension mcp-server
 ```
 
-This will create a new directory with the following structure:
+This creates a directory with the following structure:
 
 ```
 my-first-extension/
@@ -46,12 +47,11 @@ my-first-extension/
 
 ## Step 2: Understand the extension files
 
-Let's look at the key files in your new extension.
+Your new extension contains several key files that define its behavior.
 
 ### `gemini-extension.json`
 
-This is the manifest file for your extension. It tells Gemini CLI how to load
-and use your extension.
+The manifest file tells Gemini CLI how to load and use your extension.
 
 ```json
 {
@@ -69,17 +69,15 @@ and use your extension.
 
 - `name`: The unique name for your extension.
 - `version`: The version of your extension.
-- `mcpServers`: This section defines one or more Model Context Protocol (MCP)
-  servers. MCP servers are how you can add new tools for the model to use.
-  - `command`, `args`, `cwd`: These fields specify how to start your server.
-    Notice the use of the `${extensionPath}` variable, which Gemini CLI replaces
-    with the absolute path to your extension's installation directory. This
-    allows your extension to work regardless of where it's installed.
+- `mcpServers`: Defines Model Context Protocol (MCP) servers to add new tools.
+  - `command`, `args`, `cwd`: Specify how to start your server. The
+    `${extensionPath}` variable is replaced with the absolute path to your
+    extension's directory.
 
 ### `example.js`
 
-This file contains the source code for your MCP server. It's a simple Node.js
-server that uses the `@modelcontextprotocol/sdk`.
+This file contains the source code for your MCP server. It uses the
+`@modelcontextprotocol/sdk` to define tools.
 
 ```javascript
 /**
@@ -121,24 +119,49 @@ server.registerTool(
   },
 );
 
-// ... (prompt registration omitted for brevity)
-
 const transport = new StdioServerTransport();
 await server.connect(transport);
 ```
 
-This server defines a single tool called `fetch_posts` that fetches data from a
-public API.
-
 ### `package.json`
 
-This is the standard configuration file for a Node.js project. It defines
-dependencies and scripts.
+The standard configuration file for a Node.js project. It defines dependencies
+and scripts for your extension.
 
-## Step 3: Link your extension
+## Step 3: Add extension settings
 
-Before you can use the extension, you need to link it to your Gemini CLI
-installation for local development.
+Some extensions need configuration, such as API keys or user preferences. Let's
+add a setting for an API key.
+
+1.  Open `gemini-extension.json`.
+2.  Add a `settings` array to the configuration:
+
+    ```json
+    {
+      "name": "mcp-server-example",
+      "version": "1.0.0",
+      "settings": [
+        {
+          "name": "API Key",
+          "description": "The API key for the service.",
+          "envVar": "MY_SERVICE_API_KEY",
+          "sensitive": true
+        }
+      ],
+      "mcpServers": {
+        // ...
+      }
+    }
+    ```
+
+When a user installs this extension, Gemini CLI will prompt them to enter the
+"API Key". The value will be stored securely in the system keychain (because
+`sensitive` is true) and injected into the MCP server's process as the
+`MY_SERVICE_API_KEY` environment variable.
+
+## Step 4: Link your extension
+
+Link your extension to your Gemini CLI installation for local development.
 
 1.  **Install dependencies:**
 
@@ -150,20 +173,19 @@ installation for local development.
 2.  **Link the extension:**
 
     The `link` command creates a symbolic link from the Gemini CLI extensions
-    directory to your development directory. This means any changes you make
-    will be reflected immediately without needing to reinstall.
+    directory to your development directory. Changes you make are reflected
+    immediately.
 
     ```bash
     gemini extensions link .
     ```
 
-Now, restart your Gemini CLI session. The new `fetch_posts` tool will be
-available. You can test it by asking: "fetch posts".
+Restart your Gemini CLI session to use the new `fetch_posts` tool. Test it by
+asking: "fetch posts".
 
-## Step 4: Add a custom command
+## Step 5: Add a custom command
 
-Custom commands provide a way to create shortcuts for complex prompts. Let's add
-a command that searches for a pattern in your code.
+Custom commands create shortcuts for complex prompts.
 
 1.  Create a `commands` directory and a subdirectory for your command group:
 
@@ -182,18 +204,17 @@ a command that searches for a pattern in your code.
     """
     ```
 
-    This command, `/fs:grep-code`, will take an argument, run the `grep` shell
-    command with it, and pipe the results into a prompt for summarization.
+    This command, `/fs:grep-code`, takes an argument, runs the `grep` shell
+    command, and pipes the results into a prompt for summarization.
 
-After saving the file, restart the Gemini CLI. You can now run
-`/fs:grep-code "some pattern"` to use your new command.
+After saving the file, restart Gemini CLI. Run `/fs:grep-code "some pattern"` to
+use your new command.
 
-## Step 5: Add a custom `GEMINI.md`
+## Step 6: Add a custom `GEMINI.md`
 
-You can provide persistent context to the model by adding a `GEMINI.md` file to
-your extension. This is useful for giving the model instructions on how to
-behave or information about your extension's tools. Note that you may not always
-need this for extensions built to expose commands and prompts.
+Provide persistent context to the model by adding a `GEMINI.md` file to your
+extension. This is useful for setting behavior or providing essential tool
+information.
 
 1.  Create a file named `GEMINI.md` in the root of your extension directory:
 
@@ -204,7 +225,7 @@ need this for extensions built to expose commands and prompts.
     posts, use the `fetch_posts` tool. Be concise in your responses.
     ```
 
-2.  Update your `gemini-extension.json` to tell the CLI to load this file:
+2.  Update your `gemini-extension.json` to load this file:
 
     ```json
     {
@@ -221,14 +242,13 @@ need this for extensions built to expose commands and prompts.
     }
     ```
 
-Restart the CLI again. The model will now have the context from your `GEMINI.md`
-file in every session where the extension is active.
+Restart Gemini CLI. The model now has the context from your `GEMINI.md` file in
+every session where the extension is active.
 
-## (Optional) Step 6: Add an Agent Skill
+## (Optional) Step 7: Add an Agent Skill
 
-[Agent Skills](../cli/skills.md) let you bundle specialized expertise and
-procedural workflows. Unlike `GEMINI.md`, which provides persistent context,
-skills are activated only when needed, saving context tokens.
+[Agent Skills](../cli/skills.md) bundle specialized expertise and workflows.
+Skills are activated only when needed, which saves context tokens.
 
 1.  Create a `skills` directory and a subdirectory for your skill:
 
@@ -255,28 +275,18 @@ skills are activated only when needed, saving context tokens.
     3. Suggest remediation steps for any findings.
     ```
 
-Skills bundled with your extension are automatically discovered and can be
-activated by the model during a session when it identifies a relevant task.
+Gemini CLI automatically discovers skills bundled with your extension. The model
+activates them when it identifies a relevant task.
 
-## Step 7: Release your extension
+## Step 8: Release your extension
 
-Once you're happy with your extension, you can share it with others. The two
-primary ways of releasing extensions are via a Git repository or through GitHub
-Releases. Using a public Git repository is the simplest method.
+When your extension is ready, share it with others via a Git repository or
+GitHub Releases. Refer to the [Extension Releasing Guide](./releasing.md) for
+detailed instructions and learn how to list your extension in the gallery.
 
-For detailed instructions on both methods, please refer to the
-[Extension Releasing Guide](./releasing.md).
+## Next steps
 
-## Conclusion
-
-You've successfully created a Gemini CLI extension! You learned how to:
-
-- Bootstrap a new extension from a template.
-- Add custom tools with an MCP server.
-- Create convenient custom commands.
-- Provide persistent context to the model.
-- Bundle specialized Agent Skills.
-- Link your extension for local development.
-
-From here, you can explore more advanced features and build powerful new
-capabilities into the Gemini CLI.
+- [Extension reference](reference.md): Deeply understand the extension format,
+  commands, and configuration.
+- [Best practices](best-practices.md): Learn strategies for building great
+  extensions.

docs/get-started/configuration-v1.md

@@ -1,882 +0,0 @@
-# Gemini CLI configuration
-
-**Note on deprecated configuration format**
-
-This document describes the legacy v1 format for the `settings.json` file. This
-format is now deprecated.
-
-- The new format will be supported in the stable release starting
-  **[09/10/25]**.
-- Automatic migration from the old format to the new format will begin on
-  **[09/17/25]**.
-
-For details on the new, recommended format, please see the
-[current Configuration documentation](./configuration.md).
-
-Gemini CLI offers several ways to configure its behavior, including environment
-variables, command-line arguments, and settings files. This document outlines
-the different configuration methods and available settings.
-
-## Configuration layers
-
-Configuration is applied in the following order of precedence (lower numbers are
-overridden by higher numbers):
-
-1.  **Default values:** Hardcoded defaults within the application.
-2.  **System defaults file:** System-wide default settings that can be
-    overridden by other settings files.
-3.  **User settings file:** Global settings for the current user.
-4.  **Project settings file:** Project-specific settings.
-5.  **System settings file:** System-wide settings that override all other
-    settings files.
-6.  **Environment variables:** System-wide or session-specific variables,
-    potentially loaded from `.env` files.
-7.  **Command-line arguments:** Values passed when launching the CLI.
-
-## Settings files
-
-Gemini CLI uses JSON settings files for persistent configuration. There are four
-locations for these files:
-
-- **System defaults file:**
-  - **Location:** `/etc/gemini-cli/system-defaults.json` (Linux),
-    `C:\ProgramData\gemini-cli\system-defaults.json` (Windows) or
-    `/Library/Application Support/GeminiCli/system-defaults.json` (macOS). The
-    path can be overridden using the `GEMINI_CLI_SYSTEM_DEFAULTS_PATH`
-    environment variable.
-  - **Scope:** Provides a base layer of system-wide default settings. These
-    settings have the lowest precedence and are intended to be overridden by
-    user, project, or system override settings.
-- **User settings file:**
-  - **Location:** `~/.gemini/settings.json` (where `~` is your home directory).
-  - **Scope:** Applies to all Gemini CLI sessions for the current user. User
-    settings override system defaults.
-- **Project settings file:**
-  - **Location:** `.gemini/settings.json` within your project's root directory.
-  - **Scope:** Applies only when running Gemini CLI from that specific project.
-    Project settings override user settings and system defaults.
-- **System settings file:**
-  - **Location:** `/etc/gemini-cli/settings.json` (Linux),
-    `C:\ProgramData\gemini-cli\settings.json` (Windows) or
-    `/Library/Application Support/GeminiCli/settings.json` (macOS). The path can
-    be overridden using the `GEMINI_CLI_SYSTEM_SETTINGS_PATH` environment
-    variable.
-  - **Scope:** Applies to all Gemini CLI sessions on the system, for all users.
-    System settings act as overrides, taking precedence over all other settings
-    files. May be useful for system administrators at enterprises to have
-    controls over users' Gemini CLI setups.
-
-**Note on environment variables in settings:** String values within your
-`settings.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"`.
-
-> **Note for Enterprise Users:** For guidance on deploying and managing Gemini
-> CLI in a corporate environment, please see the
-> [Enterprise Configuration](../cli/enterprise.md) documentation.
-
-### The `.gemini` directory in your project
-
-In addition to a project settings file, a project's `.gemini` directory can
-contain other project-specific files related to Gemini CLI's operation, such as:
-
-- [Custom sandbox profiles](#sandboxing) (e.g.,
-  `.gemini/sandbox-macos-custom.sb`, `.gemini/sandbox.Dockerfile`).
-
-### Available settings in `settings.json`:
-
-- **`contextFileName`** (string or array of strings):
-  - **Description:** Specifies the filename for context files (e.g.,
-    `GEMINI.md`, `AGENTS.md`). Can be a single filename or a list of accepted
-    filenames.
-  - **Default:** `GEMINI.md`
-  - **Example:** `"contextFileName": "AGENTS.md"`
-
-- **`bugCommand`** (object):
-  - **Description:** Overrides the default URL for the `/bug` command.
-  - **Default:**
-    `"urlTemplate": "https://github.com/google-gemini/gemini-cli/issues/new?template=bug_report.yml&title={title}&info={info}"`
-  - **Properties:**
-    - **`urlTemplate`** (string): A URL that can contain `{title}` and `{info}`
-      placeholders.
-  - **Example:**
-    ```json
-    "bugCommand": {
-      "urlTemplate": "https://bug.example.com/new?title={title}&info={info}"
-    }
-    ```
-
-- **`fileFiltering`** (object):
-  - **Description:** Controls git-aware file filtering behavior for @ commands
-    and file discovery tools.
-  - **Default:** `"respectGitIgnore": true, "enableRecursiveFileSearch": true`
-  - **Properties:**
-    - **`respectGitIgnore`** (boolean): Whether to respect .gitignore patterns
-      when discovering files. When set to `true`, git-ignored files (like
-      `node_modules/`, `dist/`, `.env`) are automatically excluded from @
-      commands and file listing operations.
-    - **`enableRecursiveFileSearch`** (boolean): Whether to enable searching
-      recursively for filenames under the current tree when completing @
-      prefixes in the prompt.
-    - **`disableFuzzySearch`** (boolean): When `true`, disables the fuzzy search
-      capabilities when searching for files, which can improve performance on
-      projects with a large number of files.
-  - **Example:**
-    ```json
-    "fileFiltering": {
-      "respectGitIgnore": true,
-      "enableRecursiveFileSearch": false,
-      "disableFuzzySearch": true
-    }
-    ```
-
-### Troubleshooting file search performance
-
-If you are experiencing performance issues with file searching (e.g., with `@`
-completions), especially in projects with a very large number of files, here are
-a few things you can try in order of recommendation:
-
-1.  **Use `.geminiignore`:** Create a `.geminiignore` file in your project root
-    to exclude directories that contain a large number of files that you don't
-    need to reference (e.g., build artifacts, logs, `node_modules`). Reducing
-    the total number of files crawled is the most effective way to improve
-    performance.
-
-2.  **Disable fuzzy search:** If ignoring files is not enough, you can disable
-    fuzzy search by setting `disableFuzzySearch` to `true` in your
-    `settings.json` file. This will use a simpler, non-fuzzy matching algorithm,
-    which can be faster.
-
-3.  **Disable recursive file search:** As a last resort, you can disable
-    recursive file search entirely by setting `enableRecursiveFileSearch` to
-    `false`. This will be the fastest option as it avoids a recursive crawl of
-    your project. However, it means you will need to type the full path to files
-    when using `@` completions.
-
-- **`coreTools`** (array of strings):
-  - **Description:** Allows you to specify a list of core tool names that should
-    be made available to the model. This can be used to restrict the set of
-    built-in tools. See [Built-in Tools](../core/tools-api.md#built-in-tools)
-    for a list of core tools. You can also specify command-specific restrictions
-    for tools that support it, like the `ShellTool`. For example,
-    `"coreTools": ["ShellTool(ls -l)"]` will only allow the `ls -l` command to
-    be executed.
-  - **Default:** All tools available for use by the Gemini model.
-  - **Example:** `"coreTools": ["ReadFileTool", "GlobTool", "ShellTool(ls)"]`.
-
-- **`allowedTools`** (array of strings) [DEPRECATED]:
-  - **Default:** `undefined`
-  - **Description:** A list of tool names that will bypass the confirmation
-    dialog. This is useful for tools that you trust and use frequently. The
-    match semantics are the same as `coreTools`. **Deprecated**: Use the
-    [Policy Engine](../core/policy-engine.md) instead.
-  - **Example:** `"allowedTools": ["ShellTool(git status)"]`.
-
-- **`excludeTools`** (array of strings) [DEPRECATED]:
-  - **Description:** Allows you to specify a list of core tool names that should
-    be excluded from the model. A tool listed in both `excludeTools` and
-    `coreTools` is excluded. You can also specify command-specific restrictions
-    for tools that support it, like the `ShellTool`. For example,
-    `"excludeTools": ["ShellTool(rm -rf)"]` will block the `rm -rf` command.
-    **Deprecated**: Use the [Policy Engine](../core/policy-engine.md) instead.
-  - **Default**: No tools excluded.
-  - **Example:** `"excludeTools": ["run_shell_command", "findFiles"]`.
-  - **Security Note:** Command-specific restrictions in `excludeTools` for
-    `run_shell_command` are based on simple string matching and can be easily
-    bypassed. This feature is **not a security mechanism** and should not be
-    relied upon to safely execute untrusted code. It is recommended to use
-    `coreTools` to explicitly select commands that can be executed.
-
-- **`allowMCPServers`** (array of strings):
-  - **Description:** Allows you to specify a list of MCP server names that
-    should be made available to the model. This can be used to restrict the set
-    of MCP servers to connect to. Note that this will be ignored if
-    `--allowed-mcp-server-names` is set.
-  - **Default:** All MCP servers are available for use by the Gemini model.
-  - **Example:** `"allowMCPServers": ["myPythonServer"]`.
-  - **Security note:** This uses simple string matching on MCP server names,
-    which can be modified. If you're a system administrator looking to prevent
-    users from bypassing this, consider configuring the `mcpServers` at the
-    system settings level such that the user will not be able to configure any
-    MCP servers of their own. This should not be used as an airtight security
-    mechanism.
-
-- **`excludeMCPServers`** (array of strings):
-  - **Description:** Allows you to specify a list of MCP server names that
-    should be excluded from the model. A server listed in both
-    `excludeMCPServers` and `allowMCPServers` is excluded. Note that this will
-    be ignored if `--allowed-mcp-server-names` is set.
-  - **Default**: No MCP servers excluded.
-  - **Example:** `"excludeMCPServers": ["myNodeServer"]`.
-  - **Security note:** This uses simple string matching on MCP server names,
-    which can be modified. If you're a system administrator looking to prevent
-    users from bypassing this, consider configuring the `mcpServers` at the
-    system settings level such that the user will not be able to configure any
-    MCP servers of their own. This should not be used as an airtight security
-    mechanism.
-
-- **`theme`** (string):
-  - **Description:** Sets the visual [theme](../cli/themes.md) for Gemini CLI.
-  - **Default:** `"Default"`
-  - **Example:** `"theme": "GitHub"`
-
-- **`vimMode`** (boolean):
-  - **Description:** Enables or disables vim mode for input editing. When
-    enabled, the input area supports vim-style navigation and editing commands
-    with NORMAL and INSERT modes. The vim mode status is displayed in the footer
-    and persists between sessions.
-  - **Default:** `false`
-  - **Example:** `"vimMode": true`
-
-- **`sandbox`** (boolean or string):
-  - **Description:** Controls whether and how to use sandboxing for tool
-    execution. If set to `true`, Gemini CLI uses a pre-built
-    `gemini-cli-sandbox` Docker image. For more information, see
-    [Sandboxing](#sandboxing).
-  - **Default:** `false`
-  - **Example:** `"sandbox": "docker"`
-
-- **`toolDiscoveryCommand`** (string):
-  - **Description:** Defines a custom shell command for discovering tools from
-    your project. The shell command must return on `stdout` a JSON array of
-    [function declarations](https://ai.google.dev/gemini-api/docs/function-calling#function-declarations).
-    Tool wrappers are optional.
-  - **Default:** Empty
-  - **Example:** `"toolDiscoveryCommand": "bin/get_tools"`
-
-- **`toolCallCommand`** (string):
-  - **Description:** Defines a custom shell command for calling a specific tool
-    that was discovered using `toolDiscoveryCommand`. The shell command must
-    meet the following criteria:
-    - It must take function `name` (exactly as in
-      [function declaration](https://ai.google.dev/gemini-api/docs/function-calling#function-declarations))
-      as first command line argument.
-    - It must read function arguments as JSON on `stdin`, analogous to
-      [`functionCall.args`](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#functioncall).
-    - It must return function output as JSON on `stdout`, analogous to
-      [`functionResponse.response.content`](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#functionresponse).
-  - **Default:** Empty
-  - **Example:** `"toolCallCommand": "bin/call_tool"`
-
-- **`mcpServers`** (object):
-  - **Description:** Configures connections to one or more Model-Context
-    Protocol (MCP) servers for discovering and using custom tools. Gemini CLI
-    attempts to connect to each configured MCP server to discover available
-    tools. If multiple MCP servers expose a tool with the same name, the tool
-    names will be prefixed with the server alias you defined in the
-    configuration (e.g., `serverAlias__actualToolName`) to avoid conflicts. Note
-    that the system might strip certain schema properties from MCP tool
-    definitions for compatibility. At least one of `command`, `url`, or
-    `httpUrl` must be provided. If multiple are specified, the order of
-    precedence is `httpUrl`, then `url`, then `command`.
-  - **Default:** Empty
-  - **Properties:**
-    - **`<SERVER_NAME>`** (object): The server parameters for the named server.
-      - `command` (string, optional): The command to execute to start the MCP
-        server via standard I/O.
-      - `args` (array of strings, optional): Arguments to pass to the command.
-      - `env` (object, optional): Environment variables to set for the server
-        process.
-      - `cwd` (string, optional): The working directory in which to start the
-        server.
-      - `url` (string, optional): The URL of an MCP server that uses Server-Sent
-        Events (SSE) for communication.
-      - `httpUrl` (string, optional): The URL of an MCP server that uses
-        streamable HTTP for communication.
-      - `headers` (object, optional): A map of HTTP headers to send with
-        requests to `url` or `httpUrl`.
-      - `timeout` (number, optional): Timeout in milliseconds for requests to
-        this MCP server.
-      - `trust` (boolean, optional): Trust this server and bypass all tool call
-        confirmations.
-      - `description` (string, optional): A brief description of the server,
-        which may be used for display purposes.
-      - `includeTools` (array of strings, optional): List of tool names to
-        include from this MCP server. When specified, only the tools listed here
-        will be available from this server (allowlist behavior). If not
-        specified, all tools from the server are enabled by default.
-      - `excludeTools` (array of strings, optional): List of tool names to
-        exclude from this MCP server. Tools listed here will not be available to
-        the model, even if they are exposed by the server. **Note:**
-        `excludeTools` takes precedence over `includeTools` - if a tool is in
-        both lists, it will be excluded.
-  - **Example:**
-    ```json
-    "mcpServers": {
-      "myPythonServer": {
-        "command": "python",
-        "args": ["mcp_server.py", "--port", "8080"],
-        "cwd": "./mcp_tools/python",
-        "timeout": 5000,
-        "includeTools": ["safe_tool", "file_reader"],
-      },
-      "myNodeServer": {
-        "command": "node",
-        "args": ["mcp_server.js"],
-        "cwd": "./mcp_tools/node",
-        "excludeTools": ["dangerous_tool", "file_deleter"]
-      },
-      "myDockerServer": {
-        "command": "docker",
-        "args": ["run", "-i", "--rm", "-e", "API_KEY", "ghcr.io/foo/bar"],
-        "env": {
-          "API_KEY": "$MY_API_TOKEN"
-        }
-      },
-      "mySseServer": {
-        "url": "http://localhost:8081/events",
-        "headers": {
-          "Authorization": "Bearer $MY_SSE_TOKEN"
-        },
-        "description": "An example SSE-based MCP server."
-      },
-      "myStreamableHttpServer": {
-        "httpUrl": "http://localhost:8082/stream",
-        "headers": {
-          "X-API-Key": "$MY_HTTP_API_KEY"
-        },
-        "description": "An example Streamable HTTP-based MCP server."
-      }
-    }
-    ```
-
-- **`checkpointing`** (object):
-  - **Description:** Configures the checkpointing feature, which allows you to
-    save and restore conversation and file states. See the
-    [Checkpointing documentation](../cli/checkpointing.md) for more details.
-  - **Default:** `{"enabled": false}`
-  - **Properties:**
-    - **`enabled`** (boolean): When `true`, the `/restore` command is available.
-
-- **`preferredEditor`** (string):
-  - **Description:** Specifies the preferred editor to use for viewing diffs.
-  - **Default:** `vscode`
-  - **Example:** `"preferredEditor": "vscode"`
-
-- **`telemetry`** (object)
-  - **Description:** Configures logging and metrics collection for Gemini CLI.
-    For more information, see [Telemetry](../cli/telemetry.md).
-  - **Default:**
-    `{"enabled": false, "target": "local", "otlpEndpoint": "http://localhost:4317", "logPrompts": true}`
-  - **Properties:**
-    - **`enabled`** (boolean): Whether or not telemetry is enabled.
-    - **`target`** (string): The destination for collected telemetry. Supported
-      values are `local` and `gcp`.
-    - **`otlpEndpoint`** (string): The endpoint for the OTLP Exporter.
-    - **`logPrompts`** (boolean): Whether or not to include the content of user
-      prompts in the logs.
-  - **Example:**
-    ```json
-    "telemetry": {
-      "enabled": true,
-      "target": "local",
-      "otlpEndpoint": "http://localhost:16686",
-      "logPrompts": false
-    }
-    ```
-- **`usageStatisticsEnabled`** (boolean):
-  - **Description:** Enables or disables the collection of usage statistics. See
-    [Usage Statistics](#usage-statistics) for more information.
-  - **Default:** `true`
-  - **Example:**
-    ```json
-    "usageStatisticsEnabled": false
-    ```
-
-- **`hideTips`** (boolean):
-  - **Description:** Enables or disables helpful tips in the CLI interface.
-  - **Default:** `false`
-  - **Example:**
-
-    ```json
-    "hideTips": true
-    ```
-
-- **`hideBanner`** (boolean):
-  - **Description:** Enables or disables the startup banner (ASCII art logo) in
-    the CLI interface.
-  - **Default:** `false`
-  - **Example:**
-
-    ```json
-    "hideBanner": true
-    ```
-
-- **`maxSessionTurns`** (number):
-  - **Description:** Sets the maximum number of turns for a session. If the
-    session exceeds this limit, the CLI will stop processing and start a new
-    chat.
-  - **Default:** `-1` (unlimited)
-  - **Example:**
-    ```json
-    "maxSessionTurns": 10
-    ```
-
-- **`summarizeToolOutput`** (object):
-  - **Description:** Enables or disables the summarization of tool output. You
-    can specify the token budget for the summarization using the `tokenBudget`
-    setting.
-  - Note: Currently only the `run_shell_command` tool is supported.
-  - **Default:** `{}` (Disabled by default)
-  - **Example:**
-    ```json
-    "summarizeToolOutput": {
-      "run_shell_command": {
-        "tokenBudget": 2000
-      }
-    }
-    ```
-
-- **`excludedProjectEnvVars`** (array of strings):
-  - **Description:** Specifies environment variables that should be excluded
-    from being loaded from project `.env` files. This prevents project-specific
-    environment variables (like `DEBUG=true`) from interfering with gemini-cli
-    behavior. Variables from `.gemini/.env` files are never excluded.
-  - **Default:** `["DEBUG", "DEBUG_MODE"]`
-  - **Example:**
-    ```json
-    "excludedProjectEnvVars": ["DEBUG", "DEBUG_MODE", "NODE_ENV"]
-    ```
-
-- **`includeDirectories`** (array of strings):
-  - **Description:** Specifies an array of additional absolute or relative paths
-    to include in the workspace context. Missing directories will be skipped
-    with a warning by default. Paths can use `~` to refer to the user's home
-    directory. This setting can be combined with the `--include-directories`
-    command-line flag.
-  - **Default:** `[]`
-  - **Example:**
-    ```json
-    "includeDirectories": [
-      "/path/to/another/project",
-      "../shared-library",
-      "~/common-utils"
-    ]
-    ```
-
-- **`loadMemoryFromIncludeDirectories`** (boolean):
-  - **Description:** Controls the behavior of the `/memory refresh` command. If
-    set to `true`, `GEMINI.md` files should be loaded from all directories that
-    are added. If set to `false`, `GEMINI.md` should only be loaded from the
-    current directory.
-  - **Default:** `false`
-  - **Example:**
-    ```json
-    "loadMemoryFromIncludeDirectories": true
-    ```
-
-- **`showLineNumbers`** (boolean):
-  - **Description:** Controls whether line numbers are displayed in code blocks
-    in the CLI output.
-  - **Default:** `true`
-  - **Example:**
-    ```json
-    "showLineNumbers": false
-    ```
-
-- **`accessibility`** (object):
-  - **Description:** Configures accessibility features for the CLI.
-  - **Properties:**
-    - **`screenReader`** (boolean): Enables screen reader mode, which adjusts
-      the TUI for better compatibility with screen readers. This can also be
-      enabled with the `--screen-reader` command-line flag, which will take
-      precedence over the setting.
-    - **`disableLoadingPhrases`** (boolean): Disables the display of loading
-      phrases during operations.
-  - **Default:** `{"screenReader": false, "disableLoadingPhrases": false}`
-  - **Example:**
-    ```json
-    "accessibility": {
-      "screenReader": true,
-      "disableLoadingPhrases": true
-    }
-    ```
-
-### Example `settings.json`:
-
-```json
-{
-  "theme": "GitHub",
-  "sandbox": "docker",
-  "toolDiscoveryCommand": "bin/get_tools",
-  "toolCallCommand": "bin/call_tool",
-  "mcpServers": {
-    "mainServer": {
-      "command": "bin/mcp_server.py"
-    },
-    "anotherServer": {
-      "command": "node",
-      "args": ["mcp_server.js", "--verbose"]
-    }
-  },
-  "telemetry": {
-    "enabled": true,
-    "target": "local",
-    "otlpEndpoint": "http://localhost:4317",
-    "logPrompts": true
-  },
-  "usageStatisticsEnabled": true,
-  "hideTips": false,
-  "hideBanner": false,
-  "maxSessionTurns": 10,
-  "summarizeToolOutput": {
-    "run_shell_command": {
-      "tokenBudget": 100
-    }
-  },
-  "excludedProjectEnvVars": ["DEBUG", "DEBUG_MODE", "NODE_ENV"],
-  "includeDirectories": ["path/to/dir1", "~/path/to/dir2", "../path/to/dir3"],
-  "loadMemoryFromIncludeDirectories": true
-}
-```
-
-## Shell history
-
-The CLI keeps a history of shell commands you run. To avoid conflicts between
-different projects, this history is stored in a project-specific directory
-within your user's home folder.
-
-- **Location:** `~/.gemini/tmp/<project_hash>/shell_history`
-  - `<project_hash>` is a unique identifier generated from your project's root
-    path.
-  - The history is stored in a file named `shell_history`.
-
-## Environment variables and `.env` files
-
-Environment variables are a common way to configure applications, especially for
-sensitive information like API keys or for settings that might change between
-environments. For authentication setup, see the
-[Authentication documentation](./authentication.md) which covers all available
-authentication methods.
-
-The CLI automatically loads environment variables from an `.env` file. The
-loading order is:
-
-1.  `.env` file in the current working directory.
-2.  If not found, it searches upwards in parent directories until it finds an
-    `.env` file or reaches the project root (identified by a `.git` folder) or
-    the home directory.
-3.  If still not found, it looks for `~/.env` (in the user's home directory).
-
-**Environment variable exclusion:** Some environment variables (like `DEBUG` and
-`DEBUG_MODE`) are automatically excluded from being loaded from project `.env`
-files to prevent interference with gemini-cli behavior. Variables from
-`.gemini/.env` files are never excluded. You can customize this behavior using
-the `excludedProjectEnvVars` setting in your `settings.json` file.
-
-- **`GEMINI_API_KEY`**:
-  - Your API key for the Gemini API.
-  - One of several available [authentication methods](./authentication.md).
-  - Set this in your shell profile (e.g., `~/.bashrc`, `~/.zshrc`) or an `.env`
-    file.
-- **`GEMINI_MODEL`**:
-  - Specifies the default Gemini model to use.
-  - Overrides the hardcoded default
-  - Example: `export GEMINI_MODEL="gemini-2.5-flash"`
-- **`GOOGLE_API_KEY`**:
-  - Your Google Cloud API key.
-  - Required for using Vertex AI in express mode.
-  - Ensure you have the necessary permissions.
-  - Example: `export GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY"`.
-- **`GOOGLE_CLOUD_PROJECT`**:
-  - Your Google Cloud Project ID.
-  - Required for using Code Assist or Vertex AI.
-  - If using Vertex AI, ensure you have the necessary permissions in this
-    project.
-  - **Cloud Shell note:** When running in a Cloud Shell environment, this
-    variable defaults to a special project allocated for Cloud Shell users. If
-    you have `GOOGLE_CLOUD_PROJECT` set in your global environment in Cloud
-    Shell, it will be overridden by this default. To use a different project in
-    Cloud Shell, you must define `GOOGLE_CLOUD_PROJECT` in a `.env` file.
-  - Example: `export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"`.
-- **`GOOGLE_APPLICATION_CREDENTIALS`** (string):
-  - **Description:** The path to your Google Application Credentials JSON file.
-  - **Example:**
-    `export GOOGLE_APPLICATION_CREDENTIALS="/path/to/your/credentials.json"`
-- **`OTLP_GOOGLE_CLOUD_PROJECT`**:
-  - Your Google Cloud Project ID for Telemetry in Google Cloud
-  - Example: `export OTLP_GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"`.
-- **`GOOGLE_CLOUD_LOCATION`**:
-  - Your Google Cloud Project Location (e.g., us-central1).
-  - Required for using Vertex AI in non express mode.
-  - Example: `export GOOGLE_CLOUD_LOCATION="YOUR_PROJECT_LOCATION"`.
-- **`GEMINI_SANDBOX`**:
-  - Alternative to the `sandbox` setting in `settings.json`.
-  - Accepts `true`, `false`, `docker`, `podman`, or a custom command string.
-- **`HTTP_PROXY` / `HTTPS_PROXY`**:
-  - Specifies the proxy server to use for outgoing HTTP/HTTPS requests.
-  - Example: `export HTTPS_PROXY="http://proxy.example.com:8080"`
-- **`SEATBELT_PROFILE`** (macOS specific):
-  - Switches the Seatbelt (`sandbox-exec`) profile on macOS.
-  - `permissive-open`: (Default) Restricts writes to the project folder (and a
-    few other folders, see
-    `packages/cli/src/utils/sandbox-macos-permissive-open.sb`) but allows other
-    operations.
-  - `strict`: Uses a strict profile that declines operations by default.
-  - `<profile_name>`: Uses a custom profile. To define a custom profile, create
-    a file named `sandbox-macos-<profile_name>.sb` in your project's `.gemini/`
-    directory (e.g., `my-project/.gemini/sandbox-macos-custom.sb`).
-- **`DEBUG` or `DEBUG_MODE`** (often used by underlying libraries or the CLI
-  itself):
-  - Set to `true` or `1` to enable verbose debug logging, which can be helpful
-    for troubleshooting.
-  - **Note:** These variables are automatically excluded from project `.env`
-    files by default to prevent interference with gemini-cli behavior. Use
-    `.gemini/.env` files if you need to set these for gemini-cli specifically.
-- **`NO_COLOR`**:
-  - Set to any value to disable all color output in the CLI.
-- **`CLI_TITLE`**:
-  - Set to a string to customize the title of the CLI.
-- **`CODE_ASSIST_ENDPOINT`**:
-  - Specifies the endpoint for the code assist server.
-  - This is useful for development and testing.
-
-## Command-line arguments
-
-Arguments passed directly when running the CLI can override other configurations
-for that specific session.
-
-- **`--model <model_name>`** (**`-m <model_name>`**):
-  - Specifies the Gemini model to use for this session.
-  - Example: `npm start -- --model gemini-1.5-pro-latest`
-- **`--prompt <your_prompt>`** (**`-p <your_prompt>`**):
-  - Used to pass a prompt directly to the command. This invokes Gemini CLI in a
-    non-interactive mode.
-- **`--prompt-interactive <your_prompt>`** (**`-i <your_prompt>`**):
-  - Starts an interactive session with the provided prompt as the initial input.
-  - The prompt is processed within the interactive session, not before it.
-  - Cannot be used when piping input from stdin.
-  - Example: `gemini -i "explain this code"`
-- **`--sandbox`** (**`-s`**):
-  - Enables sandbox mode for this session.
-- **`--sandbox-image`**:
-  - Sets the sandbox image URI.
-- **`--debug`** (**`-d`**):
-  - Enables debug mode for this session, providing more verbose output.
-
-- **`--help`** (or **`-h`**):
-  - Displays help information about command-line arguments.
-- **`--show-memory-usage`**:
-  - Displays the current memory usage.
-- **`--yolo`**:
-  - Enables YOLO mode, which automatically approves all tool calls.
-- **`--approval-mode <mode>`**:
-  - Sets the approval mode for tool calls. Available modes:
-    - `default`: Prompt for approval on each tool call (default behavior)
-    - `auto_edit`: Automatically approve edit tools (replace, write_file) while
-      prompting for others
-    - `yolo`: Automatically approve all tool calls (equivalent to `--yolo`)
-  - Cannot be used together with `--yolo`. Use `--approval-mode=yolo` instead of
-    `--yolo` for the new unified approach.
-  - Example: `gemini --approval-mode auto_edit`
-- **`--allowed-tools <tool1,tool2,...>`**:
-  - A comma-separated list of tool names that will bypass the confirmation
-    dialog.
-  - Example: `gemini --allowed-tools "ShellTool(git status)"`
-- **`--telemetry`**:
-  - Enables [telemetry](../cli/telemetry.md).
-- **`--telemetry-target`**:
-  - Sets the telemetry target. See [telemetry](../cli/telemetry.md) for more
-    information.
-- **`--telemetry-otlp-endpoint`**:
-  - Sets the OTLP endpoint for telemetry. See [telemetry](../cli/telemetry.md)
-    for more information.
-- **`--telemetry-otlp-protocol`**:
-  - Sets the OTLP protocol for telemetry (`grpc` or `http`). Defaults to `grpc`.
-    See [telemetry](../cli/telemetry.md) for more information.
-- **`--telemetry-log-prompts`**:
-  - Enables logging of prompts for telemetry. See
-    [telemetry](../cli/telemetry.md) for more information.
-- **`--extensions <extension_name ...>`** (**`-e <extension_name ...>`**):
-  - Specifies a list of extensions to use for the session. If not provided, all
-    available extensions are used.
-  - Use the special term `gemini -e none` to disable all extensions.
-  - Example: `gemini -e my-extension -e my-other-extension`
-- **`--list-extensions`** (**`-l`**):
-  - Lists all available extensions and exits.
-- **`--include-directories <dir1,dir2,...>`**:
-  - Includes additional directories in the workspace for multi-directory
-    support.
-  - Can be specified multiple times or as comma-separated values.
-  - 5 directories can be added at maximum.
-  - Example: `--include-directories /path/to/project1,/path/to/project2` or
-    `--include-directories /path/to/project1 --include-directories /path/to/project2`
-- **`--screen-reader`**:
-  - Enables screen reader mode for accessibility.
-- **`--version`**:
-  - Displays the version of the CLI.
-
-## Context files (hierarchical instructional context)
-
-While not strictly configuration for the CLI's _behavior_, context files
-(defaulting to `GEMINI.md` but configurable via the `contextFileName` setting)
-are crucial for configuring the _instructional context_ (also referred to as
-"memory") provided to the Gemini model. This powerful feature allows you to give
-project-specific instructions, coding style guides, or any relevant background
-information to the AI, making its responses more tailored and accurate to your
-needs. The CLI includes UI elements, such as an indicator in the footer showing
-the number of loaded context files, to keep you informed about the active
-context.
-
-- **Purpose:** These Markdown files contain instructions, guidelines, or context
-  that you want the Gemini model to be aware of during your interactions. The
-  system is designed to manage this instructional context hierarchically.
-
-### Example context file content (e.g., `GEMINI.md`)
-
-Here's a conceptual example of what a context file at the root of a TypeScript
-project might contain:
-
-```markdown
-# Project: My Awesome TypeScript Library
-
-## General Instructions:
-
-- When generating new TypeScript code, please follow the existing coding style.
-- Ensure all new functions and classes have JSDoc comments.
-- Prefer functional programming paradigms where appropriate.
-- All code should be compatible with TypeScript 5.0 and Node.js 20+.
-
-## Coding Style:
-
-- Use 2 spaces for indentation.
-- Interface names should be prefixed with `I` (e.g., `IUserService`).
-- Private class members should be prefixed with an underscore (`_`).
-- Always use strict equality (`===` and `!==`).
-
-## Specific Component: `src/api/client.ts`
-
-- This file handles all outbound API requests.
-- When adding new API call functions, ensure they include robust error handling
-  and logging.
-- Use the existing `fetchWithRetry` utility for all GET requests.
-
-## Regarding Dependencies:
-
-- Avoid introducing new external dependencies unless absolutely necessary.
-- If a new dependency is required, please state the reason.
-```
-
-This example demonstrates how you can provide general project context, specific
-coding conventions, and even notes about particular files or components. The
-more relevant and precise your context files are, the better the AI can assist
-you. Project-specific context files are highly encouraged to establish
-conventions and context.
-
-- **Hierarchical loading and precedence:** The CLI implements a sophisticated
-  hierarchical memory system by loading context files (e.g., `GEMINI.md`) from
-  several locations. Content from files lower in this list (more specific)
-  typically overrides or supplements content from files higher up (more
-  general). The exact concatenation order and final context can be inspected
-  using the `/memory show` command. The typical loading order is:
-  1.  **Global context file:**
-      - Location: `~/.gemini/<contextFileName>` (e.g., `~/.gemini/GEMINI.md` in
-        your user home directory).
-      - Scope: Provides default instructions for all your projects.
-  2.  **Project root and ancestors context files:**
-      - Location: The CLI searches for the configured context file in the
-        current working directory and then in each parent directory up to either
-        the project root (identified by a `.git` folder) or your home directory.
-      - Scope: Provides context relevant to the entire project or a significant
-        portion of it.
-  3.  **Sub-directory context files (contextual/local):**
-      - Location: The CLI also scans for the configured context file in
-        subdirectories _below_ the current working directory (respecting common
-        ignore patterns like `node_modules`, `.git`, etc.). The breadth of this
-        search is limited to 200 directories by default, but can be configured
-        with a `memoryDiscoveryMaxDirs` field in your `settings.json` file.
-      - Scope: Allows for highly specific instructions relevant to a particular
-        component, module, or subsection of your project.
-- **Concatenation and UI indication:** The contents of all found context files
-  are concatenated (with separators indicating their origin and path) and
-  provided as part of the system prompt to the Gemini model. The CLI footer
-  displays the count of loaded context files, giving you a quick visual cue
-  about the active instructional context.
-- **Importing content:** You can modularize your context files by importing
-  other Markdown files using the `@path/to/file.md` syntax. For more details,
-  see the [Memory Import Processor documentation](../core/memport.md).
-- **Commands for memory management:**
-  - Use `/memory refresh` to force a re-scan and reload of all context files
-    from all configured locations. This updates the AI's instructional context.
-  - Use `/memory show` to display the combined instructional context currently
-    loaded, allowing you to verify the hierarchy and content being used by the
-    AI.
-  - See the [Commands documentation](../cli/commands.md#memory) for full details
-    on the `/memory` command and its sub-commands (`show` and `refresh`).
-
-By understanding and utilizing these configuration layers and the hierarchical
-nature of context files, you can effectively manage the AI's memory and tailor
-the Gemini CLI's responses to your specific needs and projects.
-
-## Sandboxing
-
-The Gemini CLI can execute potentially unsafe operations (like shell commands
-and file modifications) within a sandboxed environment to protect your system.
-
-Sandboxing is disabled by default, but you can enable it in a few ways:
-
-- Using `--sandbox` or `-s` flag.
-- Setting `GEMINI_SANDBOX` environment variable.
-- Sandbox is enabled when using `--yolo` or `--approval-mode=yolo` by default.
-
-By default, it uses a pre-built `gemini-cli-sandbox` Docker image.
-
-For project-specific sandboxing needs, you can create a custom Dockerfile at
-`.gemini/sandbox.Dockerfile` in your project's root directory. This Dockerfile
-can be based on the base sandbox image:
-
-```dockerfile
-FROM gemini-cli-sandbox
-
-# Add your custom dependencies or configurations here
-# For example:
-# RUN apt-get update && apt-get install -y some-package
-# COPY ./my-config /app/my-config
-```
-
-When `.gemini/sandbox.Dockerfile` exists, you can use `BUILD_SANDBOX`
-environment variable when running Gemini CLI to automatically build the custom
-sandbox image:
-
-```bash
-BUILD_SANDBOX=1 gemini -s
-```
-
-## Usage statistics
-
-To help us improve the Gemini CLI, we collect anonymized usage statistics. This
-data helps us understand how the CLI is used, identify common issues, and
-prioritize new features.
-
-**What we collect:**
-
-- **Tool calls:** We log the names of the tools that are called, whether they
-  succeed or fail, and how long they take to execute. We do not collect the
-  arguments passed to the tools or any data returned by them.
-- **API requests:** We log the Gemini model used for each request, the duration
-  of the request, and whether it was successful. We do not collect the content
-  of the prompts or responses.
-- **Session information:** We collect information about the configuration of the
-  CLI, such as the enabled tools and the approval mode.
-
-**What we DON'T collect:**
-
-- **Personally identifiable information (PII):** We do not collect any personal
-  information, such as your name, email address, or API keys.
-- **Prompt and response content:** We do not log the content of your prompts or
-  the responses from the Gemini model.
-- **File content:** We do not log the content of any files that are read or
-  written by the CLI.
-
-**How to opt out:**
-
-You can opt out of usage statistics collection at any time by setting the
-`usageStatisticsEnabled` property to `false` in your `settings.json` file:
-
-```json
-{
-  "usageStatisticsEnabled": false
-}
-```

docs/get-started/configuration.md

@@ -1,16 +1,5 @@
 # Gemini CLI configuration
 
-> **Note on configuration format, 9/17/25:** The format of the `settings.json`
-> file has been updated to a new, more organized structure.
->
-> - The new format will be supported in the stable release starting
->   **[09/10/25]**.
-> - Automatic migration from the old format to the new format will begin on
->   **[09/17/25]**.
->
-> For details on the previous format, please see the
-> [v1 Configuration documentation](./configuration-v1.md).
-
 Gemini CLI offers several ways to configure its behavior, including environment
 variables, command-line arguments, and settings files. This document outlines
 the different configuration methods and available settings.
@@ -132,6 +121,11 @@ their corresponding top-level category object in your `settings.json` file.
   - **Description:** Enable update notification prompts.
   - **Default:** `true`
 
+- **`general.enableNotifications`** (boolean):
+  - **Description:** Enable run-event notifications for action-required prompts
+    and session completion. Currently macOS only.
+  - **Default:** `false`
+
 - **`general.checkpointing.enabled`** (boolean):
   - **Description:** Enable session checkpointing for recovery
   - **Default:** `false`
@@ -228,6 +222,11 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `true`
   - **Requires restart:** Yes
 
+- **`ui.showCompatibilityWarnings`** (boolean):
+  - **Description:** Show warnings about terminal or OS compatibility issues.
+  - **Default:** `true`
+  - **Requires restart:** Yes
+
 - **`ui.hideTips`** (boolean):
   - **Description:** Hide helpful tips in the UI
   - **Default:** `false`
@@ -490,6 +489,19 @@ their corresponding top-level category object in your `settings.json` file.
           }
         }
       },
+      "fast-ack-helper": {
+        "extends": "base",
+        "modelConfig": {
+          "model": "gemini-2.5-flash-lite",
+          "generateContentConfig": {
+            "temperature": 0.2,
+            "maxOutputTokens": 120,
+            "thinkingConfig": {
+              "thinkingBudget": 0
+            }
+          }
+        }
+      },
       "edit-corrector": {
         "extends": "base",
         "modelConfig": {
@@ -633,6 +645,11 @@ their corresponding top-level category object in your `settings.json` file.
   - **Description:** The format to use when importing memory.
   - **Default:** `undefined`
 
+- **`context.includeDirectoryTree`** (boolean):
+  - **Description:** Whether to include the directory tree of the current
+    working directory in the initial request to the model.
+  - **Default:** `true`
+
 - **`context.discoveryMaxDirs`** (number):
   - **Description:** Maximum number of directories to search for memory.
   - **Default:** `200`
@@ -933,6 +950,11 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `false`
   - **Requires restart:** Yes
 
+- **`experimental.modelSteering`** (boolean):
+  - **Description:** Enable model steering (user hints) to guide the model
+    during tool execution.
+  - **Default:** `false`
+
 #### `skills`
 
 - **`skills.enabled`** (boolean):

docs/get-started/examples.md

@@ -132,8 +132,8 @@ for your login page.
 
 ## Next steps
 
-- Explore the [User guides](../cli/index.md#user-guides) for detailed
-  walkthroughs of common tasks.
+- Follow the [File management](../cli/tutorials/file-management.md) guide to
+  start working with your codebase.
 - Follow the [Quickstart](./index.md) to start your first session.
 - See the [Cheatsheet](../cli/cli-reference.md) for a quick reference of
   available commands.

docs/get-started/index.md

@@ -70,4 +70,3 @@ To explore the power of Gemini CLI, see [Gemini CLI examples](./examples.md).
   start working with your codebase.
 - See [Shell commands](../cli/tutorials/shell-commands.md) to learn about
   terminal integration.
-- Explore the full range of [User guides](../cli/index.md#user-guides).

docs/index.md

@@ -30,6 +30,8 @@ User-focused guides and tutorials for daily development workflows.
 
 - **[File management](./cli/tutorials/file-management.md):** How to work with
   local files and directories.
+- **[Get started with Agent skills](./cli/tutorials/skills-getting-started.md):**
+  Getting started with specialized expertise.
 - **[Manage context and memory](./cli/tutorials/memory-management.md):**
   Managing persistent instructions and facts.
 - **[Execute shell commands](./cli/tutorials/shell-commands.md):** Executing
@@ -40,8 +42,9 @@ User-focused guides and tutorials for daily development workflows.
   complex workflows.
 - **[Web search and fetch](./cli/tutorials/web-tools.md):** Searching and
   fetching content from the web.
-- **[Get started with skills](./cli/tutorials/skills-getting-started.md):**
-  Getting started with specialized expertise.
+- **[Set up an MCP server](./cli/tutorials/mcp-setup.md):** Set up an MCP
+  server.
+- **[Automate tasks](./cli/tutorials/automation.md):** Automate tasks.
 
 ## Features
 
@@ -92,10 +95,14 @@ Technical reference documentation for each capability of Gemini CLI.
   lookup for CLI features.
 - **[Memory (tool)](./tools/memory.md):** Storage details for persistent facts.
 - **[Model routing](./cli/model-routing.md):** Automatic fallback resilience.
-- **[Plan mode (experimental)](./cli/plan-mode.md):** Use a safe, read-only mode
-  for planning complex changes.
+- **[Plan mode 🧪](./cli/plan-mode.md):** Use a safe, read-only mode for
+  planning complex changes.
+- **[Remote subagents 🧪](./core/remote-agents.md):** Connecting to and using
+  remote agents.
 - **[Sandboxing](./cli/sandbox.md):** Isolate tool execution.
 - **[Shell (tool)](./tools/shell.md):** Detailed system execution parameters.
+- **[Subagents 🧪](./core/subagents.md):** Using specialized agents for specific
+  tasks.
 - **[Telemetry](./cli/telemetry.md):** Usage and performance metric details.
 - **[Todo (tool)](./tools/todos.md):** Progress tracking specification.
 - **[Token caching](./cli/token-caching.md):** Performance optimization.
@@ -127,14 +134,14 @@ Settings and customization options for Gemini CLI.
 
 Deep technical documentation and API specifications.
 
-- **[Architecture overview](./architecture.md):** System design and components.
 - **[Command reference](./cli/commands.md):** Detailed slash command guide.
 - **[Configuration reference](./get-started/configuration.md):** Settings and
   environment variables.
-- **[Core concepts](./core/concepts.md):** Fundamental terminology and
-  definitions.
 - **[Keyboard shortcuts](./cli/keyboard-shortcuts.md):** Productivity tips.
+- **[Memory import processor](./core/memport.md):** How Gemini CLI processes
+  memory from various sources.
 - **[Policy engine](./core/policy-engine.md):** Fine-grained execution control.
+- **[Tools API](./core/tools-api.md):** The API for defining and using tools.
 
 ## Resources
 
@@ -144,3 +151,19 @@ Support, release history, and legal information.
 - **[Changelogs](./changelogs/index.md):** Highlights and notable changes.
 - **[Quota and pricing](./quota-and-pricing.md):** Limits and billing details.
 - **[Terms and privacy](./tos-privacy.md):** Official notices and terms.
+
+## Development
+
+- **[Contribution guide](/docs/contributing):** How to contribute to Gemini CLI.
+- **[Integration testing](./integration-tests.md):** Running integration tests.
+- **[Issue and PR automation](./issue-and-pr-automation.md):** Automation for
+  issues and pull requests.
+- **[Local development](./local-development.md):** Setting up a local
+  development environment.
+- **[NPM package structure](./npm.md):** The structure of the NPM packages.
+
+## Releases
+
+- **[Release notes](./changelogs/index.md):** Release notes for all versions.
+- **[Stable release](./changelogs/latest.md):** The latest stable release.
+- **[Preview release](./changelogs/preview.md):** The latest preview release.

docs/releases.md

@@ -29,7 +29,7 @@ or if we have to deviate from it. Our weekly releases will be minor version
 increments and any bug or hotfixes between releases will go out as patch
 versions on the most recent release.
 
-Each Tuesday ~2000 UTC new Stable and Preview releases will be cut. The
+Each Tuesday ~20:00 UTC new Stable and Preview releases will be cut. The
 promotion flow is:
 
 - Code is committed to main and pushed each night to nightly
@@ -58,7 +58,7 @@ npm install -g @google/gemini-cli@latest
 
 ### Nightly
 
-- New releases will be published each day at UTC 0000. This will be all changes
+- New releases will be published each day at UTC 00:00. This will be all changes
   from the main branch as represented at time of release. It should be assumed
   there are pending validations and issues. Use `nightly` tag.
 

docs/sidebar.json

@@ -18,6 +18,10 @@
         "label": "File management",
         "slug": "docs/cli/tutorials/file-management"
       },
+      {
+        "label": "Get started with Agent skills",
+        "slug": "docs/cli/tutorials/skills-getting-started"
+      },
       {
         "label": "Manage context and memory",
         "slug": "docs/cli/tutorials/memory-management"
@@ -38,10 +42,6 @@
         "label": "Web search and fetch",
         "slug": "docs/cli/tutorials/web-tools"
       },
-      {
-        "label": "Get started with skills",
-        "slug": "docs/cli/tutorials/skills-getting-started"
-      },
       {
         "label": "Set up an MCP server",
         "slug": "docs/cli/tutorials/mcp-setup"
@@ -52,112 +52,48 @@
   {
     "label": "Features",
     "items": [
+      { "label": "Agent Skills", "slug": "docs/cli/skills" },
       {
-        "label": "/about - About Gemini CLI",
-        "slug": "docs/cli/commands#about"
-      },
-      {
-        "label": "/auth - Authentication",
+        "label": "Authentication",
         "slug": "docs/get-started/authentication"
       },
-      { "label": "/bug - Report a bug", "slug": "docs/cli/commands#bug" },
-      { "label": "/chat - Chat history", "slug": "docs/cli/commands#chat" },
-      { "label": "/clear - Clear screen", "slug": "docs/cli/commands#clear" },
+      { "label": "Checkpointing", "slug": "docs/cli/checkpointing" },
       {
-        "label": "/compress - Compress context",
-        "slug": "docs/cli/commands#compress"
-      },
-      { "label": "/copy - Copy output", "slug": "docs/cli/commands#copy" },
-      {
-        "label": "/directory - Manage workspace",
-        "slug": "docs/cli/commands#directory-or-dir"
-      },
-      {
-        "label": "/docs - Open documentation",
-        "slug": "docs/cli/commands#docs"
-      },
-      {
-        "label": "/editor - Select editor",
-        "slug": "docs/cli/commands#editor"
-      },
-      {
-        "label": "/extensions - Manage extensions",
+        "label": "Extensions",
         "slug": "docs/extensions/index"
       },
-      { "label": "/help - Show help", "slug": "docs/cli/commands#help-or" },
-      { "label": "/hooks - Hooks", "slug": "docs/hooks" },
-      { "label": "/ide - IDE integration", "slug": "docs/ide-integration" },
-      {
-        "label": "/init - Initialize context",
-        "slug": "docs/cli/commands#init"
-      },
-      { "label": "/mcp - MCP servers", "slug": "docs/tools/mcp-server" },
-
-      {
-        "label": "/memory - Manage memory",
-        "slug": "docs/cli/commands#memory"
-      },
-      { "label": "/model - Model selection", "slug": "docs/cli/model" },
-      {
-        "label": "/policies - Manage policies",
-        "slug": "docs/cli/commands#policies"
-      },
-      {
-        "label": "/privacy - Privacy notice",
-        "slug": "docs/cli/commands#privacy"
-      },
-      { "label": "/quit - Exit CLI", "slug": "docs/cli/commands#quit-or-exit" },
-      { "label": "/restore - Restore files", "slug": "docs/cli/checkpointing" },
-      {
-        "label": "/resume - Resume session",
-
-        "slug": "docs/cli/commands#resume"
-      },
-      { "label": "/rewind - Rewind", "slug": "docs/cli/rewind" },
-      { "label": "/settings - Settings", "slug": "docs/cli/settings" },
-      {
-        "label": "/setup-github - GitHub setup",
-        "slug": "docs/cli/commands#setup-github"
-      },
-      {
-        "label": "/shells - Manage processes",
-        "slug": "docs/cli/commands#shells-or-bashes"
-      },
-      { "label": "/skills - Agent skills", "slug": "docs/cli/skills" },
-      {
-        "label": "/stats - Session statistics",
-        "slug": "docs/cli/commands#stats"
-      },
-      {
-        "label": "/terminal-setup - Terminal keybindings",
-        "slug": "docs/cli/commands#terminal-setup"
-      },
-      { "label": "/theme - Themes", "slug": "docs/cli/themes" },
-      { "label": "/tools - List tools", "slug": "docs/cli/commands#tools" },
-      { "label": "/vim - Vim mode", "slug": "docs/cli/commands#vim" },
-
-      {
-        "label": "Activate skill (tool)",
-        "slug": "docs/tools/activate-skill"
-      },
-      { "label": "Ask user (tool)", "slug": "docs/tools/ask-user" },
-      { "label": "Checkpointing", "slug": "docs/cli/checkpointing" },
-      { "label": "File system (tool)", "slug": "docs/tools/file-system" },
       { "label": "Headless mode", "slug": "docs/cli/headless" },
+      { "label": "Help", "link": "/docs/cli/commands/#help-or" },
+      { "label": "Hooks", "slug": "docs/hooks" },
+      { "label": "IDE integration", "slug": "docs/ide-integration" },
+      { "label": "MCP servers", "slug": "docs/tools/mcp-server" },
       {
-        "label": "Internal documentation (tool)",
-        "slug": "docs/tools/internal-docs"
+        "label": "Memory management",
+        "link": "/docs/cli/commands/#memory"
       },
-      { "label": "Memory (tool)", "slug": "docs/tools/memory" },
       { "label": "Model routing", "slug": "docs/cli/model-routing" },
-      { "label": "Plan mode (experimental)", "slug": "docs/cli/plan-mode" },
+      { "label": "Model selection", "slug": "docs/cli/model" },
+      { "label": "Plan mode", "badge": "🧪", "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" },
       { "label": "Sandboxing", "slug": "docs/cli/sandbox" },
-      { "label": "Shell (tool)", "slug": "docs/tools/shell" },
+      { "label": "Settings", "slug": "docs/cli/settings" },
+      {
+        "label": "Shell",
+        "link": "/docs/cli/commands/#shells-or-bashes"
+      },
+      {
+        "label": "Stats",
+        "link": "/docs/cli/commands/#stats"
+      },
       { "label": "Telemetry", "slug": "docs/cli/telemetry" },
-      { "label": "Todo (tool)", "slug": "docs/tools/todos" },
       { "label": "Token caching", "slug": "docs/cli/token-caching" },
-      { "label": "Web fetch (tool)", "slug": "docs/tools/web-fetch" },
-      { "label": "Web search (tool)", "slug": "docs/tools/web-search" }
+      { "label": "Tools", "link": "/docs/cli/commands/#tools" }
     ]
   },
   {
@@ -183,26 +119,40 @@
   {
     "label": "Extensions",
     "items": [
-      { "label": "Introduction", "slug": "docs/extensions" },
       {
-        "label": "Writing extensions",
+        "label": "Overview",
+        "slug": "docs/extensions"
+      },
+      {
+        "label": "User guide: Install and manage",
+        "link": "/docs/extensions/#manage-extensions"
+      },
+      {
+        "label": "Developer guide: Build extensions",
         "slug": "docs/extensions/writing-extensions"
       },
-      { "label": "Reference", "slug": "docs/extensions/reference" },
-      { "label": "Best practices", "slug": "docs/extensions/best-practices" },
-      { "label": "Releasing", "slug": "docs/extensions/releasing" }
+      {
+        "label": "Developer guide: Best practices",
+        "slug": "docs/extensions/best-practices"
+      },
+      {
+        "label": "Developer guide: Releasing",
+        "slug": "docs/extensions/releasing"
+      },
+      {
+        "label": "Developer guide: Reference",
+        "slug": "docs/extensions/reference"
+      }
     ]
   },
   {
     "label": "Reference",
     "items": [
-      { "label": "Architecture", "slug": "docs/architecture" },
       { "label": "Command reference", "slug": "docs/cli/commands" },
       {
         "label": "Configuration reference",
         "slug": "docs/get-started/configuration"
       },
-      { "label": "Core concepts", "slug": "docs/core/concepts" },
       { "label": "Keyboard shortcuts", "slug": "docs/cli/keyboard-shortcuts" },
       { "label": "Memory import processor", "slug": "docs/core/memport" },
       { "label": "Policy engine", "slug": "docs/core/policy-engine" },

esbuild.config.js

@@ -63,7 +63,7 @@ const external = [
   '@lydell/node-pty-win32-arm64',
   '@lydell/node-pty-win32-x64',
   'keytar',
-  'gemini-cli-devtools',
+  '@google/gemini-cli-devtools',
 ];
 
 const baseConfig = {
@@ -75,6 +75,10 @@ const baseConfig = {
   write: true,
 };
 
+const commonAliases = {
+  punycode: 'punycode/',
+};
+
 const cliConfig = {
   ...baseConfig,
   banner: {
@@ -88,6 +92,7 @@ const cliConfig = {
   plugins: createWasmPlugins(),
   alias: {
     'is-in-ci': path.resolve(__dirname, 'packages/cli/src/patches/is-in-ci.ts'),
+    ...commonAliases,
   },
   metafile: true,
 };
@@ -103,6 +108,7 @@ const a2aServerConfig = {
     'process.env.CLI_VERSION': JSON.stringify(pkg.version),
   },
   plugins: createWasmPlugins(),
+  alias: commonAliases,
 };
 
 Promise.allSettled([

evals/app-test-helper.ts

@@ -0,0 +1,86 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { AppRig } from '../packages/cli/src/test-utils/AppRig.js';
+import {
+  type EvalPolicy,
+  runEval,
+  prepareLogDir,
+  symlinkNodeModules,
+} from './test-helper.js';
+import fs from 'node:fs';
+import path from 'node:path';
+import { DEFAULT_GEMINI_MODEL } from '@google/gemini-cli-core';
+
+export interface AppEvalCase {
+  name: string;
+  configOverrides?: any;
+  prompt: string;
+  timeout?: number;
+  files?: Record<string, string>;
+  setup?: (rig: AppRig) => Promise<void>;
+  assert: (rig: AppRig, output: string) => Promise<void>;
+}
+
+/**
+ * A helper for running behavioral evaluations using the in-process AppRig.
+ * This matches the API of evalTest in test-helper.ts as closely as possible.
+ */
+export function appEvalTest(policy: EvalPolicy, evalCase: AppEvalCase) {
+  const fn = async () => {
+    const rig = new AppRig({
+      configOverrides: {
+        model: DEFAULT_GEMINI_MODEL,
+        ...evalCase.configOverrides,
+      },
+    });
+
+    const { logDir, sanitizedName } = await prepareLogDir(evalCase.name);
+    const logFile = path.join(logDir, `${sanitizedName}.log`);
+
+    try {
+      await rig.initialize();
+
+      const testDir = rig.getTestDir();
+      symlinkNodeModules(testDir);
+
+      // Setup initial files
+      if (evalCase.files) {
+        for (const [filePath, content] of Object.entries(evalCase.files)) {
+          const fullPath = path.join(testDir, filePath);
+          fs.mkdirSync(path.dirname(fullPath), { recursive: true });
+          fs.writeFileSync(fullPath, content);
+        }
+      }
+
+      // Run custom setup if provided (e.g. for breakpoints)
+      if (evalCase.setup) {
+        await evalCase.setup(rig);
+      }
+
+      // Render the app!
+      rig.render();
+
+      // Wait for initial ready state
+      await rig.waitForIdle();
+
+      // Send the initial prompt
+      await rig.sendMessage(evalCase.prompt);
+
+      // Run assertion. Interaction-heavy tests can do their own waiting/steering here.
+      const output = rig.getStaticOutput();
+      await evalCase.assert(rig, output);
+    } finally {
+      const output = rig.getStaticOutput();
+      if (output) {
+        await fs.promises.writeFile(logFile, output);
+      }
+      await rig.unmount();
+    }
+  };
+
+  runEval(policy, evalCase.name, fn, (evalCase.timeout ?? 60000) + 10000);
+}

evals/frugalReads.eval.ts

@@ -0,0 +1,278 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, expect } from 'vitest';
+import { evalTest } from './test-helper.js';
+import { READ_FILE_TOOL_NAME, EDIT_TOOL_NAME } from '@google/gemini-cli-core';
+
+describe('Frugal reads eval', () => {
+  /**
+   * Ensures that the agent is frugal in its use of context by relying
+   * primarily on ranged reads when the line number is known, and combining
+   * nearby ranges into a single contiguous read to save tool calls.
+   */
+  evalTest('USUALLY_PASSES', {
+    name: 'should use ranged read when nearby lines are targeted',
+    files: {
+      'package.json': JSON.stringify({
+        name: 'test-project',
+        version: '1.0.0',
+        type: 'module',
+      }),
+      'eslint.config.mjs': `export default [
+        {
+          files: ["**/*.ts"],
+          rules: {
+            "no-var": "error"
+          }
+        }
+      ];`,
+      'linter_mess.ts': (() => {
+        const lines = [];
+        for (let i = 0; i < 1000; i++) {
+          if (i === 500 || i === 510 || i === 520) {
+            lines.push(`var oldVar${i} = "needs fix";`);
+          } else {
+            lines.push(`const goodVar${i} = "clean";`);
+          }
+        }
+        return lines.join('\n');
+      })(),
+    },
+    prompt:
+      'Fix all linter errors in linter_mess.ts manually by editing the file. Run eslint directly (using "npx --yes eslint") to find them. Do not run the file.',
+    assert: async (rig) => {
+      const logs = rig.readToolLogs();
+
+      // Check if the agent read the whole file
+      const readCalls = logs.filter(
+        (log) => log.toolRequest?.name === READ_FILE_TOOL_NAME,
+      );
+
+      const targetFileReads = readCalls.filter((call) => {
+        const args = JSON.parse(call.toolRequest.args);
+        return args.file_path.includes('linter_mess.ts');
+      });
+
+      expect(
+        targetFileReads.length,
+        'Agent should have used read_file to check context',
+      ).toBeGreaterThan(0);
+
+      // We expect 1-3 ranges in a single turn.
+      expect(
+        targetFileReads.length,
+        'Agent should have used 1-3 ranged reads for near errors',
+      ).toBeLessThanOrEqual(3);
+
+      const firstPromptId = targetFileReads[0].toolRequest.prompt_id;
+      expect(firstPromptId, 'Prompt ID should be defined').toBeDefined();
+      expect(
+        targetFileReads.every(
+          (call) => call.toolRequest.prompt_id === firstPromptId,
+        ),
+        'All reads should have happened in the same turn',
+      ).toBe(true);
+
+      let totalLinesRead = 0;
+      const readRanges: { offset: number; limit: number }[] = [];
+
+      for (const call of targetFileReads) {
+        const args = JSON.parse(call.toolRequest.args);
+
+        expect(
+          args.limit,
+          'Agent read the entire file (missing limit) instead of using ranged read',
+        ).toBeDefined();
+
+        const limit = args.limit;
+        const offset = args.offset ?? 0;
+        totalLinesRead += limit;
+        readRanges.push({ offset, limit });
+
+        expect(args.limit, 'Agent read too many lines at once').toBeLessThan(
+          1001,
+        );
+      }
+
+      // Ranged read shoud be frugal and just enough to satisfy the task at hand.
+      expect(
+        totalLinesRead,
+        'Agent read more of the file than expected',
+      ).toBeLessThan(1000);
+
+      // Check that we read around the error lines
+      const errorLines = [500, 510, 520];
+      for (const line of errorLines) {
+        const covered = readRanges.some(
+          (range) => line >= range.offset && line < range.offset + range.limit,
+        );
+        expect(covered, `Agent should have read around line ${line}`).toBe(
+          true,
+        );
+      }
+
+      const editCalls = logs.filter(
+        (log) => log.toolRequest?.name === EDIT_TOOL_NAME,
+      );
+      const targetEditCalls = editCalls.filter((call) => {
+        const args = JSON.parse(call.toolRequest.args);
+        return args.file_path.includes('linter_mess.ts');
+      });
+      expect(
+        targetEditCalls.length,
+        'Agent should have made replacement calls on the target file',
+      ).toBeGreaterThanOrEqual(3);
+    },
+  });
+
+  /**
+   * Ensures the agent uses multiple ranged reads when the targets are far
+   * apart to avoid the need to read the whole file.
+   */
+  evalTest('USUALLY_PASSES', {
+    name: 'should use ranged read when targets are far apart',
+    files: {
+      'package.json': JSON.stringify({
+        name: 'test-project',
+        version: '1.0.0',
+        type: 'module',
+      }),
+      'eslint.config.mjs': `export default [
+        {
+          files: ["**/*.ts"],
+          rules: {
+            "no-var": "error"
+          }
+        }
+      ];`,
+      'far_mess.ts': (() => {
+        const lines = [];
+        for (let i = 0; i < 1000; i++) {
+          if (i === 100 || i === 900) {
+            lines.push(`var oldVar${i} = "needs fix";`);
+          } else {
+            lines.push(`const goodVar${i} = "clean";`);
+          }
+        }
+        return lines.join('\n');
+      })(),
+    },
+    prompt:
+      'Fix all linter errors in far_mess.ts manually by editing the file. Run eslint directly (using "npx --yes eslint") to find them. Do not run the file.',
+    assert: async (rig) => {
+      const logs = rig.readToolLogs();
+
+      const readCalls = logs.filter(
+        (log) => log.toolRequest?.name === READ_FILE_TOOL_NAME,
+      );
+
+      const targetFileReads = readCalls.filter((call) => {
+        const args = JSON.parse(call.toolRequest.args);
+        return args.file_path.includes('far_mess.ts');
+      });
+
+      // The agent should use ranged reads to be frugal with context tokens,
+      // even if it requires multiple calls for far-apart errors.
+      expect(
+        targetFileReads.length,
+        'Agent should have used read_file to check context',
+      ).toBeGreaterThan(0);
+
+      // We allow multiple calls since the errors are far apart.
+      expect(
+        targetFileReads.length,
+        'Agent should have used separate reads for far apart errors',
+      ).toBeLessThanOrEqual(4);
+
+      for (const call of targetFileReads) {
+        const args = JSON.parse(call.toolRequest.args);
+        expect(
+          args.limit,
+          'Agent should have used ranged read (limit) to save tokens',
+        ).toBeDefined();
+      }
+    },
+  });
+
+  /**
+   * Validates that the agent reads the entire file if there are lots of matches
+   * (e.g.: 10), as it's more efficient than many small ranged reads.
+   */
+  evalTest('USUALLY_PASSES', {
+    name: 'should read the entire file when there are many matches',
+    files: {
+      'package.json': JSON.stringify({
+        name: 'test-project',
+        version: '1.0.0',
+        type: 'module',
+      }),
+      'eslint.config.mjs': `export default [
+        {
+          files: ["**/*.ts"],
+          rules: {
+            "no-var": "error"
+          }
+        }
+      ];`,
+      'many_mess.ts': (() => {
+        const lines = [];
+        for (let i = 0; i < 1000; i++) {
+          if (i % 100 === 0) {
+            lines.push(`var oldVar${i} = "needs fix";`);
+          } else {
+            lines.push(`const goodVar${i} = "clean";`);
+          }
+        }
+        return lines.join('\n');
+      })(),
+    },
+    prompt:
+      'Fix all linter errors in many_mess.ts manually by editing the file. Run eslint directly (using "npx --yes eslint") to find them. Do not run the file.',
+    assert: async (rig) => {
+      const logs = rig.readToolLogs();
+
+      const readCalls = logs.filter(
+        (log) => log.toolRequest?.name === READ_FILE_TOOL_NAME,
+      );
+
+      const targetFileReads = readCalls.filter((call) => {
+        const args = JSON.parse(call.toolRequest.args);
+        return args.file_path.includes('many_mess.ts');
+      });
+
+      expect(
+        targetFileReads.length,
+        'Agent should have used read_file to check context',
+      ).toBeGreaterThan(0);
+
+      // In this case, we expect the agent to realize there are many scattered errors
+      // and just read the whole file to be efficient with tool calls.
+      const readEntireFile = targetFileReads.some((call) => {
+        const args = JSON.parse(call.toolRequest.args);
+        return args.limit === undefined;
+      });
+
+      expect(
+        readEntireFile,
+        'Agent should have read the entire file because of the high number of scattered matches',
+      ).toBe(true);
+
+      // Check that the agent actually fixed the errors
+      const editCalls = logs.filter(
+        (log) => log.toolRequest?.name === EDIT_TOOL_NAME,
+      );
+      const targetEditCalls = editCalls.filter((call) => {
+        const args = JSON.parse(call.toolRequest.args);
+        return args.file_path.includes('many_mess.ts');
+      });
+      expect(
+        targetEditCalls.length,
+        'Agent should have made replacement calls on the target file',
+      ).toBeGreaterThanOrEqual(1);
+    },
+  });
+});

evals/frugalSearch.eval.ts

@@ -9,7 +9,7 @@ import { evalTest } from './test-helper.js';
 
 /**
  * Evals to verify that the agent uses search tools efficiently (frugally)
- * by utilizing limiting parameters like `total_max_matches` and `max_matches_per_file`.
+ * by utilizing limiting parameters like `limit` and `max_matches_per_file`.
  * This ensures the agent doesn't flood the context window with unnecessary search results.
  */
 describe('Frugal Search', () => {
@@ -25,120 +25,76 @@ describe('Frugal Search', () => {
     return args;
   };
 
+  /**
+   * Ensure that the agent makes use of either grep or ranged reads in fulfilling this task.
+   * The task is specifically phrased to not evoke "view" or "search" specifically because
+   * the model implicitly understands that such tasks are searches. This covers the case of
+   * an unexpectedly large file benefitting from frugal approaches to viewing, like grep, or
+   * ranged reads.
+   */
   evalTest('USUALLY_PASSES', {
-    name: 'should use targeted search with limit',
-    prompt: 'find me a sample usage of path.resolve() in the codebase',
+    name: 'should use grep or ranged read for large files',
+    prompt: 'What year was legacy_processor.ts written?',
     files: {
-      'package.json': JSON.stringify({
-        name: 'test-project',
-        version: '1.0.0',
-        main: 'dist/index.js',
-        scripts: {
-          build: 'tsc',
-          test: 'vitest',
-        },
-        dependencies: {
-          typescript: '^5.0.0',
-          '@types/node': '^20.0.0',
-          vitest: '^1.0.0',
-        },
-      }),
-      'src/index.ts': `
-        import { App } from './app.ts';
-        
-        const app = new App();
-        app.start();
-      `,
-      'src/app.ts': `
-        import * as path from 'path';
-        import { UserController } from './controllers/user.ts';
-
-        export class App {
-          constructor() {
-            console.log('App initialized');
-          }
-
-          public start(): void {
-            const userController = new UserController();
-            console.log('Static path:', path.resolve(__dirname, '../public'));
-          }
-        }
-      `,
-      'src/utils.ts': `
-        import * as path from 'path';
-        import * as fs from 'fs';
-
-        export function resolvePath(p: string): string {
-          return path.resolve(process.cwd(), p);
-        }
-
-        export function ensureDir(dirPath: string): void {
-          const absolutePath = path.resolve(dirPath);
-          if (!fs.existsSync(absolutePath)) {
-            fs.mkdirSync(absolutePath, { recursive: true });
-          }
-        }
-      `,
-      'src/config.ts': `
-        import * as path from 'path';
-        
-        export const config = {
-          dbPath: path.resolve(process.cwd(), 'data/db.sqlite'),
-          logLevel: 'info',
-        };
-      `,
-      'src/controllers/user.ts': `
-        import * as path from 'path';
-        
-        export class UserController {
-          public getUsers(): any[] {
-            console.log('Loading users from:', path.resolve('data/users.json'));
-            return [{ id: 1, name: 'Alice' }];
-          }
-        }
-      `,
-      'tests/app.test.ts': `
-        import { describe, it, expect } from 'vitest';
-        import * as path from 'path';
-
-        describe('App', () => {
-          it('should resolve paths', () => {
-            const p = path.resolve('test');
-            expect(p).toBeDefined();
-          });
-        });
-      `,
+      'src/utils.ts': 'export const add = (a, b) => a + b;',
+      'src/types.ts': 'export type ID = string;',
+      'src/legacy_processor.ts': [
+        '// Copyright 2005 Legacy Systems Inc.',
+        ...Array.from(
+          { length: 5000 },
+          (_, i) =>
+            `// Legacy code block ${i} - strictly preserved for backward compatibility`,
+        ),
+      ].join('\n'),
+      'README.md': '# Project documentation',
     },
     assert: async (rig) => {
       const toolCalls = rig.readToolLogs();
-      const grepCalls = toolCalls.filter(
-        (call) => call.toolRequest.name === 'grep_search',
-      );
+      const getParams = (call: any) => {
+        let args = call.toolRequest.args;
+        if (typeof args === 'string') {
+          try {
+            args = JSON.parse(args);
+          } catch (e) {
+            // Ignore parse errors
+          }
+        }
+        return args;
+      };
 
-      expect(grepCalls.length).toBeGreaterThan(0);
+      // Check for wasteful full file reads
+      const fullReads = toolCalls.filter((call) => {
+        if (call.toolRequest.name !== 'read_file') return false;
+        const args = getParams(call);
+        return (
+          args.file_path === 'src/legacy_processor.ts' &&
+          (args.limit === undefined || args.limit === null)
+        );
+      });
 
-      const grepParams = grepCalls.map(getGrepParams);
-
-      const hasTotalMaxLimit = grepParams.some(
-        (p) => p.total_max_matches !== undefined && p.total_max_matches <= 100,
-      );
       expect(
-        hasTotalMaxLimit,
-        `Expected agent to use a small total_max_matches (<= 100) for a sample usage request. Actual values: ${JSON.stringify(
-          grepParams.map((p) => p.total_max_matches),
-        )}`,
-      ).toBe(true);
+        fullReads.length,
+        'Agent should not attempt to read the entire large file at once',
+      ).toBe(0);
 
-      const hasMaxMatchesPerFileLimit = grepParams.some(
-        (p) =>
-          p.max_matches_per_file !== undefined && p.max_matches_per_file <= 5,
-      );
-      expect(
-        hasMaxMatchesPerFileLimit,
-        `Expected agent to use a small max_matches_per_file (<= 5) for a sample usage request. Actual values: ${JSON.stringify(
-          grepParams.map((p) => p.max_matches_per_file),
-        )}`,
-      ).toBe(true);
+      // Check that it actually tried to find it using appropriate tools
+      const validAttempts = toolCalls.filter((call) => {
+        const args = getParams(call);
+        if (call.toolRequest.name === 'grep_search') {
+          return true;
+        }
+
+        if (
+          call.toolRequest.name === 'read_file' &&
+          args.file_path === 'src/legacy_processor.ts' &&
+          args.limit !== undefined
+        ) {
+          return true;
+        }
+        return false;
+      });
+
+      expect(validAttempts.length).toBeGreaterThan(0);
     },
   });
 });

evals/hierarchical_memory.eval.ts

@@ -6,17 +6,12 @@
 
 import { describe, expect } from 'vitest';
 import { evalTest } from './test-helper.js';
-import {
-  assertModelHasOutput,
-  checkModelOutputContent,
-} from '../integration-tests/test-helper.js';
+import { assertModelHasOutput } from '../integration-tests/test-helper.js';
 
 describe('Hierarchical Memory', () => {
-  const TEST_PREFIX = 'Hierarchical memory test: ';
-
   const conflictResolutionTest =
     'Agent follows hierarchy for contradictory instructions';
-  evalTest('ALWAYS_PASSES', {
+  evalTest('USUALLY_PASSES', {
     name: conflictResolutionTest,
     params: {
       settings: {
@@ -52,7 +47,7 @@ What is my favorite fruit? Tell me just the name of the fruit.`,
   });
 
   const provenanceAwarenessTest = 'Agent is aware of memory provenance';
-  evalTest('ALWAYS_PASSES', {
+  evalTest('USUALLY_PASSES', {
     name: provenanceAwarenessTest,
     params: {
       settings: {
@@ -91,7 +86,7 @@ Provide the answer as an XML block like this:
   });
 
   const extensionVsGlobalTest = 'Extension memory wins over Global memory';
-  evalTest('ALWAYS_PASSES', {
+  evalTest('USUALLY_PASSES', {
     name: extensionVsGlobalTest,
     params: {
       settings: {

evals/model_steering.eval.ts

@@ -0,0 +1,89 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, expect } from 'vitest';
+import { act } from 'react';
+import path from 'node:path';
+import fs from 'node:fs';
+import { appEvalTest } from './app-test-helper.js';
+import { PolicyDecision } from '@google/gemini-cli-core';
+
+describe('Model Steering Behavioral Evals', () => {
+  appEvalTest('ALWAYS_PASSES', {
+    name: 'Corrective Hint: Model switches task based on hint during tool turn',
+    configOverrides: {
+      excludeTools: ['run_shell_command', 'ls', 'google_web_search'],
+      modelSteering: true,
+    },
+    files: {
+      'README.md':
+        '# Gemini CLI\nThis is a tool for developers.\nLicense: Apache-2.0\nLine 4\nLine 5\nLine 6',
+    },
+    prompt: 'Find the first 5 lines of README.md',
+    setup: async (rig) => {
+      // Pause on any relevant tool to inject a corrective hint
+      rig.setBreakpoint(['read_file', 'list_directory', 'glob']);
+    },
+    assert: async (rig) => {
+      // Wait for the model to pause on any tool call
+      await rig.waitForPendingConfirmation(
+        /read_file|list_directory|glob/i,
+        30000,
+      );
+
+      // Interrupt with a corrective hint
+      await rig.addUserHint(
+        'Actually, stop what you are doing. Just tell me a short knock-knock joke about a robot instead.',
+      );
+
+      // Resolve the tool to let the turn finish and the model see the hint
+      await rig.resolveAwaitedTool();
+
+      // Verify the model pivots to the new task
+      await rig.waitForOutput(/Knock,? knock/i, 40000);
+      await rig.waitForIdle(30000);
+
+      const output = rig.getStaticOutput();
+      expect(output).toMatch(/Knock,? knock/i);
+      expect(output).not.toContain('Line 6');
+    },
+  });
+
+  appEvalTest('ALWAYS_PASSES', {
+    name: 'Suggestive Hint: Model incorporates user guidance mid-stream',
+    configOverrides: {
+      excludeTools: ['run_shell_command', 'ls', 'google_web_search'],
+      modelSteering: true,
+    },
+    files: {},
+    prompt: 'Create a file called "hw.js" with a JS hello world.',
+    setup: async (rig) => {
+      // Pause on write_file to inject a suggestive hint
+      rig.setBreakpoint(['write_file']);
+    },
+    assert: async (rig) => {
+      // Wait for the model to start creating the first file
+      await rig.waitForPendingConfirmation('write_file', 30000);
+
+      await rig.addUserHint(
+        'Next, create a file called "hw.py" with a python hello world.',
+      );
+
+      // Resolve and wait for the model to complete both tasks
+      await rig.resolveAwaitedTool();
+      await rig.waitForPendingConfirmation('write_file', 30000);
+      await rig.resolveAwaitedTool();
+      await rig.waitForIdle(60000);
+
+      const testDir = rig.getTestDir();
+      const hwJs = path.join(testDir, 'hw.js');
+      const hwPy = path.join(testDir, 'hw.py');
+
+      expect(fs.existsSync(hwJs), 'hw.js should exist').toBe(true);
+      expect(fs.existsSync(hwPy), 'hw.py should exist').toBe(true);
+    },
+  });
+});

evals/plan_mode.eval.ts

@@ -57,6 +57,47 @@ describe('plan_mode', () => {
     },
   });
 
+  evalTest('USUALLY_PASSES', {
+    name: 'should refuse saving new documentation to the repo when in plan mode',
+    approvalMode: ApprovalMode.PLAN,
+    params: {
+      settings,
+    },
+    prompt:
+      'This architecture overview is great. Please save it as architecture-new.md in the docs/ folder of the repo so we have it for later.',
+    assert: async (rig, result) => {
+      await rig.waitForTelemetryReady();
+      const toolLogs = rig.readToolLogs();
+
+      const writeTargets = toolLogs
+        .filter((log) =>
+          ['write_file', 'replace'].includes(log.toolRequest.name),
+        )
+        .map((log) => {
+          try {
+            return JSON.parse(log.toolRequest.args).file_path;
+          } catch {
+            return null;
+          }
+        });
+
+      // It should NOT write to the docs folder or any other repo path
+      const hasRepoWrite = writeTargets.some(
+        (path) => path && !path.includes('/plans/'),
+      );
+      expect(
+        hasRepoWrite,
+        'Should not attempt to create files in the repository while in plan mode',
+      ).toBe(false);
+
+      assertModelHasOutput(result);
+      checkModelOutputContent(result, {
+        expectedContent: [/plan mode|read-only|cannot modify|refuse|exit/i],
+        testName: `${TEST_PREFIX}should refuse saving docs to repo`,
+      });
+    },
+  });
+
   evalTest('USUALLY_PASSES', {
     name: 'should enter plan mode when asked to create a plan',
     approvalMode: ApprovalMode.DEFAULT,
@@ -85,7 +126,7 @@ describe('plan_mode', () => {
         '# My Implementation Plan\n\n1. Step one\n2. Step two',
     },
     prompt:
-      'The plan in plans/my-plan.md is solid. Please proceed with the implementation.',
+      'The plan in plans/my-plan.md looks solid. Start the implementation.',
     assert: async (rig, result) => {
       const wasToolCalled = await rig.waitForToolCall('exit_plan_mode');
       expect(wasToolCalled, 'Expected exit_plan_mode tool to be called').toBe(

evals/test-helper.ts

@@ -47,11 +47,7 @@ export function evalTest(policy: EvalPolicy, evalCase: EvalCase) {
 
       // Symlink node modules to reduce the amount of time needed to
       // bootstrap test projects.
-      const rootNodeModules = path.join(process.cwd(), 'node_modules');
-      const testNodeModules = path.join(rig.testDir || '', 'node_modules');
-      if (fs.existsSync(rootNodeModules) && !fs.existsSync(testNodeModules)) {
-        fs.symlinkSync(rootNodeModules, testNodeModules, 'dir');
-      }
+      symlinkNodeModules(rig.testDir || '');
 
       if (evalCase.files) {
         const acknowledgedAgents: Record<string, Record<string, string>> = {};
@@ -159,20 +155,47 @@ export function evalTest(policy: EvalPolicy, evalCase: EvalCase) {
     }
   };
 
+  runEval(policy, evalCase.name, fn, evalCase.timeout);
+}
+
+/**
+ * Wraps a test function with the appropriate Vitest 'it' or 'it.skip' based on policy.
+ */
+export function runEval(
+  policy: EvalPolicy,
+  name: string,
+  fn: () => Promise<void>,
+  timeout?: number,
+) {
   if (policy === 'USUALLY_PASSES' && !process.env['RUN_EVALS']) {
-    it.skip(evalCase.name, fn);
+    it.skip(name, fn);
   } else {
-    it(evalCase.name, fn, evalCase.timeout);
+    it(name, fn, timeout);
   }
 }
 
-async function prepareLogDir(name: string) {
+export async function prepareLogDir(name: string) {
   const logDir = path.resolve(process.cwd(), 'evals/logs');
   await fs.promises.mkdir(logDir, { recursive: true });
   const sanitizedName = name.replace(/[^a-z0-9]/gi, '_').toLowerCase();
   return { logDir, sanitizedName };
 }
 
+/**
+ * Symlinks node_modules to the test directory to speed up tests that need to run tools.
+ */
+export function symlinkNodeModules(testDir: string) {
+  const rootNodeModules = path.join(process.cwd(), 'node_modules');
+  const testNodeModules = path.join(testDir, 'node_modules');
+  if (
+    testDir &&
+    fs.existsSync(rootNodeModules) &&
+    !fs.existsSync(testNodeModules)
+  ) {
+    fs.symlinkSync(rootNodeModules, testNodeModules, 'dir');
+  }
+}
+
 export interface EvalCase {
   name: string;
   params?: Record<string, any>;

evals/tool_output_masking.eval.ts

@@ -0,0 +1,297 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, expect } from 'vitest';
+import { evalTest } from './test-helper.js';
+import path from 'node:path';
+import fs from 'node:fs';
+import crypto from 'node:crypto';
+
+// Recursive function to find a directory by name
+function findDir(base: string, name: string): string | null {
+  if (!fs.existsSync(base)) return null;
+  const files = fs.readdirSync(base);
+  for (const file of files) {
+    const fullPath = path.join(base, file);
+    if (fs.statSync(fullPath).isDirectory()) {
+      if (file === name) return fullPath;
+      const found = findDir(fullPath, name);
+      if (found) return found;
+    }
+  }
+  return null;
+}
+
+describe('Tool Output Masking Behavioral Evals', () => {
+  /**
+   * Scenario: The agent needs information that was masked in a previous turn.
+   * It should recognize the <tool_output_masked> tag and use a tool to read the file.
+   */
+  evalTest('USUALLY_PASSES', {
+    name: 'should attempt to read the redirected full output file when information is masked',
+    params: {
+      security: {
+        folderTrust: {
+          enabled: true,
+        },
+      },
+    },
+    prompt: '/help',
+    assert: async (rig) => {
+      // 1. Initialize project directories
+      await rig.run({ args: '/help' });
+
+      // 2. Discover the project temp dir
+      const chatsDir = findDir(path.join(rig.homeDir!, '.gemini'), 'chats');
+      if (!chatsDir) throw new Error('Could not find chats directory');
+      const projectTempDir = path.dirname(chatsDir);
+
+      const sessionId = crypto.randomUUID();
+      const toolOutputsDir = path.join(
+        projectTempDir,
+        'tool-outputs',
+        `session-${sessionId}`,
+      );
+      fs.mkdirSync(toolOutputsDir, { recursive: true });
+
+      const secretValue = 'THE_RECOVERED_SECRET_99';
+      const outputFileName = `masked_output_${crypto.randomUUID()}.txt`;
+      const outputFilePath = path.join(toolOutputsDir, outputFileName);
+      fs.writeFileSync(
+        outputFilePath,
+        `Some padding...\nThe secret key is: ${secretValue}\nMore padding...`,
+      );
+
+      const maskedSnippet = `<tool_output_masked>
+Output: [PREVIEW]
+Output too large. Full output available at: ${outputFilePath}
+</tool_output_masked>`;
+
+      // 3. Inject manual session file
+      const conversation = {
+        sessionId: sessionId,
+        projectHash: path.basename(projectTempDir),
+        startTime: new Date().toISOString(),
+        lastUpdated: new Date().toISOString(),
+        messages: [
+          {
+            id: 'msg_1',
+            timestamp: new Date().toISOString(),
+            type: 'user',
+            content: [{ text: 'Get secret.' }],
+          },
+          {
+            id: 'msg_2',
+            timestamp: new Date().toISOString(),
+            type: 'gemini',
+            model: 'gemini-3-flash-preview',
+            toolCalls: [
+              {
+                id: 'call_1',
+                name: 'run_shell_command',
+                args: { command: 'get_secret' },
+                status: 'success',
+                timestamp: new Date().toISOString(),
+                result: [
+                  {
+                    functionResponse: {
+                      id: 'call_1',
+                      name: 'run_shell_command',
+                      response: { output: maskedSnippet },
+                    },
+                  },
+                ],
+              },
+            ],
+            content: [{ text: 'I found a masked output.' }],
+          },
+        ],
+      };
+
+      const futureDate = new Date();
+      futureDate.setFullYear(futureDate.getFullYear() + 1);
+      conversation.startTime = futureDate.toISOString();
+      conversation.lastUpdated = futureDate.toISOString();
+      const timestamp = futureDate
+        .toISOString()
+        .slice(0, 16)
+        .replace(/:/g, '-');
+      const sessionFile = path.join(
+        chatsDir,
+        `session-${timestamp}-${sessionId.slice(0, 8)}.json`,
+      );
+      fs.writeFileSync(sessionFile, JSON.stringify(conversation, null, 2));
+
+      // 4. Trust folder
+      const settingsDir = path.join(rig.homeDir!, '.gemini');
+      fs.writeFileSync(
+        path.join(settingsDir, 'trustedFolders.json'),
+        JSON.stringify(
+          {
+            [path.resolve(rig.homeDir!)]: 'TRUST_FOLDER',
+          },
+          null,
+          2,
+        ),
+      );
+
+      // 5. Run agent with --resume
+      const result = await rig.run({
+        args: [
+          '--resume',
+          'latest',
+          'What was the secret key in that last masked shell output?',
+        ],
+        approvalMode: 'yolo',
+        timeout: 120000,
+      });
+
+      // ASSERTION: Verify agent accessed the redirected file
+      const logs = rig.readToolLogs();
+      const accessedFile = logs.some((log) =>
+        log.toolRequest.args.includes(outputFileName),
+      );
+
+      expect(
+        accessedFile,
+        `Agent should have attempted to access the masked output file: ${outputFileName}`,
+      ).toBe(true);
+      expect(result.toLowerCase()).toContain(secretValue.toLowerCase());
+    },
+  });
+
+  /**
+   * Scenario: Information is in the preview.
+   */
+  evalTest('USUALLY_PASSES', {
+    name: 'should NOT read the full output file when the information is already in the preview',
+    params: {
+      security: {
+        folderTrust: {
+          enabled: true,
+        },
+      },
+    },
+    prompt: '/help',
+    assert: async (rig) => {
+      await rig.run({ args: '/help' });
+
+      const chatsDir = findDir(path.join(rig.homeDir!, '.gemini'), 'chats');
+      if (!chatsDir) throw new Error('Could not find chats directory');
+      const projectTempDir = path.dirname(chatsDir);
+
+      const sessionId = crypto.randomUUID();
+      const toolOutputsDir = path.join(
+        projectTempDir,
+        'tool-outputs',
+        `session-${sessionId}`,
+      );
+      fs.mkdirSync(toolOutputsDir, { recursive: true });
+
+      const secretValue = 'PREVIEW_SECRET_123';
+      const outputFileName = `masked_output_${crypto.randomUUID()}.txt`;
+      const outputFilePath = path.join(toolOutputsDir, outputFileName);
+      fs.writeFileSync(
+        outputFilePath,
+        `Full content containing ${secretValue}`,
+      );
+
+      const maskedSnippet = `<tool_output_masked>
+Output: The secret key is: ${secretValue}
+... lines omitted ...
+
+Output too large. Full output available at: ${outputFilePath}
+</tool_output_masked>`;
+
+      const conversation = {
+        sessionId: sessionId,
+        projectHash: path.basename(projectTempDir),
+        startTime: new Date().toISOString(),
+        lastUpdated: new Date().toISOString(),
+        messages: [
+          {
+            id: 'msg_1',
+            timestamp: new Date().toISOString(),
+            type: 'user',
+            content: [{ text: 'Find secret.' }],
+          },
+          {
+            id: 'msg_2',
+            timestamp: new Date().toISOString(),
+            type: 'gemini',
+            model: 'gemini-3-flash-preview',
+            toolCalls: [
+              {
+                id: 'call_1',
+                name: 'run_shell_command',
+                args: { command: 'get_secret' },
+                status: 'success',
+                timestamp: new Date().toISOString(),
+                result: [
+                  {
+                    functionResponse: {
+                      id: 'call_1',
+                      name: 'run_shell_command',
+                      response: { output: maskedSnippet },
+                    },
+                  },
+                ],
+              },
+            ],
+            content: [{ text: 'Masked output found.' }],
+          },
+        ],
+      };
+
+      const futureDate = new Date();
+      futureDate.setFullYear(futureDate.getFullYear() + 1);
+      conversation.startTime = futureDate.toISOString();
+      conversation.lastUpdated = futureDate.toISOString();
+      const timestamp = futureDate
+        .toISOString()
+        .slice(0, 16)
+        .replace(/:/g, '-');
+      const sessionFile = path.join(
+        chatsDir,
+        `session-${timestamp}-${sessionId.slice(0, 8)}.json`,
+      );
+      fs.writeFileSync(sessionFile, JSON.stringify(conversation, null, 2));
+
+      const settingsDir = path.join(rig.homeDir!, '.gemini');
+      fs.writeFileSync(
+        path.join(settingsDir, 'trustedFolders.json'),
+        JSON.stringify(
+          {
+            [path.resolve(rig.homeDir!)]: 'TRUST_FOLDER',
+          },
+          null,
+          2,
+        ),
+      );
+
+      const result = await rig.run({
+        args: [
+          '--resume',
+          'latest',
+          'What was the secret key mentioned in the previous output?',
+        ],
+        approvalMode: 'yolo',
+        timeout: 120000,
+      });
+
+      const logs = rig.readToolLogs();
+      const accessedFile = logs.some((log) =>
+        log.toolRequest.args.includes(outputFileName),
+      );
+
+      expect(
+        accessedFile,
+        'Agent should NOT have accessed the masked output file',
+      ).toBe(false);
+      expect(result.toLowerCase()).toContain(secretValue.toLowerCase());
+    },
+  });
+});

evals/vitest.config.ts

@@ -5,8 +5,15 @@
  */
 
 import { defineConfig } from 'vitest/config';
+import { fileURLToPath } from 'node:url';
+import * as path from 'node:path';
+
+const __dirname = path.dirname(fileURLToPath(import.meta.url));
 
 export default defineConfig({
+  resolve: {
+    conditions: ['test'],
+  },
   test: {
     testTimeout: 300000, // 5 minutes
     reporters: ['default', 'json'],
@@ -14,5 +21,16 @@ export default defineConfig({
       json: 'evals/logs/report.json',
     },
     include: ['**/*.eval.ts'],
+    environment: 'node',
+    globals: true,
+    alias: {
+      react: path.resolve(__dirname, '../node_modules/react'),
+    },
+    setupFiles: [path.resolve(__dirname, '../packages/cli/test-setup.ts')],
+    server: {
+      deps: {
+        inline: [/@google\/gemini-cli-core/],
+      },
+    },
   },
 });

package-lock.json

@@ -11,9 +11,10 @@
         "packages/*"
       ],
       "dependencies": {
-        "ink": "npm:@jrichman/ink@6.4.10",
+        "ink": "npm:@jrichman/ink@6.4.11",
         "latest-version": "^9.0.0",
         "proper-lockfile": "^4.1.2",
+        "punycode": "^2.3.1",
         "simple-git": "^3.28.0"
       },
       "bin": {
@@ -48,7 +49,6 @@
         "globals": "^16.0.0",
         "google-artifactregistry-auth": "^3.4.0",
         "husky": "^9.1.7",
-        "ink-testing-library": "^4.0.0",
         "json": "^11.0.0",
         "lint-staged": "^16.1.6",
         "memfs": "^4.42.0",
@@ -58,6 +58,7 @@
         "npm-run-all": "^4.1.5",
         "prettier": "^3.5.3",
         "react-devtools-core": "^6.1.2",
+        "react-dom": "^19.2.0",
         "semver": "^7.7.2",
         "strip-ansi": "^7.1.2",
         "ts-prune": "^0.10.3",
@@ -76,7 +77,6 @@
         "@lydell/node-pty-linux-x64": "1.1.0",
         "@lydell/node-pty-win32-arm64": "1.1.0",
         "@lydell/node-pty-win32-x64": "1.1.0",
-        "gemini-cli-devtools": "^0.2.1",
         "keytar": "^7.9.0",
         "node-pty": "^1.0.0"
       }
@@ -1389,6 +1389,10 @@
       "resolved": "packages/core",
       "link": true
     },
+    "node_modules/@google/gemini-cli-devtools": {
+      "resolved": "packages/devtools",
+      "link": true
+    },
     "node_modules/@google/gemini-cli-sdk": {
       "resolved": "packages/sdk",
       "link": true
@@ -9056,18 +9060,6 @@
         "node": ">=14"
       }
     },
-    "node_modules/gemini-cli-devtools": {
-      "version": "0.2.1",
-      "resolved": "https://registry.npmjs.org/gemini-cli-devtools/-/gemini-cli-devtools-0.2.1.tgz",
-      "integrity": "sha512-PcqPL9ZZjgjsp3oYhcXnUc6yNeLvdZuU/UQp0aT+DA8pt3BZzPzXthlOmIrRRqHBdLjMLPwN5GD29zR5bASXtQ==",
-      "optional": true,
-      "dependencies": {
-        "ws": "^8.16.0"
-      },
-      "engines": {
-        "node": ">=20"
-      }
-    },
     "node_modules/gemini-cli-vscode-ide-companion": {
       "resolved": "packages/vscode-ide-companion",
       "link": true
@@ -10029,9 +10021,9 @@
     },
     "node_modules/ink": {
       "name": "@jrichman/ink",
-      "version": "6.4.10",
-      "resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.4.10.tgz",
-      "integrity": "sha512-kjJqZFkGVm0QyJmga/L02rsFJroF1aP2bhXEGkpuuT7clB6/W+gxAbLNw7ZaJrG6T30DgqOT92Pu6C9mK1FWyg==",
+      "version": "6.4.11",
+      "resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.4.11.tgz",
+      "integrity": "sha512-93LQlzT7vvZ1XJcmOMwN4s+6W334QegendeHOMnEJBlhnpIzr8bws6/aOEHG8ZCuVD/vNeeea5m1msHIdAY6ig==",
       "license": "MIT",
       "dependencies": {
         "@alcalzone/ansi-tokenize": "^0.2.1",
@@ -10112,24 +10104,6 @@
         "react": ">=18.0.0"
       }
     },
-    "node_modules/ink-testing-library": {
-      "version": "4.0.0",
-      "resolved": "https://registry.npmjs.org/ink-testing-library/-/ink-testing-library-4.0.0.tgz",
-      "integrity": "sha512-yF92kj3pmBvk7oKbSq5vEALO//o7Z9Ck/OaLNlkzXNeYdwfpxMQkSowGTFUCS5MSu9bWfSZMewGpp7bFc66D7Q==",
-      "dev": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">=18"
-      },
-      "peerDependencies": {
-        "@types/react": ">=18.0.0"
-      },
-      "peerDependenciesMeta": {
-        "@types/react": {
-          "optional": true
-        }
-      }
-    },
     "node_modules/ink/node_modules/ansi-styles": {
       "version": "6.2.1",
       "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-6.2.1.tgz",
@@ -13547,7 +13521,6 @@
       "version": "2.3.1",
       "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.3.1.tgz",
       "integrity": "sha512-vYt7UD1U9Wg6138shLtLOvdAu+8DsC/ilFtEVHcH+wydcSpNE20AfSOduf6MkRFahL5FY7X1oU7nKVZFtfq8Fg==",
-      "devOptional": true,
       "license": "MIT",
       "engines": {
         "node": ">=6"
@@ -13709,9 +13682,9 @@
       }
     },
     "node_modules/react": {
-      "version": "19.2.0",
-      "resolved": "https://registry.npmjs.org/react/-/react-19.2.0.tgz",
-      "integrity": "sha512-tmbWg6W31tQLeB5cdIBOicJDJRR2KzXsV7uSK9iNfLWQ5bIZfxuPEHp7M8wiHyHnn0DD1i7w3Zmin0FtkrwoCQ==",
+      "version": "19.2.4",
+      "resolved": "https://registry.npmjs.org/react/-/react-19.2.4.tgz",
+      "integrity": "sha512-9nfp2hYpCwOjAN+8TZFGhtWEwgvWHXqESH8qT89AT/lWklpLON22Lc8pEtnpsZz7VmawabSU0gCjnj8aC0euHQ==",
       "license": "MIT",
       "engines": {
         "node": ">=0.10.0"
@@ -13750,6 +13723,26 @@
         }
       }
     },
+    "node_modules/react-dom": {
+      "version": "19.2.4",
+      "resolved": "https://registry.npmjs.org/react-dom/-/react-dom-19.2.4.tgz",
+      "integrity": "sha512-AXJdLo8kgMbimY95O2aKQqsz2iWi9jMgKJhRBAxECE4IFxfcazB2LmzloIoibJI3C12IlY20+KFaLv+71bUJeQ==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "scheduler": "^0.27.0"
+      },
+      "peerDependencies": {
+        "react": "^19.2.4"
+      }
+    },
+    "node_modules/react-dom/node_modules/scheduler": {
+      "version": "0.27.0",
+      "resolved": "https://registry.npmjs.org/scheduler/-/scheduler-0.27.0.tgz",
+      "integrity": "sha512-eNv+WrVbKu1f3vbYJT/xtiF5syA5HPIMtf9IgY/nKg0sWqzAUEvqY/xm7OcZc/qafLx/iO9FgOmeSAp4v5ti/Q==",
+      "dev": true,
+      "license": "MIT"
+    },
     "node_modules/react-is": {
       "version": "16.13.1",
       "resolved": "https://registry.npmjs.org/react-is/-/react-is-16.13.1.tgz",
@@ -15564,9 +15557,9 @@
       }
     },
     "node_modules/tar": {
-      "version": "7.5.7",
-      "resolved": "https://registry.npmjs.org/tar/-/tar-7.5.7.tgz",
-      "integrity": "sha512-fov56fJiRuThVFXD6o6/Q354S7pnWMJIVlDBYijsTNx6jKSE4pvrDTs6lUnmGvNyfJwFQQwWy3owKz1ucIhveQ==",
+      "version": "7.5.8",
+      "resolved": "https://registry.npmjs.org/tar/-/tar-7.5.8.tgz",
+      "integrity": "sha512-SYkBtK99u0yXa+IWL0JRzzcl7RxNpvX/U08Z+8DKnysfno7M+uExnTZH8K+VGgShf2qFPKtbNr9QBl8n7WBP6Q==",
       "license": "BlueOak-1.0.0",
       "dependencies": {
         "@isaacs/fs-minipass": "^4.0.0",
@@ -17262,7 +17255,7 @@
         "express": "^5.1.0",
         "fs-extra": "^11.3.0",
         "strip-json-comments": "^3.1.1",
-        "tar": "^7.5.2",
+        "tar": "^7.5.8",
         "uuid": "^13.0.0",
         "winston": "^3.17.0"
       },
@@ -17325,6 +17318,7 @@
         "chalk": "^4.1.2",
         "cli-spinners": "^2.9.2",
         "clipboardy": "^5.0.0",
+        "color-convert": "^2.0.1",
         "command-exists": "^1.2.9",
         "comment-json": "^4.2.5",
         "diff": "^8.0.3",
@@ -17333,7 +17327,7 @@
         "fzf": "^0.5.2",
         "glob": "^12.0.0",
         "highlight.js": "^11.11.1",
-        "ink": "npm:@jrichman/ink@6.4.10",
+        "ink": "npm:@jrichman/ink@6.4.11",
         "ink-gradient": "^3.0.0",
         "ink-spinner": "^5.0.0",
         "latest-version": "^9.0.0",
@@ -17348,7 +17342,7 @@
         "string-width": "^8.1.0",
         "strip-ansi": "^7.1.0",
         "strip-json-comments": "^3.1.1",
-        "tar": "^7.5.2",
+        "tar": "^7.5.8",
         "tinygradient": "^1.1.5",
         "undici": "^7.10.0",
         "ws": "^8.16.0",
@@ -17359,6 +17353,7 @@
         "gemini": "dist/index.js"
       },
       "devDependencies": {
+        "@google/gemini-cli-devtools": "file:../devtools",
         "@google/gemini-cli-test-utils": "file:../test-utils",
         "@types/command-exists": "^1.2.3",
         "@types/hast": "^3.0.4",
@@ -17368,7 +17363,7 @@
         "@types/shell-quote": "^1.7.5",
         "@types/ws": "^8.5.10",
         "@types/yargs": "^17.0.32",
-        "ink-testing-library": "^4.0.0",
+        "@xterm/headless": "^5.5.0",
         "typescript": "^5.3.3",
         "vitest": "^3.1.1"
       },
@@ -17573,6 +17568,21 @@
         "uuid": "dist-node/bin/uuid"
       }
     },
+    "packages/devtools": {
+      "name": "@google/gemini-cli-devtools",
+      "version": "0.30.0-nightly.20260210.a2174751d",
+      "license": "Apache-2.0",
+      "dependencies": {
+        "ws": "^8.16.0"
+      },
+      "devDependencies": {
+        "react": "^19.2.0",
+        "react-dom": "^19.2.0"
+      },
+      "engines": {
+        "node": ">=20"
+      }
+    },
     "packages/sdk": {
       "name": "@google/gemini-cli-sdk",
       "version": "0.29.0-nightly.20260203.71f46f116",

package.json

@@ -37,7 +37,7 @@
     "build:all": "npm run build && npm run build:sandbox && npm run build:vscode",
     "build:packages": "npm run build --workspaces",
     "build:sandbox": "node scripts/build_sandbox.js",
-    "bundle": "npm run generate && node esbuild.config.js && node scripts/copy_bundle_assets.js",
+    "bundle": "npm run generate && npm run build --workspace=@google/gemini-cli-devtools && node esbuild.config.js && node scripts/copy_bundle_assets.js",
     "test": "npm run test --workspaces --if-present",
     "test:ci": "npm run test:ci --workspaces --if-present && npm run test:scripts",
     "test:scripts": "vitest run --config ./scripts/tests/vitest.config.ts",
@@ -64,7 +64,7 @@
     "pre-commit": "node scripts/pre-commit.js"
   },
   "overrides": {
-    "ink": "npm:@jrichman/ink@6.4.10",
+    "ink": "npm:@jrichman/ink@6.4.11",
     "wrap-ansi": "9.0.2",
     "cliui": {
       "wrap-ansi": "7.0.0"
@@ -107,7 +107,6 @@
     "globals": "^16.0.0",
     "google-artifactregistry-auth": "^3.4.0",
     "husky": "^9.1.7",
-    "ink-testing-library": "^4.0.0",
     "json": "^11.0.0",
     "lint-staged": "^16.1.6",
     "memfs": "^4.42.0",
@@ -117,6 +116,7 @@
     "npm-run-all": "^4.1.5",
     "prettier": "^3.5.3",
     "react-devtools-core": "^6.1.2",
+    "react-dom": "^19.2.0",
     "semver": "^7.7.2",
     "strip-ansi": "^7.1.2",
     "ts-prune": "^0.10.3",
@@ -126,9 +126,10 @@
     "yargs": "^17.7.2"
   },
   "dependencies": {
-    "ink": "npm:@jrichman/ink@6.4.10",
+    "ink": "npm:@jrichman/ink@6.4.11",
     "latest-version": "^9.0.0",
     "proper-lockfile": "^4.1.2",
+    "punycode": "^2.3.1",
     "simple-git": "^3.28.0"
   },
   "optionalDependencies": {
@@ -138,7 +139,6 @@
     "@lydell/node-pty-linux-x64": "1.1.0",
     "@lydell/node-pty-win32-arm64": "1.1.0",
     "@lydell/node-pty-win32-x64": "1.1.0",
-    "gemini-cli-devtools": "^0.2.1",
     "keytar": "^7.9.0",
     "node-pty": "^1.0.0"
   },

packages/a2a-server/package.json

@@ -31,7 +31,7 @@
     "express": "^5.1.0",
     "fs-extra": "^11.3.0",
     "strip-json-comments": "^3.1.1",
-    "tar": "^7.5.2",
+    "tar": "^7.5.8",
     "uuid": "^13.0.0",
     "winston": "^3.17.0"
   },

packages/cli/package.json

@@ -39,6 +39,7 @@
     "chalk": "^4.1.2",
     "cli-spinners": "^2.9.2",
     "clipboardy": "^5.0.0",
+    "color-convert": "^2.0.1",
     "command-exists": "^1.2.9",
     "comment-json": "^4.2.5",
     "diff": "^8.0.3",
@@ -47,7 +48,7 @@
     "fzf": "^0.5.2",
     "glob": "^12.0.0",
     "highlight.js": "^11.11.1",
-    "ink": "npm:@jrichman/ink@6.4.10",
+    "ink": "npm:@jrichman/ink@6.4.11",
     "ink-gradient": "^3.0.0",
     "ink-spinner": "^5.0.0",
     "latest-version": "^9.0.0",
@@ -62,7 +63,7 @@
     "string-width": "^8.1.0",
     "strip-ansi": "^7.1.0",
     "strip-json-comments": "^3.1.1",
-    "tar": "^7.5.2",
+    "tar": "^7.5.8",
     "tinygradient": "^1.1.5",
     "undici": "^7.10.0",
     "ws": "^8.16.0",
@@ -70,6 +71,7 @@
     "zod": "^3.23.8"
   },
   "devDependencies": {
+    "@google/gemini-cli-devtools": "file:../devtools",
     "@google/gemini-cli-test-utils": "file:../test-utils",
     "@types/command-exists": "^1.2.3",
     "@types/hast": "^3.0.4",
@@ -79,7 +81,7 @@
     "@types/shell-quote": "^1.7.5",
     "@types/ws": "^8.5.10",
     "@types/yargs": "^17.0.32",
-    "ink-testing-library": "^4.0.0",
+    "@xterm/headless": "^5.5.0",
     "typescript": "^5.3.3",
     "vitest": "^3.1.1"
   },

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

@@ -1344,6 +1344,36 @@ describe('Approval mode tool exclusion logic', () => {
       'Invalid approval mode: invalid_mode. Valid values are: yolo, auto_edit, plan, default',
     );
   });
+
+  it('should fall back to default approval mode if plan mode is requested but not enabled', async () => {
+    process.argv = ['node', 'script.js'];
+    const settings = createTestMergedSettings({
+      general: {
+        defaultApprovalMode: 'plan',
+      },
+      experimental: {
+        plan: false,
+      },
+    });
+    const argv = await parseArguments(settings);
+    const config = await loadCliConfig(settings, 'test-session', argv);
+    expect(config.getApprovalMode()).toBe(ApprovalMode.DEFAULT);
+  });
+
+  it('should allow plan approval mode if experimental plan is enabled', async () => {
+    process.argv = ['node', 'script.js'];
+    const settings = createTestMergedSettings({
+      general: {
+        defaultApprovalMode: 'plan',
+      },
+      experimental: {
+        plan: true,
+      },
+    });
+    const argv = await parseArguments(settings);
+    const config = await loadCliConfig(settings, 'test-session', argv);
+    expect(config.getApprovalMode()).toBe(ApprovalMode.PLAN);
+  });
 });
 
 describe('loadCliConfig with allowed-mcp-server-names', () => {
@@ -2556,9 +2586,8 @@ describe('loadCliConfig approval mode', () => {
       },
     });
 
-    await expect(loadCliConfig(settings, 'test-session', argv)).rejects.toThrow(
-      'Approval mode "plan" is only available when experimental.plan is enabled.',
-    );
+    const config = await loadCliConfig(settings, 'test-session', argv);
+    expect(config.getApprovalMode()).toBe(ApprovalMode.DEFAULT);
   });
 
   it('should throw error when --approval-mode=plan is used but experimental.plan setting is missing', async () => {
@@ -2566,9 +2595,8 @@ describe('loadCliConfig approval mode', () => {
     const argv = await parseArguments(createTestMergedSettings());
     const settings = createTestMergedSettings({});
 
-    await expect(loadCliConfig(settings, 'test-session', argv)).rejects.toThrow(
-      'Approval mode "plan" is only available when experimental.plan is enabled.',
-    );
+    const config = await loadCliConfig(settings, 'test-session', argv);
+    expect(config.getApprovalMode()).toBe(ApprovalMode.DEFAULT);
   });
 
   // --- Untrusted Folder Scenarios ---
@@ -2678,11 +2706,8 @@ describe('loadCliConfig approval mode', () => {
         experimental: { plan: false },
       });
       const argv = await parseArguments(settings);
-      await expect(
-        loadCliConfig(settings, 'test-session', argv),
-      ).rejects.toThrow(
-        'Approval mode "plan" is only available when experimental.plan is enabled.',
-      );
+      const config = await loadCliConfig(settings, 'test-session', argv);
+      expect(config.getApprovalMode()).toBe(ApprovalMode.DEFAULT);
     });
   });
 });

packages/cli/src/config/config.ts

@@ -454,6 +454,7 @@ export async function loadCliConfig(
   }
 
   const memoryImportFormat = settings.context?.importFormat || 'tree';
+  const includeDirectoryTree = settings.context?.includeDirectoryTree ?? true;
 
   const ideMode = settings.ide?.enabled ?? false;
 
@@ -554,11 +555,13 @@ export async function loadCliConfig(
         break;
       case 'plan':
         if (!(settings.experimental?.plan ?? false)) {
-          throw new Error(
-            'Approval mode "plan" is only available when experimental.plan is enabled.',
+          debugLogger.warn(
+            'Approval mode "plan" is only available when experimental.plan is enabled. Falling back to "default".',
           );
+          approvalMode = ApprovalMode.DEFAULT;
+        } else {
+          approvalMode = ApprovalMode.PLAN;
         }
-        approvalMode = ApprovalMode.PLAN;
         break;
       case 'default':
         approvalMode = ApprovalMode.DEFAULT;
@@ -745,6 +748,7 @@ export async function loadCliConfig(
     embeddingModel: DEFAULT_GEMINI_EMBEDDING_MODEL,
     sandbox: sandboxConfig,
     targetDir: cwd,
+    includeDirectoryTree,
     includeDirectories,
     loadMemoryFromIncludeDirectories:
       settings.context?.loadMemoryFromIncludeDirectories || false,
@@ -814,6 +818,7 @@ export async function loadCliConfig(
     skillsSupport: settings.skills?.enabled ?? true,
     disabledSkills: settings.skills?.disabled,
     experimentalJitContext: settings.experimental?.jitContext,
+    modelSteering: settings.experimental?.modelSteering,
     toolOutputMasking: settings.experimental?.toolOutputMasking,
     noBrowser: !!process.env['NO_BROWSER'],
     summarizeToolOutput: settings.model?.summarizeToolOutput,

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

@@ -269,7 +269,7 @@ describe('github.ts', () => {
 
     it('should return NOT_UPDATABLE if local extension config cannot be loaded', async () => {
       vi.mocked(mockExtensionManager.loadExtensionConfig).mockImplementation(
-        () => {
+        async () => {
           throw new Error('Config not found');
         },
       );

packages/cli/src/config/keyBindings.ts

@@ -178,6 +178,7 @@ export const defaultKeyBindings: KeyBindingConfig = {
   [Command.DELETE_WORD_FORWARD]: [
     { key: 'delete', ctrl: true },
     { key: 'delete', alt: true },
+    { key: 'd', alt: true },
   ],
   [Command.DELETE_CHAR_LEFT]: [{ key: 'backspace' }, { key: 'h', ctrl: true }],
   [Command.DELETE_CHAR_RIGHT]: [{ key: 'delete' }, { key: 'd', ctrl: true }],
@@ -211,7 +212,7 @@ export const defaultKeyBindings: KeyBindingConfig = {
   [Command.REVERSE_SEARCH]: [{ key: 'r', ctrl: true }],
   [Command.REWIND]: [{ key: 'double escape' }],
   [Command.SUBMIT_REVERSE_SEARCH]: [{ key: 'return', ctrl: false }],
-  [Command.ACCEPT_SUGGESTION_REVERSE_SEARCH]: [{ key: 'tab' }],
+  [Command.ACCEPT_SUGGESTION_REVERSE_SEARCH]: [{ key: 'tab', shift: false }],
 
   // Navigation
   [Command.NAVIGATION_UP]: [{ key: 'up', shift: false }],
@@ -230,7 +231,10 @@ export const defaultKeyBindings: KeyBindingConfig = {
   [Command.DIALOG_PREV]: [{ key: 'tab', shift: true }],
 
   // Suggestions & Completions
-  [Command.ACCEPT_SUGGESTION]: [{ key: 'tab' }, { key: 'return', ctrl: false }],
+  [Command.ACCEPT_SUGGESTION]: [
+    { key: 'tab', shift: false },
+    { key: 'return', ctrl: false },
+  ],
   [Command.COMPLETION_UP]: [
     { key: 'up', shift: false },
     { key: 'p', shift: false, ctrl: true },
@@ -496,7 +500,7 @@ export const commandDescriptions: Readonly<Record<Command, string>> = {
   [Command.TOGGLE_COPY_MODE]: 'Toggle copy mode when in alternate buffer mode.',
   [Command.TOGGLE_YOLO]: 'Toggle YOLO (auto-approval) mode for tool calls.',
   [Command.CYCLE_APPROVAL_MODE]:
-    'Cycle through approval modes: default (prompt), auto_edit (auto-approve edits), and plan (read-only).',
+    'Cycle through approval modes: default (prompt), auto_edit (auto-approve edits), and plan (read-only). Plan mode is skipped when the agent is busy.',
   [Command.SHOW_MORE_LINES]:
     'Expand and collapse blocks of content when not in alternate buffer mode.',
   [Command.EXPAND_PASTE]:

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

@@ -353,6 +353,17 @@ describe('SettingsSchema', () => {
       ).toBe('Show the "? for shortcuts" hint above the input.');
     });
 
+    it('should have enableNotifications setting in schema', () => {
+      const setting =
+        getSettingsSchema().general.properties.enableNotifications;
+      expect(setting).toBeDefined();
+      expect(setting.type).toBe('boolean');
+      expect(setting.category).toBe('General');
+      expect(setting.default).toBe(false);
+      expect(setting.requiresRestart).toBe(false);
+      expect(setting.showInDialog).toBe(true);
+    });
+
     it('should have enableAgents setting in schema', () => {
       const setting = getSettingsSchema().experimental.properties.enableAgents;
       expect(setting).toBeDefined();

packages/cli/src/config/settingsSchema.ts

@@ -236,6 +236,16 @@ const SETTINGS_SCHEMA = {
         description: 'Enable update notification prompts.',
         showInDialog: false,
       },
+      enableNotifications: {
+        type: 'boolean',
+        label: 'Enable Notifications',
+        category: 'General',
+        requiresRestart: false,
+        default: false,
+        description:
+          'Enable run-event notifications for action-required prompts and session completion. Currently macOS only.',
+        showInDialog: true,
+      },
       checkpointing: {
         type: 'object',
         label: 'Checkpointing',
@@ -475,6 +485,15 @@ const SETTINGS_SCHEMA = {
           'Show a warning when running Gemini CLI in the home directory.',
         showInDialog: true,
       },
+      showCompatibilityWarnings: {
+        type: 'boolean',
+        label: 'Show Compatibility Warnings',
+        category: 'UI',
+        requiresRestart: true,
+        default: true,
+        description: 'Show warnings about terminal or OS compatibility issues.',
+        showInDialog: true,
+      },
       hideTips: {
         type: 'boolean',
         label: 'Hide Tips',
@@ -949,6 +968,16 @@ const SETTINGS_SCHEMA = {
         description: 'The format to use when importing memory.',
         showInDialog: false,
       },
+      includeDirectoryTree: {
+        type: 'boolean',
+        label: 'Include Directory Tree',
+        category: 'Context',
+        requiresRestart: false,
+        default: true,
+        description:
+          'Whether to include the directory tree of the current working directory in the initial request to the model.',
+        showInDialog: false,
+      },
       discoveryMaxDirs: {
         type: 'number',
         label: 'Memory Discovery Max Dirs',
@@ -1615,6 +1644,16 @@ const SETTINGS_SCHEMA = {
         description: 'Enable planning features (Plan Mode and tools).',
         showInDialog: true,
       },
+      modelSteering: {
+        type: 'boolean',
+        label: 'Model Steering',
+        category: 'Experimental',
+        requiresRestart: false,
+        default: false,
+        description:
+          'Enable model steering (user hints) to guide the model during tool execution.',
+        showInDialog: true,
+      },
     },
   },
 

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

@@ -491,25 +491,33 @@ describe('Trusted Folders', () => {
     });
   });
 
+  const itif = (condition: boolean) => (condition ? it : it.skip);
+
   describe('Symlinks Support', () => {
     const mockSettings: Settings = {
       security: { folderTrust: { enabled: true } },
     };
 
-    it('should trust a folder if the rule matches the realpath', () => {
-      // Create a real directory and a symlink
-      const realDir = path.join(tempDir, 'real');
-      const symlinkDir = path.join(tempDir, 'symlink');
-      fs.mkdirSync(realDir);
-      fs.symlinkSync(realDir, symlinkDir);
+    // TODO: issue 19387 - Enable symlink tests on Windows
+    itif(process.platform !== 'win32')(
+      'should trust a folder if the rule matches the realpath',
+      () => {
+        // Create a real directory and a symlink
+        const realDir = path.join(tempDir, 'real');
+        const symlinkDir = path.join(tempDir, 'symlink');
+        fs.mkdirSync(realDir);
+        fs.symlinkSync(realDir, symlinkDir);
 
-      // Rule uses realpath
-      const config = { [realDir]: TrustLevel.TRUST_FOLDER };
-      fs.writeFileSync(trustedFoldersPath, JSON.stringify(config), 'utf-8');
+        // Rule uses realpath
+        const config = { [realDir]: TrustLevel.TRUST_FOLDER };
+        fs.writeFileSync(trustedFoldersPath, JSON.stringify(config), 'utf-8');
 
-      // Check against symlink path
-      expect(isWorkspaceTrusted(mockSettings, symlinkDir).isTrusted).toBe(true);
-    });
+        // Check against symlink path
+        expect(isWorkspaceTrusted(mockSettings, symlinkDir).isTrusted).toBe(
+          true,
+        );
+      },
+    );
   });
 
   describe('Verification: Auth and Trust Interaction', () => {

packages/cli/src/gemini.test.tsx

@@ -56,6 +56,20 @@ vi.mock('./nonInteractiveCli.js', () => ({
   runNonInteractive: runNonInteractiveSpy,
 }));
 
+const terminalNotificationMocks = vi.hoisted(() => ({
+  notifyViaTerminal: vi.fn().mockResolvedValue(true),
+  buildRunEventNotificationContent: vi.fn(() => ({
+    title: 'Session complete',
+    body: 'done',
+    subtitle: 'Run finished',
+  })),
+}));
+vi.mock('./utils/terminalNotifications.js', () => ({
+  notifyViaTerminal: terminalNotificationMocks.notifyViaTerminal,
+  buildRunEventNotificationContent:
+    terminalNotificationMocks.buildRunEventNotificationContent,
+}));
+
 vi.mock('@google/gemini-cli-core', async (importOriginal) => {
   const actual =
     await importOriginal<typeof import('@google/gemini-cli-core')>();
@@ -837,6 +851,10 @@ describe('gemini.tsx main function kitty protocol', () => {
     expect(runNonInteractive).toHaveBeenCalled();
     const callArgs = vi.mocked(runNonInteractive).mock.calls[0][0];
     expect(callArgs.input).toBe('stdin-data\n\ntest-question');
+    expect(
+      terminalNotificationMocks.buildRunEventNotificationContent,
+    ).not.toHaveBeenCalled();
+    expect(terminalNotificationMocks.notifyViaTerminal).not.toHaveBeenCalled();
     expect(processExitSpy).toHaveBeenCalledWith(0);
     processExitSpy.mockRestore();
   });

packages/cli/src/gemini_cleanup.test.tsx

@@ -9,14 +9,6 @@ import { main } from './gemini.js';
 import { debugLogger } from '@google/gemini-cli-core';
 import { type Config } from '@google/gemini-cli-core';
 
-// Custom error to identify mock process.exit calls
-class MockProcessExitError extends Error {
-  constructor(readonly code?: string | number | null | undefined) {
-    super('PROCESS_EXIT_MOCKED');
-    this.name = 'MockProcessExitError';
-  }
-}
-
 vi.mock('@google/gemini-cli-core', async (importOriginal) => {
   const actual =
     await importOriginal<typeof import('@google/gemini-cli-core')>();
@@ -124,10 +116,39 @@ vi.mock('./validateNonInterActiveAuth.js', () => ({
   validateNonInteractiveAuth: vi.fn().mockResolvedValue({}),
 }));
 
+vi.mock('./core/initializer.js', () => ({
+  initializeApp: vi.fn().mockResolvedValue({
+    authError: null,
+    themeError: null,
+    shouldOpenAuthDialog: false,
+    geminiMdFileCount: 0,
+  }),
+}));
+
 vi.mock('./nonInteractiveCli.js', () => ({
   runNonInteractive: vi.fn().mockResolvedValue(undefined),
 }));
 
+vi.mock('./utils/cleanup.js', async (importOriginal) => {
+  const actual = await importOriginal<typeof import('./utils/cleanup.js')>();
+  return {
+    ...actual,
+    cleanupCheckpoints: vi.fn().mockResolvedValue(undefined),
+    registerCleanup: vi.fn(),
+    registerSyncCleanup: vi.fn(),
+    registerTelemetryConfig: vi.fn(),
+    runExitCleanup: vi.fn().mockResolvedValue(undefined),
+  };
+});
+
+vi.mock('./zed-integration/zedIntegration.js', () => ({
+  runZedIntegration: vi.fn().mockResolvedValue(undefined),
+}));
+
+vi.mock('./utils/readStdin.js', () => ({
+  readStdin: vi.fn().mockResolvedValue(''),
+}));
+
 const { cleanupMockState } = vi.hoisted(() => ({
   cleanupMockState: { shouldThrow: false, called: false },
 }));
@@ -169,12 +190,6 @@ describe('gemini.tsx main function cleanup', () => {
     const debugLoggerErrorSpy = vi
       .spyOn(debugLogger, 'error')
       .mockImplementation(() => {});
-    const processExitSpy = vi
-      .spyOn(process, 'exit')
-      .mockImplementation((code) => {
-        throw new MockProcessExitError(code);
-      });
-
     vi.mocked(loadSettings).mockReturnValue({
       merged: { advanced: {}, security: { auth: {} }, ui: {} },
       workspace: { settings: {} },
@@ -201,7 +216,7 @@ describe('gemini.tsx main function cleanup', () => {
       getMcpServers: () => ({}),
       getMcpClientManager: vi.fn(),
       getIdeMode: vi.fn(() => false),
-      getExperimentalZedIntegration: vi.fn(() => false),
+      getExperimentalZedIntegration: vi.fn(() => true),
       getScreenReader: vi.fn(() => false),
       getGeminiMdFileCount: vi.fn(() => 0),
       getProjectRoot: vi.fn(() => '/'),
@@ -224,18 +239,12 @@ describe('gemini.tsx main function cleanup', () => {
       getRemoteAdminSettings: vi.fn(() => undefined),
     } as any); // eslint-disable-line @typescript-eslint/no-explicit-any
 
-    try {
-      await main();
-    } catch (e) {
-      if (!(e instanceof MockProcessExitError)) throw e;
-    }
+    await main();
 
     expect(cleanupMockState.called).toBe(true);
     expect(debugLoggerErrorSpy).toHaveBeenCalledWith(
       'Failed to cleanup expired sessions:',
       expect.objectContaining({ message: 'Cleanup failed' }),
     );
-    expect(processExitSpy).toHaveBeenCalledWith(0); // Should not exit on cleanup failure
-    processExitSpy.mockRestore();
   });
 });

packages/cli/src/integration-tests/modelSteering.test.tsx

@@ -0,0 +1,84 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, afterEach } from 'vitest';
+import { AppRig } from '../test-utils/AppRig.js';
+import path from 'node:path';
+import { fileURLToPath } from 'node:url';
+import { PolicyDecision } from '@google/gemini-cli-core';
+
+const __dirname = path.dirname(fileURLToPath(import.meta.url));
+
+describe('Model Steering Integration', () => {
+  let rig: AppRig | undefined;
+
+  afterEach(async () => {
+    await rig?.unmount();
+  });
+
+  it('should steer the model using a hint during a tool turn', async () => {
+    const fakeResponsesPath = path.join(
+      __dirname,
+      '../test-utils/fixtures/steering.responses',
+    );
+    rig = new AppRig({
+      fakeResponsesPath,
+      configOverrides: { modelSteering: true },
+    });
+    await rig.initialize();
+    rig.render();
+    await rig.waitForIdle();
+
+    rig.setToolPolicy('list_directory', PolicyDecision.ASK_USER);
+    rig.setToolPolicy('read_file', PolicyDecision.ASK_USER);
+
+    rig.setMockCommands([
+      {
+        command: /list_directory/,
+        result: {
+          output: 'file1.txt\nfile2.js\nfile3.md',
+          exitCode: 0,
+        },
+      },
+      {
+        command: /read_file file1.txt/,
+        result: {
+          output: 'This is file1.txt content.',
+          exitCode: 0,
+        },
+      },
+    ]);
+
+    // Start a long task
+    await rig.type('Start long task');
+    await rig.pressEnter();
+
+    // Wait for the model to call 'list_directory' (Confirming state)
+    await rig.waitForOutput('ReadFolder');
+
+    // Injected a hint while the model is in a tool turn
+    await rig.addUserHint('focus on .txt');
+
+    // Resolve list_directory (Proceed)
+    await rig.resolveTool('ReadFolder');
+
+    // Wait for the model to process the hint and output the next action
+    // Based on steering.responses, it should first acknowledge the hint
+    await rig.waitForOutput('ACK: I will focus on .txt files now.');
+
+    // Then it should proceed with the next action
+    await rig.waitForOutput(
+      /Since you want me to focus on .txt files,[\s\S]*I will read file1.txt/,
+    );
+    await rig.waitForOutput('ReadFile');
+
+    // Resolve read_file (Proceed)
+    await rig.resolveTool('ReadFile');
+
+    // Wait for final completion
+    await rig.waitForOutput('Task complete.');
+  });
+});

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

@@ -0,0 +1,88 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, afterEach, expect } from 'vitest';
+import { act } from 'react';
+import { AppRig } from './AppRig.js';
+import path from 'node:path';
+import { fileURLToPath } from 'node:url';
+import { debugLogger } from '@google/gemini-cli-core';
+
+const __dirname = path.dirname(fileURLToPath(import.meta.url));
+
+describe('AppRig', () => {
+  let rig: AppRig | undefined;
+
+  afterEach(async () => {
+    await rig?.unmount();
+  });
+
+  it('should handle deterministic tool turns with breakpoints', async () => {
+    const fakeResponsesPath = path.join(
+      __dirname,
+      'fixtures',
+      'steering.responses',
+    );
+    rig = new AppRig({
+      fakeResponsesPath,
+      configOverrides: { modelSteering: true },
+    });
+    await rig.initialize();
+    rig.render();
+    await rig.waitForIdle();
+
+    // Set breakpoints on the canonical tool names
+    rig.setBreakpoint('list_directory');
+    rig.setBreakpoint('read_file');
+
+    // Start a task
+    debugLogger.log('[Test] Sending message: Start long task');
+    await rig.sendMessage('Start long task');
+
+    // Wait for the first breakpoint (list_directory)
+    const pending1 = await rig.waitForPendingConfirmation('list_directory');
+    expect(pending1.toolName).toBe('list_directory');
+
+    // Injected a hint
+    await rig.addUserHint('focus on .txt');
+
+    // Resolve and wait for the NEXT breakpoint (read_file)
+    // resolveTool will automatically remove the breakpoint policy for list_directory
+    await rig.resolveTool('list_directory');
+
+    const pending2 = await rig.waitForPendingConfirmation('read_file');
+    expect(pending2.toolName).toBe('read_file');
+
+    // Resolve and finish. Also removes read_file breakpoint.
+    await rig.resolveTool('read_file');
+    await rig.waitForOutput('Task complete.', 100000);
+  });
+
+  it('should render the app and handle a simple message', async () => {
+    const fakeResponsesPath = path.join(
+      __dirname,
+      'fixtures',
+      'simple.responses',
+    );
+    rig = new AppRig({ fakeResponsesPath });
+    await rig.initialize();
+    await act(async () => {
+      rig!.render();
+      // Allow async initializations (like banners) to settle within the act boundary
+      await new Promise((resolve) => setTimeout(resolve, 0));
+    });
+
+    // Wait for initial render
+    await rig.waitForIdle();
+
+    // Type a message
+    await rig.type('Hello');
+    await rig.pressEnter();
+
+    // Wait for model response
+    await rig.waitForOutput('Hello! How can I help you today?');
+  });
+});

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

@@ -0,0 +1,581 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { vi } from 'vitest';
+import { act } from 'react';
+import stripAnsi from 'strip-ansi';
+import os from 'node:os';
+import path from 'node:path';
+import fs from 'node:fs';
+import { AppContainer } from '../ui/AppContainer.js';
+import { renderWithProviders } from './render.js';
+import {
+  makeFakeConfig,
+  type Config,
+  type ConfigParameters,
+  ExtensionLoader,
+  AuthType,
+  ApprovalMode,
+  createPolicyEngineConfig,
+  PolicyDecision,
+  ToolConfirmationOutcome,
+  MessageBusType,
+  type ToolCallsUpdateMessage,
+  coreEvents,
+  ideContextStore,
+  createContentGenerator,
+  IdeClient,
+  debugLogger,
+} from '@google/gemini-cli-core';
+import {
+  type MockShellCommand,
+  MockShellExecutionService,
+} from './MockShellExecutionService.js';
+import { createMockSettings } from './settings.js';
+import { type LoadedSettings } from '../config/settings.js';
+import { AuthState } from '../ui/types.js';
+
+// Mock core functions globally for tests using AppRig.
+vi.mock('@google/gemini-cli-core', async (importOriginal) => {
+  const original =
+    await importOriginal<typeof import('@google/gemini-cli-core')>();
+  const { MockShellExecutionService: MockService } = await import(
+    './MockShellExecutionService.js'
+  );
+  // Register the real execution logic so MockShellExecutionService can fall back to it
+  MockService.setOriginalImplementation(original.ShellExecutionService.execute);
+
+  return {
+    ...original,
+    ShellExecutionService: MockService,
+  };
+});
+
+// Mock useAuthCommand to bypass authentication flows in tests
+vi.mock('../ui/auth/useAuth.js', () => ({
+  useAuthCommand: () => ({
+    authState: AuthState.Authenticated,
+    setAuthState: vi.fn(),
+    authError: null,
+    onAuthError: vi.fn(),
+    apiKeyDefaultValue: 'test-api-key',
+    reloadApiKey: vi.fn().mockResolvedValue('test-api-key'),
+  }),
+  validateAuthMethodWithSettings: () => null,
+}));
+
+// A minimal mock ExtensionManager to satisfy AppContainer's forceful cast
+class MockExtensionManager extends ExtensionLoader {
+  getExtensions = vi.fn().mockReturnValue([]);
+  setRequestConsent = vi.fn();
+  setRequestSetting = vi.fn();
+}
+
+// Mock GeminiRespondingSpinner to disable animations (avoiding 'act()' warnings) without triggering screen reader mode.
+vi.mock('../ui/components/GeminiRespondingSpinner.js', async () => {
+  const React = await import('react');
+  const { Text } = await import('ink');
+  return {
+    GeminiSpinner: () => React.createElement(Text, null, '...'),
+    GeminiRespondingSpinner: ({
+      nonRespondingDisplay,
+    }: {
+      nonRespondingDisplay: string;
+    }) => React.createElement(Text, null, nonRespondingDisplay || '...'),
+  };
+});
+
+export interface AppRigOptions {
+  fakeResponsesPath?: string;
+  terminalWidth?: number;
+  terminalHeight?: number;
+  configOverrides?: Partial<ConfigParameters>;
+}
+
+export interface PendingConfirmation {
+  toolName: string;
+  toolDisplayName?: string;
+  correlationId: string;
+}
+
+export class AppRig {
+  private renderResult: ReturnType<typeof renderWithProviders> | undefined;
+  private config: Config | undefined;
+  private settings: LoadedSettings | undefined;
+  private testDir: string;
+  private sessionId: string;
+
+  private pendingConfirmations = new Map<string, PendingConfirmation>();
+  private breakpointTools = new Set<string | undefined>();
+  private lastAwaitedConfirmation: PendingConfirmation | undefined;
+
+  constructor(private options: AppRigOptions = {}) {
+    this.testDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gemini-app-rig-'));
+    this.sessionId = `test-session-${Math.random().toString(36).slice(2, 9)}`;
+  }
+
+  async initialize() {
+    this.setupEnvironment();
+    this.settings = this.createRigSettings();
+
+    const approvalMode =
+      this.options.configOverrides?.approvalMode ?? ApprovalMode.DEFAULT;
+    const policyEngineConfig = await createPolicyEngineConfig(
+      this.settings.merged,
+      approvalMode,
+    );
+
+    const configParams: ConfigParameters = {
+      sessionId: this.sessionId,
+      targetDir: this.testDir,
+      cwd: this.testDir,
+      debugMode: false,
+      model: 'test-model',
+      fakeResponses: this.options.fakeResponsesPath,
+      interactive: true,
+      approvalMode,
+      policyEngineConfig,
+      enableEventDrivenScheduler: true,
+      extensionLoader: new MockExtensionManager(),
+      excludeTools: this.options.configOverrides?.excludeTools,
+      ...this.options.configOverrides,
+    };
+    this.config = makeFakeConfig(configParams);
+
+    if (this.options.fakeResponsesPath) {
+      this.stubRefreshAuth();
+    }
+
+    this.setupMessageBusListeners();
+
+    await act(async () => {
+      await this.config!.initialize();
+      // Since we mocked useAuthCommand, we must manually trigger the first
+      // refreshAuth to ensure contentGenerator is initialized.
+      await this.config!.refreshAuth(AuthType.USE_GEMINI);
+    });
+  }
+
+  private setupEnvironment() {
+    // Stub environment variables to avoid interference from developer's machine
+    vi.stubEnv('GEMINI_CLI_HOME', this.testDir);
+    if (this.options.fakeResponsesPath) {
+      vi.stubEnv('GEMINI_API_KEY', 'test-api-key');
+      MockShellExecutionService.setPassthrough(false);
+    } else {
+      if (!process.env['GEMINI_API_KEY']) {
+        throw new Error(
+          'GEMINI_API_KEY must be set in the environment for live model tests.',
+        );
+      }
+      // For live tests, we allow falling through to the real shell service if no mock matches
+      MockShellExecutionService.setPassthrough(true);
+    }
+    vi.stubEnv('GEMINI_DEFAULT_AUTH_TYPE', AuthType.USE_GEMINI);
+  }
+
+  private createRigSettings(): LoadedSettings {
+    return createMockSettings({
+      user: {
+        path: path.join(this.testDir, '.gemini', 'user_settings.json'),
+        settings: {
+          security: {
+            auth: {
+              selectedType: AuthType.USE_GEMINI,
+              useExternal: true,
+            },
+            folderTrust: {
+              enabled: true,
+            },
+          },
+          ide: {
+            enabled: false,
+            hasSeenNudge: true,
+          },
+        },
+        originalSettings: {},
+      },
+      merged: {
+        security: {
+          auth: {
+            selectedType: AuthType.USE_GEMINI,
+            useExternal: true,
+          },
+          folderTrust: {
+            enabled: true,
+          },
+        },
+        ide: {
+          enabled: false,
+          hasSeenNudge: true,
+        },
+      },
+    });
+  }
+
+  private stubRefreshAuth() {
+    // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion, @typescript-eslint/no-explicit-any
+    const gcConfig = this.config as any;
+    gcConfig.refreshAuth = async (authMethod: AuthType) => {
+      gcConfig.modelAvailabilityService.reset();
+
+      const newContentGeneratorConfig = {
+        authType: authMethod,
+        proxy: gcConfig.getProxy(),
+        apiKey: process.env['GEMINI_API_KEY'] || 'test-api-key',
+      };
+
+      gcConfig.contentGenerator = await createContentGenerator(
+        newContentGeneratorConfig,
+        this.config!,
+        gcConfig.getSessionId(),
+      );
+      gcConfig.contentGeneratorConfig = newContentGeneratorConfig;
+
+      // Initialize BaseLlmClient now that the ContentGenerator is available
+      const { BaseLlmClient } = await import('@google/gemini-cli-core');
+      gcConfig.baseLlmClient = new BaseLlmClient(
+        gcConfig.contentGenerator,
+        this.config!,
+      );
+    };
+  }
+
+  private setupMessageBusListeners() {
+    if (!this.config) return;
+    const messageBus = this.config.getMessageBus();
+
+    messageBus.subscribe(
+      MessageBusType.TOOL_CALLS_UPDATE,
+      (message: ToolCallsUpdateMessage) => {
+        for (const call of message.toolCalls) {
+          if (call.status === 'awaiting_approval' && call.correlationId) {
+            const details = call.confirmationDetails;
+            const title = 'title' in details ? details.title : '';
+            const toolDisplayName =
+              call.tool?.displayName || title.replace(/^Confirm:\s*/, '');
+            if (!this.pendingConfirmations.has(call.correlationId)) {
+              this.pendingConfirmations.set(call.correlationId, {
+                toolName: call.request.name,
+                toolDisplayName,
+                correlationId: call.correlationId,
+              });
+            }
+          } else if (call.status !== 'awaiting_approval') {
+            for (const [
+              correlationId,
+              pending,
+            ] of this.pendingConfirmations.entries()) {
+              if (pending.toolName === call.request.name) {
+                this.pendingConfirmations.delete(correlationId);
+                break;
+              }
+            }
+          }
+        }
+      },
+    );
+  }
+
+  render() {
+    if (!this.config || !this.settings)
+      throw new Error('AppRig not initialized');
+
+    act(() => {
+      this.renderResult = renderWithProviders(
+        <AppContainer
+          config={this.config!}
+          version="test-version"
+          initializationResult={{
+            authError: null,
+            themeError: null,
+            shouldOpenAuthDialog: false,
+            geminiMdFileCount: 0,
+          }}
+        />,
+        {
+          config: this.config!,
+          settings: this.settings!,
+          width: this.options.terminalWidth ?? 120,
+          useAlternateBuffer: false,
+          uiState: {
+            terminalHeight: this.options.terminalHeight ?? 40,
+          },
+        },
+      );
+    });
+  }
+
+  setMockCommands(commands: MockShellCommand[]) {
+    MockShellExecutionService.setMockCommands(commands);
+  }
+
+  setToolPolicy(
+    toolName: string | undefined,
+    decision: PolicyDecision,
+    priority = 10,
+  ) {
+    if (!this.config) throw new Error('AppRig not initialized');
+    this.config.getPolicyEngine().addRule({
+      toolName,
+      decision,
+      priority,
+      source: 'AppRig Override',
+    });
+  }
+
+  setBreakpoint(toolName: string | string[] | undefined) {
+    if (Array.isArray(toolName)) {
+      for (const name of toolName) {
+        this.setBreakpoint(name);
+      }
+    } else {
+      this.setToolPolicy(toolName, PolicyDecision.ASK_USER, 100);
+      this.breakpointTools.add(toolName);
+    }
+  }
+
+  removeToolPolicy(toolName?: string, source = 'AppRig Override') {
+    if (!this.config) throw new Error('AppRig not initialized');
+    this.config
+      .getPolicyEngine()
+      // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
+      .removeRulesForTool(toolName as string, source);
+    this.breakpointTools.delete(toolName);
+  }
+
+  getTestDir(): string {
+    return this.testDir;
+  }
+
+  getPendingConfirmations() {
+    return Array.from(this.pendingConfirmations.values());
+  }
+
+  private async waitUntil(
+    predicate: () => boolean | Promise<boolean>,
+    options: { timeout?: number; interval?: number; message?: string } = {},
+  ) {
+    const {
+      timeout = 30000,
+      interval = 100,
+      message = 'Condition timed out',
+    } = options;
+    const start = Date.now();
+
+    while (true) {
+      if (await predicate()) return;
+
+      if (Date.now() - start > timeout) {
+        throw new Error(message);
+      }
+
+      await act(async () => {
+        await new Promise((resolve) => setTimeout(resolve, interval));
+      });
+    }
+  }
+
+  async waitForPendingConfirmation(
+    toolNameOrDisplayName?: string | RegExp,
+    timeout = 30000,
+  ): Promise<PendingConfirmation> {
+    const matches = (p: PendingConfirmation) => {
+      if (!toolNameOrDisplayName) return true;
+      if (typeof toolNameOrDisplayName === 'string') {
+        return (
+          p.toolName === toolNameOrDisplayName ||
+          p.toolDisplayName === toolNameOrDisplayName
+        );
+      }
+      return (
+        toolNameOrDisplayName.test(p.toolName) ||
+        toolNameOrDisplayName.test(p.toolDisplayName || '')
+      );
+    };
+
+    let matched: PendingConfirmation | undefined;
+    await this.waitUntil(
+      () => {
+        matched = this.getPendingConfirmations().find(matches);
+        return !!matched;
+      },
+      {
+        timeout,
+        message: `Timed out waiting for pending confirmation: ${toolNameOrDisplayName || 'any'}. Current pending: ${this.getPendingConfirmations()
+          .map((p) => p.toolName)
+          .join(', ')}`,
+      },
+    );
+
+    this.lastAwaitedConfirmation = matched;
+    return matched!;
+  }
+
+  async resolveTool(
+    toolNameOrDisplayName: string | RegExp | PendingConfirmation,
+    outcome: ToolConfirmationOutcome = ToolConfirmationOutcome.ProceedOnce,
+  ): Promise<void> {
+    if (!this.config) throw new Error('AppRig not initialized');
+    const messageBus = this.config.getMessageBus();
+
+    let pending: PendingConfirmation;
+    if (
+      typeof toolNameOrDisplayName === 'object' &&
+      'correlationId' in toolNameOrDisplayName
+    ) {
+      pending = toolNameOrDisplayName;
+    } else {
+      pending = await this.waitForPendingConfirmation(toolNameOrDisplayName);
+    }
+
+    await act(async () => {
+      this.pendingConfirmations.delete(pending.correlationId);
+
+      if (this.breakpointTools.has(pending.toolName)) {
+        this.removeToolPolicy(pending.toolName);
+      }
+
+      // eslint-disable-next-line @typescript-eslint/no-floating-promises
+      messageBus.publish({
+        type: MessageBusType.TOOL_CONFIRMATION_RESPONSE,
+        correlationId: pending.correlationId,
+        confirmed: outcome !== ToolConfirmationOutcome.Cancel,
+        outcome,
+      });
+    });
+
+    await act(async () => {
+      await new Promise((resolve) => setTimeout(resolve, 100));
+    });
+  }
+
+  async resolveAwaitedTool(
+    outcome: ToolConfirmationOutcome = ToolConfirmationOutcome.ProceedOnce,
+  ): Promise<void> {
+    if (!this.lastAwaitedConfirmation) {
+      throw new Error('No tool has been awaited yet');
+    }
+    await this.resolveTool(this.lastAwaitedConfirmation, outcome);
+    this.lastAwaitedConfirmation = undefined;
+  }
+
+  async addUserHint(hint: string) {
+    if (!this.config) throw new Error('AppRig not initialized');
+    await act(async () => {
+      this.config!.userHintService.addUserHint(hint);
+    });
+  }
+
+  getConfig(): Config {
+    if (!this.config) throw new Error('AppRig not initialized');
+    return this.config;
+  }
+
+  async type(text: string) {
+    if (!this.renderResult) throw new Error('AppRig not initialized');
+    await act(async () => {
+      this.renderResult!.stdin.write(text);
+    });
+    await act(async () => {
+      await new Promise((resolve) => setTimeout(resolve, 50));
+    });
+  }
+
+  async pressEnter() {
+    await this.type('\r');
+  }
+
+  async pressKey(key: string) {
+    if (!this.renderResult) throw new Error('AppRig not initialized');
+    await act(async () => {
+      this.renderResult!.stdin.write(key);
+    });
+    await act(async () => {
+      await new Promise((resolve) => setTimeout(resolve, 50));
+    });
+  }
+
+  get lastFrame() {
+    if (!this.renderResult) return '';
+    return stripAnsi(this.renderResult.lastFrame({ allowEmpty: true }) || '');
+  }
+
+  getStaticOutput() {
+    if (!this.renderResult) return '';
+    return stripAnsi(this.renderResult.stdout.lastFrame() || '');
+  }
+
+  async waitForOutput(pattern: string | RegExp, timeout = 30000) {
+    await this.waitUntil(
+      () => {
+        const frame = this.lastFrame;
+        return typeof pattern === 'string'
+          ? frame.includes(pattern)
+          : pattern.test(frame);
+      },
+      {
+        timeout,
+        message: `Timed out waiting for output: ${pattern}\nLast frame:\n${this.lastFrame}`,
+      },
+    );
+  }
+
+  async waitForIdle(timeout = 20000) {
+    await this.waitForOutput('Type your message', timeout);
+  }
+
+  async sendMessage(text: string) {
+    await this.type(text);
+    await this.pressEnter();
+  }
+
+  async unmount() {
+    // Poison the chat recording service to prevent late writes to the test directory
+    if (this.config) {
+      const recordingService = this.config
+        .getGeminiClient()
+        ?.getChatRecordingService();
+      if (recordingService) {
+        // eslint-disable-next-line @typescript-eslint/no-explicit-any, @typescript-eslint/no-unsafe-type-assertion
+        (recordingService as any).conversationFile = null;
+      }
+    }
+
+    if (this.renderResult) {
+      this.renderResult.unmount();
+    }
+
+    await act(async () => {
+      await new Promise((resolve) => setTimeout(resolve, 500));
+    });
+
+    vi.unstubAllEnvs();
+
+    coreEvents.removeAllListeners();
+    coreEvents.drainBacklogs();
+    MockShellExecutionService.reset();
+    ideContextStore.clear();
+    // Forcefully clear IdeClient singleton promise
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any, @typescript-eslint/no-unsafe-type-assertion
+    (IdeClient as any).instancePromise = null;
+    vi.clearAllMocks();
+
+    this.config = undefined;
+    this.renderResult = undefined;
+
+    if (this.testDir && fs.existsSync(this.testDir)) {
+      try {
+        fs.rmSync(this.testDir, { recursive: true, force: true });
+      } catch (e) {
+        debugLogger.warn(
+          `Failed to cleanup test directory ${this.testDir}:`,
+          e,
+        );
+      }
+    }
+  }
+}

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

@@ -0,0 +1,140 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { vi } from 'vitest';
+import type {
+  ShellExecutionHandle,
+  ShellExecutionResult,
+  ShellOutputEvent,
+  ShellExecutionConfig,
+} from '@google/gemini-cli-core';
+
+export interface MockShellCommand {
+  command: string | RegExp;
+  result: Partial<ShellExecutionResult>;
+  events?: ShellOutputEvent[];
+}
+
+type ShellExecutionServiceExecute = (
+  commandToExecute: string,
+  cwd: string,
+  onOutputEvent: (event: ShellOutputEvent) => void,
+  abortSignal: AbortSignal,
+  shouldUseNodePty: boolean,
+  shellExecutionConfig: ShellExecutionConfig,
+) => Promise<ShellExecutionHandle>;
+
+export class MockShellExecutionService {
+  private static mockCommands: MockShellCommand[] = [];
+  private static originalExecute: ShellExecutionServiceExecute | undefined;
+  private static passthroughEnabled = false;
+
+  /**
+   * Registers the original implementation to allow falling back to real shell execution.
+   */
+  static setOriginalImplementation(
+    implementation: ShellExecutionServiceExecute,
+  ) {
+    this.originalExecute = implementation;
+  }
+
+  /**
+   * Enables or disables passthrough to the real implementation when no mock matches.
+   */
+  static setPassthrough(enabled: boolean) {
+    this.passthroughEnabled = enabled;
+  }
+
+  static setMockCommands(commands: MockShellCommand[]) {
+    this.mockCommands = commands;
+  }
+
+  static reset() {
+    this.mockCommands = [];
+    this.passthroughEnabled = false;
+    this.writeToPty.mockClear();
+    this.kill.mockClear();
+    this.background.mockClear();
+    this.resizePty.mockClear();
+    this.scrollPty.mockClear();
+  }
+
+  static async execute(
+    commandToExecute: string,
+    cwd: string,
+    onOutputEvent: (event: ShellOutputEvent) => void,
+    abortSignal: AbortSignal,
+    shouldUseNodePty: boolean,
+    shellExecutionConfig: ShellExecutionConfig,
+  ): Promise<ShellExecutionHandle> {
+    const mock = this.mockCommands.find((m) =>
+      typeof m.command === 'string'
+        ? m.command === commandToExecute
+        : m.command.test(commandToExecute),
+    );
+
+    const pid = Math.floor(Math.random() * 10000);
+
+    if (mock) {
+      if (mock.events) {
+        for (const event of mock.events) {
+          onOutputEvent(event);
+        }
+      }
+
+      const result: ShellExecutionResult = {
+        rawOutput: Buffer.from(mock.result.output || ''),
+        output: mock.result.output || '',
+        exitCode: mock.result.exitCode ?? 0,
+        signal: mock.result.signal ?? null,
+        error: mock.result.error ?? null,
+        aborted: false,
+        pid,
+        executionMethod: 'none',
+        ...mock.result,
+      };
+
+      return {
+        pid,
+        result: Promise.resolve(result),
+      };
+    }
+
+    if (this.passthroughEnabled && this.originalExecute) {
+      return this.originalExecute(
+        commandToExecute,
+        cwd,
+        onOutputEvent,
+        abortSignal,
+        shouldUseNodePty,
+        shellExecutionConfig,
+      );
+    }
+
+    return {
+      pid,
+      result: Promise.resolve({
+        rawOutput: Buffer.from(''),
+        output: `Command not found: ${commandToExecute}`,
+        exitCode: 127,
+        signal: null,
+        error: null,
+        aborted: false,
+        pid,
+        executionMethod: 'none',
+      }),
+    };
+  }
+
+  static writeToPty = vi.fn();
+  static isPtyActive = vi.fn(() => false);
+  static onExit = vi.fn(() => () => {});
+  static kill = vi.fn();
+  static background = vi.fn();
+  static subscribe = vi.fn(() => () => {});
+  static resizePty = vi.fn();
+  static scrollPty = vi.fn();
+}

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

@@ -13,14 +13,14 @@ import { vi } from 'vitest';
 // The version of waitFor from vitest is still fine to use if you aren't waiting
 // for React state updates.
 export async function waitFor(
-  assertion: () => void,
+  assertion: () => void | Promise<void>,
   { timeout = 2000, interval = 50 } = {},
 ): Promise<void> {
   const startTime = Date.now();
 
   while (true) {
     try {
-      assertion();
+      await assertion();
       return;
     } catch (error) {
       if (Date.now() - startTime > timeout) {

packages/cli/src/test-utils/fixtures/simple.responses

@@ -0,0 +1 @@
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"text":"Hello! How can I help you today?"}],"role":"model"},"finishReason":"STOP"}]}]}

packages/cli/src/test-utils/fixtures/steering.responses

@@ -0,0 +1,4 @@
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"role":"model","parts":[{"text":"Starting a long task. First, I'll list the files."},{"functionCall":{"name":"list_directory","args":{"dir_path":"."}}}]},"finishReason":"STOP"}]}]}
+{"method":"generateContent","response":{"candidates":[{"content":{"role":"model","parts":[{"text":"ACK: I will focus on .txt files now."}]},"finishReason":"STOP"}]}}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"role":"model","parts":[{"text":"I see the files. Since you want me to focus on .txt files, I will read file1.txt."},{"functionCall":{"name":"read_file","args":{"file_path":"file1.txt"}}}]},"finishReason":"STOP"}]}]}
+{"method":"generateContentStream","response":[{"candidates":[{"content":{"role":"model","parts":[{"text":"I have read file1.txt. Task complete."}]},"finishReason":"STOP"}]}]}

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

@@ -5,36 +5,48 @@
  */
 
 import { describe, it, expect, vi } from 'vitest';
-import { useState, useEffect } from 'react';
+import { useState, useEffect, act } from 'react';
 import { Text } from 'ink';
 import { renderHook, render } from './render.js';
 import { waitFor } from './async.js';
 
 describe('render', () => {
-  it('should render a component', () => {
-    const { lastFrame } = render(<Text>Hello World</Text>);
-    expect(lastFrame()).toBe('Hello World');
+  it('should render a component', async () => {
+    const { lastFrame, waitUntilReady, unmount } = render(
+      <Text>Hello World</Text>,
+    );
+    await waitUntilReady();
+    expect(lastFrame()).toBe('Hello World\n');
+    unmount();
   });
 
-  it('should support rerender', () => {
-    const { lastFrame, rerender } = render(<Text>Hello</Text>);
-    expect(lastFrame()).toBe('Hello');
+  it('should support rerender', async () => {
+    const { lastFrame, rerender, waitUntilReady, unmount } = render(
+      <Text>Hello</Text>,
+    );
+    await waitUntilReady();
+    expect(lastFrame()).toBe('Hello\n');
 
-    rerender(<Text>World</Text>);
-    expect(lastFrame()).toBe('World');
+    await act(async () => {
+      rerender(<Text>World</Text>);
+    });
+    await waitUntilReady();
+    expect(lastFrame()).toBe('World\n');
+    unmount();
   });
 
-  it('should support unmount', () => {
-    const cleanup = vi.fn();
+  it('should support unmount', async () => {
+    const cleanupMock = vi.fn();
     function TestComponent() {
-      useEffect(() => cleanup, []);
+      useEffect(() => cleanupMock, []);
       return <Text>Hello</Text>;
     }
 
-    const { unmount } = render(<TestComponent />);
+    const { unmount, waitUntilReady } = render(<TestComponent />);
+    await waitUntilReady();
     unmount();
 
-    expect(cleanup).toHaveBeenCalled();
+    expect(cleanupMock).toHaveBeenCalled();
   });
 });
 
@@ -48,49 +60,74 @@ describe('renderHook', () => {
       return { count, value };
     };
 
-    const { result, rerender } = renderHook(useTestHook, {
-      initialProps: { value: 1 },
-    });
+    const { result, rerender, waitUntilReady, unmount } = renderHook(
+      useTestHook,
+      {
+        initialProps: { value: 1 },
+      },
+    );
+    await waitUntilReady();
 
     expect(result.current.value).toBe(1);
     await waitFor(() => expect(result.current.count).toBe(1));
 
     // Rerender with new props
-    rerender({ value: 2 });
+    await act(async () => {
+      rerender({ value: 2 });
+    });
+    await waitUntilReady();
     expect(result.current.value).toBe(2);
     await waitFor(() => expect(result.current.count).toBe(2));
 
     // Rerender without arguments should use previous props (value: 2)
     // This would previously crash or pass undefined if not fixed
-    rerender();
+    await act(async () => {
+      rerender();
+    });
+    await waitUntilReady();
     expect(result.current.value).toBe(2);
     // Count should not increase because value didn't change
     await waitFor(() => expect(result.current.count).toBe(2));
+    unmount();
   });
 
-  it('should handle initial render without props', () => {
+  it('should handle initial render without props', async () => {
     const useTestHook = () => {
       const [count, setCount] = useState(0);
       return { count, increment: () => setCount((c) => c + 1) };
     };
 
-    const { result, rerender } = renderHook(useTestHook);
+    const { result, rerender, waitUntilReady, unmount } =
+      renderHook(useTestHook);
+    await waitUntilReady();
 
     expect(result.current.count).toBe(0);
 
-    rerender();
+    await act(async () => {
+      rerender();
+    });
+    await waitUntilReady();
     expect(result.current.count).toBe(0);
+    unmount();
   });
 
-  it('should update props if undefined is passed explicitly', () => {
+  it('should update props if undefined is passed explicitly', async () => {
     const useTestHook = (val: string | undefined) => val;
-    const { result, rerender } = renderHook(useTestHook, {
-      initialProps: 'initial',
-    });
+    const { result, rerender, waitUntilReady, unmount } = renderHook(
+      useTestHook,
+      {
+        initialProps: 'initial' as string | undefined,
+      },
+    );
+    await waitUntilReady();
 
     expect(result.current).toBe('initial');
 
-    rerender(undefined);
+    await act(async () => {
+      rerender(undefined);
+    });
+    await waitUntilReady();
     expect(result.current).toBeUndefined();
+    unmount();
   });
 });

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

@@ -4,10 +4,13 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-import { render as inkRender } from 'ink-testing-library';
+import { render as inkRenderDirect, type Instance as InkInstance } from 'ink';
+import { EventEmitter } from 'node:events';
 import { Box } from 'ink';
 import type React from 'react';
+import { Terminal } from '@xterm/headless';
 import { vi } from 'vitest';
+import stripAnsi from 'strip-ansi';
 import { act, useState } from 'react';
 import os from 'node:os';
 import { LoadedSettings } from '../config/settings.js';
@@ -33,12 +36,22 @@ import { makeFakeConfig, type Config } from '@google/gemini-cli-core';
 import { FakePersistentState } from './persistentStateFake.js';
 import { AppContext, type AppState } from '../ui/contexts/AppContext.js';
 import { createMockSettings } from './settings.js';
+import { SessionStatsProvider } from '../ui/contexts/SessionContext.js';
 import { themeManager, DEFAULT_THEME } from '../ui/themes/theme-manager.js';
 import { DefaultLight } from '../ui/themes/default-light.js';
 import { pickDefaultThemeName } from '../ui/themes/theme.js';
 
 export const persistentStateMock = new FakePersistentState();
 
+if (process.env['NODE_ENV'] === 'test') {
+  // We mock NODE_ENV to development during tests that use render.tsx
+  // so that animations (which check process.env.NODE_ENV !== 'test')
+  // are actually tested. We mutate process.env directly here because
+  // vi.stubEnv() is cleared by vi.unstubAllEnvs() in test-setup.ts
+  // after each test.
+  process.env['NODE_ENV'] = 'development';
+}
+
 vi.mock('../utils/persistentState.js', () => ({
   persistentState: persistentStateMock,
 }));
@@ -49,51 +62,356 @@ vi.mock('../ui/utils/terminalUtils.js', () => ({
   isITerm2: vi.fn(() => false),
 }));
 
-// Wrapper around ink-testing-library's render that ensures act() is called
+type TerminalState = {
+  terminal: Terminal;
+  cols: number;
+  rows: number;
+};
+
+class XtermStdout extends EventEmitter {
+  private state: TerminalState;
+  private pendingWrites = 0;
+  private renderCount = 0;
+  private queue: { promise: Promise<void> };
+  isTTY = true;
+
+  private lastRenderOutput: string | undefined = undefined;
+  private lastRenderStaticContent: string | undefined = undefined;
+
+  constructor(state: TerminalState, queue: { promise: Promise<void> }) {
+    super();
+    this.state = state;
+    this.queue = queue;
+  }
+
+  get columns() {
+    return this.state.terminal.cols;
+  }
+
+  get rows() {
+    return this.state.terminal.rows;
+  }
+
+  get frames(): string[] {
+    return [];
+  }
+
+  write = (data: string) => {
+    this.pendingWrites++;
+    this.queue.promise = this.queue.promise.then(async () => {
+      await new Promise<void>((resolve) =>
+        this.state.terminal.write(data, resolve),
+      );
+      this.pendingWrites--;
+    });
+  };
+
+  clear = () => {
+    this.state.terminal.reset();
+    this.lastRenderOutput = undefined;
+    this.lastRenderStaticContent = undefined;
+  };
+
+  dispose = () => {
+    this.state.terminal.dispose();
+  };
+
+  onRender = (staticContent: string, output: string) => {
+    this.renderCount++;
+    this.lastRenderStaticContent = staticContent;
+    this.lastRenderOutput = output;
+    this.emit('render');
+  };
+
+  lastFrame = (options: { allowEmpty?: boolean } = {}) => {
+    let result: string;
+    // On Windows, xterm.js headless can sometimes have timing or rendering issues
+    // that lead to duplicated content or incorrect buffer state in tests.
+    // As a fallback, we can trust the raw output Ink provided during onRender.
+    if (os.platform() === 'win32') {
+      result =
+        (this.lastRenderStaticContent ?? '') + (this.lastRenderOutput ?? '');
+    } else {
+      const buffer = this.state.terminal.buffer.active;
+      const allLines: string[] = [];
+      for (let i = 0; i < buffer.length; i++) {
+        allLines.push(buffer.getLine(i)?.translateToString(true) ?? '');
+      }
+
+      const trimmed = [...allLines];
+      while (trimmed.length > 0 && trimmed[trimmed.length - 1] === '') {
+        trimmed.pop();
+      }
+      result = trimmed.join('\n');
+    }
+
+    // Normalize for cross-platform snapshot stability:
+    // Normalize any \r\n to \n
+    const normalized = result.replace(/\r\n/g, '\n');
+
+    if (normalized === '' && !options.allowEmpty) {
+      throw new Error(
+        'lastFrame() returned an empty string. If this is intentional, use lastFrame({ allowEmpty: true }). ' +
+          'Otherwise, ensure you are calling await waitUntilReady() and that the component is rendering correctly.',
+      );
+    }
+    return normalized === '' ? normalized : normalized + '\n';
+  };
+
+  async waitUntilReady() {
+    const startRenderCount = this.renderCount;
+    if (!vi.isFakeTimers()) {
+      // Give Ink a chance to start its rendering loop
+      await new Promise((resolve) => setImmediate(resolve));
+    }
+    await act(async () => {
+      if (vi.isFakeTimers()) {
+        await vi.advanceTimersByTimeAsync(50);
+      } else {
+        // Wait for at least one render to be called if we haven't rendered yet or since start of this call,
+        // but don't wait forever as some renders might be synchronous or skipped.
+        if (this.renderCount === startRenderCount) {
+          const renderPromise = new Promise((resolve) =>
+            this.once('render', resolve),
+          );
+          const timeoutPromise = new Promise((resolve) =>
+            setTimeout(resolve, 50),
+          );
+          await Promise.race([renderPromise, timeoutPromise]);
+        }
+      }
+    });
+
+    let attempts = 0;
+    const maxAttempts = 50;
+
+    let lastCurrent = '';
+    let lastExpected = '';
+
+    while (attempts < maxAttempts) {
+      // Ensure all pending writes to the terminal are processed.
+      await this.queue.promise;
+
+      const currentFrame = stripAnsi(
+        this.lastFrame({ allowEmpty: true }),
+      ).trim();
+      const expectedFrame = stripAnsi(
+        (this.lastRenderStaticContent ?? '') + (this.lastRenderOutput ?? ''),
+      )
+        .trim()
+        .replace(/\r\n/g, '\n');
+
+      lastCurrent = currentFrame;
+      lastExpected = expectedFrame;
+
+      const isMatch = () => {
+        if (expectedFrame === '...') {
+          return currentFrame !== '';
+        }
+
+        // If both are empty, it's a match.
+        // We consider undefined lastRenderOutput as effectively empty for this check
+        // to support hook testing where Ink may skip rendering completely.
+        if (
+          (this.lastRenderOutput === undefined || expectedFrame === '') &&
+          currentFrame === ''
+        ) {
+          return true;
+        }
+
+        if (this.lastRenderOutput === undefined) {
+          return false;
+        }
+
+        // If Ink expects nothing but terminal has content, or vice-versa, it's NOT a match.
+        if (expectedFrame === '' || currentFrame === '') {
+          return false;
+        }
+
+        // Check if the current frame contains the expected content.
+        // We use includes because xterm might have some formatting or
+        // extra whitespace that Ink doesn't account for in its raw output metrics.
+        return currentFrame.includes(expectedFrame);
+      };
+
+      if (this.pendingWrites === 0 && isMatch()) {
+        return;
+      }
+
+      attempts++;
+      await act(async () => {
+        if (vi.isFakeTimers()) {
+          await vi.advanceTimersByTimeAsync(10);
+        } else {
+          await new Promise((resolve) => setTimeout(resolve, 10));
+        }
+      });
+    }
+
+    throw new Error(
+      `waitUntilReady() timed out after ${maxAttempts} attempts.\n` +
+        `Expected content (stripped ANSI):\n"${lastExpected}"\n` +
+        `Actual content (stripped ANSI):\n"${lastCurrent}"\n` +
+        `Pending writes: ${this.pendingWrites}\n` +
+        `Render count: ${this.renderCount}`,
+    );
+  }
+}
+
+class XtermStderr extends EventEmitter {
+  private state: TerminalState;
+  private pendingWrites = 0;
+  private queue: { promise: Promise<void> };
+  isTTY = true;
+
+  constructor(state: TerminalState, queue: { promise: Promise<void> }) {
+    super();
+    this.state = state;
+    this.queue = queue;
+  }
+
+  write = (data: string) => {
+    this.pendingWrites++;
+    this.queue.promise = this.queue.promise.then(async () => {
+      await new Promise<void>((resolve) =>
+        this.state.terminal.write(data, resolve),
+      );
+      this.pendingWrites--;
+    });
+  };
+
+  dispose = () => {
+    this.state.terminal.dispose();
+  };
+
+  lastFrame = () => '';
+}
+
+class XtermStdin extends EventEmitter {
+  isTTY = true;
+  data: string | null = null;
+  constructor(options: { isTTY?: boolean } = {}) {
+    super();
+    this.isTTY = options.isTTY ?? true;
+  }
+
+  write = (data: string) => {
+    this.data = data;
+    this.emit('readable');
+    this.emit('data', data);
+  };
+
+  setEncoding() {}
+  setRawMode() {}
+  resume() {}
+  pause() {}
+  ref() {}
+  unref() {}
+
+  read = () => {
+    const { data } = this;
+    this.data = null;
+    return data;
+  };
+}
+
+export type RenderInstance = {
+  rerender: (tree: React.ReactElement) => void;
+  unmount: () => void;
+  cleanup: () => void;
+  stdout: XtermStdout;
+  stderr: XtermStderr;
+  stdin: XtermStdin;
+  frames: string[];
+  lastFrame: (options?: { allowEmpty?: boolean }) => string;
+  terminal: Terminal;
+  waitUntilReady: () => Promise<void>;
+};
+
+const instances: InkInstance[] = [];
+
+// Wrapper around ink's render that ensures act() is called and uses Xterm for output
 export const render = (
   tree: React.ReactElement,
   terminalWidth?: number,
-): ReturnType<typeof inkRender> => {
-  let renderResult: ReturnType<typeof inkRender> =
-    // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
-    undefined as unknown as ReturnType<typeof inkRender>;
-  act(() => {
-    renderResult = inkRender(tree);
+): RenderInstance => {
+  const cols = terminalWidth ?? 100;
+  const rows = 40;
+  const terminal = new Terminal({
+    cols,
+    rows,
+    allowProposedApi: true,
+    convertEol: true,
   });
 
-  if (terminalWidth !== undefined && renderResult?.stdout) {
-    // Override the columns getter on the stdout instance provided by ink-testing-library
-    Object.defineProperty(renderResult.stdout, 'columns', {
-      get: () => terminalWidth,
-      configurable: true,
-    });
+  const state: TerminalState = {
+    terminal,
+    cols,
+    rows,
+  };
+  const writeQueue = { promise: Promise.resolve() };
+  const stdout = new XtermStdout(state, writeQueue);
+  const stderr = new XtermStderr(state, writeQueue);
+  const stdin = new XtermStdin();
 
-    // Trigger a rerender so Ink can pick up the new terminal width
-    act(() => {
-      renderResult.rerender(tree);
+  let instance!: InkInstance;
+  stdout.clear();
+  act(() => {
+    instance = inkRenderDirect(tree, {
+      // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
+      stdout: stdout as unknown as NodeJS.WriteStream,
+      // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
+      stderr: stderr as unknown as NodeJS.WriteStream,
+      // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
+      stdin: stdin as unknown as NodeJS.ReadStream,
+      debug: false,
+      exitOnCtrlC: false,
+      patchConsole: false,
+      onRender: (metrics: { output: string; staticOutput?: string }) => {
+        stdout.onRender(metrics.staticOutput ?? '', metrics.output);
+      },
     });
-  }
+  });
 
-  const originalUnmount = renderResult.unmount;
-  const originalRerender = renderResult.rerender;
+  instances.push(instance);
 
   return {
-    ...renderResult,
-    unmount: () => {
-      act(() => {
-        originalUnmount();
-      });
-    },
     rerender: (newTree: React.ReactElement) => {
       act(() => {
-        originalRerender(newTree);
+        stdout.clear();
+        instance.rerender(newTree);
       });
     },
+    unmount: () => {
+      act(() => {
+        instance.unmount();
+      });
+      stdout.dispose();
+      stderr.dispose();
+    },
+    cleanup: instance.cleanup,
+    stdout,
+    stderr,
+    stdin,
+    frames: stdout.frames,
+    lastFrame: stdout.lastFrame,
+    terminal: state.terminal,
+    waitUntilReady: () => stdout.waitUntilReady(),
   };
 };
 
+export const cleanup = () => {
+  for (const instance of instances) {
+    act(() => {
+      instance.unmount();
+    });
+    instance.cleanup();
+  }
+  instances.length = 0;
+};
+
 export const simulateClick = async (
-  stdin: ReturnType<typeof inkRender>['stdin'],
+  stdin: XtermStdin,
   col: number,
   row: number,
   button: 0 | 1 | 2 = 0, // 0 for left, 1 for middle, 2 for right
@@ -150,11 +468,12 @@ export const mockSettings = new LoadedSettings(
 const baseMockUiState = {
   renderMarkdown: true,
   streamingState: StreamingState.Idle,
-  terminalWidth: 120,
+  terminalWidth: 100,
   terminalHeight: 40,
   currentModel: 'gemini-pro',
   terminalBackgroundColor: 'black',
   cleanUiDetailsVisible: false,
+  allowPlanMode: true,
   activePtyId: undefined,
   backgroundShells: new Map(),
   backgroundShellHeight: 0,
@@ -164,6 +483,8 @@ const baseMockUiState = {
     proQuotaRequest: null,
     validationRequest: null,
   },
+  hintMode: false,
+  hintBuffer: '',
 };
 
 export const mockAppState: AppState = {
@@ -217,6 +538,10 @@ const mockUIActions: UIActions = {
   setActiveBackgroundShellPid: vi.fn(),
   setIsBackgroundShellListOpen: vi.fn(),
   setAuthContext: vi.fn(),
+  onHintInput: vi.fn(),
+  onHintBackspace: vi.fn(),
+  onHintClear: vi.fn(),
+  onHintSubmit: vi.fn(),
   handleRestart: vi.fn(),
   handleNewAgentsSelect: vi.fn(),
 };
@@ -250,7 +575,13 @@ export const renderWithProviders = (
     };
     appState?: AppState;
   } = {},
-): ReturnType<typeof render> & { simulateClick: typeof simulateClick } => {
+): RenderInstance & {
+  simulateClick: (
+    col: number,
+    row: number,
+    button?: 0 | 1 | 2,
+  ) => Promise<void>;
+} => {
   // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
   const baseState: UIState = new Proxy(
     { ...baseMockUiState, ...providedUiState },
@@ -323,39 +654,43 @@ export const renderWithProviders = (
           <UIStateContext.Provider value={finalUiState}>
             <VimModeProvider settings={finalSettings}>
               <ShellFocusContext.Provider value={shellFocus}>
-                <StreamingContext.Provider value={finalUiState.streamingState}>
-                  <UIActionsContext.Provider value={finalUIActions}>
-                    <ToolActionsProvider
-                      config={config}
-                      toolCalls={allToolCalls}
-                    >
-                      <AskUserActionsProvider
-                        request={null}
-                        onSubmit={vi.fn()}
-                        onCancel={vi.fn()}
+                <SessionStatsProvider>
+                  <StreamingContext.Provider
+                    value={finalUiState.streamingState}
+                  >
+                    <UIActionsContext.Provider value={finalUIActions}>
+                      <ToolActionsProvider
+                        config={config}
+                        toolCalls={allToolCalls}
                       >
-                        <KeypressProvider>
-                          <MouseProvider
-                            mouseEventsEnabled={mouseEventsEnabled}
-                          >
-                            <TerminalProvider>
-                              <ScrollProvider>
-                                <Box
-                                  width={terminalWidth}
-                                  flexShrink={0}
-                                  flexGrow={0}
-                                  flexDirection="column"
-                                >
-                                  {component}
-                                </Box>
-                              </ScrollProvider>
-                            </TerminalProvider>
-                          </MouseProvider>
-                        </KeypressProvider>
-                      </AskUserActionsProvider>
-                    </ToolActionsProvider>
-                  </UIActionsContext.Provider>
-                </StreamingContext.Provider>
+                        <AskUserActionsProvider
+                          request={null}
+                          onSubmit={vi.fn()}
+                          onCancel={vi.fn()}
+                        >
+                          <KeypressProvider>
+                            <MouseProvider
+                              mouseEventsEnabled={mouseEventsEnabled}
+                            >
+                              <TerminalProvider>
+                                <ScrollProvider>
+                                  <Box
+                                    width={terminalWidth}
+                                    flexShrink={0}
+                                    flexGrow={0}
+                                    flexDirection="column"
+                                  >
+                                    {component}
+                                  </Box>
+                                </ScrollProvider>
+                              </TerminalProvider>
+                            </MouseProvider>
+                          </KeypressProvider>
+                        </AskUserActionsProvider>
+                      </ToolActionsProvider>
+                    </UIActionsContext.Provider>
+                  </StreamingContext.Provider>
+                </SessionStatsProvider>
               </ShellFocusContext.Provider>
             </VimModeProvider>
           </UIStateContext.Provider>
@@ -365,7 +700,11 @@ export const renderWithProviders = (
     terminalWidth,
   );
 
-  return { ...renderResult, simulateClick };
+  return {
+    ...renderResult,
+    simulateClick: (col: number, row: number, button?: 0 | 1 | 2) =>
+      simulateClick(renderResult.stdin, col, row, button),
+  };
 };
 
 export function renderHook<Result, Props>(
@@ -378,6 +717,7 @@ export function renderHook<Result, Props>(
   result: { current: Result };
   rerender: (props?: Props) => void;
   unmount: () => void;
+  waitUntilReady: () => Promise<void>;
 } {
   // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
   const result = { current: undefined as unknown as Result };
@@ -399,6 +739,7 @@ export function renderHook<Result, Props>(
 
   let inkRerender: (tree: React.ReactElement) => void = () => {};
   let unmount: () => void = () => {};
+  let waitUntilReady: () => Promise<void> = async () => {};
 
   act(() => {
     const renderResult = render(
@@ -408,6 +749,7 @@ export function renderHook<Result, Props>(
     );
     inkRerender = renderResult.rerender;
     unmount = renderResult.unmount;
+    waitUntilReady = renderResult.waitUntilReady;
   });
 
   function rerender(props?: Props) {
@@ -424,7 +766,7 @@ export function renderHook<Result, Props>(
     });
   }
 
-  return { result, rerender, unmount };
+  return { result, rerender, unmount, waitUntilReady };
 }
 
 export function renderHookWithProviders<Result, Props>(
@@ -445,6 +787,7 @@ export function renderHookWithProviders<Result, Props>(
   result: { current: Result };
   rerender: (props?: Props) => void;
   unmount: () => void;
+  waitUntilReady: () => Promise<void>;
 } {
   // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
   const result = { current: undefined as unknown as Result };
@@ -494,5 +837,6 @@ export function renderHookWithProviders<Result, Props>(
         renderResult.unmount();
       });
     },
+    waitUntilReady: () => renderResult.waitUntilReady(),
   };
 }

packages/cli/src/ui/App.test.tsx

@@ -92,32 +92,42 @@ describe('App', () => {
     backgroundShells: new Map(),
   };
 
-  it('should render main content and composer when not quitting', () => {
-    const { lastFrame } = renderWithProviders(<App />, {
-      uiState: mockUIState,
-      useAlternateBuffer: false,
-    });
+  it('should render main content and composer when not quitting', async () => {
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+      <App />,
+      {
+        uiState: mockUIState,
+        useAlternateBuffer: false,
+      },
+    );
+    await waitUntilReady();
 
     expect(lastFrame()).toContain('Tips for getting started');
     expect(lastFrame()).toContain('Notifications');
     expect(lastFrame()).toContain('Composer');
+    unmount();
   });
 
-  it('should render quitting display when quittingMessages is set', () => {
+  it('should render quitting display when quittingMessages is set', async () => {
     const quittingUIState = {
       ...mockUIState,
       quittingMessages: [{ id: 1, type: 'user', text: 'test' }],
     } as UIState;
 
-    const { lastFrame } = renderWithProviders(<App />, {
-      uiState: quittingUIState,
-      useAlternateBuffer: false,
-    });
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+      <App />,
+      {
+        uiState: quittingUIState,
+        useAlternateBuffer: false,
+      },
+    );
+    await waitUntilReady();
 
     expect(lastFrame()).toContain('Quitting...');
+    unmount();
   });
 
-  it('should render full history in alternate buffer mode when quittingMessages is set', () => {
+  it('should render full history in alternate buffer mode when quittingMessages is set', async () => {
     const quittingUIState = {
       ...mockUIState,
       quittingMessages: [{ id: 1, type: 'user', text: 'test' }],
@@ -125,28 +135,38 @@ describe('App', () => {
       pendingHistoryItems: [{ type: 'user', text: 'pending item' }],
     } as UIState;
 
-    const { lastFrame } = renderWithProviders(<App />, {
-      uiState: quittingUIState,
-      useAlternateBuffer: true,
-    });
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+      <App />,
+      {
+        uiState: quittingUIState,
+        useAlternateBuffer: true,
+      },
+    );
+    await waitUntilReady();
 
     expect(lastFrame()).toContain('HistoryItemDisplay');
     expect(lastFrame()).toContain('Quitting...');
+    unmount();
   });
 
-  it('should render dialog manager when dialogs are visible', () => {
+  it('should render dialog manager when dialogs are visible', async () => {
     const dialogUIState = {
       ...mockUIState,
       dialogsVisible: true,
     } as UIState;
 
-    const { lastFrame } = renderWithProviders(<App />, {
-      uiState: dialogUIState,
-    });
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+      <App />,
+      {
+        uiState: dialogUIState,
+      },
+    );
+    await waitUntilReady();
 
     expect(lastFrame()).toContain('Tips for getting started');
     expect(lastFrame()).toContain('Notifications');
     expect(lastFrame()).toContain('DialogManager');
+    unmount();
   });
 
   it.each([
@@ -154,47 +174,62 @@ describe('App', () => {
     { key: 'D', stateKey: 'ctrlDPressedOnce' },
   ])(
     'should show Ctrl+$key exit prompt when dialogs are visible and $stateKey is true',
-    ({ key, stateKey }) => {
+    async ({ key, stateKey }) => {
       const uiState = {
         ...mockUIState,
         dialogsVisible: true,
         [stateKey]: true,
       } as UIState;
 
-      const { lastFrame } = renderWithProviders(<App />, {
-        uiState,
-      });
+      const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+        <App />,
+        {
+          uiState,
+        },
+      );
+      await waitUntilReady();
 
       expect(lastFrame()).toContain(`Press Ctrl+${key} again to exit.`);
+      unmount();
     },
   );
 
-  it('should render ScreenReaderAppLayout when screen reader is enabled', () => {
+  it('should render ScreenReaderAppLayout when screen reader is enabled', async () => {
     (useIsScreenReaderEnabled as Mock).mockReturnValue(true);
 
-    const { lastFrame } = renderWithProviders(<App />, {
-      uiState: mockUIState,
-    });
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+      <App />,
+      {
+        uiState: mockUIState,
+      },
+    );
+    await waitUntilReady();
 
     expect(lastFrame()).toContain('Notifications');
     expect(lastFrame()).toContain('Footer');
     expect(lastFrame()).toContain('Tips for getting started');
     expect(lastFrame()).toContain('Composer');
+    unmount();
   });
 
-  it('should render DefaultAppLayout when screen reader is not enabled', () => {
+  it('should render DefaultAppLayout when screen reader is not enabled', async () => {
     (useIsScreenReaderEnabled as Mock).mockReturnValue(false);
 
-    const { lastFrame } = renderWithProviders(<App />, {
-      uiState: mockUIState,
-    });
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+      <App />,
+      {
+        uiState: mockUIState,
+      },
+    );
+    await waitUntilReady();
 
     expect(lastFrame()).toContain('Tips for getting started');
     expect(lastFrame()).toContain('Notifications');
     expect(lastFrame()).toContain('Composer');
+    unmount();
   });
 
-  it('should render ToolConfirmationQueue along with Composer when tool is confirming and experiment is on', () => {
+  it('should render ToolConfirmationQueue along with Composer when tool is confirming and experiment is on', async () => {
     (useIsScreenReaderEnabled as Mock).mockReturnValue(false);
 
     const toolCalls = [
@@ -216,52 +251,82 @@ describe('App', () => {
 
     const stateWithConfirmingTool = {
       ...mockUIState,
-      pendingHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
-      pendingGeminiHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
+      pendingHistoryItems: [
+        {
+          type: 'tool_group',
+          tools: toolCalls,
+        },
+      ],
+      pendingGeminiHistoryItems: [
+        {
+          type: 'tool_group',
+          tools: toolCalls,
+        },
+      ],
     } as UIState;
 
     const configWithExperiment = makeFakeConfig();
     vi.spyOn(configWithExperiment, 'isTrustedFolder').mockReturnValue(true);
     vi.spyOn(configWithExperiment, 'getIdeMode').mockReturnValue(false);
 
-    const { lastFrame } = renderWithProviders(<App />, {
-      uiState: stateWithConfirmingTool,
-      config: configWithExperiment,
-    });
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+      <App />,
+      {
+        uiState: stateWithConfirmingTool,
+        config: configWithExperiment,
+      },
+    );
+    await waitUntilReady();
 
     expect(lastFrame()).toContain('Tips for getting started');
     expect(lastFrame()).toContain('Notifications');
     expect(lastFrame()).toContain('Action Required'); // From ToolConfirmationQueue
     expect(lastFrame()).toContain('Composer');
     expect(lastFrame()).toMatchSnapshot();
+    unmount();
   });
 
   describe('Snapshots', () => {
-    it('renders default layout correctly', () => {
+    it('renders default layout correctly', async () => {
       (useIsScreenReaderEnabled as Mock).mockReturnValue(false);
-      const { lastFrame } = renderWithProviders(<App />, {
-        uiState: mockUIState,
-      });
+      const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+        <App />,
+        {
+          uiState: mockUIState,
+        },
+      );
+      await waitUntilReady();
       expect(lastFrame()).toMatchSnapshot();
+      unmount();
     });
 
-    it('renders screen reader layout correctly', () => {
+    it('renders screen reader layout correctly', async () => {
       (useIsScreenReaderEnabled as Mock).mockReturnValue(true);
-      const { lastFrame } = renderWithProviders(<App />, {
-        uiState: mockUIState,
-      });
+      const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+        <App />,
+        {
+          uiState: mockUIState,
+        },
+      );
+      await waitUntilReady();
       expect(lastFrame()).toMatchSnapshot();
+      unmount();
     });
 
-    it('renders with dialogs visible', () => {
+    it('renders with dialogs visible', async () => {
       const dialogUIState = {
         ...mockUIState,
         dialogsVisible: true,
       } as UIState;
-      const { lastFrame } = renderWithProviders(<App />, {
-        uiState: dialogUIState,
-      });
+      const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+        <App />,
+        {
+          uiState: dialogUIState,
+        },
+      );
+      await waitUntilReady();
       expect(lastFrame()).toMatchSnapshot();
+      unmount();
     });
   });
 });

packages/cli/src/ui/AppContainer.test.tsx

@@ -14,9 +14,8 @@ import {
   type Mock,
   type MockedObject,
 } from 'vitest';
-import { render, persistentStateMock } from '../test-utils/render.js';
+import { render, cleanup, persistentStateMock } from '../test-utils/render.js';
 import { waitFor } from '../test-utils/async.js';
-import { cleanup } from 'ink-testing-library';
 import { act, useContext, type ReactElement } from 'react';
 import { AppContainer } from './AppContainer.js';
 import { SettingsContext } from './contexts/SettingsContext.js';
@@ -49,6 +48,15 @@ const mockIdeClient = vi.hoisted(() => ({
 const mocks = vi.hoisted(() => ({
   mockStdout: { write: vi.fn() },
 }));
+const terminalNotificationsMocks = vi.hoisted(() => ({
+  notifyViaTerminal: vi.fn().mockResolvedValue(true),
+  isNotificationsEnabled: vi.fn(() => true),
+  buildRunEventNotificationContent: vi.fn((event) => ({
+    title: 'Mock Notification',
+    subtitle: 'Mock Subtitle',
+    body: JSON.stringify(event),
+  })),
+}));
 
 vi.mock('@google/gemini-cli-core', async (importOriginal) => {
   const actual =
@@ -88,6 +96,7 @@ import ansiEscapes from 'ansi-escapes';
 import { mergeSettings, type LoadedSettings } from '../config/settings.js';
 import type { InitializationResult } from '../core/initializer.js';
 import { useQuotaAndFallback } from './hooks/useQuotaAndFallback.js';
+import { StreamingState } from './types.js';
 import { UIStateContext, type UIState } from './contexts/UIStateContext.js';
 import {
   UIActionsContext,
@@ -164,6 +173,12 @@ vi.mock('./hooks/useShellInactivityStatus.js', () => ({
     inactivityStatus: 'none',
   })),
 }));
+vi.mock('../utils/terminalNotifications.js', () => ({
+  notifyViaTerminal: terminalNotificationsMocks.notifyViaTerminal,
+  isNotificationsEnabled: terminalNotificationsMocks.isNotificationsEnabled,
+  buildRunEventNotificationContent:
+    terminalNotificationsMocks.buildRunEventNotificationContent,
+}));
 vi.mock('./hooks/useTerminalTheme.js', () => ({
   useTerminalTheme: vi.fn(),
 }));
@@ -171,6 +186,7 @@ vi.mock('./hooks/useTerminalTheme.js', () => ({
 import { useHookDisplayState } from './hooks/useHookDisplayState.js';
 import { useTerminalTheme } from './hooks/useTerminalTheme.js';
 import { useShellInactivityStatus } from './hooks/useShellInactivityStatus.js';
+import { useFocus } from './hooks/useFocus.js';
 
 // Mock external utilities
 vi.mock('../utils/events.js');
@@ -279,6 +295,7 @@ describe('AppContainer State Management', () => {
   const mockedUseHookDisplayState = useHookDisplayState as Mock;
   const mockedUseTerminalTheme = useTerminalTheme as Mock;
   const mockedUseShellInactivityStatus = useShellInactivityStatus as Mock;
+  const mockedUseFocusState = useFocus as Mock;
 
   const DEFAULT_GEMINI_STREAM_MOCK = {
     streamingState: 'idle',
@@ -416,6 +433,10 @@ describe('AppContainer State Management', () => {
       shouldShowFocusHint: false,
       inactivityStatus: 'none',
     });
+    mockedUseFocusState.mockReturnValue({
+      isFocused: true,
+      hasReceivedFocusEvent: true,
+    });
 
     // Mock Config
     mockConfig = makeFakeConfig();
@@ -524,6 +545,358 @@ describe('AppContainer State Management', () => {
   });
 
   describe('State Initialization', () => {
+    it('sends a macOS notification when confirmation is pending and terminal is unfocused', async () => {
+      mockedUseFocusState.mockReturnValue({
+        isFocused: false,
+        hasReceivedFocusEvent: true,
+      });
+      mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
+        pendingHistoryItems: [
+          {
+            type: 'tool_group',
+            tools: [
+              {
+                callId: 'call-1',
+                name: 'run_shell_command',
+                description: 'Run command',
+                resultDisplay: undefined,
+                status: CoreToolCallStatus.AwaitingApproval,
+                confirmationDetails: {
+                  type: 'exec',
+                  title: 'Run shell command',
+                  command: 'ls',
+                  rootCommand: 'ls',
+                  rootCommands: ['ls'],
+                },
+              },
+            ],
+          },
+        ],
+      });
+
+      let unmount: (() => void) | undefined;
+      await act(async () => {
+        const rendered = renderAppContainer();
+        unmount = rendered.unmount;
+      });
+
+      await waitFor(() =>
+        expect(terminalNotificationsMocks.notifyViaTerminal).toHaveBeenCalled(),
+      );
+      expect(
+        terminalNotificationsMocks.buildRunEventNotificationContent,
+      ).toHaveBeenCalledWith(
+        expect.objectContaining({
+          type: 'attention',
+        }),
+      );
+
+      await act(async () => {
+        unmount?.();
+      });
+    });
+
+    it('does not send attention notification when terminal is focused', async () => {
+      mockedUseFocusState.mockReturnValue({
+        isFocused: true,
+        hasReceivedFocusEvent: true,
+      });
+      mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
+        pendingHistoryItems: [
+          {
+            type: 'tool_group',
+            tools: [
+              {
+                callId: 'call-2',
+                name: 'run_shell_command',
+                description: 'Run command',
+                resultDisplay: undefined,
+                status: CoreToolCallStatus.AwaitingApproval,
+                confirmationDetails: {
+                  type: 'exec',
+                  title: 'Run shell command',
+                  command: 'ls',
+                  rootCommand: 'ls',
+                  rootCommands: ['ls'],
+                },
+              },
+            ],
+          },
+        ],
+      });
+
+      let unmount: (() => void) | undefined;
+      await act(async () => {
+        const rendered = renderAppContainer();
+        unmount = rendered.unmount;
+      });
+
+      expect(
+        terminalNotificationsMocks.notifyViaTerminal,
+      ).not.toHaveBeenCalled();
+
+      await act(async () => {
+        unmount?.();
+      });
+    });
+
+    it('sends attention notification when focus reporting is unavailable', async () => {
+      mockedUseFocusState.mockReturnValue({
+        isFocused: true,
+        hasReceivedFocusEvent: false,
+      });
+      mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
+        pendingHistoryItems: [
+          {
+            type: 'tool_group',
+            tools: [
+              {
+                callId: 'call-focus-unknown',
+                name: 'run_shell_command',
+                description: 'Run command',
+                resultDisplay: undefined,
+                status: CoreToolCallStatus.AwaitingApproval,
+                confirmationDetails: {
+                  type: 'exec',
+                  title: 'Run shell command',
+                  command: 'ls',
+                  rootCommand: 'ls',
+                  rootCommands: ['ls'],
+                },
+              },
+            ],
+          },
+        ],
+      });
+
+      let unmount: (() => void) | undefined;
+      await act(async () => {
+        const rendered = renderAppContainer();
+        unmount = rendered.unmount;
+      });
+
+      await waitFor(() =>
+        expect(terminalNotificationsMocks.notifyViaTerminal).toHaveBeenCalled(),
+      );
+
+      await act(async () => {
+        unmount?.();
+      });
+    });
+
+    it('sends a macOS notification when a response completes while unfocused', async () => {
+      mockedUseFocusState.mockReturnValue({
+        isFocused: false,
+        hasReceivedFocusEvent: true,
+      });
+      let currentStreamingState: 'idle' | 'responding' = 'responding';
+      mockedUseGeminiStream.mockImplementation(() => ({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
+        streamingState: currentStreamingState,
+      }));
+
+      let unmount: (() => void) | undefined;
+      let rerender: ((tree: ReactElement) => void) | undefined;
+
+      await act(async () => {
+        const rendered = renderAppContainer();
+        unmount = rendered.unmount;
+        rerender = rendered.rerender;
+      });
+
+      currentStreamingState = 'idle';
+      await act(async () => {
+        rerender?.(getAppContainer());
+      });
+
+      await waitFor(() =>
+        expect(
+          terminalNotificationsMocks.buildRunEventNotificationContent,
+        ).toHaveBeenCalledWith(
+          expect.objectContaining({
+            type: 'session_complete',
+            detail: 'Gemini CLI finished responding.',
+          }),
+        ),
+      );
+      expect(terminalNotificationsMocks.notifyViaTerminal).toHaveBeenCalled();
+
+      await act(async () => {
+        unmount?.();
+      });
+    });
+
+    it('sends completion notification when focus reporting is unavailable', async () => {
+      mockedUseFocusState.mockReturnValue({
+        isFocused: true,
+        hasReceivedFocusEvent: false,
+      });
+      let currentStreamingState: 'idle' | 'responding' = 'responding';
+      mockedUseGeminiStream.mockImplementation(() => ({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
+        streamingState: currentStreamingState,
+      }));
+
+      let unmount: (() => void) | undefined;
+      let rerender: ((tree: ReactElement) => void) | undefined;
+
+      await act(async () => {
+        const rendered = renderAppContainer();
+        unmount = rendered.unmount;
+        rerender = rendered.rerender;
+      });
+
+      currentStreamingState = 'idle';
+      await act(async () => {
+        rerender?.(getAppContainer());
+      });
+
+      await waitFor(() =>
+        expect(
+          terminalNotificationsMocks.buildRunEventNotificationContent,
+        ).toHaveBeenCalledWith(
+          expect.objectContaining({
+            type: 'session_complete',
+            detail: 'Gemini CLI finished responding.',
+          }),
+        ),
+      );
+
+      await act(async () => {
+        unmount?.();
+      });
+    });
+
+    it('does not send completion notification when another action-required dialog is pending', async () => {
+      mockedUseFocusState.mockReturnValue({
+        isFocused: false,
+        hasReceivedFocusEvent: true,
+      });
+      mockedUseQuotaAndFallback.mockReturnValue({
+        proQuotaRequest: { kind: 'upgrade' },
+        handleProQuotaChoice: vi.fn(),
+      });
+      let currentStreamingState: 'idle' | 'responding' = 'responding';
+      mockedUseGeminiStream.mockImplementation(() => ({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
+        streamingState: currentStreamingState,
+      }));
+
+      let unmount: (() => void) | undefined;
+      let rerender: ((tree: ReactElement) => void) | undefined;
+
+      await act(async () => {
+        const rendered = renderAppContainer();
+        unmount = rendered.unmount;
+        rerender = rendered.rerender;
+      });
+
+      currentStreamingState = 'idle';
+      await act(async () => {
+        rerender?.(getAppContainer());
+      });
+
+      expect(
+        terminalNotificationsMocks.notifyViaTerminal,
+      ).not.toHaveBeenCalled();
+
+      await act(async () => {
+        unmount?.();
+      });
+    });
+
+    it('can send repeated attention notifications for the same key after pending state clears', async () => {
+      mockedUseFocusState.mockReturnValue({
+        isFocused: false,
+        hasReceivedFocusEvent: true,
+      });
+
+      let pendingHistoryItems = [
+        {
+          type: 'tool_group',
+          tools: [
+            {
+              callId: 'repeat-key-call',
+              name: 'run_shell_command',
+              description: 'Run command',
+              resultDisplay: undefined,
+              status: CoreToolCallStatus.AwaitingApproval,
+              confirmationDetails: {
+                type: 'exec',
+                title: 'Run shell command',
+                command: 'ls',
+                rootCommand: 'ls',
+                rootCommands: ['ls'],
+              },
+            },
+          ],
+        },
+      ];
+
+      mockedUseGeminiStream.mockImplementation(() => ({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
+        pendingHistoryItems,
+      }));
+
+      let unmount: (() => void) | undefined;
+      let rerender: ((tree: ReactElement) => void) | undefined;
+
+      await act(async () => {
+        const rendered = renderAppContainer();
+        unmount = rendered.unmount;
+        rerender = rendered.rerender;
+      });
+
+      await waitFor(() =>
+        expect(
+          terminalNotificationsMocks.notifyViaTerminal,
+        ).toHaveBeenCalledTimes(1),
+      );
+
+      pendingHistoryItems = [];
+      await act(async () => {
+        rerender?.(getAppContainer());
+      });
+
+      pendingHistoryItems = [
+        {
+          type: 'tool_group',
+          tools: [
+            {
+              callId: 'repeat-key-call',
+              name: 'run_shell_command',
+              description: 'Run command',
+              resultDisplay: undefined,
+              status: CoreToolCallStatus.AwaitingApproval,
+              confirmationDetails: {
+                type: 'exec',
+                title: 'Run shell command',
+                command: 'ls',
+                rootCommand: 'ls',
+                rootCommands: ['ls'],
+              },
+            },
+          ],
+        },
+      ];
+      await act(async () => {
+        rerender?.(getAppContainer());
+      });
+
+      await waitFor(() =>
+        expect(
+          terminalNotificationsMocks.notifyViaTerminal,
+        ).toHaveBeenCalledTimes(2),
+      );
+
+      await act(async () => {
+        unmount?.();
+      });
+    });
+
     it('initializes with theme error from initialization result', async () => {
       const initResultWithError = {
         ...mockInitResult,
@@ -2979,4 +3352,98 @@ describe('AppContainer State Management', () => {
       },
     );
   });
+
+  describe('Plan Mode Availability', () => {
+    it('should allow plan mode when enabled and idle', async () => {
+      vi.spyOn(mockConfig, 'isPlanEnabled').mockReturnValue(true);
+      mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
+        pendingHistoryItems: [],
+      });
+
+      let unmount: () => void;
+      await act(async () => {
+        const result = renderAppContainer();
+        unmount = result.unmount;
+      });
+
+      await waitFor(() => {
+        expect(capturedUIState).toBeTruthy();
+        expect(capturedUIState.allowPlanMode).toBe(true);
+      });
+      unmount!();
+    });
+
+    it('should NOT allow plan mode when disabled in config', async () => {
+      vi.spyOn(mockConfig, 'isPlanEnabled').mockReturnValue(false);
+      mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
+        pendingHistoryItems: [],
+      });
+
+      let unmount: () => void;
+      await act(async () => {
+        const result = renderAppContainer();
+        unmount = result.unmount;
+      });
+
+      await waitFor(() => {
+        expect(capturedUIState).toBeTruthy();
+        expect(capturedUIState.allowPlanMode).toBe(false);
+      });
+      unmount!();
+    });
+
+    it('should NOT allow plan mode when streaming', async () => {
+      vi.spyOn(mockConfig, 'isPlanEnabled').mockReturnValue(true);
+      mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
+        streamingState: StreamingState.Responding,
+        pendingHistoryItems: [],
+      });
+
+      let unmount: () => void;
+      await act(async () => {
+        const result = renderAppContainer();
+        unmount = result.unmount;
+      });
+
+      await waitFor(() => {
+        expect(capturedUIState).toBeTruthy();
+        expect(capturedUIState.allowPlanMode).toBe(false);
+      });
+      unmount!();
+    });
+
+    it('should NOT allow plan mode when a tool is awaiting confirmation', async () => {
+      vi.spyOn(mockConfig, 'isPlanEnabled').mockReturnValue(true);
+      mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
+        streamingState: StreamingState.Idle,
+        pendingHistoryItems: [
+          {
+            type: 'tool_group',
+            tools: [
+              {
+                name: 'test_tool',
+                status: CoreToolCallStatus.AwaitingApproval,
+              },
+            ],
+          },
+        ],
+      });
+
+      let unmount: () => void;
+      await act(async () => {
+        const result = renderAppContainer();
+        unmount = result.unmount;
+      });
+
+      await waitFor(() => {
+        expect(capturedUIState).toBeTruthy();
+        expect(capturedUIState.allowPlanMode).toBe(false);
+      });
+      unmount!();
+    });
+  });
 });

packages/cli/src/ui/AppContainer.tsx

@@ -79,6 +79,8 @@ import {
   type AgentsDiscoveredPayload,
   ChangeAuthRequestedError,
   CoreToolCallStatus,
+  generateSteeringAckMessage,
+  buildUserSteeringHintPrompt,
 } from '@google/gemini-cli-core';
 import { validateAuthMethod } from '../config/auth.js';
 import process from 'node:process';
@@ -156,6 +158,8 @@ import { useTerminalTheme } from './hooks/useTerminalTheme.js';
 import { useTimedMessage } from './hooks/useTimedMessage.js';
 import { shouldDismissShortcutsHelpOnHotkey } from './utils/shortcutsHelp.js';
 import { useSuspend } from './hooks/useSuspend.js';
+import { useRunEventNotifications } from './hooks/useRunEventNotifications.js';
+import { isNotificationsEnabled } from '../utils/terminalNotifications.js';
 
 function isToolExecuting(pendingHistoryItems: HistoryItemWithoutId[]) {
   return pendingHistoryItems.some((item) => {
@@ -209,6 +213,7 @@ const SHELL_HEIGHT_PADDING = 10;
 export const AppContainer = (props: AppContainerProps) => {
   const { config, initializationResult, resumedSessionData } = props;
   const settings = useSettings();
+  const notificationsEnabled = isNotificationsEnabled(settings);
 
   const historyManager = useHistory({
     chatRecordingService: config.getGeminiClient()?.getChatRecordingService(),
@@ -694,6 +699,7 @@ export const AppContainer = (props: AppContainerProps) => {
         settings.setValue(scope, 'security.auth.selectedType', authType);
 
         try {
+          config.setRemoteAdminSettings(undefined);
           await config.refreshAuth(authType);
           setAuthState(AuthState.Authenticated);
         } catch (e) {
@@ -993,6 +999,30 @@ Logging in with Google... Restarting Gemini CLI to continue.
     }
   }, [pendingRestorePrompt, inputHistory, historyManager.history]);
 
+  const pendingHintsRef = useRef<string[]>([]);
+  const [pendingHintCount, setPendingHintCount] = useState(0);
+
+  const consumePendingHints = useCallback(() => {
+    if (pendingHintsRef.current.length === 0) {
+      return null;
+    }
+    const hint = pendingHintsRef.current.join('\n');
+    pendingHintsRef.current = [];
+    setPendingHintCount(0);
+    return hint;
+  }, []);
+
+  useEffect(() => {
+    const hintListener = (hint: string) => {
+      pendingHintsRef.current.push(hint);
+      setPendingHintCount((prev) => prev + 1);
+    };
+    config.userHintService.onUserHint(hintListener);
+    return () => {
+      config.userHintService.offUserHint(hintListener);
+    };
+  }, [config]);
+
   const {
     streamingState,
     submitQuery,
@@ -1031,6 +1061,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
     terminalWidth,
     terminalHeight,
     embeddedShellFocused,
+    consumePendingHints,
   );
 
   toggleBackgroundShellRef.current = toggleBackgroundShell;
@@ -1087,14 +1118,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
     ],
   );
 
-  // Auto-accept indicator
-  const showApprovalModeIndicator = useApprovalModeIndicator({
-    config,
-    addItem: historyManager.addItem,
-    onApprovalModeChange: handleApprovalModeChangeWithUiReveal,
-    isActive: !embeddedShellFocused,
-  });
-
   const { isMcpReady } = useMcpStatus(config);
 
   const {
@@ -1147,10 +1170,38 @@ Logging in with Google... Restarting Gemini CLI to continue.
     ],
   );
 
+  const handleHintSubmit = useCallback(
+    (hint: string) => {
+      const trimmed = hint.trim();
+      if (!trimmed) {
+        return;
+      }
+      config.userHintService.addUserHint(trimmed);
+      // Render hints with a distinct style.
+      historyManager.addItem({
+        type: 'hint',
+        text: trimmed,
+      });
+    },
+    [config, historyManager],
+  );
+
   const handleFinalSubmit = useCallback(
     async (submittedValue: string) => {
       const isSlash = isSlashCommand(submittedValue.trim());
       const isIdle = streamingState === StreamingState.Idle;
+      const isAgentRunning =
+        streamingState === StreamingState.Responding ||
+        isToolExecuting([
+          ...pendingSlashCommandHistoryItems,
+          ...pendingGeminiHistoryItems,
+        ]);
+
+      if (config.isModelSteeringEnabled() && isAgentRunning && !isSlash) {
+        handleHintSubmit(submittedValue);
+        addInput(submittedValue);
+        return;
+      }
 
       if (isSlash || (isIdle && isMcpReady)) {
         if (!isSlash) {
@@ -1192,7 +1243,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
       isMcpReady,
       streamingState,
       messageQueue.length,
+      pendingSlashCommandHistoryItems,
+      pendingGeminiHistoryItems,
       config,
+      handleHintSubmit,
     ],
   );
 
@@ -1255,7 +1309,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
     sanitizationConfig: config.sanitizationConfig,
   });
 
-  const isFocused = useFocus();
+  const { isFocused, hasReceivedFocusEvent } = useFocus();
 
   // Context file names computation
   const contextFileNames = useMemo(() => {
@@ -1887,16 +1941,48 @@ Logging in with Google... Restarting Gemini CLI to continue.
     [pendingHistoryItems],
   );
 
+  const hasConfirmUpdateExtensionRequests =
+    confirmUpdateExtensionRequests.length > 0;
+  const hasLoopDetectionConfirmationRequest =
+    !!loopDetectionConfirmationRequest;
+
   const hasPendingActionRequired =
     hasPendingToolConfirmation ||
     !!commandConfirmationRequest ||
     !!authConsentRequest ||
-    confirmUpdateExtensionRequests.length > 0 ||
-    !!loopDetectionConfirmationRequest ||
+    hasConfirmUpdateExtensionRequests ||
+    hasLoopDetectionConfirmationRequest ||
     !!proQuotaRequest ||
     !!validationRequest ||
     !!customDialog;
 
+  const allowPlanMode =
+    config.isPlanEnabled() &&
+    streamingState === StreamingState.Idle &&
+    !hasPendingActionRequired;
+
+  const showApprovalModeIndicator = useApprovalModeIndicator({
+    config,
+    addItem: historyManager.addItem,
+    onApprovalModeChange: handleApprovalModeChangeWithUiReveal,
+    isActive: !embeddedShellFocused,
+    allowPlanMode,
+  });
+
+  useRunEventNotifications({
+    notificationsEnabled,
+    isFocused,
+    hasReceivedFocusEvent,
+    streamingState,
+    hasPendingActionRequired,
+    pendingHistoryItems,
+    commandConfirmationRequest,
+    authConsentRequest,
+    permissionConfirmationRequest,
+    hasConfirmUpdateExtensionRequests,
+    hasLoopDetectionConfirmationRequest,
+  });
+
   const isPassiveShortcutsHelpState =
     isInputActive &&
     streamingState === StreamingState.Idle &&
@@ -1912,6 +1998,44 @@ Logging in with Google... Restarting Gemini CLI to continue.
     setShortcutsHelpVisible,
   ]);
 
+  useEffect(() => {
+    if (
+      !isConfigInitialized ||
+      !config.isModelSteeringEnabled() ||
+      streamingState !== StreamingState.Idle ||
+      !isMcpReady ||
+      isToolAwaitingConfirmation(pendingHistoryItems)
+    ) {
+      return;
+    }
+
+    const pendingHint = consumePendingHints();
+    if (!pendingHint) {
+      return;
+    }
+
+    void generateSteeringAckMessage(
+      config.getBaseLlmClient(),
+      pendingHint,
+    ).then((ackText) => {
+      historyManager.addItem({
+        type: 'info',
+        text: ackText,
+      });
+    });
+    void submitQuery([{ text: buildUserSteeringHintPrompt(pendingHint) }]);
+  }, [
+    config,
+    historyManager,
+    isConfigInitialized,
+    isMcpReady,
+    streamingState,
+    submitQuery,
+    consumePendingHints,
+    pendingHistoryItems,
+    pendingHintCount,
+  ]);
+
   const allToolCalls = useMemo(
     () =>
       pendingHistoryItems
@@ -2031,6 +2155,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       messageQueue,
       queueErrorMessage,
       showApprovalModeIndicator,
+      allowPlanMode,
       currentModel,
       quota: {
         userTier,
@@ -2077,6 +2202,13 @@ Logging in with Google... Restarting Gemini CLI to continue.
       isBackgroundShellListOpen,
       adminSettingsChanged,
       newAgents,
+      hintMode:
+        config.isModelSteeringEnabled() &&
+        isToolExecuting([
+          ...pendingSlashCommandHistoryItems,
+          ...pendingGeminiHistoryItems,
+        ]),
+      hintBuffer: '',
     }),
     [
       isThemeDialogOpen,
@@ -2145,6 +2277,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       messageQueue,
       queueErrorMessage,
       showApprovalModeIndicator,
+      allowPlanMode,
       userTier,
       quotaStats,
       proQuotaRequest,
@@ -2247,6 +2380,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
       setActiveBackgroundShellPid,
       setIsBackgroundShellListOpen,
       setAuthContext,
+      onHintInput: () => {},
+      onHintBackspace: () => {},
+      onHintClear: () => {},
+      onHintSubmit: () => {},
       handleRestart: async () => {
         if (process.send) {
           const remoteSettings = config.getRemoteAdminSettings();

packages/cli/src/ui/IdeIntegrationNudge.test.tsx

@@ -11,8 +11,6 @@ import { IdeIntegrationNudge } from './IdeIntegrationNudge.js';
 import { KeypressProvider } from './contexts/KeypressContext.js';
 import { debugLogger } from '@google/gemini-cli-core';
 
-const delay = (ms: number) => new Promise((resolve) => setTimeout(resolve, ms));
-
 // Mock debugLogger
 vi.mock('@google/gemini-cli-core', async (importOriginal) => {
   const actual =
@@ -56,128 +54,129 @@ describe('IdeIntegrationNudge', () => {
   });
 
   it('renders correctly with default options', async () => {
-    const { lastFrame } = render(
+    const { lastFrame, waitUntilReady, unmount } = render(
       <KeypressProvider>
         <IdeIntegrationNudge {...defaultProps} />
       </KeypressProvider>,
     );
-    await act(async () => {
-      await delay(100);
-    });
+    await waitUntilReady();
     const frame = lastFrame();
 
     expect(frame).toContain('Do you want to connect VS Code to Gemini CLI?');
     expect(frame).toContain('Yes');
     expect(frame).toContain('No (esc)');
     expect(frame).toContain("No, don't ask again");
+    unmount();
   });
 
   it('handles "Yes" selection', async () => {
     const onComplete = vi.fn();
-    const { stdin } = render(
+    const { stdin, waitUntilReady, unmount } = render(
       <KeypressProvider>
         <IdeIntegrationNudge {...defaultProps} onComplete={onComplete} />
       </KeypressProvider>,
     );
 
-    await act(async () => {
-      await delay(100);
-    });
+    await waitUntilReady();
 
     // "Yes" is the first option and selected by default usually.
     await act(async () => {
       stdin.write('\r');
-      await delay(100);
     });
+    await waitUntilReady();
 
     expect(onComplete).toHaveBeenCalledWith({
       userSelection: 'yes',
       isExtensionPreInstalled: false,
     });
+    unmount();
   });
 
   it('handles "No" selection', async () => {
     const onComplete = vi.fn();
-    const { stdin } = render(
+    const { stdin, waitUntilReady, unmount } = render(
       <KeypressProvider>
         <IdeIntegrationNudge {...defaultProps} onComplete={onComplete} />
       </KeypressProvider>,
     );
 
-    await act(async () => {
-      await delay(100);
-    });
+    await waitUntilReady();
 
     // Navigate down to "No (esc)"
     await act(async () => {
       stdin.write('\u001B[B'); // Down arrow
-      await delay(100);
     });
+    await waitUntilReady();
+
     await act(async () => {
       stdin.write('\r'); // Enter
-      await delay(100);
     });
+    await waitUntilReady();
 
     expect(onComplete).toHaveBeenCalledWith({
       userSelection: 'no',
       isExtensionPreInstalled: false,
     });
+    unmount();
   });
 
   it('handles "Dismiss" selection', async () => {
     const onComplete = vi.fn();
-    const { stdin } = render(
+    const { stdin, waitUntilReady, unmount } = render(
       <KeypressProvider>
         <IdeIntegrationNudge {...defaultProps} onComplete={onComplete} />
       </KeypressProvider>,
     );
 
-    await act(async () => {
-      await delay(100);
-    });
+    await waitUntilReady();
 
     // Navigate down to "No, don't ask again"
     await act(async () => {
       stdin.write('\u001B[B'); // Down arrow
-      await delay(100);
     });
+    await waitUntilReady();
+
     await act(async () => {
       stdin.write('\u001B[B'); // Down arrow
-      await delay(100);
     });
+    await waitUntilReady();
+
     await act(async () => {
       stdin.write('\r'); // Enter
-      await delay(100);
     });
+    await waitUntilReady();
 
     expect(onComplete).toHaveBeenCalledWith({
       userSelection: 'dismiss',
       isExtensionPreInstalled: false,
     });
+    unmount();
   });
 
   it('handles Escape key press', async () => {
     const onComplete = vi.fn();
-    const { stdin } = render(
+    const { stdin, waitUntilReady, unmount } = render(
       <KeypressProvider>
         <IdeIntegrationNudge {...defaultProps} onComplete={onComplete} />
       </KeypressProvider>,
     );
 
-    await act(async () => {
-      await delay(100);
-    });
+    await waitUntilReady();
 
     // Press Escape
     await act(async () => {
       stdin.write('\u001B');
-      await delay(100);
+    });
+    // Escape key has a timeout in KeypressContext, so we need to wrap waitUntilReady in act
+    await act(async () => {
+      await waitUntilReady();
     });
 
     expect(onComplete).toHaveBeenCalledWith({
       userSelection: 'no',
       isExtensionPreInstalled: false,
     });
+    unmount();
   });
 
   it('displays correct text and handles selection when extension is pre-installed', async () => {
@@ -185,15 +184,13 @@ describe('IdeIntegrationNudge', () => {
     vi.stubEnv('GEMINI_CLI_IDE_WORKSPACE_PATH', '/tmp');
 
     const onComplete = vi.fn();
-    const { lastFrame, stdin } = render(
+    const { lastFrame, stdin, waitUntilReady, unmount } = render(
       <KeypressProvider>
         <IdeIntegrationNudge {...defaultProps} onComplete={onComplete} />
       </KeypressProvider>,
     );
 
-    await act(async () => {
-      await delay(100);
-    });
+    await waitUntilReady();
 
     const frame = lastFrame();
 
@@ -205,12 +202,13 @@ describe('IdeIntegrationNudge', () => {
     // Select "Yes"
     await act(async () => {
       stdin.write('\r');
-      await delay(100);
     });
+    await waitUntilReady();
 
     expect(onComplete).toHaveBeenCalledWith({
       userSelection: 'yes',
       isExtensionPreInstalled: true,
     });
+    unmount();
   });
 });

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

@@ -61,7 +61,8 @@ Tips for getting started:
 2. Be specific for the best results.
 3. Create GEMINI.md files to customize your interactions with Gemini.
 4. /help for more information.
-Composer"
+Composer
+"
 `;
 
 exports[`App > Snapshots > renders with dialogs visible 1`] = `
@@ -124,19 +125,19 @@ Tips for getting started:
 3. Create GEMINI.md files to customize your interactions with Gemini.
 4. /help for more information.
 HistoryItemDisplay
-╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
-│ Action Required                                                                                                      │
-│                                                                                                                      │
-│ ?  ls list directory                                                                                                 │
-│                                                                                                                      │
-│ ls                                                                                                                   │
-│ Allow execution of: 'ls'?                                                                                            │
-│                                                                                                                      │
-│ ● 1. Allow once                                                                                                      │
-│   2. Allow for this session                                                                                          │
-│   3. No, suggest changes (esc)                                                                                       │
-│                                                                                                                      │
-╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
+╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
+│ Action Required                                                                                  │
+│                                                                                                  │
+│ ?  ls list directory                                                                             │
+│                                                                                                  │
+│ ls                                                                                               │
+│ Allow execution of: 'ls'?                                                                        │
+│                                                                                                  │
+│ ● 1. Allow once                                                                                  │
+│   2. Allow for this session                                                                      │
+│   3. No, suggest changes (esc)                                                                   │
+│                                                                                                  │
+╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
 
 
 

packages/cli/src/ui/auth/ApiAuthDialog.test.tsx

@@ -65,21 +65,24 @@ describe('ApiAuthDialog', () => {
     mockedUseTextBuffer.mockReturnValue(mockBuffer);
   });
 
-  it('renders correctly', () => {
-    const { lastFrame } = render(
+  it('renders correctly', async () => {
+    const { lastFrame, waitUntilReady, unmount } = render(
       <ApiAuthDialog onSubmit={onSubmit} onCancel={onCancel} />,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
+    unmount();
   });
 
-  it('renders with a defaultValue', () => {
-    render(
+  it('renders with a defaultValue', async () => {
+    const { waitUntilReady, unmount } = render(
       <ApiAuthDialog
         onSubmit={onSubmit}
         onCancel={onCancel}
         defaultValue="test-key"
       />,
     );
+    await waitUntilReady();
     expect(mockedUseTextBuffer).toHaveBeenCalledWith(
       expect.objectContaining({
         initialText: 'test-key',
@@ -88,6 +91,7 @@ describe('ApiAuthDialog', () => {
         }),
       }),
     );
+    unmount();
   });
 
   it.each([
@@ -100,9 +104,12 @@ describe('ApiAuthDialog', () => {
     { keyName: 'escape', sequence: '\u001b', expectedCall: onCancel, args: [] },
   ])(
     'calls $expectedCall.name when $keyName is pressed',
-    ({ keyName, sequence, expectedCall, args }) => {
+    async ({ keyName, sequence, expectedCall, args }) => {
       mockBuffer.text = 'submitted-key'; // Set for the onSubmit case
-      render(<ApiAuthDialog onSubmit={onSubmit} onCancel={onCancel} />);
+      const { waitUntilReady, unmount } = render(
+        <ApiAuthDialog onSubmit={onSubmit} onCancel={onCancel} />,
+      );
+      await waitUntilReady();
       // calls[0] is the ApiAuthDialog's useKeypress (Ctrl+C handler)
       // calls[1] is the TextInput's useKeypress (typing handler)
       const keypressHandler = mockedUseKeypress.mock.calls[1][0];
@@ -117,23 +124,29 @@ describe('ApiAuthDialog', () => {
       });
 
       expect(expectedCall).toHaveBeenCalledWith(...args);
+      unmount();
     },
   );
 
-  it('displays an error message', () => {
-    const { lastFrame } = render(
+  it('displays an error message', async () => {
+    const { lastFrame, waitUntilReady, unmount } = render(
       <ApiAuthDialog
         onSubmit={onSubmit}
         onCancel={onCancel}
         error="Invalid API Key"
       />,
     );
+    await waitUntilReady();
 
     expect(lastFrame()).toContain('Invalid API Key');
+    unmount();
   });
 
   it('calls clearApiKey and clears buffer when Ctrl+C is pressed', async () => {
-    render(<ApiAuthDialog onSubmit={onSubmit} onCancel={onCancel} />);
+    const { waitUntilReady, unmount } = render(
+      <ApiAuthDialog onSubmit={onSubmit} onCancel={onCancel} />,
+    );
+    await waitUntilReady();
     // Call 0 is ApiAuthDialog (isActive: true)
     // Call 1 is TextInput (isActive: true, priority: true)
     const keypressHandler = mockedUseKeypress.mock.calls[0][0];
@@ -149,5 +162,6 @@ describe('ApiAuthDialog', () => {
       expect(clearApiKey).toHaveBeenCalled();
       expect(mockBuffer.setText).toHaveBeenCalledWith('');
     });
+    unmount();
   });
 });

packages/cli/src/ui/auth/AuthDialog.test.tsx

@@ -139,11 +139,14 @@ describe('AuthDialog', () => {
       },
     ])(
       'correctly shows/hides COMPUTE_ADC options $desc',
-      ({ env, shouldContain, shouldNotContain }) => {
+      async ({ env, shouldContain, shouldNotContain }) => {
         for (const [key, value] of Object.entries(env)) {
           vi.stubEnv(key, value as string);
         }
-        renderWithProviders(<AuthDialog {...props} />);
+        const { waitUntilReady, unmount } = renderWithProviders(
+          <AuthDialog {...props} />,
+        );
+        await waitUntilReady();
         const items = mockedRadioButtonSelect.mock.calls[0][0].items;
         for (const item of shouldContain) {
           expect(items).toContainEqual(item);
@@ -151,23 +154,32 @@ describe('AuthDialog', () => {
         for (const item of shouldNotContain) {
           expect(items).not.toContainEqual(item);
         }
+        unmount();
       },
     );
   });
 
-  it('filters auth types when enforcedType is set', () => {
+  it('filters auth types when enforcedType is set', async () => {
     props.settings.merged.security.auth.enforcedType = AuthType.USE_GEMINI;
-    renderWithProviders(<AuthDialog {...props} />);
+    const { waitUntilReady, unmount } = renderWithProviders(
+      <AuthDialog {...props} />,
+    );
+    await waitUntilReady();
     const items = mockedRadioButtonSelect.mock.calls[0][0].items;
     expect(items).toHaveLength(1);
     expect(items[0].value).toBe(AuthType.USE_GEMINI);
+    unmount();
   });
 
-  it('sets initial index to 0 when enforcedType is set', () => {
+  it('sets initial index to 0 when enforcedType is set', async () => {
     props.settings.merged.security.auth.enforcedType = AuthType.USE_GEMINI;
-    renderWithProviders(<AuthDialog {...props} />);
+    const { waitUntilReady, unmount } = renderWithProviders(
+      <AuthDialog {...props} />,
+    );
+    await waitUntilReady();
     const { initialIndex } = mockedRadioButtonSelect.mock.calls[0][0];
     expect(initialIndex).toBe(0);
+    unmount();
   });
 
   describe('Initial Auth Type Selection', () => {
@@ -199,18 +211,25 @@ describe('AuthDialog', () => {
         expected: AuthType.LOGIN_WITH_GOOGLE,
         desc: 'defaults to Login with Google',
       },
-    ])('selects initial auth type $desc', ({ setup, expected }) => {
+    ])('selects initial auth type $desc', async ({ setup, expected }) => {
       setup();
-      renderWithProviders(<AuthDialog {...props} />);
+      const { waitUntilReady, unmount } = renderWithProviders(
+        <AuthDialog {...props} />,
+      );
+      await waitUntilReady();
       const { items, initialIndex } = mockedRadioButtonSelect.mock.calls[0][0];
       expect(items[initialIndex].value).toBe(expected);
+      unmount();
     });
   });
 
   describe('handleAuthSelect', () => {
-    it('calls onAuthError if validation fails', () => {
+    it('calls onAuthError if validation fails', async () => {
       mockedValidateAuthMethod.mockReturnValue('Invalid method');
-      renderWithProviders(<AuthDialog {...props} />);
+      const { waitUntilReady, unmount } = renderWithProviders(
+        <AuthDialog {...props} />,
+      );
+      await waitUntilReady();
       const { onSelect: handleAuthSelect } =
         mockedRadioButtonSelect.mock.calls[0][0];
       handleAuthSelect(AuthType.USE_GEMINI);
@@ -221,11 +240,15 @@ describe('AuthDialog', () => {
       );
       expect(props.onAuthError).toHaveBeenCalledWith('Invalid method');
       expect(props.settings.setValue).not.toHaveBeenCalled();
+      unmount();
     });
 
     it('sets auth context with requiresRestart: true for LOGIN_WITH_GOOGLE', async () => {
       mockedValidateAuthMethod.mockReturnValue(null);
-      renderWithProviders(<AuthDialog {...props} />);
+      const { waitUntilReady, unmount } = renderWithProviders(
+        <AuthDialog {...props} />,
+      );
+      await waitUntilReady();
       const { onSelect: handleAuthSelect } =
         mockedRadioButtonSelect.mock.calls[0][0];
       await handleAuthSelect(AuthType.LOGIN_WITH_GOOGLE);
@@ -233,16 +256,21 @@ describe('AuthDialog', () => {
       expect(props.setAuthContext).toHaveBeenCalledWith({
         requiresRestart: true,
       });
+      unmount();
     });
 
     it('sets auth context with empty object for other auth types', async () => {
       mockedValidateAuthMethod.mockReturnValue(null);
-      renderWithProviders(<AuthDialog {...props} />);
+      const { waitUntilReady, unmount } = renderWithProviders(
+        <AuthDialog {...props} />,
+      );
+      await waitUntilReady();
       const { onSelect: handleAuthSelect } =
         mockedRadioButtonSelect.mock.calls[0][0];
       await handleAuthSelect(AuthType.USE_GEMINI);
 
       expect(props.setAuthContext).toHaveBeenCalledWith({});
+      unmount();
     });
 
     it('skips API key dialog on initial setup if env var is present', async () => {
@@ -250,7 +278,10 @@ describe('AuthDialog', () => {
       vi.stubEnv('GEMINI_API_KEY', 'test-key-from-env');
       // props.settings.merged.security.auth.selectedType is undefined here, simulating initial setup
 
-      renderWithProviders(<AuthDialog {...props} />);
+      const { waitUntilReady, unmount } = renderWithProviders(
+        <AuthDialog {...props} />,
+      );
+      await waitUntilReady();
       const { onSelect: handleAuthSelect } =
         mockedRadioButtonSelect.mock.calls[0][0];
       await handleAuthSelect(AuthType.USE_GEMINI);
@@ -258,6 +289,7 @@ describe('AuthDialog', () => {
       expect(props.setAuthState).toHaveBeenCalledWith(
         AuthState.Unauthenticated,
       );
+      unmount();
     });
 
     it('skips API key dialog if env var is present but empty', async () => {
@@ -265,7 +297,10 @@ describe('AuthDialog', () => {
       vi.stubEnv('GEMINI_API_KEY', ''); // Empty string
       // props.settings.merged.security.auth.selectedType is undefined here
 
-      renderWithProviders(<AuthDialog {...props} />);
+      const { waitUntilReady, unmount } = renderWithProviders(
+        <AuthDialog {...props} />,
+      );
+      await waitUntilReady();
       const { onSelect: handleAuthSelect } =
         mockedRadioButtonSelect.mock.calls[0][0];
       await handleAuthSelect(AuthType.USE_GEMINI);
@@ -273,6 +308,7 @@ describe('AuthDialog', () => {
       expect(props.setAuthState).toHaveBeenCalledWith(
         AuthState.Unauthenticated,
       );
+      unmount();
     });
 
     it('shows API key dialog on initial setup if no env var is present', async () => {
@@ -280,7 +316,10 @@ describe('AuthDialog', () => {
       // process.env['GEMINI_API_KEY'] is not set
       // props.settings.merged.security.auth.selectedType is undefined here, simulating initial setup
 
-      renderWithProviders(<AuthDialog {...props} />);
+      const { waitUntilReady, unmount } = renderWithProviders(
+        <AuthDialog {...props} />,
+      );
+      await waitUntilReady();
       const { onSelect: handleAuthSelect } =
         mockedRadioButtonSelect.mock.calls[0][0];
       await handleAuthSelect(AuthType.USE_GEMINI);
@@ -288,6 +327,7 @@ describe('AuthDialog', () => {
       expect(props.setAuthState).toHaveBeenCalledWith(
         AuthState.AwaitingApiKeyInput,
       );
+      unmount();
     });
 
     it('skips API key dialog on re-auth if env var is present (cannot edit)', async () => {
@@ -297,7 +337,10 @@ describe('AuthDialog', () => {
       props.settings.merged.security.auth.selectedType =
         AuthType.LOGIN_WITH_GOOGLE;
 
-      renderWithProviders(<AuthDialog {...props} />);
+      const { waitUntilReady, unmount } = renderWithProviders(
+        <AuthDialog {...props} />,
+      );
+      await waitUntilReady();
       const { onSelect: handleAuthSelect } =
         mockedRadioButtonSelect.mock.calls[0][0];
       await handleAuthSelect(AuthType.USE_GEMINI);
@@ -305,6 +348,7 @@ describe('AuthDialog', () => {
       expect(props.setAuthState).toHaveBeenCalledWith(
         AuthState.Unauthenticated,
       );
+      unmount();
     });
 
     it('exits process for Login with Google when browser is suppressed', async () => {
@@ -316,7 +360,10 @@ describe('AuthDialog', () => {
       vi.mocked(props.config.isBrowserLaunchSuppressed).mockReturnValue(true);
       mockedValidateAuthMethod.mockReturnValue(null);
 
-      renderWithProviders(<AuthDialog {...props} />);
+      const { waitUntilReady, unmount } = renderWithProviders(
+        <AuthDialog {...props} />,
+      );
+      await waitUntilReady();
       const { onSelect: handleAuthSelect } =
         mockedRadioButtonSelect.mock.calls[0][0];
       await act(async () => {
@@ -330,13 +377,18 @@ describe('AuthDialog', () => {
       exitSpy.mockRestore();
       logSpy.mockRestore();
       vi.useRealTimers();
+      unmount();
     });
   });
 
-  it('displays authError when provided', () => {
+  it('displays authError when provided', async () => {
     props.authError = 'Something went wrong';
-    const { lastFrame } = renderWithProviders(<AuthDialog {...props} />);
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+      <AuthDialog {...props} />,
+    );
+    await waitUntilReady();
     expect(lastFrame()).toContain('Something went wrong');
+    unmount();
   });
 
   describe('useKeypress', () => {
@@ -375,31 +427,47 @@ describe('AuthDialog', () => {
           expect(p.settings.setValue).not.toHaveBeenCalled();
         },
       },
-    ])('$desc', ({ setup, expectations }) => {
+    ])('$desc', async ({ setup, expectations }) => {
       setup();
-      renderWithProviders(<AuthDialog {...props} />);
+      const { waitUntilReady, unmount } = renderWithProviders(
+        <AuthDialog {...props} />,
+      );
+      await waitUntilReady();
       const keypressHandler = mockedUseKeypress.mock.calls[0][0];
       keypressHandler({ name: 'escape' });
       expectations(props);
+      unmount();
     });
   });
 
   describe('Snapshots', () => {
-    it('renders correctly with default props', () => {
-      const { lastFrame } = renderWithProviders(<AuthDialog {...props} />);
+    it('renders correctly with default props', async () => {
+      const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+        <AuthDialog {...props} />,
+      );
+      await waitUntilReady();
       expect(lastFrame()).toMatchSnapshot();
+      unmount();
     });
 
-    it('renders correctly with auth error', () => {
+    it('renders correctly with auth error', async () => {
       props.authError = 'Something went wrong';
-      const { lastFrame } = renderWithProviders(<AuthDialog {...props} />);
+      const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+        <AuthDialog {...props} />,
+      );
+      await waitUntilReady();
       expect(lastFrame()).toMatchSnapshot();
+      unmount();
     });
 
-    it('renders correctly with enforced auth type', () => {
+    it('renders correctly with enforced auth type', async () => {
       props.settings.merged.security.auth.enforcedType = AuthType.USE_GEMINI;
-      const { lastFrame } = renderWithProviders(<AuthDialog {...props} />);
+      const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+        <AuthDialog {...props} />,
+      );
+      await waitUntilReady();
       expect(lastFrame()).toMatchSnapshot();
+      unmount();
     });
   });
 });

packages/cli/src/ui/auth/AuthInProgress.test.tsx

@@ -54,48 +54,80 @@ describe('AuthInProgress', () => {
     vi.useRealTimers();
   });
 
-  it('renders initial state with spinner', () => {
-    const { lastFrame } = render(<AuthInProgress onTimeout={onTimeout} />);
+  it('renders initial state with spinner', async () => {
+    const { lastFrame, waitUntilReady, unmount } = render(
+      <AuthInProgress onTimeout={onTimeout} />,
+    );
+    await waitUntilReady();
     expect(lastFrame()).toContain('[Spinner] Waiting for auth...');
     expect(lastFrame()).toContain('Press ESC or CTRL+C to cancel');
+    unmount();
   });
 
-  it('calls onTimeout when ESC is pressed', () => {
-    render(<AuthInProgress onTimeout={onTimeout} />);
+  it('calls onTimeout when ESC is pressed', async () => {
+    const { waitUntilReady, unmount } = render(
+      <AuthInProgress onTimeout={onTimeout} />,
+    );
+    await waitUntilReady();
     const keypressHandler = vi.mocked(useKeypress).mock.calls[0][0];
 
-    keypressHandler({ name: 'escape' } as unknown as Key);
+    await act(async () => {
+      keypressHandler({ name: 'escape' } as unknown as Key);
+    });
+    // Escape key has a 50ms timeout in KeypressContext, so we need to wrap waitUntilReady in act
+    await act(async () => {
+      await waitUntilReady();
+    });
+
     expect(onTimeout).toHaveBeenCalled();
+    unmount();
   });
 
-  it('calls onTimeout when Ctrl+C is pressed', () => {
-    render(<AuthInProgress onTimeout={onTimeout} />);
+  it('calls onTimeout when Ctrl+C is pressed', async () => {
+    const { waitUntilReady, unmount } = render(
+      <AuthInProgress onTimeout={onTimeout} />,
+    );
+    await waitUntilReady();
     const keypressHandler = vi.mocked(useKeypress).mock.calls[0][0];
 
-    keypressHandler({ name: 'c', ctrl: true } as unknown as Key);
+    await act(async () => {
+      keypressHandler({ name: 'c', ctrl: true } as unknown as Key);
+    });
+    await waitUntilReady();
+
     expect(onTimeout).toHaveBeenCalled();
+    unmount();
   });
 
   it('calls onTimeout and shows timeout message after 3 minutes', async () => {
-    const { lastFrame } = render(<AuthInProgress onTimeout={onTimeout} />);
+    const { lastFrame, waitUntilReady, unmount } = render(
+      <AuthInProgress onTimeout={onTimeout} />,
+    );
+    await waitUntilReady();
 
     await act(async () => {
       vi.advanceTimersByTime(180000);
     });
+    await waitUntilReady();
 
     expect(onTimeout).toHaveBeenCalled();
-    await vi.waitUntil(
-      () => lastFrame()?.includes('Authentication timed out'),
-      { timeout: 1000 },
-    );
+    expect(lastFrame()).toContain('Authentication timed out');
+    unmount();
   });
 
-  it('clears timer on unmount', () => {
-    const { unmount } = render(<AuthInProgress onTimeout={onTimeout} />);
-    act(() => {
+  it('clears timer on unmount', async () => {
+    const { waitUntilReady, unmount } = render(
+      <AuthInProgress onTimeout={onTimeout} />,
+    );
+    await waitUntilReady();
+
+    await act(async () => {
       unmount();
     });
-    vi.advanceTimersByTime(180000);
+
+    await act(async () => {
+      vi.advanceTimersByTime(180000);
+    });
     expect(onTimeout).not.toHaveBeenCalled();
   });
 });

packages/cli/src/ui/auth/LoginWithGoogleRestartDialog.test.tsx

@@ -40,23 +40,26 @@ describe('LoginWithGoogleRestartDialog', () => {
     vi.useRealTimers();
   });
 
-  it('renders correctly', () => {
-    const { lastFrame } = render(
+  it('renders correctly', async () => {
+    const { lastFrame, waitUntilReady, unmount } = render(
       <LoginWithGoogleRestartDialog
         onDismiss={onDismiss}
         config={mockConfig}
       />,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
+    unmount();
   });
 
-  it('calls onDismiss when escape is pressed', () => {
-    render(
+  it('calls onDismiss when escape is pressed', async () => {
+    const { waitUntilReady, unmount } = render(
       <LoginWithGoogleRestartDialog
         onDismiss={onDismiss}
         config={mockConfig}
       />,
     );
+    await waitUntilReady();
     const keypressHandler = mockedUseKeypress.mock.calls[0][0];
 
     keypressHandler({
@@ -68,6 +71,7 @@ describe('LoginWithGoogleRestartDialog', () => {
     });
 
     expect(onDismiss).toHaveBeenCalledTimes(1);
+    unmount();
   });
 
   it.each(['r', 'R'])(
@@ -75,12 +79,13 @@ describe('LoginWithGoogleRestartDialog', () => {
     async (keyName) => {
       vi.useFakeTimers();
 
-      render(
+      const { waitUntilReady, unmount } = render(
         <LoginWithGoogleRestartDialog
           onDismiss={onDismiss}
           config={mockConfig}
         />,
       );
+      await waitUntilReady();
       const keypressHandler = mockedUseKeypress.mock.calls[0][0];
 
       keypressHandler({
@@ -98,6 +103,7 @@ describe('LoginWithGoogleRestartDialog', () => {
       expect(exitSpy).toHaveBeenCalledWith(RELAUNCH_EXIT_CODE);
 
       vi.useRealTimers();
+      unmount();
     },
   );
 });

packages/cli/src/ui/auth/__snapshots__/ApiAuthDialog.test.tsx.snap

@@ -14,5 +14,6 @@ exports[`ApiAuthDialog > renders correctly 1`] = `
 │                                                                                                  │
 │ (Press Enter to submit, Esc to cancel, Ctrl+C to clear stored key)                               │
 │                                                                                                  │
-╰──────────────────────────────────────────────────────────────────────────────────────────────────╯"
+╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
+"
 `;

packages/cli/src/ui/auth/__snapshots__/AuthDialog.test.tsx.snap

@@ -1,57 +1,60 @@
 // Vitest Snapshot v1, https://vitest.dev/guide/snapshot.html
 
 exports[`AuthDialog > Snapshots > renders correctly with auth error 1`] = `
-"╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
-│                                                                                                                      │
-│ ? Get started                                                                                                        │
-│                                                                                                                      │
-│   How would you like to authenticate for this project?                                                               │
-│                                                                                                                      │
-│   (selected) Login with Google(not selected) Use Gemini API Key(not selected) Vertex AI                              │
-│                                                                                                                      │
-│   Something went wrong                                                                                               │
-│                                                                                                                      │
-│   (Use Enter to select)                                                                                              │
-│                                                                                                                      │
-│   Terms of Services and Privacy Notice for Gemini CLI                                                                │
-│                                                                                                                      │
-│   https://github.com/google-gemini/gemini-cli/blob/main/docs/tos-privacy.md                                          │
-│                                                                                                                      │
-╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯"
+"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
+│                                                                                                  │
+│ ? Get started                                                                                    │
+│                                                                                                  │
+│   How would you like to authenticate for this project?                                           │
+│                                                                                                  │
+│   (selected) Login with Google(not selected) Use Gemini API Key(not selected) Vertex AI          │
+│                                                                                                  │
+│   Something went wrong                                                                           │
+│                                                                                                  │
+│   (Use Enter to select)                                                                          │
+│                                                                                                  │
+│   Terms of Services and Privacy Notice for Gemini CLI                                            │
+│                                                                                                  │
+│   https://github.com/google-gemini/gemini-cli/blob/main/docs/tos-privacy.md                      │
+│                                                                                                  │
+╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
+"
 `;
 
 exports[`AuthDialog > Snapshots > renders correctly with default props 1`] = `
-"╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
-│                                                                                                                      │
-│ ? Get started                                                                                                        │
-│                                                                                                                      │
-│   How would you like to authenticate for this project?                                                               │
-│                                                                                                                      │
-│   (selected) Login with Google(not selected) Use Gemini API Key(not selected) Vertex AI                              │
-│                                                                                                                      │
-│   (Use Enter to select)                                                                                              │
-│                                                                                                                      │
-│   Terms of Services and Privacy Notice for Gemini CLI                                                                │
-│                                                                                                                      │
-│   https://github.com/google-gemini/gemini-cli/blob/main/docs/tos-privacy.md                                          │
-│                                                                                                                      │
-╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯"
+"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
+│                                                                                                  │
+│ ? Get started                                                                                    │
+│                                                                                                  │
+│   How would you like to authenticate for this project?                                           │
+│                                                                                                  │
+│   (selected) Login with Google(not selected) Use Gemini API Key(not selected) Vertex AI          │
+│                                                                                                  │
+│   (Use Enter to select)                                                                          │
+│                                                                                                  │
+│   Terms of Services and Privacy Notice for Gemini CLI                                            │
+│                                                                                                  │
+│   https://github.com/google-gemini/gemini-cli/blob/main/docs/tos-privacy.md                      │
+│                                                                                                  │
+╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
+"
 `;
 
 exports[`AuthDialog > Snapshots > renders correctly with enforced auth type 1`] = `
-"╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
-│                                                                                                                      │
-│ ? Get started                                                                                                        │
-│                                                                                                                      │
-│   How would you like to authenticate for this project?                                                               │
-│                                                                                                                      │
-│   (selected) Use Gemini API Key                                                                                      │
-│                                                                                                                      │
-│   (Use Enter to select)                                                                                              │
-│                                                                                                                      │
-│   Terms of Services and Privacy Notice for Gemini CLI                                                                │
-│                                                                                                                      │
-│   https://github.com/google-gemini/gemini-cli/blob/main/docs/tos-privacy.md                                          │
-│                                                                                                                      │
-╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯"
+"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
+│                                                                                                  │
+│ ? Get started                                                                                    │
+│                                                                                                  │
+│   How would you like to authenticate for this project?                                           │
+│                                                                                                  │
+│   (selected) Use Gemini API Key                                                                  │
+│                                                                                                  │
+│   (Use Enter to select)                                                                          │
+│                                                                                                  │
+│   Terms of Services and Privacy Notice for Gemini CLI                                            │
+│                                                                                                  │
+│   https://github.com/google-gemini/gemini-cli/blob/main/docs/tos-privacy.md                      │
+│                                                                                                  │
+╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
+"
 `;

packages/cli/src/ui/auth/__snapshots__/LoginWithGoogleRestartDialog.test.tsx.snap

@@ -4,5 +4,6 @@ exports[`LoginWithGoogleRestartDialog > renders correctly 1`] = `
 "╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
 │ You have successfully logged in with Google. Gemini CLI needs to be restarted. Press 'r' to      │
 │ restart, or 'escape' to choose a different auth method.                                          │
-╰──────────────────────────────────────────────────────────────────────────────────────────────────╯"
+╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
+"
 `;

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

@@ -27,9 +27,11 @@ import { uiTelemetryService } from '@google/gemini-cli-core';
 describe('clearCommand', () => {
   let mockContext: CommandContext;
   let mockResetChat: ReturnType<typeof vi.fn>;
+  let mockHintClear: ReturnType<typeof vi.fn>;
 
   beforeEach(() => {
     mockResetChat = vi.fn().mockResolvedValue(undefined);
+    mockHintClear = vi.fn();
     const mockGetChatRecordingService = vi.fn();
     vi.clearAllMocks();
 
@@ -50,12 +52,15 @@ describe('clearCommand', () => {
             fireSessionEndEvent: vi.fn().mockResolvedValue(undefined),
             fireSessionStartEvent: vi.fn().mockResolvedValue(undefined),
           }),
+          userHintService: {
+            clear: mockHintClear,
+          },
         },
       },
     });
   });
 
-  it('should set debug message, reset chat, reset telemetry, and clear UI when config is available', async () => {
+  it('should set debug message, reset chat, reset telemetry, clear hints, and clear UI when config is available', async () => {
     if (!clearCommand.action) {
       throw new Error('clearCommand must have an action.');
     }
@@ -68,6 +73,7 @@ describe('clearCommand', () => {
     expect(mockContext.ui.setDebugMessage).toHaveBeenCalledTimes(1);
 
     expect(mockResetChat).toHaveBeenCalledTimes(1);
+    expect(mockHintClear).toHaveBeenCalledTimes(1);
     expect(uiTelemetryService.setLastPromptTokenCount).toHaveBeenCalledWith(0);
     expect(uiTelemetryService.setLastPromptTokenCount).toHaveBeenCalledTimes(1);
     expect(mockContext.ui.clear).toHaveBeenCalledTimes(1);

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

@@ -43,6 +43,9 @@ export const clearCommand: SlashCommand = {
       context.ui.setDebugMessage('Clearing terminal.');
     }
 
+    // Reset user steering hints
+    config?.userHintService.clear();
+
     // Start a new conversation recording with a new session ID
     if (config && chatRecordingService) {
       const newSessionId = randomUUID();

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

@@ -290,7 +290,7 @@ describe('extensionsCommand', () => {
 
     it('should inform user if there are no extensions to update with --all', async () => {
       mockDispatchExtensionState.mockImplementationOnce(
-        (action: ExtensionUpdateAction) => {
+        async (action: ExtensionUpdateAction) => {
           if (action.type === 'SCHEDULE_UPDATE') {
             action.payload.onComplete([]);
           }
@@ -306,7 +306,7 @@ describe('extensionsCommand', () => {
 
     it('should call setPendingItem and addItem in a finally block on success', async () => {
       mockDispatchExtensionState.mockImplementationOnce(
-        (action: ExtensionUpdateAction) => {
+        async (action: ExtensionUpdateAction) => {
           if (action.type === 'SCHEDULE_UPDATE') {
             action.payload.onComplete([
               {
@@ -357,7 +357,7 @@ describe('extensionsCommand', () => {
 
     it('should update a single extension by name', async () => {
       mockDispatchExtensionState.mockImplementationOnce(
-        (action: ExtensionUpdateAction) => {
+        async (action: ExtensionUpdateAction) => {
           if (action.type === 'SCHEDULE_UPDATE') {
             action.payload.onComplete([
               {
@@ -382,7 +382,7 @@ describe('extensionsCommand', () => {
 
     it('should update multiple extensions by name', async () => {
       mockDispatchExtensionState.mockImplementationOnce(
-        (action: ExtensionUpdateAction) => {
+        async (action: ExtensionUpdateAction) => {
           if (action.type === 'SCHEDULE_UPDATE') {
             action.payload.onComplete([
               {

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

@@ -24,8 +24,11 @@ describe('AboutBox', () => {
     ideClient: '',
   };
 
-  it('renders with required props', () => {
-    const { lastFrame } = renderWithProviders(<AboutBox {...defaultProps} />);
+  it('renders with required props', async () => {
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+      <AboutBox {...defaultProps} />,
+    );
+    await waitUntilReady();
     const output = lastFrame();
     expect(output).toContain('About Gemini CLI');
     expect(output).toContain('1.0.0');
@@ -34,31 +37,44 @@ describe('AboutBox', () => {
     expect(output).toContain('default');
     expect(output).toContain('macOS');
     expect(output).toContain('Logged in with Google');
+    unmount();
   });
 
   it.each([
     ['gcpProject', 'my-project', 'GCP Project'],
     ['ideClient', 'vscode', 'IDE Client'],
     ['tier', 'Enterprise', 'Tier'],
-  ])('renders optional prop %s', (prop, value, label) => {
+  ])('renders optional prop %s', async (prop, value, label) => {
     const props = { ...defaultProps, [prop]: value };
-    const { lastFrame } = renderWithProviders(<AboutBox {...props} />);
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+      <AboutBox {...props} />,
+    );
+    await waitUntilReady();
     const output = lastFrame();
     expect(output).toContain(label);
     expect(output).toContain(value);
+    unmount();
   });
 
-  it('renders Auth Method with email when userEmail is provided', () => {
+  it('renders Auth Method with email when userEmail is provided', async () => {
     const props = { ...defaultProps, userEmail: 'test@example.com' };
-    const { lastFrame } = renderWithProviders(<AboutBox {...props} />);
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+      <AboutBox {...props} />,
+    );
+    await waitUntilReady();
     const output = lastFrame();
     expect(output).toContain('Logged in with Google (test@example.com)');
+    unmount();
   });
 
-  it('renders Auth Method correctly when not oauth', () => {
+  it('renders Auth Method correctly when not oauth', async () => {
     const props = { ...defaultProps, selectedAuthType: 'api-key' };
-    const { lastFrame } = renderWithProviders(<AboutBox {...props} />);
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+      <AboutBox {...props} />,
+    );
+    await waitUntilReady();
     const output = lastFrame();
     expect(output).toContain('api-key');
+    unmount();
   });
 });

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

@@ -16,17 +16,24 @@ describe('AdminSettingsChangedDialog', () => {
     vi.restoreAllMocks();
   });
 
-  it('renders correctly', () => {
-    const { lastFrame } = renderWithProviders(<AdminSettingsChangedDialog />);
+  it('renders correctly', async () => {
+    const { lastFrame, waitUntilReady } = renderWithProviders(
+      <AdminSettingsChangedDialog />,
+    );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
   it('restarts on "r" key press', async () => {
-    const { stdin } = renderWithProviders(<AdminSettingsChangedDialog />, {
-      uiActions: {
-        handleRestart: handleRestartMock,
+    const { stdin, waitUntilReady } = renderWithProviders(
+      <AdminSettingsChangedDialog />,
+      {
+        uiActions: {
+          handleRestart: handleRestartMock,
+        },
       },
-    });
+    );
+    await waitUntilReady();
 
     act(() => {
       stdin.write('r');
@@ -36,11 +43,15 @@ describe('AdminSettingsChangedDialog', () => {
   });
 
   it.each(['r', 'R'])('restarts on "%s" key press', async (key) => {
-    const { stdin } = renderWithProviders(<AdminSettingsChangedDialog />, {
-      uiActions: {
-        handleRestart: handleRestartMock,
+    const { stdin, waitUntilReady } = renderWithProviders(
+      <AdminSettingsChangedDialog />,
+      {
+        uiActions: {
+          handleRestart: handleRestartMock,
+        },
       },
-    });
+    );
+    await waitUntilReady();
 
     act(() => {
       stdin.write(key);

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

@@ -118,11 +118,11 @@ describe('AgentConfigDialog', () => {
     mockOnSave = vi.fn();
   });
 
-  const renderDialog = (
+  const renderDialog = async (
     settings: LoadedSettings,
     definition: AgentDefinition = createMockAgentDefinition(),
-  ) =>
-    render(
+  ) => {
+    const result = render(
       <KeypressProvider>
         <AgentConfigDialog
           agentName="test-agent"
@@ -134,18 +134,21 @@ describe('AgentConfigDialog', () => {
         />
       </KeypressProvider>,
     );
+    await result.waitUntilReady();
+    return result;
+  };
 
   describe('rendering', () => {
-    it('should render the dialog with title', () => {
+    it('should render the dialog with title', async () => {
       const settings = createMockSettings();
-      const { lastFrame } = renderDialog(settings);
-
+      const { lastFrame, unmount } = await renderDialog(settings);
       expect(lastFrame()).toContain('Configure: Test Agent');
+      unmount();
     });
 
-    it('should render all configuration fields', () => {
+    it('should render all configuration fields', async () => {
       const settings = createMockSettings();
-      const { lastFrame } = renderDialog(settings);
+      const { lastFrame, unmount } = await renderDialog(settings);
       const frame = lastFrame();
 
       expect(frame).toContain('Enabled');
@@ -156,44 +159,53 @@ describe('AgentConfigDialog', () => {
       expect(frame).toContain('Max Output Tokens');
       expect(frame).toContain('Max Time (minutes)');
       expect(frame).toContain('Max Turns');
+      unmount();
     });
 
-    it('should render scope selector', () => {
+    it('should render scope selector', async () => {
       const settings = createMockSettings();
-      const { lastFrame } = renderDialog(settings);
+      const { lastFrame, unmount } = await renderDialog(settings);
 
       expect(lastFrame()).toContain('Apply To');
       expect(lastFrame()).toContain('User Settings');
       expect(lastFrame()).toContain('Workspace Settings');
+      unmount();
     });
 
-    it('should render help text', () => {
+    it('should render help text', async () => {
       const settings = createMockSettings();
-      const { lastFrame } = renderDialog(settings);
+      const { lastFrame, unmount } = await renderDialog(settings);
 
       expect(lastFrame()).toContain('Use Enter to select');
       expect(lastFrame()).toContain('Tab to change focus');
       expect(lastFrame()).toContain('Esc to close');
+      unmount();
     });
   });
 
   describe('keyboard navigation', () => {
     it('should close dialog on Escape', async () => {
       const settings = createMockSettings();
-      const { stdin } = renderDialog(settings);
+      const { stdin, waitUntilReady, unmount } = await renderDialog(settings);
 
       await act(async () => {
         stdin.write(TerminalKeys.ESCAPE);
       });
+      // Escape key has a 50ms timeout in KeypressContext, so we need to wrap waitUntilReady in act
+      await act(async () => {
+        await waitUntilReady();
+      });
 
       await waitFor(() => {
         expect(mockOnClose).toHaveBeenCalled();
       });
+      unmount();
     });
 
     it('should navigate down with arrow key', async () => {
       const settings = createMockSettings();
-      const { lastFrame, stdin } = renderDialog(settings);
+      const { lastFrame, stdin, waitUntilReady, unmount } =
+        await renderDialog(settings);
 
       // Initially first item (Enabled) should be active
       expect(lastFrame()).toContain('●');
@@ -202,16 +214,19 @@ describe('AgentConfigDialog', () => {
       await act(async () => {
         stdin.write(TerminalKeys.DOWN_ARROW);
       });
+      await waitUntilReady();
 
       await waitFor(() => {
         // Model field should now be highlighted
         expect(lastFrame()).toContain('Model');
       });
+      unmount();
     });
 
     it('should switch focus with Tab', async () => {
       const settings = createMockSettings();
-      const { lastFrame, stdin } = renderDialog(settings);
+      const { lastFrame, stdin, waitUntilReady, unmount } =
+        await renderDialog(settings);
 
       // Initially settings section is focused
       expect(lastFrame()).toContain('> Configure: Test Agent');
@@ -220,22 +235,25 @@ describe('AgentConfigDialog', () => {
       await act(async () => {
         stdin.write(TerminalKeys.TAB);
       });
+      await waitUntilReady();
 
       await waitFor(() => {
         expect(lastFrame()).toContain('> Apply To');
       });
+      unmount();
     });
   });
 
   describe('boolean toggle', () => {
     it('should toggle enabled field on Enter', async () => {
       const settings = createMockSettings();
-      const { stdin } = renderDialog(settings);
+      const { stdin, waitUntilReady, unmount } = await renderDialog(settings);
 
       // Press Enter to toggle the first field (Enabled)
       await act(async () => {
         stdin.write(TerminalKeys.ENTER);
       });
+      await waitUntilReady();
 
       await waitFor(() => {
         expect(settings.setValue).toHaveBeenCalledWith(
@@ -245,11 +263,12 @@ describe('AgentConfigDialog', () => {
         );
         expect(mockOnSave).toHaveBeenCalled();
       });
+      unmount();
     });
   });
 
   describe('default values', () => {
-    it('should show values from agent definition as defaults', () => {
+    it('should show values from agent definition as defaults', async () => {
       const definition = createMockAgentDefinition({
         modelConfig: {
           model: 'gemini-2.0-flash',
@@ -263,29 +282,31 @@ describe('AgentConfigDialog', () => {
         },
       });
       const settings = createMockSettings();
-      const { lastFrame } = renderDialog(settings, definition);
+      const { lastFrame, unmount } = await renderDialog(settings, definition);
       const frame = lastFrame();
 
       expect(frame).toContain('gemini-2.0-flash');
       expect(frame).toContain('0.7');
       expect(frame).toContain('10');
       expect(frame).toContain('20');
+      unmount();
     });
 
-    it('should show experimental agents as disabled by default', () => {
+    it('should show experimental agents as disabled by default', async () => {
       const definition = createMockAgentDefinition({
         experimental: true,
       });
       const settings = createMockSettings();
-      const { lastFrame } = renderDialog(settings, definition);
+      const { lastFrame, unmount } = await renderDialog(settings, definition);
 
       // Experimental agents default to disabled
       expect(lastFrame()).toContain('false');
+      unmount();
     });
   });
 
   describe('existing overrides', () => {
-    it('should show existing override values with * indicator', () => {
+    it('should show existing override values with * indicator', async () => {
       const settings = createMockSettings({
         agents: {
           overrides: {
@@ -298,12 +319,13 @@ describe('AgentConfigDialog', () => {
           },
         },
       });
-      const { lastFrame } = renderDialog(settings);
+      const { lastFrame, unmount } = await renderDialog(settings);
       const frame = lastFrame();
 
       // Should show the overridden values
       expect(frame).toContain('custom-model');
       expect(frame).toContain('false');
+      unmount();
     });
   });
 });

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

@@ -106,9 +106,9 @@ describe('AlternateBufferQuittingDisplay', () => {
     },
   };
 
-  it('renders with active and pending tool messages', () => {
+  it('renders with active and pending tool messages', async () => {
     persistentStateMock.setData({ tipsShown: 0 });
-    const { lastFrame } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
       <AlternateBufferQuittingDisplay />,
       {
         uiState: {
@@ -118,12 +118,14 @@ describe('AlternateBufferQuittingDisplay', () => {
         },
       },
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot('with_history_and_pending');
+    unmount();
   });
 
-  it('renders with empty history and no pending items', () => {
+  it('renders with empty history and no pending items', async () => {
     persistentStateMock.setData({ tipsShown: 0 });
-    const { lastFrame } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
       <AlternateBufferQuittingDisplay />,
       {
         uiState: {
@@ -133,12 +135,14 @@ describe('AlternateBufferQuittingDisplay', () => {
         },
       },
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot('empty');
+    unmount();
   });
 
-  it('renders with history but no pending items', () => {
+  it('renders with history but no pending items', async () => {
     persistentStateMock.setData({ tipsShown: 0 });
-    const { lastFrame } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
       <AlternateBufferQuittingDisplay />,
       {
         uiState: {
@@ -148,12 +152,14 @@ describe('AlternateBufferQuittingDisplay', () => {
         },
       },
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot('with_history_no_pending');
+    unmount();
   });
 
-  it('renders with pending items but no history', () => {
+  it('renders with pending items but no history', async () => {
     persistentStateMock.setData({ tipsShown: 0 });
-    const { lastFrame } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
       <AlternateBufferQuittingDisplay />,
       {
         uiState: {
@@ -163,10 +169,12 @@ describe('AlternateBufferQuittingDisplay', () => {
         },
       },
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot('with_pending_no_history');
+    unmount();
   });
 
-  it('renders with a tool awaiting confirmation', () => {
+  it('renders with a tool awaiting confirmation', async () => {
     persistentStateMock.setData({ tipsShown: 0 });
     const pendingHistoryItems: HistoryItemWithoutId[] = [
       {
@@ -187,7 +195,7 @@ describe('AlternateBufferQuittingDisplay', () => {
         ],
       },
     ];
-    const { lastFrame } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
       <AlternateBufferQuittingDisplay />,
       {
         uiState: {
@@ -197,20 +205,22 @@ describe('AlternateBufferQuittingDisplay', () => {
         },
       },
     );
+    await waitUntilReady();
     const output = lastFrame();
     expect(output).toContain('Action Required (was prompted):');
     expect(output).toContain('confirming_tool');
     expect(output).toContain('Confirming tool description');
     expect(output).toMatchSnapshot('with_confirming_tool');
+    unmount();
   });
 
-  it('renders with user and gemini messages', () => {
+  it('renders with user and gemini messages', async () => {
     persistentStateMock.setData({ tipsShown: 0 });
     const history: HistoryItem[] = [
       { id: 1, type: 'user', text: 'Hello Gemini' },
       { id: 2, type: 'gemini', text: 'Hello User!' },
     ];
-    const { lastFrame } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
       <AlternateBufferQuittingDisplay />,
       {
         uiState: {
@@ -220,6 +230,8 @@ describe('AlternateBufferQuittingDisplay', () => {
         },
       },
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot('with_user_gemini_messages');
+    unmount();
   });
 });

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

@@ -53,8 +53,6 @@ export const AlternateBufferQuittingDisplay = () => {
           terminalWidth={uiState.mainAreaWidth}
           item={{ ...item, id: 0 }}
           isPending={true}
-          activeShellPtyId={uiState.activePtyId}
-          embeddedShellFocused={uiState.embeddedShellFocused}
         />
       ))}
       {showPromptedTool && (

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

@@ -22,15 +22,19 @@ const createAnsiToken = (overrides: Partial<AnsiToken>): AnsiToken => ({
 });
 
 describe('<AnsiOutputText />', () => {
-  it('renders a simple AnsiOutput object correctly', () => {
+  it('renders a simple AnsiOutput object correctly', async () => {
     const data: AnsiOutput = [
       [
         createAnsiToken({ text: 'Hello, ' }),
         createAnsiToken({ text: 'world!' }),
       ],
     ];
-    const { lastFrame } = render(<AnsiOutputText data={data} width={80} />);
-    expect(lastFrame()).toBe('Hello, world!');
+    const { lastFrame, waitUntilReady, unmount } = render(
+      <AnsiOutputText data={data} width={80} />,
+    );
+    await waitUntilReady();
+    expect(lastFrame()).toBe('Hello, world!\n');
+    unmount();
   });
 
   // Note: ink-testing-library doesn't render styles, so we can only check the text.
@@ -41,73 +45,89 @@ describe('<AnsiOutputText />', () => {
     { style: { underline: true }, text: 'Underline' },
     { style: { dim: true }, text: 'Dim' },
     { style: { inverse: true }, text: 'Inverse' },
-  ])('correctly applies style $text', ({ style, text }) => {
+  ])('correctly applies style $text', async ({ style, text }) => {
     const data: AnsiOutput = [[createAnsiToken({ text, ...style })]];
-    const { lastFrame } = render(<AnsiOutputText data={data} width={80} />);
-    expect(lastFrame()).toBe(text);
+    const { lastFrame, waitUntilReady, unmount } = render(
+      <AnsiOutputText data={data} width={80} />,
+    );
+    await waitUntilReady();
+    expect(lastFrame()).toBe(text + '\n');
+    unmount();
   });
 
   it.each([
     { color: { fg: '#ff0000' }, text: 'Red FG' },
     { color: { bg: '#0000ff' }, text: 'Blue BG' },
     { color: { fg: '#00ff00', bg: '#ff00ff' }, text: 'Green FG Magenta BG' },
-  ])('correctly applies color $text', ({ color, text }) => {
+  ])('correctly applies color $text', async ({ color, text }) => {
     const data: AnsiOutput = [[createAnsiToken({ text, ...color })]];
-    const { lastFrame } = render(<AnsiOutputText data={data} width={80} />);
-    expect(lastFrame()).toBe(text);
+    const { lastFrame, waitUntilReady, unmount } = render(
+      <AnsiOutputText data={data} width={80} />,
+    );
+    await waitUntilReady();
+    expect(lastFrame()).toBe(text + '\n');
+    unmount();
   });
 
-  it('handles empty lines and empty tokens', () => {
+  it('handles empty lines and empty tokens', async () => {
     const data: AnsiOutput = [
       [createAnsiToken({ text: 'First line' })],
       [],
       [createAnsiToken({ text: 'Third line' })],
       [createAnsiToken({ text: '' })],
     ];
-    const { lastFrame } = render(<AnsiOutputText data={data} width={80} />);
+    const { lastFrame, waitUntilReady, unmount } = render(
+      <AnsiOutputText data={data} width={80} />,
+    );
+    await waitUntilReady();
     const output = lastFrame();
     expect(output).toBeDefined();
-    const lines = output!.split('\n');
+    const lines = output.split('\n');
     expect(lines[0].trim()).toBe('First line');
     expect(lines[1].trim()).toBe('');
     expect(lines[2].trim()).toBe('Third line');
+    unmount();
   });
 
-  it('respects the availableTerminalHeight prop and slices the lines correctly', () => {
+  it('respects the availableTerminalHeight prop and slices the lines correctly', async () => {
     const data: AnsiOutput = [
       [createAnsiToken({ text: 'Line 1' })],
       [createAnsiToken({ text: 'Line 2' })],
       [createAnsiToken({ text: 'Line 3' })],
       [createAnsiToken({ text: 'Line 4' })],
     ];
-    const { lastFrame } = render(
+    const { lastFrame, waitUntilReady, unmount } = render(
       <AnsiOutputText data={data} availableTerminalHeight={2} width={80} />,
     );
+    await waitUntilReady();
     const output = lastFrame();
     expect(output).not.toContain('Line 1');
     expect(output).not.toContain('Line 2');
     expect(output).toContain('Line 3');
     expect(output).toContain('Line 4');
+    unmount();
   });
 
-  it('respects the maxLines prop and slices the lines correctly', () => {
+  it('respects the maxLines prop and slices the lines correctly', async () => {
     const data: AnsiOutput = [
       [createAnsiToken({ text: 'Line 1' })],
       [createAnsiToken({ text: 'Line 2' })],
       [createAnsiToken({ text: 'Line 3' })],
       [createAnsiToken({ text: 'Line 4' })],
     ];
-    const { lastFrame } = render(
+    const { lastFrame, waitUntilReady, unmount } = render(
       <AnsiOutputText data={data} maxLines={2} width={80} />,
     );
+    await waitUntilReady();
     const output = lastFrame();
     expect(output).not.toContain('Line 1');
     expect(output).not.toContain('Line 2');
     expect(output).toContain('Line 3');
     expect(output).toContain('Line 4');
+    unmount();
   });
 
-  it('prioritizes maxLines over availableTerminalHeight if maxLines is smaller', () => {
+  it('prioritizes maxLines over availableTerminalHeight if maxLines is smaller', async () => {
     const data: AnsiOutput = [
       [createAnsiToken({ text: 'Line 1' })],
       [createAnsiToken({ text: 'Line 2' })],
@@ -115,7 +135,7 @@ describe('<AnsiOutputText />', () => {
       [createAnsiToken({ text: 'Line 4' })],
     ];
     // availableTerminalHeight=3, maxLines=2 => show 2 lines
-    const { lastFrame } = render(
+    const { lastFrame, waitUntilReady, unmount } = render(
       <AnsiOutputText
         data={data}
         availableTerminalHeight={3}
@@ -123,21 +143,25 @@ describe('<AnsiOutputText />', () => {
         width={80}
       />,
     );
+    await waitUntilReady();
     const output = lastFrame();
     expect(output).not.toContain('Line 2');
     expect(output).toContain('Line 3');
     expect(output).toContain('Line 4');
+    unmount();
   });
 
-  it('renders a large AnsiOutput object without crashing', () => {
+  it('renders a large AnsiOutput object without crashing', async () => {
     const largeData: AnsiOutput = [];
     for (let i = 0; i < 1000; i++) {
       largeData.push([createAnsiToken({ text: `Line ${i}` })]);
     }
-    const { lastFrame } = render(
+    const { lastFrame, waitUntilReady, unmount } = render(
       <AnsiOutputText data={largeData} width={80} />,
     );
+    await waitUntilReady();
     // We are just checking that it renders something without crashing.
     expect(lastFrame()).toBeDefined();
+    unmount();
   });
 });

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

@@ -18,7 +18,7 @@ vi.mock('../utils/terminalSetup.js', () => ({
 }));
 
 describe('<AppHeader />', () => {
-  it('should render the banner with default text', () => {
+  it('should render the banner with default text', async () => {
     const mockConfig = makeFakeConfig();
     const uiState = {
       history: [],
@@ -29,20 +29,21 @@ describe('<AppHeader />', () => {
       bannerVisible: true,
     };
 
-    const { lastFrame, unmount } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
       {
         config: mockConfig,
         uiState,
       },
     );
+    await waitUntilReady();
 
     expect(lastFrame()).toContain('This is the default banner');
     expect(lastFrame()).toMatchSnapshot();
     unmount();
   });
 
-  it('should render the banner with warning text', () => {
+  it('should render the banner with warning text', async () => {
     const mockConfig = makeFakeConfig();
     const uiState = {
       history: [],
@@ -53,20 +54,21 @@ describe('<AppHeader />', () => {
       bannerVisible: true,
     };
 
-    const { lastFrame, unmount } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
       {
         config: mockConfig,
         uiState,
       },
     );
+    await waitUntilReady();
 
     expect(lastFrame()).toContain('There are capacity issues');
     expect(lastFrame()).toMatchSnapshot();
     unmount();
   });
 
-  it('should not render the banner when no flags are set', () => {
+  it('should not render the banner when no flags are set', async () => {
     const mockConfig = makeFakeConfig();
     const uiState = {
       history: [],
@@ -76,20 +78,21 @@ describe('<AppHeader />', () => {
       },
     };
 
-    const { lastFrame, unmount } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
       {
         config: mockConfig,
         uiState,
       },
     );
+    await waitUntilReady();
 
     expect(lastFrame()).not.toContain('Banner');
     expect(lastFrame()).toMatchSnapshot();
     unmount();
   });
 
-  it('should not render the default banner if shown count is 5 or more', () => {
+  it('should not render the default banner if shown count is 5 or more', async () => {
     const mockConfig = makeFakeConfig();
     const uiState = {
       history: [],
@@ -108,20 +111,21 @@ describe('<AppHeader />', () => {
       },
     });
 
-    const { lastFrame, unmount } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
       {
         config: mockConfig,
         uiState,
       },
     );
+    await waitUntilReady();
 
     expect(lastFrame()).not.toContain('This is the default banner');
     expect(lastFrame()).toMatchSnapshot();
     unmount();
   });
 
-  it('should increment the version count when default banner is displayed', () => {
+  it('should increment the version count when default banner is displayed', async () => {
     const mockConfig = makeFakeConfig();
     const uiState = {
       history: [],
@@ -135,10 +139,14 @@ describe('<AppHeader />', () => {
     // and interfering with the expected persistentState.set call.
     persistentStateMock.setData({ tipsShown: 10 });
 
-    const { unmount } = renderWithProviders(<AppHeader version="1.0.0" />, {
-      config: mockConfig,
-      uiState,
-    });
+    const { waitUntilReady, unmount } = renderWithProviders(
+      <AppHeader version="1.0.0" />,
+      {
+        config: mockConfig,
+        uiState,
+      },
+    );
+    await waitUntilReady();
 
     expect(persistentStateMock.set).toHaveBeenCalledWith(
       'defaultBannerShownCount',
@@ -152,7 +160,7 @@ describe('<AppHeader />', () => {
     unmount();
   });
 
-  it('should render banner text with unescaped newlines', () => {
+  it('should render banner text with unescaped newlines', async () => {
     const mockConfig = makeFakeConfig();
     const uiState = {
       history: [],
@@ -163,19 +171,20 @@ describe('<AppHeader />', () => {
       bannerVisible: true,
     };
 
-    const { lastFrame, unmount } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
       {
         config: mockConfig,
         uiState,
       },
     );
+    await waitUntilReady();
 
     expect(lastFrame()).not.toContain('First line\\nSecond line');
     unmount();
   });
 
-  it('should render Tips when tipsShown is less than 10', () => {
+  it('should render Tips when tipsShown is less than 10', async () => {
     const mockConfig = makeFakeConfig();
     const uiState = {
       history: [],
@@ -188,36 +197,38 @@ describe('<AppHeader />', () => {
 
     persistentStateMock.setData({ tipsShown: 5 });
 
-    const { lastFrame, unmount } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
       {
         config: mockConfig,
         uiState,
       },
     );
+    await waitUntilReady();
 
     expect(lastFrame()).toContain('Tips');
     expect(persistentStateMock.set).toHaveBeenCalledWith('tipsShown', 6);
     unmount();
   });
 
-  it('should NOT render Tips when tipsShown is 10 or more', () => {
+  it('should NOT render Tips when tipsShown is 10 or more', async () => {
     const mockConfig = makeFakeConfig();
 
     persistentStateMock.setData({ tipsShown: 10 });
 
-    const { lastFrame, unmount } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
       {
         config: mockConfig,
       },
     );
+    await waitUntilReady();
 
     expect(lastFrame()).not.toContain('Tips');
     unmount();
   });
 
-  it('should show tips until they have been shown 10 times (persistence flow)', () => {
+  it('should show tips until they have been shown 10 times (persistence flow)', async () => {
     persistentStateMock.setData({ tipsShown: 9 });
 
     const mockConfig = makeFakeConfig();
@@ -235,6 +246,7 @@ describe('<AppHeader />', () => {
       config: mockConfig,
       uiState,
     });
+    await session1.waitUntilReady();
 
     expect(session1.lastFrame()).toContain('Tips');
     expect(persistentStateMock.get('tipsShown')).toBe(10);
@@ -244,6 +256,7 @@ describe('<AppHeader />', () => {
     const session2 = renderWithProviders(<AppHeader version="1.0.0" />, {
       config: mockConfig,
     });
+    await session2.waitUntilReady();
 
     expect(session2.lastFrame()).not.toContain('Tips');
     session2.unmount();

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

@@ -10,51 +10,57 @@ import { describe, it, expect } from 'vitest';
 import { ApprovalMode } from '@google/gemini-cli-core';
 
 describe('ApprovalModeIndicator', () => {
-  it('renders correctly for AUTO_EDIT mode', () => {
-    const { lastFrame } = render(
+  it('renders correctly for AUTO_EDIT mode', async () => {
+    const { lastFrame, waitUntilReady } = render(
       <ApprovalModeIndicator approvalMode={ApprovalMode.AUTO_EDIT} />,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
-  it('renders correctly for AUTO_EDIT mode with plan enabled', () => {
-    const { lastFrame } = render(
+  it('renders correctly for AUTO_EDIT mode with plan enabled', async () => {
+    const { lastFrame, waitUntilReady } = render(
       <ApprovalModeIndicator
         approvalMode={ApprovalMode.AUTO_EDIT}
-        isPlanEnabled={true}
+        allowPlanMode={true}
       />,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
-  it('renders correctly for PLAN mode', () => {
-    const { lastFrame } = render(
+  it('renders correctly for PLAN mode', async () => {
+    const { lastFrame, waitUntilReady } = render(
       <ApprovalModeIndicator approvalMode={ApprovalMode.PLAN} />,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
-  it('renders correctly for YOLO mode', () => {
-    const { lastFrame } = render(
+  it('renders correctly for YOLO mode', async () => {
+    const { lastFrame, waitUntilReady } = render(
       <ApprovalModeIndicator approvalMode={ApprovalMode.YOLO} />,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
-  it('renders correctly for DEFAULT mode', () => {
-    const { lastFrame } = render(
+  it('renders correctly for DEFAULT mode', async () => {
+    const { lastFrame, waitUntilReady } = render(
       <ApprovalModeIndicator approvalMode={ApprovalMode.DEFAULT} />,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
-  it('renders correctly for DEFAULT mode with plan enabled', () => {
-    const { lastFrame } = render(
+  it('renders correctly for DEFAULT mode with plan enabled', async () => {
+    const { lastFrame, waitUntilReady } = render(
       <ApprovalModeIndicator
         approvalMode={ApprovalMode.DEFAULT}
-        isPlanEnabled={true}
+        allowPlanMode={true}
       />,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 });

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

@@ -11,7 +11,7 @@ import { ApprovalMode } from '@google/gemini-cli-core';
 
 interface ApprovalModeIndicatorProps {
   approvalMode: ApprovalMode;
-  isPlanEnabled?: boolean;
+  allowPlanMode?: boolean;
 }
 
 export const APPROVAL_MODE_TEXT = {
@@ -26,7 +26,7 @@ export const APPROVAL_MODE_TEXT = {
 
 export const ApprovalModeIndicator: React.FC<ApprovalModeIndicatorProps> = ({
   approvalMode,
-  isPlanEnabled,
+  allowPlanMode,
 }) => {
   let textColor = '';
   let textContent = '';
@@ -36,7 +36,7 @@ export const ApprovalModeIndicator: React.FC<ApprovalModeIndicatorProps> = ({
     case ApprovalMode.AUTO_EDIT:
       textColor = theme.status.warning;
       textContent = APPROVAL_MODE_TEXT.AUTO_EDIT;
-      subText = isPlanEnabled
+      subText = allowPlanMode
         ? APPROVAL_MODE_TEXT.HINT_SWITCH_TO_PLAN_MODE
         : APPROVAL_MODE_TEXT.HINT_SWITCH_TO_MANUAL_MODE;
       break;

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

@@ -46,8 +46,8 @@ describe('AskUserDialog', () => {
     },
   ];
 
-  it('renders question and options', () => {
-    const { lastFrame } = renderWithProviders(
+  it('renders question and options', async () => {
+    const { lastFrame, waitUntilReady } = renderWithProviders(
       <AskUserDialog
         questions={authQuestion}
         onSubmit={vi.fn()}
@@ -57,6 +57,7 @@ describe('AskUserDialog', () => {
       { width: 120 },
     );
 
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
@@ -125,7 +126,7 @@ describe('AskUserDialog', () => {
 
       actions(stdin);
 
-      await waitFor(() => {
+      await waitFor(async () => {
         expect(onSubmit).toHaveBeenCalledWith(expectedSubmit);
       });
     });
@@ -133,7 +134,7 @@ describe('AskUserDialog', () => {
 
   it('handles custom option in single select with inline typing', async () => {
     const onSubmit = vi.fn();
-    const { stdin, lastFrame } = renderWithProviders(
+    const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
       <AskUserDialog
         questions={authQuestion}
         onSubmit={onSubmit}
@@ -147,7 +148,8 @@ describe('AskUserDialog', () => {
     writeKey(stdin, '\x1b[B');
     writeKey(stdin, '\x1b[B');
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toContain('Enter a custom value');
     });
 
@@ -156,14 +158,15 @@ describe('AskUserDialog', () => {
       writeKey(stdin, char);
     }
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toContain('API Key');
     });
 
     // Press Enter to submit the custom value
     writeKey(stdin, '\r');
 
-    await waitFor(() => {
+    await waitFor(async () => {
       expect(onSubmit).toHaveBeenCalledWith({ '0': 'API Key' });
     });
   });
@@ -180,7 +183,7 @@ describe('AskUserDialog', () => {
     ];
 
     const onSubmit = vi.fn();
-    const { stdin, lastFrame } = renderWithProviders(
+    const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
       <AskUserDialog
         questions={authQuestionWithOther}
         onSubmit={onSubmit}
@@ -207,15 +210,17 @@ describe('AskUserDialog', () => {
       writeKey(stdin, char);
     }
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toContain('Line 1');
+      await waitUntilReady();
       expect(lastFrame()).toContain('Line 2');
     });
 
     // Press Enter to submit
     writeKey(stdin, '\r');
 
-    await waitFor(() => {
+    await waitFor(async () => {
       expect(onSubmit).toHaveBeenCalledWith({ '0': 'Line 1\nLine 2' });
     });
   });
@@ -240,7 +245,7 @@ describe('AskUserDialog', () => {
           },
         ];
 
-        const { lastFrame } = renderWithProviders(
+        const { lastFrame, waitUntilReady } = renderWithProviders(
           <AskUserDialog
             questions={questions}
             onSubmit={vi.fn()}
@@ -251,14 +256,19 @@ describe('AskUserDialog', () => {
           { useAlternateBuffer },
         );
 
-        await waitFor(() => {
+        await waitFor(async () => {
           if (expectedArrows) {
+            await waitUntilReady();
             expect(lastFrame()).toContain('▲');
+            await waitUntilReady();
             expect(lastFrame()).toContain('▼');
           } else {
+            await waitUntilReady();
             expect(lastFrame()).not.toContain('▲');
+            await waitUntilReady();
             expect(lastFrame()).not.toContain('▼');
           }
+          await waitUntilReady();
           expect(lastFrame()).toMatchSnapshot();
         });
       });
@@ -266,7 +276,7 @@ describe('AskUserDialog', () => {
   );
 
   it('navigates to custom option when typing unbound characters (Type-to-Jump)', async () => {
-    const { stdin, lastFrame } = renderWithProviders(
+    const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
       <AskUserDialog
         questions={authQuestion}
         onSubmit={vi.fn()}
@@ -279,10 +289,12 @@ describe('AskUserDialog', () => {
     // Type a character without navigating down
     writeKey(stdin, 'A');
 
-    await waitFor(() => {
+    await waitFor(async () => {
       // Should show the custom input with 'A'
       // Placeholder is hidden when text is present
+      await waitUntilReady();
       expect(lastFrame()).toContain('A');
+      await waitUntilReady();
       expect(lastFrame()).toContain('3.  A');
     });
 
@@ -290,12 +302,13 @@ describe('AskUserDialog', () => {
     writeKey(stdin, 'P');
     writeKey(stdin, 'I');
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toContain('API');
     });
   });
 
-  it('shows progress header for multiple questions', () => {
+  it('shows progress header for multiple questions', async () => {
     const multiQuestions: Question[] = [
       {
         question: 'Which database should we use?',
@@ -319,7 +332,7 @@ describe('AskUserDialog', () => {
       },
     ];
 
-    const { lastFrame } = renderWithProviders(
+    const { lastFrame, waitUntilReady } = renderWithProviders(
       <AskUserDialog
         questions={multiQuestions}
         onSubmit={vi.fn()}
@@ -329,11 +342,12 @@ describe('AskUserDialog', () => {
       { width: 120 },
     );
 
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
-  it('hides progress header for single question', () => {
-    const { lastFrame } = renderWithProviders(
+  it('hides progress header for single question', async () => {
+    const { lastFrame, waitUntilReady } = renderWithProviders(
       <AskUserDialog
         questions={authQuestion}
         onSubmit={vi.fn()}
@@ -343,11 +357,12 @@ describe('AskUserDialog', () => {
       { width: 120 },
     );
 
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
-  it('shows keyboard hints', () => {
-    const { lastFrame } = renderWithProviders(
+  it('shows keyboard hints', async () => {
+    const { lastFrame, waitUntilReady } = renderWithProviders(
       <AskUserDialog
         questions={authQuestion}
         onSubmit={vi.fn()}
@@ -357,6 +372,7 @@ describe('AskUserDialog', () => {
       { width: 120 },
     );
 
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
@@ -380,7 +396,7 @@ describe('AskUserDialog', () => {
       },
     ];
 
-    const { stdin, lastFrame } = renderWithProviders(
+    const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
       <AskUserDialog
         questions={multiQuestions}
         onSubmit={vi.fn()}
@@ -390,17 +406,20 @@ describe('AskUserDialog', () => {
       { width: 120 },
     );
 
+    await waitUntilReady();
     expect(lastFrame()).toContain('Which testing framework?');
 
     writeKey(stdin, '\x1b[C'); // Right arrow
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toContain('Which CI provider?');
     });
 
     writeKey(stdin, '\x1b[D'); // Left arrow
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toContain('Which testing framework?');
     });
   });
@@ -424,7 +443,7 @@ describe('AskUserDialog', () => {
     ];
 
     const onSubmit = vi.fn();
-    const { stdin, lastFrame } = renderWithProviders(
+    const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
       <AskUserDialog
         questions={multiQuestions}
         onSubmit={onSubmit}
@@ -437,40 +456,44 @@ describe('AskUserDialog', () => {
     // Answer first question (should auto-advance)
     writeKey(stdin, '\r');
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toContain('Which bundler?');
     });
 
     // Navigate back
     writeKey(stdin, '\x1b[D');
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toContain('Which package manager?');
     });
 
     // Navigate forward
     writeKey(stdin, '\x1b[C');
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toContain('Which bundler?');
     });
 
     // Answer second question
     writeKey(stdin, '\r');
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toContain('Review your answers:');
     });
 
     // Submit from Review
     writeKey(stdin, '\r');
 
-    await waitFor(() => {
+    await waitFor(async () => {
       expect(onSubmit).toHaveBeenCalledWith({ '0': 'pnpm', '1': 'Vite' });
     });
   });
 
-  it('shows Review tab in progress header for multiple questions', () => {
+  it('shows Review tab in progress header for multiple questions', async () => {
     const multiQuestions: Question[] = [
       {
         question: 'Which framework?',
@@ -494,7 +517,7 @@ describe('AskUserDialog', () => {
       },
     ];
 
-    const { lastFrame } = renderWithProviders(
+    const { lastFrame, waitUntilReady } = renderWithProviders(
       <AskUserDialog
         questions={multiQuestions}
         onSubmit={vi.fn()}
@@ -504,6 +527,7 @@ describe('AskUserDialog', () => {
       { width: 120 },
     );
 
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
@@ -525,7 +549,7 @@ describe('AskUserDialog', () => {
       },
     ];
 
-    const { stdin, lastFrame } = renderWithProviders(
+    const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
       <AskUserDialog
         questions={multiQuestions}
         onSubmit={vi.fn()}
@@ -537,19 +561,22 @@ describe('AskUserDialog', () => {
 
     writeKey(stdin, '\x1b[C'); // Right arrow
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toContain('Add documentation?');
     });
 
     writeKey(stdin, '\x1b[C'); // Right arrow to Review
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toMatchSnapshot();
     });
 
     writeKey(stdin, '\x1b[D'); // Left arrow back
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toContain('Add documentation?');
     });
   });
@@ -572,7 +599,7 @@ describe('AskUserDialog', () => {
       },
     ];
 
-    const { stdin, lastFrame } = renderWithProviders(
+    const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
       <AskUserDialog
         questions={multiQuestions}
         onSubmit={vi.fn()}
@@ -586,7 +613,8 @@ describe('AskUserDialog', () => {
     writeKey(stdin, '\x1b[C');
     writeKey(stdin, '\x1b[C');
 
-    await waitFor(() => {
+    await waitFor(async () => {
+      await waitUntilReady();
       expect(lastFrame()).toMatchSnapshot();
     });
   });
@@ -627,13 +655,13 @@ describe('AskUserDialog', () => {
     // Submit
     writeKey(stdin, '\r');
 
-    await waitFor(() => {
+    await waitFor(async () => {
       expect(onSubmit).toHaveBeenCalledWith({ '0': 'Node 20' });
     });
   });
 
   describe('Text type questions', () => {
-    it('renders text input for type: "text"', () => {
+    it('renders text input for type: "text"', async () => {
       const textQuestion: Question[] = [
         {
           question: 'What should we name this component?',
@@ -643,7 +671,7 @@ describe('AskUserDialog', () => {
         },
       ];
 
-      const { lastFrame } = renderWithProviders(
+      const { lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={textQuestion}
           onSubmit={vi.fn()}
@@ -653,10 +681,11 @@ describe('AskUserDialog', () => {
         { width: 120 },
       );
 
+      await waitUntilReady();
       expect(lastFrame()).toMatchSnapshot();
     });
 
-    it('shows default placeholder when none provided', () => {
+    it('shows default placeholder when none provided', async () => {
       const textQuestion: Question[] = [
         {
           question: 'Enter the database connection string:',
@@ -665,7 +694,7 @@ describe('AskUserDialog', () => {
         },
       ];
 
-      const { lastFrame } = renderWithProviders(
+      const { lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={textQuestion}
           onSubmit={vi.fn()}
@@ -675,6 +704,7 @@ describe('AskUserDialog', () => {
         { width: 120 },
       );
 
+      await waitUntilReady();
       expect(lastFrame()).toMatchSnapshot();
     });
 
@@ -687,7 +717,7 @@ describe('AskUserDialog', () => {
         },
       ];
 
-      const { stdin, lastFrame } = renderWithProviders(
+      const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={textQuestion}
           onSubmit={vi.fn()}
@@ -701,19 +731,22 @@ describe('AskUserDialog', () => {
         writeKey(stdin, char);
       }
 
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('abc');
       });
 
       writeKey(stdin, '\x7f'); // Backspace
 
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('ab');
+        await waitUntilReady();
         expect(lastFrame()).not.toContain('abc');
       });
     });
 
-    it('shows correct keyboard hints for text type', () => {
+    it('shows correct keyboard hints for text type', async () => {
       const textQuestion: Question[] = [
         {
           question: 'Enter the variable name:',
@@ -722,7 +755,7 @@ describe('AskUserDialog', () => {
         },
       ];
 
-      const { lastFrame } = renderWithProviders(
+      const { lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={textQuestion}
           onSubmit={vi.fn()}
@@ -732,6 +765,7 @@ describe('AskUserDialog', () => {
         { width: 120 },
       );
 
+      await waitUntilReady();
       expect(lastFrame()).toMatchSnapshot();
     });
 
@@ -754,7 +788,7 @@ describe('AskUserDialog', () => {
         },
       ];
 
-      const { stdin, lastFrame } = renderWithProviders(
+      const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={mixedQuestions}
           onSubmit={vi.fn()}
@@ -770,13 +804,15 @@ describe('AskUserDialog', () => {
 
       writeKey(stdin, '\t'); // Use Tab instead of Right arrow when text input is active
 
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('Should it be async?');
       });
 
       writeKey(stdin, '\x1b[D'); // Left arrow should work when NOT focusing a text input
 
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('useAuth');
       });
     });
@@ -802,7 +838,7 @@ describe('AskUserDialog', () => {
       ];
 
       const onSubmit = vi.fn();
-      const { stdin, lastFrame } = renderWithProviders(
+      const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={mixedQuestions}
           onSubmit={onSubmit}
@@ -818,23 +854,29 @@ describe('AskUserDialog', () => {
 
       writeKey(stdin, '\r');
 
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('Which styling approach?');
       });
 
       writeKey(stdin, '\r');
 
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('Review your answers:');
+        await waitUntilReady();
         expect(lastFrame()).toContain('Name');
+        await waitUntilReady();
         expect(lastFrame()).toContain('DataTable');
+        await waitUntilReady();
         expect(lastFrame()).toContain('Style');
+        await waitUntilReady();
         expect(lastFrame()).toContain('CSS Modules');
       });
 
       writeKey(stdin, '\r');
 
-      await waitFor(() => {
+      await waitFor(async () => {
         expect(onSubmit).toHaveBeenCalledWith({
           '0': 'DataTable',
           '1': 'CSS Modules',
@@ -864,7 +906,7 @@ describe('AskUserDialog', () => {
 
       writeKey(stdin, '\r');
 
-      await waitFor(() => {
+      await waitFor(async () => {
         expect(onSubmit).toHaveBeenCalledWith({});
       });
     });
@@ -879,7 +921,7 @@ describe('AskUserDialog', () => {
       ];
 
       const onCancel = vi.fn();
-      const { stdin, lastFrame } = renderWithProviders(
+      const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={textQuestion}
           onSubmit={vi.fn()}
@@ -893,16 +935,19 @@ describe('AskUserDialog', () => {
         writeKey(stdin, char);
       }
 
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('SomeText');
       });
 
       // Send Ctrl+C
       writeKey(stdin, '\x03'); // Ctrl+C
 
-      await waitFor(() => {
+      await waitFor(async () => {
         // Text should be cleared
+        await waitUntilReady();
         expect(lastFrame()).not.toContain('SomeText');
+        await waitUntilReady();
         expect(lastFrame()).toContain('>');
       });
 
@@ -926,7 +971,7 @@ describe('AskUserDialog', () => {
         },
       ];
 
-      const { stdin, lastFrame } = renderWithProviders(
+      const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={multiQuestions}
           onSubmit={vi.fn()}
@@ -938,13 +983,15 @@ describe('AskUserDialog', () => {
 
       // 1. Move to Text Q (Right arrow works for Choice Q)
       writeKey(stdin, '\x1b[C');
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('Text Q?');
       });
 
       // 2. Type something in Text Q to make isEditingCustomOption true
       writeKey(stdin, 'a');
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('a');
       });
 
@@ -952,18 +999,21 @@ describe('AskUserDialog', () => {
       // When typing 'a', cursor is at index 1.
       // We need to move cursor to index 0 first for Left arrow to work for navigation.
       writeKey(stdin, '\x1b[D'); // Left arrow moves cursor to index 0
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('Text Q?');
       });
 
       writeKey(stdin, '\x1b[D'); // Second Left arrow should now trigger navigation
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('Choice Q?');
       });
 
       // 4. Immediately try Right arrow to go back to Text Q
       writeKey(stdin, '\x1b[C');
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('Text Q?');
       });
     });
@@ -987,7 +1037,7 @@ describe('AskUserDialog', () => {
       ];
 
       const onSubmit = vi.fn();
-      const { stdin, lastFrame } = renderWithProviders(
+      const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={multiQuestions}
           onSubmit={onSubmit}
@@ -1001,14 +1051,16 @@ describe('AskUserDialog', () => {
       act(() => {
         stdin.write('\r'); // Select A1 for Q1 -> triggers autoAdvance
       });
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('Question 2?');
       });
 
       act(() => {
         stdin.write('\r'); // Select A2 for Q2 -> triggers autoAdvance to Review
       });
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toContain('Review your answers:');
       });
 
@@ -1016,7 +1068,7 @@ describe('AskUserDialog', () => {
         stdin.write('\r'); // Submit from Review
       });
 
-      await waitFor(() => {
+      await waitFor(async () => {
         expect(onSubmit).toHaveBeenCalledWith({
           '0': 'A1',
           '1': 'A2',
@@ -1037,7 +1089,7 @@ describe('AskUserDialog', () => {
         },
       ];
 
-      const { lastFrame } = renderWithProviders(
+      const { lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={questions}
           onSubmit={vi.fn()}
@@ -1048,7 +1100,8 @@ describe('AskUserDialog', () => {
         { width: 120 },
       );
 
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         const frame = lastFrame();
         // Plain text should be rendered as bold
         expect(frame).toContain(chalk.bold('Which option do you prefer?'));
@@ -1066,7 +1119,7 @@ describe('AskUserDialog', () => {
         },
       ];
 
-      const { lastFrame } = renderWithProviders(
+      const { lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={questions}
           onSubmit={vi.fn()}
@@ -1077,7 +1130,8 @@ describe('AskUserDialog', () => {
         { width: 120 },
       );
 
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         const frame = lastFrame();
         // Should NOT have double-bold (the whole question bolded AND "this" bolded)
         // "Is " should not be bold, only "this" should be bold
@@ -1098,7 +1152,7 @@ describe('AskUserDialog', () => {
         },
       ];
 
-      const { lastFrame } = renderWithProviders(
+      const { lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={questions}
           onSubmit={vi.fn()}
@@ -1109,7 +1163,8 @@ describe('AskUserDialog', () => {
         { width: 120 },
       );
 
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         const frame = lastFrame();
         // Check for chalk.bold('this') - asterisks should be gone, text should be bold
         expect(frame).toContain(chalk.bold('this'));
@@ -1128,7 +1183,7 @@ describe('AskUserDialog', () => {
         },
       ];
 
-      const { lastFrame } = renderWithProviders(
+      const { lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={questions}
           onSubmit={vi.fn()}
@@ -1139,7 +1194,8 @@ describe('AskUserDialog', () => {
         { width: 120 },
       );
 
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         const frame = lastFrame();
         // Backticks should be removed
         expect(frame).toContain('npm start');
@@ -1148,7 +1204,7 @@ describe('AskUserDialog', () => {
     });
   });
 
-  it('uses availableTerminalHeight from UIStateContext if availableHeight prop is missing', () => {
+  it('uses availableTerminalHeight from UIStateContext if availableHeight prop is missing', async () => {
     const questions: Question[] = [
       {
         question: 'Choose an option',
@@ -1166,7 +1222,7 @@ describe('AskUserDialog', () => {
       availableTerminalHeight: 5, // Small height to force scroll arrows
     } as UIState;
 
-    const { lastFrame } = renderWithProviders(
+    const { lastFrame, waitUntilReady } = renderWithProviders(
       <UIStateContext.Provider value={mockUIState}>
         <AskUserDialog
           questions={questions}
@@ -1179,11 +1235,13 @@ describe('AskUserDialog', () => {
     );
 
     // With height 5 and alternate buffer disabled, it should show scroll arrows (▲)
+    await waitUntilReady();
     expect(lastFrame()).toContain('▲');
+    await waitUntilReady();
     expect(lastFrame()).toContain('▼');
   });
 
-  it('does NOT truncate the question when in alternate buffer mode even with small height', () => {
+  it('does NOT truncate the question when in alternate buffer mode even with small height', async () => {
     const longQuestion =
       'This is a very long question ' + 'with many words '.repeat(10);
     const questions: Question[] = [
@@ -1200,7 +1258,7 @@ describe('AskUserDialog', () => {
       availableTerminalHeight: 5,
     } as UIState;
 
-    const { lastFrame } = renderWithProviders(
+    const { lastFrame, waitUntilReady } = renderWithProviders(
       <UIStateContext.Provider value={mockUIState}>
         <AskUserDialog
           questions={questions}
@@ -1213,8 +1271,10 @@ describe('AskUserDialog', () => {
     );
 
     // Should NOT contain the truncation message
+    await waitUntilReady();
     expect(lastFrame()).not.toContain('hidden ...');
     // Should contain the full long question (or at least its parts)
+    await waitUntilReady();
     expect(lastFrame()).toContain('This is a very long question');
   });
 
@@ -1234,7 +1294,7 @@ describe('AskUserDialog', () => {
         },
       ];
 
-      const { stdin, lastFrame } = renderWithProviders(
+      const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={questions}
           onSubmit={vi.fn()}
@@ -1248,7 +1308,8 @@ describe('AskUserDialog', () => {
       writeKey(stdin, '\x1b[B'); // Down
       writeKey(stdin, '\x1b[B'); // Down to Other
 
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toMatchSnapshot();
       });
     });
@@ -1267,7 +1328,7 @@ describe('AskUserDialog', () => {
         },
       ];
 
-      const { stdin, lastFrame } = renderWithProviders(
+      const { stdin, lastFrame, waitUntilReady } = renderWithProviders(
         <AskUserDialog
           questions={questions}
           onSubmit={vi.fn()}
@@ -1281,7 +1342,8 @@ describe('AskUserDialog', () => {
       writeKey(stdin, '\x1b[B'); // Down
       writeKey(stdin, '\x1b[B'); // Down to Other
 
-      await waitFor(() => {
+      await waitFor(async () => {
+        await waitUntilReady();
         expect(lastFrame()).toMatchSnapshot();
       });
     });

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

@@ -14,8 +14,6 @@ import { type Key, type KeypressHandler } from '../contexts/KeypressContext.js';
 import { ScrollProvider } from '../contexts/ScrollProvider.js';
 import { Box } from 'ink';
 
-const delay = (ms: number) => new Promise((resolve) => setTimeout(resolve, ms));
-
 // Mock dependencies
 const mockDismissBackgroundShell = vi.fn();
 const mockSetActiveBackgroundShellPid = vi.fn();
@@ -142,81 +140,84 @@ describe('<BackgroundShellDisplay />', () => {
   });
 
   it('renders the output of the active shell', async () => {
-    const { lastFrame } = render(
+    const width = 80;
+    const { lastFrame, waitUntilReady, unmount } = render(
       <ScrollProvider>
         <BackgroundShellDisplay
           shells={mockShells}
           activePid={shell1.pid}
-          width={80}
+          width={width}
           height={24}
           isFocused={false}
           isListOpenProp={false}
         />
       </ScrollProvider>,
+      width,
     );
-    await act(async () => {
-      await delay(0);
-    });
+    await waitUntilReady();
 
     expect(lastFrame()).toMatchSnapshot();
+    unmount();
   });
 
   it('renders tabs for multiple shells', async () => {
-    const { lastFrame } = render(
+    const width = 100;
+    const { lastFrame, waitUntilReady, unmount } = render(
       <ScrollProvider>
         <BackgroundShellDisplay
           shells={mockShells}
           activePid={shell1.pid}
-          width={100}
+          width={width}
           height={24}
           isFocused={false}
           isListOpenProp={false}
         />
       </ScrollProvider>,
+      width,
     );
-    await act(async () => {
-      await delay(0);
-    });
+    await waitUntilReady();
 
     expect(lastFrame()).toMatchSnapshot();
+    unmount();
   });
 
   it('highlights the focused state', async () => {
-    const { lastFrame } = render(
+    const width = 80;
+    const { lastFrame, waitUntilReady, unmount } = render(
       <ScrollProvider>
         <BackgroundShellDisplay
           shells={mockShells}
           activePid={shell1.pid}
-          width={80}
+          width={width}
           height={24}
-          isFocused={true} // Focused
+          isFocused={true}
           isListOpenProp={false}
         />
       </ScrollProvider>,
+      width,
     );
-    await act(async () => {
-      await delay(0);
-    });
+    await waitUntilReady();
 
     expect(lastFrame()).toMatchSnapshot();
+    unmount();
   });
 
   it('resizes the PTY on mount and when dimensions change', async () => {
-    const { rerender } = render(
+    const width = 80;
+    const { rerender, waitUntilReady, unmount } = render(
       <ScrollProvider>
         <BackgroundShellDisplay
           shells={mockShells}
           activePid={shell1.pid}
-          width={80}
+          width={width}
           height={24}
           isFocused={false}
           isListOpenProp={false}
         />
       </ScrollProvider>,
+      width,
     );
-    await act(async () => {
-      await delay(0);
-    });
+    await waitUntilReady();
 
     expect(ShellExecutionService.resizePty).toHaveBeenCalledWith(
       shell1.pid,
@@ -236,143 +237,152 @@ describe('<BackgroundShellDisplay />', () => {
         />
       </ScrollProvider>,
     );
-    await act(async () => {
-      await delay(0);
-    });
+    await waitUntilReady();
 
     expect(ShellExecutionService.resizePty).toHaveBeenCalledWith(
       shell1.pid,
       96,
       27,
     );
+    unmount();
   });
 
   it('renders the process list when isListOpenProp is true', async () => {
-    const { lastFrame } = render(
+    const width = 80;
+    const { lastFrame, waitUntilReady, unmount } = render(
       <ScrollProvider>
         <BackgroundShellDisplay
           shells={mockShells}
           activePid={shell1.pid}
-          width={80}
+          width={width}
           height={24}
           isFocused={true}
           isListOpenProp={true}
         />
       </ScrollProvider>,
+      width,
     );
-    await act(async () => {
-      await delay(0);
-    });
+    await waitUntilReady();
 
     expect(lastFrame()).toMatchSnapshot();
+    unmount();
   });
 
   it('selects the current process and closes the list when Ctrl+L is pressed in list view', async () => {
-    render(
+    const width = 80;
+    const { waitUntilReady, unmount } = render(
       <ScrollProvider>
         <BackgroundShellDisplay
           shells={mockShells}
           activePid={shell1.pid}
-          width={80}
+          width={width}
           height={24}
           isFocused={true}
           isListOpenProp={true}
         />
       </ScrollProvider>,
+      width,
     );
-    await act(async () => {
-      await delay(0);
-    });
+    await waitUntilReady();
 
     // Simulate down arrow to select the second process (handled by RadioButtonSelect)
-    act(() => {
+    await act(async () => {
       simulateKey({ name: 'down' });
     });
+    await waitUntilReady();
 
     // Simulate Ctrl+L (handled by BackgroundShellDisplay)
-    act(() => {
+    await act(async () => {
       simulateKey({ name: 'l', ctrl: true });
     });
+    await waitUntilReady();
 
     expect(mockSetActiveBackgroundShellPid).toHaveBeenCalledWith(shell2.pid);
     expect(mockSetIsBackgroundShellListOpen).toHaveBeenCalledWith(false);
+    unmount();
   });
 
   it('kills the highlighted process when Ctrl+K is pressed in list view', async () => {
-    render(
+    const width = 80;
+    const { waitUntilReady, unmount } = render(
       <ScrollProvider>
         <BackgroundShellDisplay
           shells={mockShells}
           activePid={shell1.pid}
-          width={80}
+          width={width}
           height={24}
           isFocused={true}
           isListOpenProp={true}
         />
       </ScrollProvider>,
+      width,
     );
-    await act(async () => {
-      await delay(0);
-    });
+    await waitUntilReady();
 
     // Initial state: shell1 (active) is highlighted
 
     // Move to shell2
-    act(() => {
+    await act(async () => {
       simulateKey({ name: 'down' });
     });
+    await waitUntilReady();
 
     // Press Ctrl+K
-    act(() => {
+    await act(async () => {
       simulateKey({ name: 'k', ctrl: true });
     });
+    await waitUntilReady();
 
     expect(mockDismissBackgroundShell).toHaveBeenCalledWith(shell2.pid);
+    unmount();
   });
 
   it('kills the active process when Ctrl+K is pressed in output view', async () => {
-    render(
+    const width = 80;
+    const { waitUntilReady, unmount } = render(
       <ScrollProvider>
         <BackgroundShellDisplay
           shells={mockShells}
           activePid={shell1.pid}
-          width={80}
+          width={width}
           height={24}
           isFocused={true}
           isListOpenProp={false}
         />
       </ScrollProvider>,
+      width,
     );
-    await act(async () => {
-      await delay(0);
-    });
+    await waitUntilReady();
 
-    act(() => {
+    await act(async () => {
       simulateKey({ name: 'k', ctrl: true });
     });
+    await waitUntilReady();
 
     expect(mockDismissBackgroundShell).toHaveBeenCalledWith(shell1.pid);
+    unmount();
   });
 
   it('scrolls to active shell when list opens', async () => {
     // shell2 is active
-    const { lastFrame } = render(
+    const width = 80;
+    const { lastFrame, waitUntilReady, unmount } = render(
       <ScrollProvider>
         <BackgroundShellDisplay
           shells={mockShells}
           activePid={shell2.pid}
-          width={80}
+          width={width}
           height={24}
           isFocused={true}
           isListOpenProp={true}
         />
       </ScrollProvider>,
+      width,
     );
-    await act(async () => {
-      await delay(0);
-    });
+    await waitUntilReady();
 
     expect(lastFrame()).toMatchSnapshot();
+    unmount();
   });
 
   it('keeps exit code status color even when selected', async () => {
@@ -387,22 +397,23 @@ describe('<BackgroundShellDisplay />', () => {
     };
     mockShells.set(exitedShell.pid, exitedShell);
 
-    const { lastFrame } = render(
+    const width = 80;
+    const { lastFrame, waitUntilReady, unmount } = render(
       <ScrollProvider>
         <BackgroundShellDisplay
           shells={mockShells}
           activePid={exitedShell.pid}
-          width={80}
+          width={width}
           height={24}
           isFocused={true}
           isListOpenProp={true}
         />
       </ScrollProvider>,
+      width,
     );
-    await act(async () => {
-      await delay(0);
-    });
+    await waitUntilReady();
 
     expect(lastFrame()).toMatchSnapshot();
+    unmount();
   });
 });

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

@@ -12,18 +12,22 @@ describe('Banner', () => {
   it.each([
     ['warning mode', true, 'Warning Message'],
     ['info mode', false, 'Info Message'],
-  ])('renders in %s', (_, isWarning, text) => {
-    const { lastFrame } = render(
+  ])('renders in %s', async (_, isWarning, text) => {
+    const { lastFrame, waitUntilReady, unmount } = render(
       <Banner bannerText={text} isWarning={isWarning} width={80} />,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
+    unmount();
   });
 
-  it('handles newlines in text', () => {
+  it('handles newlines in text', async () => {
     const text = 'Line 1\\nLine 2';
-    const { lastFrame } = render(
+    const { lastFrame, waitUntilReady, unmount } = render(
       <Banner bannerText={text} isWarning={false} width={80} />,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
+    unmount();
   });
 });

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

@@ -17,26 +17,28 @@ describe('<Checklist />', () => {
     { status: 'cancelled', label: 'Task 4' },
   ];
 
-  it('renders nothing when list is empty', () => {
-    const { lastFrame } = render(
+  it('renders nothing when list is empty', async () => {
+    const { lastFrame, waitUntilReady } = render(
       <Checklist title="Test List" items={[]} isExpanded={true} />,
     );
-    expect(lastFrame()).toBe('');
+    await waitUntilReady();
+    expect(lastFrame({ allowEmpty: true })).toBe('');
   });
 
-  it('renders nothing when collapsed and no active items', () => {
+  it('renders nothing when collapsed and no active items', async () => {
     const inactiveItems: ChecklistItemData[] = [
       { status: 'completed', label: 'Task 1' },
       { status: 'cancelled', label: 'Task 2' },
     ];
-    const { lastFrame } = render(
+    const { lastFrame, waitUntilReady } = render(
       <Checklist title="Test List" items={inactiveItems} isExpanded={false} />,
     );
-    expect(lastFrame()).toBe('');
+    await waitUntilReady();
+    expect(lastFrame({ allowEmpty: true })).toBe('');
   });
 
-  it('renders summary view correctly (collapsed)', () => {
-    const { lastFrame } = render(
+  it('renders summary view correctly (collapsed)', async () => {
+    const { lastFrame, waitUntilReady } = render(
       <Checklist
         title="Test List"
         items={items}
@@ -44,11 +46,12 @@ describe('<Checklist />', () => {
         toggleHint="toggle me"
       />,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
-  it('renders expanded view correctly', () => {
-    const { lastFrame } = render(
+  it('renders expanded view correctly', async () => {
+    const { lastFrame, waitUntilReady } = render(
       <Checklist
         title="Test List"
         items={items}
@@ -56,17 +59,19 @@ describe('<Checklist />', () => {
         toggleHint="toggle me"
       />,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
-  it('renders summary view without in-progress item if none exists', () => {
+  it('renders summary view without in-progress item if none exists', async () => {
     const pendingItems: ChecklistItemData[] = [
       { status: 'completed', label: 'Task 1' },
       { status: 'pending', label: 'Task 2' },
     ];
-    const { lastFrame } = render(
+    const { lastFrame, waitUntilReady } = render(
       <Checklist title="Test List" items={pendingItems} isExpanded={false} />,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 });

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

@@ -15,36 +15,39 @@ describe('<ChecklistItem />', () => {
     { status: 'in_progress', label: 'Doing this' },
     { status: 'completed', label: 'Done this' },
     { status: 'cancelled', label: 'Skipped this' },
-  ] as ChecklistItemData[])('renders %s item correctly', (item) => {
-    const { lastFrame } = render(<ChecklistItem item={item} />);
+  ] as ChecklistItemData[])('renders %s item correctly', async (item) => {
+    const { lastFrame, waitUntilReady } = render(<ChecklistItem item={item} />);
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
-  it('truncates long text when wrap="truncate"', () => {
+  it('truncates long text when wrap="truncate"', async () => {
     const item: ChecklistItemData = {
       status: 'in_progress',
       label:
         'This is a very long text that should be truncated because the wrap prop is set to truncate',
     };
-    const { lastFrame } = render(
+    const { lastFrame, waitUntilReady } = render(
       <Box width={30}>
         <ChecklistItem item={item} wrap="truncate" />
       </Box>,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 
-  it('wraps long text by default', () => {
+  it('wraps long text by default', async () => {
     const item: ChecklistItemData = {
       status: 'in_progress',
       label:
         'This is a very long text that should wrap because the default behavior is wrapping',
     };
-    const { lastFrame } = render(
+    const { lastFrame, waitUntilReady } = render(
       <Box width={30}>
         <ChecklistItem item={item} />
       </Box>,
     );
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 });

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

@@ -15,17 +15,23 @@ describe('<CliSpinner />', () => {
     debugState.debugNumAnimatedComponents = 0;
   });
 
-  it('should increment debugNumAnimatedComponents on mount and decrement on unmount', () => {
+  it('should increment debugNumAnimatedComponents on mount and decrement on unmount', async () => {
     expect(debugState.debugNumAnimatedComponents).toBe(0);
-    const { unmount } = renderWithProviders(<CliSpinner />);
+    const { waitUntilReady, unmount } = renderWithProviders(<CliSpinner />);
+    await waitUntilReady();
     expect(debugState.debugNumAnimatedComponents).toBe(1);
     unmount();
     expect(debugState.debugNumAnimatedComponents).toBe(0);
   });
 
-  it('should not render when showSpinner is false', () => {
+  it('should not render when showSpinner is false', async () => {
     const settings = createMockSettings({ ui: { showSpinner: false } });
-    const { lastFrame } = renderWithProviders(<CliSpinner />, { settings });
-    expect(lastFrame()).toBe('');
+    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+      <CliSpinner />,
+      { settings },
+    );
+    await waitUntilReady();
+    expect(lastFrame({ allowEmpty: true })).toBe('');
+    unmount();
   });
 });

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

@@ -245,13 +245,13 @@ const createMockConfig = (overrides = {}): Config =>
     ...overrides,
   }) as unknown as Config;
 
-const renderComposer = (
+const renderComposer = async (
   uiState: UIState,
   settings = createMockSettings(),
   config = createMockConfig(),
   uiActions = createMockUIActions(),
-) =>
-  render(
+) => {
+  const result = render(
     <ConfigContext.Provider value={config as unknown as Config}>
       <SettingsContext.Provider value={settings as unknown as LoadedSettings}>
         <UIStateContext.Provider value={uiState}>
@@ -262,6 +262,9 @@ const renderComposer = (
       </SettingsContext.Provider>
     </ConfigContext.Provider>,
   );
+  await result.waitUntilReady();
+  return result;
+};
 
 describe('Composer', () => {
   beforeEach(() => {
@@ -274,20 +277,20 @@ describe('Composer', () => {
   });
 
   describe('Footer Display Settings', () => {
-    it('renders Footer by default when hideFooter is false', () => {
+    it('renders Footer by default when hideFooter is false', async () => {
       const uiState = createMockUIState();
       const settings = createMockSettings({ ui: { hideFooter: false } });
 
-      const { lastFrame } = renderComposer(uiState, settings);
+      const { lastFrame } = await renderComposer(uiState, settings);
 
       expect(lastFrame()).toContain('Footer');
     });
 
-    it('does NOT render Footer when hideFooter is true', () => {
+    it('does NOT render Footer when hideFooter is true', async () => {
       const uiState = createMockUIState();
       const settings = createMockSettings({ ui: { hideFooter: true } });
 
-      const { lastFrame } = renderComposer(uiState, settings);
+      const { lastFrame } = await renderComposer(uiState, settings);
 
       // Check for content that only appears IN the Footer component itself
       expect(lastFrame()).not.toContain('[NORMAL]'); // Vim mode indicator
@@ -331,7 +334,7 @@ describe('Composer', () => {
         setVimMode: vi.fn(),
       } as unknown as ReturnType<typeof useVimMode>);
 
-      const { lastFrame } = renderComposer(uiState, settings, config);
+      const { lastFrame } = await renderComposer(uiState, settings, config);
 
       expect(lastFrame()).toContain('Footer');
       // Footer should be rendered with all the state passed through
@@ -339,7 +342,7 @@ describe('Composer', () => {
   });
 
   describe('Loading Indicator', () => {
-    it('renders LoadingIndicator with thought when streaming', () => {
+    it('renders LoadingIndicator with thought when streaming', async () => {
       const uiState = createMockUIState({
         streamingState: StreamingState.Responding,
         thought: {
@@ -350,13 +353,13 @@ describe('Composer', () => {
         elapsedTime: 1500,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       const output = lastFrame();
       expect(output).toContain('LoadingIndicator: Processing');
     });
 
-    it('renders generic thinking text in loading indicator when full inline thinking is enabled', () => {
+    it('renders generic thinking text in loading indicator when full inline thinking is enabled', async () => {
       const uiState = createMockUIState({
         streamingState: StreamingState.Responding,
         thought: {
@@ -368,27 +371,27 @@ describe('Composer', () => {
         ui: { inlineThinkingMode: 'full' },
       });
 
-      const { lastFrame } = renderComposer(uiState, settings);
+      const { lastFrame } = await renderComposer(uiState, settings);
 
       const output = lastFrame();
       expect(output).toContain('LoadingIndicator: Thinking ...');
     });
 
-    it('hides shortcuts hint while loading', () => {
+    it('hides shortcuts hint while loading', async () => {
       const uiState = createMockUIState({
         streamingState: StreamingState.Responding,
         elapsedTime: 1,
         cleanUiDetailsVisible: false,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       const output = lastFrame();
       expect(output).toContain('LoadingIndicator');
       expect(output).not.toContain('ShortcutsHint');
     });
 
-    it('renders LoadingIndicator without thought when accessibility disables loading phrases', () => {
+    it('renders LoadingIndicator without thought when accessibility disables loading phrases', async () => {
       const uiState = createMockUIState({
         streamingState: StreamingState.Responding,
         thought: { subject: 'Hidden', description: 'Should not show' },
@@ -397,14 +400,14 @@ describe('Composer', () => {
         getAccessibility: vi.fn(() => ({ enableLoadingPhrases: false })),
       });
 
-      const { lastFrame } = renderComposer(uiState, undefined, config);
+      const { lastFrame } = await renderComposer(uiState, undefined, config);
 
       const output = lastFrame();
       expect(output).toContain('LoadingIndicator');
       expect(output).not.toContain('Should not show');
     });
 
-    it('does not render LoadingIndicator when waiting for confirmation', () => {
+    it('does not render LoadingIndicator when waiting for confirmation', async () => {
       const uiState = createMockUIState({
         streamingState: StreamingState.WaitingForConfirmation,
         thought: {
@@ -413,13 +416,13 @@ describe('Composer', () => {
         },
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       const output = lastFrame();
       expect(output).not.toContain('LoadingIndicator');
     });
 
-    it('does not render LoadingIndicator when a tool confirmation is pending', () => {
+    it('does not render LoadingIndicator when a tool confirmation is pending', async () => {
       const uiState = createMockUIState({
         streamingState: StreamingState.Responding,
         pendingHistoryItems: [
@@ -439,27 +442,27 @@ describe('Composer', () => {
         ],
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       const output = lastFrame();
       expect(output).not.toContain('LoadingIndicator');
       expect(output).not.toContain('esc to cancel');
     });
 
-    it('renders LoadingIndicator when embedded shell is focused but background shell is visible', () => {
+    it('renders LoadingIndicator when embedded shell is focused but background shell is visible', async () => {
       const uiState = createMockUIState({
         streamingState: StreamingState.Responding,
         embeddedShellFocused: true,
         isBackgroundShellVisible: true,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       const output = lastFrame();
       expect(output).toContain('LoadingIndicator');
     });
 
-    it('renders both LoadingIndicator and ApprovalModeIndicator when streaming in full UI mode', () => {
+    it('renders both LoadingIndicator and ApprovalModeIndicator when streaming in full UI mode', async () => {
       const uiState = createMockUIState({
         streamingState: StreamingState.Responding,
         thought: {
@@ -469,21 +472,21 @@ describe('Composer', () => {
         showApprovalModeIndicator: ApprovalMode.PLAN,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       const output = lastFrame();
       expect(output).toContain('LoadingIndicator: Thinking');
       expect(output).toContain('ApprovalModeIndicator');
     });
 
-    it('does NOT render LoadingIndicator when embedded shell is focused and background shell is NOT visible', () => {
+    it('does NOT render LoadingIndicator when embedded shell is focused and background shell is NOT visible', async () => {
       const uiState = createMockUIState({
         streamingState: StreamingState.Responding,
         embeddedShellFocused: true,
         isBackgroundShellVisible: false,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       const output = lastFrame();
       expect(output).not.toContain('LoadingIndicator');
@@ -491,7 +494,7 @@ describe('Composer', () => {
   });
 
   describe('Message Queue Display', () => {
-    it('displays queued messages when present', () => {
+    it('displays queued messages when present', async () => {
       const uiState = createMockUIState({
         messageQueue: [
           'First queued message',
@@ -500,7 +503,7 @@ describe('Composer', () => {
         ],
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       const output = lastFrame();
       expect(output).toContain('First queued message');
@@ -508,12 +511,12 @@ describe('Composer', () => {
       expect(output).toContain('Third queued message');
     });
 
-    it('renders QueuedMessageDisplay with empty message queue', () => {
+    it('renders QueuedMessageDisplay with empty message queue', async () => {
       const uiState = createMockUIState({
         messageQueue: [],
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       // The component should render but return null for empty queue
       // This test verifies that the component receives the correct prop
@@ -523,14 +526,14 @@ describe('Composer', () => {
   });
 
   describe('Context and Status Display', () => {
-    it('shows StatusDisplay and ApprovalModeIndicator in normal state', () => {
+    it('shows StatusDisplay and ApprovalModeIndicator in normal state', async () => {
       const uiState = createMockUIState({
         ctrlCPressedOnce: false,
         ctrlDPressedOnce: false,
         showEscapePrompt: false,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       const output = lastFrame();
       expect(output).toContain('StatusDisplay');
@@ -538,12 +541,12 @@ describe('Composer', () => {
       expect(output).not.toContain('ToastDisplay');
     });
 
-    it('shows ToastDisplay and hides ApprovalModeIndicator when a toast is present', () => {
+    it('shows ToastDisplay and hides ApprovalModeIndicator when a toast is present', async () => {
       const uiState = createMockUIState({
         ctrlCPressedOnce: true,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       const output = lastFrame();
       expect(output).toContain('ToastDisplay');
@@ -551,7 +554,7 @@ describe('Composer', () => {
       expect(output).toContain('StatusDisplay');
     });
 
-    it('shows ToastDisplay for other toast types', () => {
+    it('shows ToastDisplay for other toast types', async () => {
       const uiState = createMockUIState({
         transientMessage: {
           text: 'Warning',
@@ -559,7 +562,7 @@ describe('Composer', () => {
         },
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       const output = lastFrame();
       expect(output).toContain('ToastDisplay');
@@ -568,12 +571,12 @@ describe('Composer', () => {
   });
 
   describe('Input and Indicators', () => {
-    it('hides non-essential UI details in clean mode', () => {
+    it('hides non-essential UI details in clean mode', async () => {
       const uiState = createMockUIState({
         cleanUiDetailsVisible: false,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       const output = lastFrame();
       expect(output).toContain('ShortcutsHint');
@@ -583,22 +586,22 @@ describe('Composer', () => {
       expect(output).not.toContain('ContextSummaryDisplay');
     });
 
-    it('renders InputPrompt when input is active', () => {
+    it('renders InputPrompt when input is active', async () => {
       const uiState = createMockUIState({
         isInputActive: true,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).toContain('InputPrompt');
     });
 
-    it('does not render InputPrompt when input is inactive', () => {
+    it('does not render InputPrompt when input is inactive', async () => {
       const uiState = createMockUIState({
         isInputActive: false,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).not.toContain('InputPrompt');
     });
@@ -610,44 +613,44 @@ describe('Composer', () => {
       [ApprovalMode.YOLO],
     ])(
       'shows ApprovalModeIndicator when approval mode is %s and shell mode is inactive',
-      (mode) => {
+      async (mode) => {
         const uiState = createMockUIState({
           showApprovalModeIndicator: mode,
           shellModeActive: false,
         });
 
-        const { lastFrame } = renderComposer(uiState);
+        const { lastFrame } = await renderComposer(uiState);
 
         expect(lastFrame()).toMatch(/ApprovalModeIndic[\s\S]*ator/);
       },
     );
 
-    it('shows ShellModeIndicator when shell mode is active', () => {
+    it('shows ShellModeIndicator when shell mode is active', async () => {
       const uiState = createMockUIState({
         shellModeActive: true,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).toMatch(/ShellModeIndic[\s\S]*tor/);
     });
 
-    it('shows RawMarkdownIndicator when renderMarkdown is false', () => {
+    it('shows RawMarkdownIndicator when renderMarkdown is false', async () => {
       const uiState = createMockUIState({
         renderMarkdown: false,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).toContain('raw markdown mode');
     });
 
-    it('does not show RawMarkdownIndicator when renderMarkdown is true', () => {
+    it('does not show RawMarkdownIndicator when renderMarkdown is true', async () => {
       const uiState = createMockUIState({
         renderMarkdown: true,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).not.toContain('raw markdown mode');
     });
@@ -658,18 +661,18 @@ describe('Composer', () => {
       [ApprovalMode.AUTO_EDIT, 'auto edit'],
     ])(
       'shows minimal mode badge "%s" when clean UI details are hidden',
-      (mode, label) => {
+      async (mode, label) => {
         const uiState = createMockUIState({
           cleanUiDetailsVisible: false,
           showApprovalModeIndicator: mode,
         });
 
-        const { lastFrame } = renderComposer(uiState);
+        const { lastFrame } = await renderComposer(uiState);
         expect(lastFrame()).toContain(label);
       },
     );
 
-    it('hides minimal mode badge while loading in clean mode', () => {
+    it('hides minimal mode badge while loading in clean mode', async () => {
       const uiState = createMockUIState({
         cleanUiDetailsVisible: false,
         streamingState: StreamingState.Responding,
@@ -677,14 +680,14 @@ describe('Composer', () => {
         showApprovalModeIndicator: ApprovalMode.PLAN,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
       const output = lastFrame();
       expect(output).toContain('LoadingIndicator');
       expect(output).not.toContain('plan');
       expect(output).not.toContain('ShortcutsHint');
     });
 
-    it('hides minimal mode badge while action-required state is active', () => {
+    it('hides minimal mode badge while action-required state is active', async () => {
       const uiState = createMockUIState({
         cleanUiDetailsVisible: false,
         showApprovalModeIndicator: ApprovalMode.PLAN,
@@ -695,26 +698,26 @@ describe('Composer', () => {
         ),
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
       const output = lastFrame();
       expect(output).not.toContain('plan');
       expect(output).not.toContain('ShortcutsHint');
     });
 
-    it('shows Esc rewind prompt in minimal mode without showing full UI', () => {
+    it('shows Esc rewind prompt in minimal mode without showing full UI', async () => {
       const uiState = createMockUIState({
         cleanUiDetailsVisible: false,
         showEscapePrompt: true,
         history: [{ id: 1, type: 'user', text: 'msg' }],
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
       const output = lastFrame();
       expect(output).toContain('ToastDisplay');
       expect(output).not.toContain('ContextSummaryDisplay');
     });
 
-    it('shows context usage bleed-through when over 60%', () => {
+    it('shows context usage bleed-through when over 60%', async () => {
       const model = 'gemini-2.5-pro';
       const uiState = createMockUIState({
         cleanUiDetailsVisible: false,
@@ -734,13 +737,13 @@ describe('Composer', () => {
         },
       });
 
-      const { lastFrame } = renderComposer(uiState, settings);
+      const { lastFrame } = await renderComposer(uiState, settings);
       expect(lastFrame()).toContain('%');
     });
   });
 
   describe('Error Details Display', () => {
-    it('shows DetailedMessagesDisplay when showErrorDetails is true', () => {
+    it('shows DetailedMessagesDisplay when showErrorDetails is true', async () => {
       const uiState = createMockUIState({
         showErrorDetails: true,
         filteredConsoleMessages: [
@@ -752,18 +755,18 @@ describe('Composer', () => {
         ],
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).toContain('DetailedMessagesDisplay');
       expect(lastFrame()).toContain('ShowMoreLines');
     });
 
-    it('does not show error details when showErrorDetails is false', () => {
+    it('does not show error details when showErrorDetails is false', async () => {
       const uiState = createMockUIState({
         showErrorDetails: false,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).not.toContain('DetailedMessagesDisplay');
     });
@@ -780,7 +783,7 @@ describe('Composer', () => {
         setVimMode: vi.fn(),
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).toContain(
         "InputPrompt:   Press 'Esc' for NORMAL mode.",
@@ -797,7 +800,7 @@ describe('Composer', () => {
         setVimMode: vi.fn(),
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).toContain(
         "InputPrompt:   Press 'i' for INSERT mode.",
@@ -806,7 +809,7 @@ describe('Composer', () => {
   });
 
   describe('Shortcuts Hint', () => {
-    it('hides shortcuts hint when showShortcutsHint setting is false', () => {
+    it('hides shortcuts hint when showShortcutsHint setting is false', async () => {
       const uiState = createMockUIState();
       const settings = createMockSettings({
         ui: {
@@ -814,12 +817,12 @@ describe('Composer', () => {
         },
       });
 
-      const { lastFrame } = renderComposer(uiState, settings);
+      const { lastFrame } = await renderComposer(uiState, settings);
 
       expect(lastFrame()).not.toContain('ShortcutsHint');
     });
 
-    it('hides shortcuts hint when a action is required (e.g. dialog is open)', () => {
+    it('hides shortcuts hint when a action is required (e.g. dialog is open)', async () => {
       const uiState = createMockUIState({
         customDialog: (
           <Box>
@@ -829,55 +832,55 @@ describe('Composer', () => {
         ),
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).not.toContain('ShortcutsHint');
     });
 
-    it('keeps shortcuts hint visible when no action is required', () => {
+    it('keeps shortcuts hint visible when no action is required', async () => {
       const uiState = createMockUIState({
         cleanUiDetailsVisible: false,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).toContain('ShortcutsHint');
     });
 
-    it('shows shortcuts hint when full UI details are visible', () => {
+    it('shows shortcuts hint when full UI details are visible', async () => {
       const uiState = createMockUIState({
         cleanUiDetailsVisible: true,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).toContain('ShortcutsHint');
     });
 
-    it('hides shortcuts hint while loading in minimal mode', () => {
+    it('hides shortcuts hint while loading in minimal mode', async () => {
       const uiState = createMockUIState({
         cleanUiDetailsVisible: false,
         streamingState: StreamingState.Responding,
         elapsedTime: 1,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).not.toContain('ShortcutsHint');
     });
 
-    it('shows shortcuts help in minimal mode when toggled on', () => {
+    it('shows shortcuts help in minimal mode when toggled on', async () => {
       const uiState = createMockUIState({
         cleanUiDetailsVisible: false,
         shortcutsHelpVisible: true,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).toContain('ShortcutsHelp');
     });
 
-    it('hides shortcuts hint when suggestions are visible above input in alternate buffer', () => {
+    it('hides shortcuts hint when suggestions are visible above input in alternate buffer', async () => {
       composerTestControls.isAlternateBuffer = true;
       composerTestControls.suggestionsVisible = true;
 
@@ -886,13 +889,13 @@ describe('Composer', () => {
         showApprovalModeIndicator: ApprovalMode.PLAN,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).not.toContain('ShortcutsHint');
       expect(lastFrame()).not.toContain('plan');
     });
 
-    it('hides approval mode indicator when suggestions are visible above input in alternate buffer', () => {
+    it('hides approval mode indicator when suggestions are visible above input in alternate buffer', async () => {
       composerTestControls.isAlternateBuffer = true;
       composerTestControls.suggestionsVisible = true;
 
@@ -901,12 +904,12 @@ describe('Composer', () => {
         showApprovalModeIndicator: ApprovalMode.YOLO,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).not.toContain('ApprovalModeIndicator');
     });
 
-    it('keeps shortcuts hint when suggestions are visible below input in regular buffer', () => {
+    it('keeps shortcuts hint when suggestions are visible below input in regular buffer', async () => {
       composerTestControls.isAlternateBuffer = false;
       composerTestControls.suggestionsVisible = true;
 
@@ -914,36 +917,36 @@ describe('Composer', () => {
         cleanUiDetailsVisible: false,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).toContain('ShortcutsHint');
     });
   });
 
   describe('Shortcuts Help', () => {
-    it('shows shortcuts help in passive state', () => {
+    it('shows shortcuts help in passive state', async () => {
       const uiState = createMockUIState({
         shortcutsHelpVisible: true,
         streamingState: StreamingState.Idle,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).toContain('ShortcutsHelp');
     });
 
-    it('hides shortcuts help while streaming', () => {
+    it('hides shortcuts help while streaming', async () => {
       const uiState = createMockUIState({
         shortcutsHelpVisible: true,
         streamingState: StreamingState.Responding,
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).not.toContain('ShortcutsHelp');
     });
 
-    it('hides shortcuts help when action is required', () => {
+    it('hides shortcuts help when action is required', async () => {
       const uiState = createMockUIState({
         shortcutsHelpVisible: true,
         customDialog: (
@@ -953,20 +956,20 @@ describe('Composer', () => {
         ),
       });
 
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
 
       expect(lastFrame()).not.toContain('ShortcutsHelp');
     });
   });
 
   describe('Snapshots', () => {
-    it('matches snapshot in idle state', () => {
+    it('matches snapshot in idle state', async () => {
       const uiState = createMockUIState();
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
       expect(lastFrame()).toMatchSnapshot();
     });
 
-    it('matches snapshot while streaming', () => {
+    it('matches snapshot while streaming', async () => {
       const uiState = createMockUIState({
         streamingState: StreamingState.Responding,
         thought: {
@@ -974,33 +977,33 @@ describe('Composer', () => {
           description: 'Thinking about the meaning of life...',
         },
       });
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
       expect(lastFrame()).toMatchSnapshot();
     });
 
-    it('matches snapshot in narrow view', () => {
+    it('matches snapshot in narrow view', async () => {
       const uiState = createMockUIState({
         terminalWidth: 40,
       });
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
       expect(lastFrame()).toMatchSnapshot();
     });
 
-    it('matches snapshot in minimal UI mode', () => {
+    it('matches snapshot in minimal UI mode', async () => {
       const uiState = createMockUIState({
         cleanUiDetailsVisible: false,
       });
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
       expect(lastFrame()).toMatchSnapshot();
     });
 
-    it('matches snapshot in minimal UI mode while loading', () => {
+    it('matches snapshot in minimal UI mode while loading', async () => {
       const uiState = createMockUIState({
         cleanUiDetailsVisible: false,
         streamingState: StreamingState.Responding,
         elapsedTime: 1000,
       });
-      const { lastFrame } = renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);
       expect(lastFrame()).toMatchSnapshot();
     });
   });

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

@@ -346,7 +346,7 @@ export const Composer = ({ isFocused = true }: { isFocused?: boolean }) => {
                   {showApprovalIndicator && (
                     <ApprovalModeIndicator
                       approvalMode={showApprovalModeIndicator}
-                      isPlanEnabled={config.isPlanEnabled()}
+                      allowPlanMode={uiState.allowPlanMode}
                     />
                   )}
                   {!showLoadingIndicator && (

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

@@ -42,8 +42,9 @@ describe('ConfigInitDisplay', () => {
     vi.restoreAllMocks();
   });
 
-  it('renders initial state', () => {
-    const { lastFrame } = render(<ConfigInitDisplay />);
+  it('renders initial state', async () => {
+    const { lastFrame, waitUntilReady } = render(<ConfigInitDisplay />);
+    await waitUntilReady();
     expect(lastFrame()).toMatchSnapshot();
   });
 

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

@@ -31,15 +31,16 @@ describe('ConsentPrompt', () => {
     vi.clearAllMocks();
   });
 
-  it('renders a string prompt with MarkdownDisplay', () => {
+  it('renders a string prompt with MarkdownDisplay', async () => {
     const prompt = 'Are you sure?';
-    const { unmount } = render(
+    const { waitUntilReady, unmount } = render(
       <ConsentPrompt
         prompt={prompt}
         onConfirm={onConfirm}
         terminalWidth={terminalWidth}
       />,
     );
+    await waitUntilReady();
 
     expect(MockedMarkdownDisplay).toHaveBeenCalledWith(
       {
@@ -52,15 +53,16 @@ describe('ConsentPrompt', () => {
     unmount();
   });
 
-  it('renders a ReactNode prompt directly', () => {
+  it('renders a ReactNode prompt directly', async () => {
     const prompt = <Text>Are you sure?</Text>;
-    const { lastFrame, unmount } = render(
+    const { lastFrame, waitUntilReady, unmount } = render(
       <ConsentPrompt
         prompt={prompt}
         onConfirm={onConfirm}
         terminalWidth={terminalWidth}
       />,
     );
+    await waitUntilReady();
 
     expect(MockedMarkdownDisplay).not.toHaveBeenCalled();
     expect(lastFrame()).toContain('Are you sure?');
@@ -69,18 +71,20 @@ describe('ConsentPrompt', () => {
 
   it('calls onConfirm with true when "Yes" is selected', async () => {
     const prompt = 'Are you sure?';
-    const { unmount } = render(
+    const { waitUntilReady, unmount } = render(
       <ConsentPrompt
         prompt={prompt}
         onConfirm={onConfirm}
         terminalWidth={terminalWidth}
       />,
     );
+    await waitUntilReady();
 
     const onSelect = MockedRadioButtonSelect.mock.calls[0][0].onSelect;
     await act(async () => {
       onSelect(true);
     });
+    await waitUntilReady();
 
     expect(onConfirm).toHaveBeenCalledWith(true);
     unmount();
@@ -88,32 +92,35 @@ describe('ConsentPrompt', () => {
 
   it('calls onConfirm with false when "No" is selected', async () => {
     const prompt = 'Are you sure?';
-    const { unmount } = render(
+    const { waitUntilReady, unmount } = render(
       <ConsentPrompt
         prompt={prompt}
         onConfirm={onConfirm}
         terminalWidth={terminalWidth}
       />,
     );
+    await waitUntilReady();
 
     const onSelect = MockedRadioButtonSelect.mock.calls[0][0].onSelect;
     await act(async () => {
       onSelect(false);
     });
+    await waitUntilReady();
 
     expect(onConfirm).toHaveBeenCalledWith(false);
     unmount();
   });
 
-  it('passes correct items to RadioButtonSelect', () => {
+  it('passes correct items to RadioButtonSelect', async () => {
     const prompt = 'Are you sure?';
-    const { unmount } = render(
+    const { waitUntilReady, unmount } = render(
       <ConsentPrompt
         prompt={prompt}
         onConfirm={onConfirm}
         terminalWidth={terminalWidth}
       />,
     );
+    await waitUntilReady();
 
     expect(MockedRadioButtonSelect).toHaveBeenCalledWith(
       expect.objectContaining({

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

@@ -9,19 +9,27 @@ import { ConsoleSummaryDisplay } from './ConsoleSummaryDisplay.js';
 import { describe, it, expect } from 'vitest';
 
 describe('ConsoleSummaryDisplay', () => {
-  it('renders nothing when errorCount is 0', () => {
-    const { lastFrame } = render(<ConsoleSummaryDisplay errorCount={0} />);
-    expect(lastFrame()).toBe('');
+  it('renders nothing when errorCount is 0', async () => {
+    const { lastFrame, waitUntilReady, unmount } = render(
+      <ConsoleSummaryDisplay errorCount={0} />,
+    );
+    await waitUntilReady();
+    expect(lastFrame({ allowEmpty: true })).toBe('');
+    unmount();
   });
 
   it.each([
     [1, '1 error'],
     [5, '5 errors'],
-  ])('renders correct message for %i errors', (count, expectedText) => {
-    const { lastFrame } = render(<ConsoleSummaryDisplay errorCount={count} />);
+  ])('renders correct message for %i errors', async (count, expectedText) => {
+    const { lastFrame, waitUntilReady, unmount } = render(
+      <ConsoleSummaryDisplay errorCount={count} />,
+    );
+    await waitUntilReady();
     const output = lastFrame();
     expect(output).toContain(expectedText);
     expect(output).toContain('✖');
     expect(output).toContain('(F12 for details)');
+    unmount();
   });
 });

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

@@ -21,12 +21,14 @@ afterEach(() => {
   vi.useRealTimers();
 });
 
-const renderWithWidth = (
+const renderWithWidth = async (
   width: number,
   props: React.ComponentProps<typeof ContextSummaryDisplay>,
 ) => {
   useTerminalSizeMock.mockReturnValue({ columns: width, rows: 24 });
-  return render(<ContextSummaryDisplay {...props} />);
+  const result = render(<ContextSummaryDisplay {...props} />);
+  await result.waitUntilReady();
+  return result;
 };
 
 describe('<ContextSummaryDisplay />', () => {
@@ -42,7 +44,7 @@ describe('<ContextSummaryDisplay />', () => {
     skillCount: 1,
   };
 
-  it('should render on a single line on a wide screen', () => {
+  it('should render on a single line on a wide screen', async () => {
     const props = {
       ...baseProps,
       geminiMdFileCount: 1,
@@ -54,12 +56,12 @@ describe('<ContextSummaryDisplay />', () => {
         },
       },
     };
-    const { lastFrame, unmount } = renderWithWidth(120, props);
+    const { lastFrame, unmount } = await renderWithWidth(120, props);
     expect(lastFrame()).toMatchSnapshot();
     unmount();
   });
 
-  it('should render on multiple lines on a narrow screen', () => {
+  it('should render on multiple lines on a narrow screen', async () => {
     const props = {
       ...baseProps,
       geminiMdFileCount: 1,
@@ -71,12 +73,12 @@ describe('<ContextSummaryDisplay />', () => {
         },
       },
     };
-    const { lastFrame, unmount } = renderWithWidth(60, props);
+    const { lastFrame, unmount } = await renderWithWidth(60, props);
     expect(lastFrame()).toMatchSnapshot();
     unmount();
   });
 
-  it('should switch layout at the 80-column breakpoint', () => {
+  it('should switch layout at the 80-column breakpoint', async () => {
     const props = {
       ...baseProps,
       geminiMdFileCount: 1,
@@ -90,23 +92,19 @@ describe('<ContextSummaryDisplay />', () => {
     };
 
     // At 80 columns, should be on one line
-    const { lastFrame: wideFrame, unmount: unmountWide } = renderWithWidth(
-      80,
-      props,
-    );
-    expect(wideFrame()!.includes('\n')).toBe(false);
+    const { lastFrame: wideFrame, unmount: unmountWide } =
+      await renderWithWidth(80, props);
+    expect(wideFrame().trim().includes('\n')).toBe(false);
     unmountWide();
 
     // At 79 columns, should be on multiple lines
-    const { lastFrame: narrowFrame, unmount: unmountNarrow } = renderWithWidth(
-      79,
-      props,
-    );
-    expect(narrowFrame()!.includes('\n')).toBe(true);
-    expect(narrowFrame()!.split('\n').length).toBe(4);
+    const { lastFrame: narrowFrame, unmount: unmountNarrow } =
+      await renderWithWidth(79, props);
+    expect(narrowFrame().trim().includes('\n')).toBe(true);
+    expect(narrowFrame().trim().split('\n').length).toBe(4);
     unmountNarrow();
   });
-  it('should not render empty parts', () => {
+  it('should not render empty parts', async () => {
     const props = {
       ...baseProps,
       geminiMdFileCount: 0,
@@ -119,7 +117,7 @@ describe('<ContextSummaryDisplay />', () => {
         },
       },
     };
-    const { lastFrame, unmount } = renderWithWidth(60, props);
+    const { lastFrame, unmount } = await renderWithWidth(60, props);
     expect(lastFrame()).toMatchSnapshot();
     unmount();
   });

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

@@ -27,40 +27,46 @@ vi.mock('../../config/settings.js', () => ({
 }));
 
 describe('ContextUsageDisplay', () => {
-  it('renders correct percentage left', () => {
-    const { lastFrame } = render(
+  it('renders correct percentage left', async () => {
+    const { lastFrame, waitUntilReady, unmount } = render(
       <ContextUsageDisplay
         promptTokenCount={5000}
         model="gemini-pro"
         terminalWidth={120}
       />,
     );
+    await waitUntilReady();
     const output = lastFrame();
     expect(output).toContain('50% context left');
+    unmount();
   });
 
-  it('renders short label when terminal width is small', () => {
-    const { lastFrame } = render(
+  it('renders short label when terminal width is small', async () => {
+    const { lastFrame, waitUntilReady, unmount } = render(
       <ContextUsageDisplay
         promptTokenCount={2000}
         model="gemini-pro"
         terminalWidth={80}
       />,
     );
+    await waitUntilReady();
     const output = lastFrame();
     expect(output).toContain('80%');
     expect(output).not.toContain('context left');
+    unmount();
   });
 
-  it('renders 0% when full', () => {
-    const { lastFrame } = render(
+  it('renders 0% when full', async () => {
+    const { lastFrame, waitUntilReady, unmount } = render(
       <ContextUsageDisplay
         promptTokenCount={10000}
         model="gemini-pro"
         terminalWidth={120}
       />,
     );
+    await waitUntilReady();
     const output = lastFrame();
     expect(output).toContain('0% context left');
+    unmount();
   });
 });

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

@@ -18,20 +18,24 @@ describe('CopyModeWarning', () => {
     vi.clearAllMocks();
   });
 
-  it('renders nothing when copy mode is disabled', () => {
+  it('renders nothing when copy mode is disabled', async () => {
     mockUseUIState.mockReturnValue({
       copyModeEnabled: false,
     } as unknown as UIState);
-    const { lastFrame } = render(<CopyModeWarning />);
-    expect(lastFrame()).toBe('');
+    const { lastFrame, waitUntilReady, unmount } = render(<CopyModeWarning />);
+    await waitUntilReady();
+    expect(lastFrame({ allowEmpty: true })).toBe('');
+    unmount();
   });
 
-  it('renders warning when copy mode is enabled', () => {
+  it('renders warning when copy mode is enabled', async () => {
     mockUseUIState.mockReturnValue({
       copyModeEnabled: true,
     } as unknown as UIState);
-    const { lastFrame } = render(<CopyModeWarning />);
+    const { lastFrame, waitUntilReady, unmount } = render(<CopyModeWarning />);
+    await waitUntilReady();
     expect(lastFrame()).toContain('In Copy Mode');
     expect(lastFrame()).toContain('Press any key to exit');
+    unmount();
   });
 });

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

@@ -231,28 +231,24 @@ describe('DebugProfiler Component', () => {
       showDebugProfiler: false,
       constrainHeight: false,
     } as unknown as UIState);
-
-    // Mock process.stdin and stdout
-    // We need to be careful not to break the test runner's own output
-    // So we might want to skip mocking them if they are not strictly needed for the simple render test
-    // or mock them safely.
-    // For now, let's assume the component uses them in useEffect.
   });
 
   afterEach(() => {
     vi.restoreAllMocks();
   });
 
-  it('should return null when showDebugProfiler is false', () => {
+  it('should return null when showDebugProfiler is false', async () => {
     vi.mocked(useUIState).mockReturnValue({
       showDebugProfiler: false,
       constrainHeight: false,
     } as unknown as UIState);
-    const { lastFrame } = render(<DebugProfiler />);
-    expect(lastFrame()).toBe('');
+    const { lastFrame, waitUntilReady, unmount } = render(<DebugProfiler />);
+    await waitUntilReady();
+    expect(lastFrame({ allowEmpty: true })).toBe('');
+    unmount();
   });
 
-  it('should render stats when showDebugProfiler is true', () => {
+  it('should render stats when showDebugProfiler is true', async () => {
     vi.mocked(useUIState).mockReturnValue({
       showDebugProfiler: true,
       constrainHeight: false,
@@ -261,12 +257,14 @@ describe('DebugProfiler Component', () => {
     profiler.totalIdleFrames = 5;
     profiler.totalFlickerFrames = 2;
 
-    const { lastFrame } = render(<DebugProfiler />);
+    const { lastFrame, waitUntilReady, unmount } = render(<DebugProfiler />);
+    await waitUntilReady();
     const output = lastFrame();
 
     expect(output).toContain('Renders: 10 (total)');
     expect(output).toContain('5 (idle)');
     expect(output).toContain('2 (flicker)');
+    unmount();
   });
 
   it('should report an action when a CoreEvent is emitted', async () => {
@@ -277,11 +275,13 @@ describe('DebugProfiler Component', () => {
 
     const reportActionSpy = vi.spyOn(profiler, 'reportAction');
 
-    const { unmount } = render(<DebugProfiler />);
+    const { waitUntilReady, unmount } = render(<DebugProfiler />);
+    await waitUntilReady();
 
-    act(() => {
+    await act(async () => {
       coreEvents.emitModelChanged('new-model');
     });
+    await waitUntilReady();
 
     expect(reportActionSpy).toHaveBeenCalled();
     unmount();
@@ -295,11 +295,13 @@ describe('DebugProfiler Component', () => {
 
     const reportActionSpy = vi.spyOn(profiler, 'reportAction');
 
-    const { unmount } = render(<DebugProfiler />);
+    const { waitUntilReady, unmount } = render(<DebugProfiler />);
+    await waitUntilReady();
 
-    act(() => {
+    await act(async () => {
       appEvents.emit(AppEvent.SelectionWarning);
     });
+    await waitUntilReady();
 
     expect(reportActionSpy).toHaveBeenCalled();
     unmount();