feat(core): Remove legacy settings. (#17244)

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

.gemini/skills/code-reviewer/SKILL.md

@@ -0,0 +1,65 @@
+---
+name: code-reviewer
+description:
+  Use this skill to review code. It supports both local changes (staged or working tree)
+  and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability,
+  and adherence to project standards.
+---
+
+# Code Reviewer
+
+This skill guides the agent in conducting professional and thorough code reviews for both local development and remote Pull Requests.
+
+## Workflow
+
+### 1. Determine Review Target
+*   **Remote PR**: If the user provides a PR number or URL (e.g., "Review PR #123"), target that remote PR.
+*   **Local Changes**: If no specific PR is mentioned, or if the user asks to "review my changes", target the current local file system states (staged and unstaged changes).
+
+### 2. Preparation
+
+#### For Remote PRs:
+1.  **Checkout**: Use the GitHub CLI to checkout the PR.
+    ```bash
+    gh pr checkout <PR_NUMBER>
+    ```
+2.  **Preflight**: Execute the project's standard verification suite to catch automated failures early.
+    ```bash
+    npm run preflight
+    ```
+3.  **Context**: Read the PR description and any existing comments to understand the goal and history.
+
+#### For Local Changes:
+1.  **Identify Changes**:
+    *   Check status: `git status`
+    *   Read diffs: `git diff` (working tree) and/or `git diff --staged` (staged).
+2.  **Preflight (Optional)**: If the changes are substantial, ask the user if they want to run `npm run preflight` before reviewing.
+
+### 3. In-Depth Analysis
+Analyze the code changes based on the following pillars:
+
+*   **Correctness**: Does the code achieve its stated purpose without bugs or logical errors?
+*   **Maintainability**: Is the code clean, well-structured, and easy to understand and modify in the future? Consider factors like code clarity, modularity, and adherence to established design patterns.
+*   **Readability**: Is the code well-commented (where necessary) and consistently formatted according to our project's coding style guidelines?
+*   **Efficiency**: Are there any obvious performance bottlenecks or resource inefficiencies introduced by the changes?
+*   **Security**: Are there any potential security vulnerabilities or insecure coding practices?
+*   **Edge Cases and Error Handling**: Does the code appropriately handle edge cases and potential errors?
+*   **Testability**: Is the new or modified code adequately covered by tests (even if preflight checks pass)? Suggest additional test cases that would improve coverage or robustness.
+
+### 4. Provide Feedback
+
+#### Structure
+*   **Summary**: A high-level overview of the review.
+*   **Findings**:
+    *   **Critical**: Bugs, security issues, or breaking changes.
+    *   **Improvements**: Suggestions for better code quality or performance.
+    *   **Nitpicks**: Formatting or minor style issues (optional).
+*   **Conclusion**: Clear recommendation (Approved / Request Changes).
+
+#### Tone
+*   Be constructive, professional, and friendly.
+*   Explain *why* a change is requested.
+*   For approvals, acknowledge the specific value of the contribution.
+
+### 5. Cleanup (Remote PRs only)
+*   After the review, ask the user if they want to switch back to the default branch (e.g., `main` or `master`).

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

@@ -0,0 +1,63 @@
+---
+name: docs-writer
+description:
+  Use this skill when asked to write documentation (`/docs` directory)
+  for Gemini CLI.
+---
+
+# `docs-writer` skill instructions
+
+As an expert technical writer for the Gemini CLI project, your goal is to
+produce documentation that is accurate, clear, and consistent with the project's
+standards. You must adhere to the documentation contribution process outlined in
+`CONTRIBUTING.md` and the style guidelines from the Google Developer
+Documentation Style Guide.
+
+## Step 1: Understand the goal and create a plan
+
+1.  **Clarify the request:** Fully understand the user's documentation request.
+    Identify the core feature, command, or concept that needs to be documented.
+2.  **Ask questions:** If the request is ambiguous or lacks detail, ask
+    clarifying questions. Don't invent or assume. It's better to ask than to
+    write incorrect documentation.
+3.  **Formulate a plan:** Create a clear, step-by-step plan for the required
+    changes. If requested or necessary, store this plan in a temporary file or
+    a file identified by the user.
+
+## Step 2: Investigate and gather information
+
+1.  **Read the code:** Thoroughly examine the relevant codebase, primarily within
+    the `packages/` directory, to ensure your writing is backed by the
+    implementation.
+2.  **Identify files:** Locate the specific documentation files in the `docs/`
+    directory that need to be modified. Always read the latest
+    version of a file before you begin to edit it.
+3.  **Check for connections:** Consider related documentation. If you add a new
+    page, check if `docs/sidebar.json` needs to be updated. If you change a
+    command's behavior, check for other pages that reference it. Make sure links
+    in these pages are up to date.
+
+## Step 3: Draft the documentation
+
+1.  **Follow the style guide:**
+    - Text must be wrapped at 80 characters. Exceptions are long links or
+      tables, unless otherwise stated by the user.
+    - Use sentence case for headings, titles, and bolded text.
+    - Address the reader as "you".
+    - Use contractions to keep the tone more casual.
+    - Use simple, direct, and active language and the present tense.
+    - Keep paragraphs short and focused.
+    - Always refer to Gemini CLI as `Gemini CLI`, never `the Gemini CLI`.
+2.  **Use `replace` and `write_file`:** Use the file system tools to apply your
+    planned changes precisely. For small edits, `replace` is preferred. For new
+    files or large rewrites, `write_file` is more appropriate.
+
+## Step 4: Verify and finalize
+
+1.  **Review your work:** After making changes, re-read the files to ensure the
+    documentation is well-formatted, content is correct and based on existing
+    code, and that all new links are valid.
+2.  **Offer to run npm format:** Once all changes are complete and the user
+    confirms they have no more requests, offer to run the project's formatting
+    script to ensure consistency. Propose the following command:
+    `npm run format`

.gemini/skills/pr-creator/SKILL.md

@@ -14,16 +14,25 @@ repository's standards.
 
 Follow these steps to create a Pull Request:
 
-1.  **Locate Template**: Search for a pull request template in the repository.
+1.  **Branch Management**: Check the current branch to avoid working directly
+    on `main`.
+    - Run `git branch --show-current`.
+    - If the current branch is `main`, create and switch to a new descriptive
+      branch:
+      ```bash
+      git checkout -b <new-branch-name>
+      ```
+
+2.  **Locate Template**: Search for a pull request template in the repository.
     - Check `.github/pull_request_template.md`
     - Check `.github/PULL_REQUEST_TEMPLATE.md`
     - If multiple templates exist (e.g., in `.github/PULL_REQUEST_TEMPLATE/`),
       ask the user which one to use or select the most appropriate one based on
       the context (e.g., `bug_fix.md` vs `feature.md`).
 
-2.  **Read Template**: Read the content of the identified template file.
+3.  **Read Template**: Read the content of the identified template file.
 
-3.  **Draft Description**: Create a PR description that strictly follows the
+4.  **Draft Description**: Create a PR description that strictly follows the
     template's structure.
     - **Headings**: Keep all headings from the template.
     - **Checklists**: Review each item. Mark with `[x]` if completed. If an item
@@ -35,7 +44,14 @@ Follow these steps to create a Pull Request:
     - **Related Issues**: Link any issues fixed or related to this PR (e.g.,
       "Fixes #123").
 
-4.  **Create PR**: Use the `gh` CLI to create the PR. To avoid shell escaping
+5.  **Preflight Check**: Before creating the PR, run the workspace preflight
+    script to ensure all build, lint, and test checks pass.
+    ```bash
+    npm run preflight
+    ```
+    If any checks fail, address the issues before proceeding to create the PR.
+
+6.  **Create PR**: Use the `gh` CLI to create the PR. To avoid shell escaping
     issues with multi-line Markdown, write the description to a temporary file
     first.
     ```bash

.github/workflows/evals-nightly.yml

@@ -9,6 +9,10 @@ on:
         description: 'Run all evaluations (including usually passing)'
         type: 'boolean'
         default: true
+      test_name_pattern:
+        description: 'Test name pattern or file name'
+        required: false
+        type: 'string'
 
 permissions:
   contents: 'read'
@@ -22,6 +26,12 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
+        model:
+          - 'gemini-3-pro-preview'
+          - 'gemini-3-flash-preview'
+          - 'gemini-2.5-pro'
+          - 'gemini-2.5-flash'
+          - 'gemini-2.5-flash-lite'
         run_attempt: [1, 2, 3]
     steps:
       - name: 'Checkout'
@@ -43,16 +53,31 @@ jobs:
         run: 'mkdir -p evals/logs'
 
       - name: 'Run Evals'
+        continue-on-error: true
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GEMINI_MODEL: '${{ matrix.model }}'
           RUN_EVALS: "${{ github.event.inputs.run_all != 'false' }}"
-        run: 'npm run test:all_evals'
+          TEST_NAME_PATTERN: '${{ github.event.inputs.test_name_pattern }}'
+        run: |
+          CMD="npm run test:all_evals"
+          PATTERN="${{ env.TEST_NAME_PATTERN }}"
+
+          if [[ -n "$PATTERN" ]]; then
+            if [[ "$PATTERN" == *.ts || "$PATTERN" == *.js || "$PATTERN" == */* ]]; then
+              $CMD -- "$PATTERN"
+            else
+              $CMD -- -t "$PATTERN"
+            fi
+          else
+            $CMD
+          fi
 
       - name: 'Upload Logs'
         if: 'always()'
         uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
         with:
-          name: 'eval-logs-${{ matrix.run_attempt }}'
+          name: 'eval-logs-${{ matrix.model }}-${{ matrix.run_attempt }}'
           path: 'evals/logs'
           retention-days: 7
 

.github/workflows/label-workstream-rollup.yml

@@ -23,16 +23,32 @@ jobs:
             const allowedParentUrls = [
               'https://github.com/google-gemini/gemini-cli/issues/15374',
               'https://github.com/google-gemini/gemini-cli/issues/15456',
-              'https://github.com/google-gemini/gemini-cli/issues/15324'
+              'https://github.com/google-gemini/gemini-cli/issues/15324',
+              'https://github.com/google-gemini/gemini-cli/issues/17202',
+              'https://github.com/google-gemini/gemini-cli/issues/17203'
             ];
 
-            async function getIssueParent(owner, repo, number) {
+            // Single issue processing (for event triggers)
+            async function processSingleIssue(owner, repo, number) {
               const query = `
                 query($owner:String!, $repo:String!, $number:Int!) {
                   repository(owner:$owner, name:$repo) {
                     issue(number:$number) {
+                      number
                       parent {
                         url
+                        parent {
+                          url
+                          parent {
+                            url
+                            parent {
+                              url
+                              parent {
+                                url
+                              }
+                            }
+                          }
+                        }
                       }
                     }
                   }
@@ -40,55 +56,119 @@ jobs:
               `;
               try {
                 const result = await github.graphql(query, { owner, repo, number });
-                return result.repository.issue.parent ? result.repository.issue.parent.url : null;
+
+                if (!result || !result.repository || !result.repository.issue) {
+                  console.log(`Issue #${number} not found or data missing.`);
+                  return;
+                }
+
+                const issue = result.repository.issue;
+                await checkAndLabel(issue, owner, repo);
               } catch (error) {
-                console.error(`Failed to fetch parent for #${number}:`, error);
-                return null;
+                console.error(`Failed to process issue #${number}:`, error);
+                throw error; // Re-throw to be caught by main execution
               }
             }
 
-            // Determine which issues to process
-            let issuesToProcess = [];
+            // Bulk processing (for schedule/dispatch)
+            async function processAllOpenIssues(owner, repo) {
+              const query = `
+                query($owner:String!, $repo:String!, $cursor:String) {
+                  repository(owner:$owner, name:$repo) {
+                    issues(first: 100, states: OPEN, after: $cursor) {
+                      pageInfo {
+                        hasNextPage
+                        endCursor
+                      }
+                      nodes {
+                        number
+                        parent {
+                          url
+                          parent {
+                            url
+                            parent {
+                              url
+                              parent {
+                                url
+                                parent {
+                                  url
+                                }
+                              }
+                            }
+                          }
+                        }
+                      }
+                    }
+                  }
+                }
+              `;
 
-            if (context.eventName === 'issues') {
-               // Context payload for 'issues' event already has the issue object
-               issuesToProcess.push({
-                 number: context.payload.issue.number,
-                 owner: context.repo.owner,
-                 repo: context.repo.repo
-               });
-            } else {
-              // For schedule/dispatch, fetch open issues (lightweight list)
-              console.log(`Running for event: ${context.eventName}. Fetching open issues...`);
-              const openIssues = await github.paginate(github.rest.issues.listForRepo, {
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                state: 'open'
-              });
-              issuesToProcess = openIssues.map(i => ({
-                number: i.number,
-                owner: context.repo.owner,
-                repo: context.repo.repo
-              }));
+              let hasNextPage = true;
+              let cursor = null;
+
+              while (hasNextPage) {
+                try {
+                  const result = await github.graphql(query, { owner, repo, cursor });
+
+                  if (!result || !result.repository || !result.repository.issues) {
+                     console.error('Invalid response structure from GitHub API');
+                     break;
+                  }
+
+                  const issues = result.repository.issues.nodes || [];
+
+                  console.log(`Processing batch of ${issues.length} issues...`);
+                  for (const issue of issues) {
+                    await checkAndLabel(issue, owner, repo);
+                  }
+
+                  hasNextPage = result.repository.issues.pageInfo.hasNextPage;
+                  cursor = result.repository.issues.pageInfo.endCursor;
+                } catch (error) {
+                  console.error('Failed to fetch issues batch:', error);
+                  throw error; // Re-throw to be caught by main execution
+                }
+              }
             }
 
-            console.log(`Processing ${issuesToProcess.length} issue(s)...`);
+            async function checkAndLabel(issue, owner, repo) {
+              if (!issue || !issue.parent) return;
 
-            for (const issue of issuesToProcess) {
-              const parentUrl = await getIssueParent(issue.owner, issue.repo, issue.number);
+              let currentParent = issue.parent;
+              let tracedParents = [];
+              let matched = false;
 
-              if (parentUrl && allowedParentUrls.includes(parentUrl)) {
-                console.log(`SUCCESS: Issue #${issue.number} is a direct child of ${parentUrl}. Adding label.`);
-                await github.rest.issues.addLabels({
-                  owner: issue.owner,
-                  repo: issue.repo,
-                  issue_number: issue.number,
-                  labels: [labelToAdd]
-                });
+              while (currentParent) {
+                tracedParents.push(currentParent.url);
+
+                if (allowedParentUrls.includes(currentParent.url)) {
+                  console.log(`SUCCESS: Issue #${issue.number} is a descendant of ${currentParent.url}. Trace: ${tracedParents.join(' -> ')}. Adding label.`);
+                  await github.rest.issues.addLabels({
+                    owner,
+                    repo,
+                    issue_number: issue.number,
+                    labels: [labelToAdd]
+                  });
+                  matched = true;
+                  break;
+                }
+                currentParent = currentParent.parent;
+              }
+
+              if (!matched && context.eventName === 'issues') {
+                 console.log(`Issue #${issue.number} did not match any allowed workstreams. Trace: ${tracedParents.join(' -> ') || 'None'}.`);
+              }
+            }
+
+            // Main execution
+            try {
+              if (context.eventName === 'issues') {
+                console.log(`Processing single issue #${context.payload.issue.number}...`);
+                await processSingleIssue(context.repo.owner, context.repo.repo, context.payload.issue.number);
               } else {
-                 // logging only for single execution to avoid spam
-                 if (context.eventName === 'issues') {
-                    console.log(`Issue #${issue.number} parent is ${parentUrl || 'None'}. No action.`);
-                 }
+                console.log(`Running for event: ${context.eventName}. Processing all open issues...`);
+                await processAllOpenIssues(context.repo.owner, context.repo.repo);
               }
+            } catch (error) {
+              core.setFailed(`Workflow failed: ${error.message}`);
             }

GEMINI.md

@@ -1,420 +1,70 @@
-## Building and running
-
-Before submitting any changes, it is crucial to validate them by running the
-full preflight check. This command will build the repository, run all tests,
-check for type errors, and lint the code.
-
-To run the full suite of checks, execute the following command:
-
-```bash
-npm run preflight
-```
-
-This single command ensures that your changes meet all the quality gates of the
-project. While you can run the individual steps (`build`, `test`, `typecheck`,
-`lint`) separately, it is highly recommended to use `npm run preflight` to
-ensure a comprehensive validation.
-
-## Running Tests in Workspaces\*\*: To run a specific test file within a
-
-workspace, use the command:
-`npm test -w <workspace-name> -- <path/to/test-file.test.ts>`. **CRITICAL**: The
-`<path/to/test-file.test.ts>` MUST be relative to the workspace directory root,
-NOT the project root.
-
-- _Example (Core package)_:
-  `npm test -w @google/gemini-cli-core -- src/routing/modelRouterService.test.ts`
-- _Common workspaces_: `@google/gemini-cli`, `@google/gemini-cli-core`.
-
-## Writing Tests
-
-This project uses **Vitest** as its primary testing framework. When writing
-tests, aim to follow existing patterns. Key conventions include:
-
-### Test Structure and Framework
-
-- **Framework**: All tests are written using Vitest (`describe`, `it`, `expect`,
-  `vi`).
-- **File Location**: Test files (`*.test.ts` for logic, `*.test.tsx` for React
-  components) are co-located with the source files they test.
-- **Configuration**: Test environments are defined in `vitest.config.ts` files.
-- **Setup/Teardown**: Use `beforeEach` and `afterEach`. Commonly,
-  `vi.resetAllMocks()` is called in `beforeEach` and `vi.restoreAllMocks()` in
-  `afterEach`.
-
-### Mocking (`vi` from Vitest)
-
-- **ES Modules**: Mock with
-  `vi.mock('module-name', async (importOriginal) => { ... })`. Use
-  `importOriginal` for selective mocking.
-  - _Example_:
-    `vi.mock('os', async (importOriginal) => { const actual = await importOriginal(); return { ...actual, homedir: vi.fn() }; });`
-- **Mocking Order**: For critical dependencies (e.g., `os`, `fs`) that affect
-  module-level constants, place `vi.mock` at the _very top_ of the test file,
-  before other imports.
-- **Hoisting**: Use `const myMock = vi.hoisted(() => vi.fn());` if a mock
-  function needs to be defined before its use in a `vi.mock` factory.
-- **Mock Functions**: Create with `vi.fn()`. Define behavior with
-  `mockImplementation()`, `mockResolvedValue()`, or `mockRejectedValue()`.
-- **Spying**: Use `vi.spyOn(object, 'methodName')`. Restore spies with
-  `mockRestore()` in `afterEach`.
-
-### Commonly Mocked Modules
-
-- **Node.js built-ins**: `fs`, `fs/promises`, `os` (especially `os.homedir()`),
-  `path`, `child_process` (`execSync`, `spawn`).
-- **External SDKs**: `@google/genai`, `@modelcontextprotocol/sdk`.
-- **Internal Project Modules**: Dependencies from other project packages are
-  often mocked.
-
-### React Component Testing (CLI UI - Ink)
-
-- Use `render()` from `ink-testing-library`.
-- Assert output with `lastFrame()`.
-- Wrap components in necessary `Context.Provider`s.
-- Mock custom React hooks and complex child components using `vi.mock()`.
-
-### Asynchronous Testing
-
-- Use `async/await`.
-- For timers, use `vi.useFakeTimers()`, `vi.advanceTimersByTimeAsync()`,
-  `vi.runAllTimersAsync()`.
-- Test promise rejections with `await expect(promise).rejects.toThrow(...)`.
-
-### General Guidance
-
-- When adding tests, first examine existing tests to understand and conform to
-  established conventions.
-- Pay close attention to the mocks at the top of existing test files; they
-  reveal critical dependencies and how they are managed in a test environment.
-
-## Git Repo
-
-The main branch for this project is called "main"
-
-## JavaScript/TypeScript
-
-When contributing to this React, Node, and TypeScript codebase, please
-prioritize the use of plain JavaScript objects with accompanying TypeScript
-interface or type declarations over JavaScript class syntax. This approach
-offers significant advantages, especially concerning interoperability with React
-and overall code maintainability.
-
-### Preferring Plain Objects over Classes
-
-JavaScript classes, by their nature, are designed to encapsulate internal state
-and behavior. While this can be useful in some object-oriented paradigms, it
-often introduces unnecessary complexity and friction when working with React's
-component-based architecture. Here's why plain objects are preferred:
-
-- Seamless React Integration: React components thrive on explicit props and
-  state management. Classes' tendency to store internal state directly within
-  instances can make prop and state propagation harder to reason about and
-  maintain. Plain objects, on the other hand, are inherently immutable (when
-  used thoughtfully) and can be easily passed as props, simplifying data flow
-  and reducing unexpected side effects.
-
-- Reduced Boilerplate and Increased Conciseness: Classes often promote the use
-  of constructors, this binding, getters, setters, and other boilerplate that
-  can unnecessarily bloat code. TypeScript interface and type declarations
-  provide powerful static type checking without the runtime overhead or
-  verbosity of class definitions. This allows for more succinct and readable
-  code, aligning with JavaScript's strengths in functional programming.
-
-- Enhanced Readability and Predictability: Plain objects, especially when their
-  structure is clearly defined by TypeScript interfaces, are often easier to
-  read and understand. Their properties are directly accessible, and there's no
-  hidden internal state or complex inheritance chains to navigate. This
-  predictability leads to fewer bugs and a more maintainable codebase.
-
-- Simplified Immutability: While not strictly enforced, plain objects encourage
-  an immutable approach to data. When you need to modify an object, you
-  typically create a new one with the desired changes, rather than mutating the
-  original. This pattern aligns perfectly with React's reconciliation process
-  and helps prevent subtle bugs related to shared mutable state.
-
-- Better Serialization and Deserialization: Plain JavaScript objects are
-  naturally easy to serialize to JSON and deserialize back, which is a common
-  requirement in web development (e.g., for API communication or local storage).
-  Classes, with their methods and prototypes, can complicate this process.
-
-### Embracing ES Module Syntax for Encapsulation
-
-Rather than relying on Java-esque private or public class members, which can be
-verbose and sometimes limit flexibility, we strongly prefer leveraging ES module
-syntax (`import`/`export`) for encapsulating private and public APIs.
-
-- Clearer Public API Definition: With ES modules, anything that is exported is
-  part of the public API of that module, while anything not exported is
-  inherently private to that module. This provides a very clear and explicit way
-  to define what parts of your code are meant to be consumed by other modules.
-
-- Enhanced Testability (Without Exposing Internals): By default, unexported
-  functions or variables are not accessible from outside the module. This
-  encourages you to test the public API of your modules, rather than their
-  internal implementation details. If you find yourself needing to spy on or
-  stub an unexported function for testing purposes, it's often a "code smell"
-  indicating that the function might be a good candidate for extraction into its
-  own separate, testable module with a well-defined public API. This promotes a
-  more robust and maintainable testing strategy.
-
-- Reduced Coupling: Explicitly defined module boundaries through import/export
-  help reduce coupling between different parts of your codebase. This makes it
-  easier to refactor, debug, and understand individual components in isolation.
-
-### Avoiding `any` Types and Type Assertions; Preferring `unknown`
-
-TypeScript's power lies in its ability to provide static type checking, catching
-potential errors before your code runs. To fully leverage this, it's crucial to
-avoid the `any` type and be judicious with type assertions.
-
-- **The Dangers of `any`**: Using any effectively opts out of TypeScript's type
-  checking for that particular variable or expression. While it might seem
-  convenient in the short term, it introduces significant risks:
-  - **Loss of Type Safety**: You lose all the benefits of type checking, making
-    it easy to introduce runtime errors that TypeScript would otherwise have
-    caught.
-  - **Reduced Readability and Maintainability**: Code with `any` types is harder
-    to understand and maintain, as the expected type of data is no longer
-    explicitly defined.
-  - **Masking Underlying Issues**: Often, the need for any indicates a deeper
-    problem in the design of your code or the way you're interacting with
-    external libraries. It's a sign that you might need to refine your types or
-    refactor your code.
-
-- **Preferring `unknown` over `any`**: When you absolutely cannot determine the
-  type of a value at compile time, and you're tempted to reach for any, consider
-  using unknown instead. unknown is a type-safe counterpart to any. While a
-  variable of type unknown can hold any value, you must perform type narrowing
-  (e.g., using typeof or instanceof checks, or a type assertion) before you can
-  perform any operations on it. This forces you to handle the unknown type
-  explicitly, preventing accidental runtime errors.
-
-  ```ts
-  function processValue(value: unknown) {
-    if (typeof value === 'string') {
-      // value is now safely a string
-      console.log(value.toUpperCase());
-    } else if (typeof value === 'number') {
-      // value is now safely a number
-      console.log(value * 2);
-    }
-    // Without narrowing, you cannot access properties or methods on 'value'
-    // console.log(value.someProperty); // Error: Object is of type 'unknown'.
-  }
-  ```
-
-- **Type Assertions (`as Type`) - Use with Caution**: Type assertions tell the
-  TypeScript compiler, "Trust me, I know what I'm doing; this is definitely of
-  this type." While there are legitimate use cases (e.g., when dealing with
-  external libraries that don't have perfect type definitions, or when you have
-  more information than the compiler), they should be used sparingly and with
-  extreme caution.
-  - **Bypassing Type Checking**: Like `any`, type assertions bypass TypeScript's
-    safety checks. If your assertion is incorrect, you introduce a runtime error
-    that TypeScript would not have warned you about.
-  - **Code Smell in Testing**: A common scenario where `any` or type assertions
-    might be tempting is when trying to test "private" implementation details
-    (e.g., spying on or stubbing an unexported function within a module). This
-    is a strong indication of a "code smell" in your testing strategy and
-    potentially your code structure. Instead of trying to force access to
-    private internals, consider whether those internal details should be
-    refactored into a separate module with a well-defined public API. This makes
-    them inherently testable without compromising encapsulation.
-
-### Type narrowing `switch` clauses
-
-Use the `checkExhaustive` helper in the default clause of a switch statement.
-This will ensure that all of the possible options within the value or
-enumeration are used.
-
-This helper method can be found in `packages/cli/src/utils/checks.ts`
-
-### Embracing JavaScript's Array Operators
-
-To further enhance code cleanliness and promote safe functional programming
-practices, leverage JavaScript's rich set of array operators as much as
-possible. Methods like `.map()`, `.filter()`, `.reduce()`, `.slice()`,
-`.sort()`, and others are incredibly powerful for transforming and manipulating
-data collections in an immutable and declarative way.
-
-Using these operators:
-
-- Promotes Immutability: Most array operators return new arrays, leaving the
-  original array untouched. This functional approach helps prevent unintended
-  side effects and makes your code more predictable.
-- Improves Readability: Chaining array operators often lead to more concise and
-  expressive code than traditional for loops or imperative logic. The intent of
-  the operation is clear at a glance.
-- Facilitates Functional Programming: These operators are cornerstones of
-  functional programming, encouraging the creation of pure functions that take
-  inputs and produce outputs without causing side effects. This paradigm is
-  highly beneficial for writing robust and testable code that pairs well with
-  React.
-
-By consistently applying these principles, we can maintain a codebase that is
-not only efficient and performant but also a joy to work with, both now and in
-the future.
-
-## React (mirrored and adjusted from [react-mcp-server](https://github.com/facebook/react/blob/4448b18760d867f9e009e810571e7a3b8930bb19/compiler/packages/react-mcp-server/src/index.ts#L376C1-L441C94))
-
-### Role
-
-You are a React assistant that helps users write more efficient and optimizable
-React code. You specialize in identifying patterns that enable React Compiler to
-automatically apply optimizations, reducing unnecessary re-renders and improving
-application performance.
-
-### Follow these guidelines in all code you produce and suggest
-
-Use functional components with Hooks: Do not generate class components or use
-old lifecycle methods. Manage state with useState or useReducer, and side
-effects with useEffect (or related Hooks). Always prefer functions and Hooks for
-any new component logic.
-
-Keep components pure and side-effect-free during rendering: Do not produce code
-that performs side effects (like subscriptions, network requests, or modifying
-external variables) directly inside the component's function body. Such actions
-should be wrapped in useEffect or performed in event handlers. Ensure your
-render logic is a pure function of props and state.
-
-Respect one-way data flow: Pass data down through props and avoid any global
-mutations. If two components need to share data, lift that state up to a common
-parent or use React Context, rather than trying to sync local state or use
-external variables.
-
-Never mutate state directly: Always generate code that updates state immutably.
-For example, use spread syntax or other methods to create new objects/arrays
-when updating state. Do not use assignments like state.someValue = ... or array
-mutations like array.push() on state variables. Use the state setter (setState
-from useState, etc.) to update state.
-
-Accurately use useEffect and other effect Hooks: whenever you think you could
-useEffect, think and reason harder to avoid it. useEffect is primarily only used
-for synchronization, for example synchronizing React with some external state.
-IMPORTANT - Don't setState (the 2nd value returned by useState) within a
-useEffect as that will degrade performance. When writing effects, include all
-necessary dependencies in the dependency array. Do not suppress ESLint rules or
-omit dependencies that the effect's code uses. Structure the effect callbacks to
-handle changing values properly (e.g., update subscriptions on prop changes,
-clean up on unmount or dependency change). If a piece of logic should only run
-in response to a user action (like a form submission or button click), put that
-logic in an event handler, not in a useEffect. Where possible, useEffects should
-return a cleanup function.
-
-Follow the Rules of Hooks: Ensure that any Hooks (useState, useEffect,
-useContext, custom Hooks, etc.) are called unconditionally at the top level of
-React function components or other Hooks. Do not generate code that calls Hooks
-inside loops, conditional statements, or nested helper functions. Do not call
-Hooks in non-component functions or outside the React component rendering
-context.
-
-Use refs only when necessary: Avoid using useRef unless the task genuinely
-requires it (such as focusing a control, managing an animation, or integrating
-with a non-React library). Do not use refs to store application state that
-should be reactive. If you do use refs, never write to or read from ref.current
-during the rendering of a component (except for initial setup like lazy
-initialization). Any ref usage should not affect the rendered output directly.
-
-Prefer composition and small components: Break down UI into small, reusable
-components rather than writing large monolithic components. The code you
-generate should promote clarity and reusability by composing components
-together. Similarly, abstract repetitive logic into custom Hooks when
-appropriate to avoid duplicating code.
-
-Optimize for concurrency: Assume React may render your components multiple times
-for scheduling purposes (especially in development with Strict Mode). Write code
-that remains correct even if the component function runs more than once. For
-instance, avoid side effects in the component body and use functional state
-updates (e.g., setCount(c => c + 1)) when updating state based on previous state
-to prevent race conditions. Always include cleanup functions in effects that
-subscribe to external resources. Don't write useEffects for "do this when this
-changes" side effects. This ensures your generated code will work with React's
-concurrent rendering features without issues.
-
-Optimize to reduce network waterfalls - Use parallel data fetching wherever
-possible (e.g., start multiple requests at once rather than one after another).
-Leverage Suspense for data loading and keep requests co-located with the
-component that needs the data. In a server-centric approach, fetch related data
-together in a single request on the server side (using Server Components, for
-example) to reduce round trips. Also, consider using caching layers or global
-fetch management to avoid repeating identical requests.
-
-Rely on React Compiler - useMemo, useCallback, and React.memo can be omitted if
-React Compiler is enabled. Avoid premature optimization with manual memoization.
-Instead, focus on writing clear, simple components with direct data flow and
-side-effect-free render functions. Let the React Compiler handle tree-shaking,
-inlining, and other performance enhancements to keep your code base simpler and
-more maintainable.
-
-Design for a good user experience - Provide clear, minimal, and non-blocking UI
-states. When data is loading, show lightweight placeholders (e.g., skeleton
-screens) rather than intrusive spinners everywhere. Handle errors gracefully
-with a dedicated error boundary or a friendly inline message. Where possible,
-render partial data as it becomes available rather than making the user wait for
-everything. Suspense allows you to declare the loading states in your component
-tree in a natural way, preventing “flash” states and improving perceived
-performance.
-
-### Process
-
-1. Analyze the user's code for optimization opportunities:
-   - Check for React anti-patterns that prevent compiler optimization
-   - Look for component structure issues that limit compiler effectiveness
-   - Think about each suggestion you are making and consult React docs for best
-     practices
-
-2. Provide actionable guidance:
-   - Explain specific code changes with clear reasoning
-   - Show before/after examples when suggesting changes
-   - Only suggest changes that meaningfully improve optimization potential
-
-### Optimization Guidelines
-
-- State updates should be structured to enable granular updates
-- Side effects should be isolated and dependencies clearly defined
-
-## Documentation guidelines
-
-When working in the `/docs` directory, follow the guidelines in this section:
-
-- **Role:** You are an expert technical writer and AI assistant for contributors
-  to Gemini CLI. Produce professional, accurate, and consistent documentation to
-  guide users of Gemini CLI.
-- **Technical Accuracy:** Do not invent facts, commands, code, API names, or
-  output. All technical information specific to Gemini CLI must be based on code
-  found within this directory and its subdirectories.
-- **Style Authority:** Your source for writing guidance and style is the
-  "Documentation contribution process" section in the root directory's
-  `CONTRIBUTING.md` file, as well as any guidelines provided this section.
-- **Information Architecture Consideration:** Before proposing documentation
-  changes, consider the information architecture. If a change adds significant
-  new content to existing documents, evaluate if creating a new, more focused
-  page or changes to `sidebar.json` would provide a better user experience.
-- **Proactive User Consideration:** The user experience should be a primary
-  concern when making changes to documentation. Aim to fill gaps in existing
-  knowledge whenever possible while keeping documentation concise and easy for
-  users to understand. If changes might hinder user understanding or
-  accessibility, proactively raise these concerns and propose alternatives.
-
-## Comments policy
-
-Only write high-value comments if at all. Avoid talking to the user through
-comments.
-
-## Logging and Error Handling
-
-- **Avoid Console Statements:** Do not use `console.log`, `console.error`, or
-  similar methods directly.
-- **Non-User-Facing Logs:** For developer-facing debug messages, use
-  `debugLogger` (from `@google/gemini-cli-core`).
-- **User-Facing Feedback:** To surface errors or warnings to the user, use
-  `coreEvents.emitFeedback` (from `@google/gemini-cli-core`).
-
-## General requirements
-
-- If there is something you do not understand or is ambiguous, seek confirmation
-  or clarification from the user before making changes based on assumptions.
-- Use hyphens instead of underscores in flag names (e.g. `my-flag` instead of
-  `my_flag`).
-- Always refer to Gemini CLI as `Gemini CLI`, never `the Gemini CLI`.
+# Gemini CLI Project Context
+
+Gemini CLI is an open-source AI agent that brings the power of Gemini directly
+into the terminal. It is designed to be a terminal-first, extensible, and
+powerful tool for developers.
+
+## Project Overview
+
+- **Purpose:** Provide a seamless terminal interface for Gemini models,
+  supporting code understanding, generation, automation, and integration via MCP
+  (Model Context Protocol).
+- **Main Technologies:**
+  - **Runtime:** Node.js (>=20.0.0, recommended ~20.19.0 for development)
+  - **Language:** TypeScript
+  - **UI Framework:** React (using [Ink](https://github.com/vadimdemedes/ink)
+    for CLI rendering)
+  - **Testing:** Vitest
+  - **Bundling:** esbuild
+  - **Linting/Formatting:** ESLint, Prettier
+- **Architecture:** Monorepo structure using npm workspaces.
+  - `packages/cli`: User-facing terminal UI, input processing, and display
+    rendering.
+  - `packages/core`: Backend logic, Gemini API orchestration, prompt
+    construction, and tool execution.
+  - `packages/core/src/tools/`: Built-in tools for file system, shell, and web
+    operations.
+  - `packages/a2a-server`: Experimental Agent-to-Agent server.
+  - `packages/vscode-ide-companion`: VS Code extension pairing with the CLI.
+
+## Building and Running
+
+- **Install Dependencies:** `npm install`
+- **Build All:** `npm run build:all` (Builds packages, sandbox, and VS Code
+  companion)
+- **Build Packages:** `npm run build`
+- **Run in Development:** `npm run start`
+- **Run in Debug Mode:** `npm run debug` (Enables Node.js inspector)
+- **Bundle Project:** `npm run bundle`
+- **Clean Artifacts:** `npm run clean`
+
+## Testing and Quality
+
+- **Test Commands:**
+  - **Unit (All):** `npm run test`
+  - **Integration (E2E):** `npm run test:e2e`
+  - **Workspace-Specific:** `npm test -w <pkg> -- <path>` (Note: `<path>` must
+    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.)
+- **Individual Checks:** `npm run lint` / `npm run format` / `npm run typecheck`
+
+## Development Conventions
+
+- **Contributions:** Follow the process outlined in `CONTRIBUTING.md`. Requires
+  signing the Google CLA.
+- **Pull Requests:** Keep PRs small, focused, and linked to an existing issue.
+- **Commit Messages:** Follow the
+  [Conventional Commits](https://www.conventionalcommits.org/) standard.
+- **Coding Style:** Adhere to existing patterns in `packages/cli` (React/Ink)
+  and `packages/core` (Backend logic).
+- **Imports:** Use specific imports and avoid restricted relative imports
+  between packages (enforced by ESLint).
+
+## Documentation
+
+- Suggest documentation updates when code changes render existing documentation
+  obsolete or incomplete.
+- Located in the `docs/` directory.
+- Use the `docs-writer` skill.

docs/changelogs/index.md

@@ -18,6 +18,93 @@ on GitHub.
 | [Preview](preview.md) | Experimental features ready for early feedback. |
 | [Stable](latest.md)   | Stable, recommended for general use.            |
 
+## Announcements: v0.25.0 - 2026-01-20
+
+- **Skills and Agents Improvements:** We've enhanced the `activate_skill` tool,
+  added a new `pr-creator` skill
+  ([#16232](https://github.com/google-gemini/gemini-cli/pull/16232) by
+  [@NTaylorMullen](https://github.com/NTaylorMullen)), enabled skills by
+  default, improved the `cli_help` agent
+  ([#16100](https://github.com/google-gemini/gemini-cli/pull/16100) by
+  [@scidomino](https://github.com/scidomino)), and added a new `/agents refresh`
+  command ([#16204](https://github.com/google-gemini/gemini-cli/pull/16204) by
+  [@joshualitt](https://github.com/joshualitt)).
+- **UI/UX Refinements:** You'll notice more transparent feedback for skills
+  ([#15954](https://github.com/google-gemini/gemini-cli/pull/15954) by
+  [@NTaylorMullen](https://github.com/NTaylorMullen)), the ability to switch
+  focus between the shell and input with Tab
+  ([#14332](https://github.com/google-gemini/gemini-cli/pull/14332) by
+  [@jacob314](https://github.com/jacob314)), and dynamic terminal tab titles
+  ([#16378](https://github.com/google-gemini/gemini-cli/pull/16378) by
+  [@NTaylorMullen](https://github.com/NTaylorMullen)).
+- **Core Functionality & Performance:** This release includes support for
+  built-in agent skills
+  ([#16045](https://github.com/google-gemini/gemini-cli/pull/16045) by
+  [@NTaylorMullen](https://github.com/NTaylorMullen)), refined Gemini 3 system
+  instructions ([#16139](https://github.com/google-gemini/gemini-cli/pull/16139)
+  by [@NTaylorMullen](https://github.com/NTaylorMullen)), caching for ignore
+  instances to improve performance
+  ([#16185](https://github.com/google-gemini/gemini-cli/pull/16185) by
+  [@EricRahm](https://github.com/EricRahm)), and enhanced retry mechanisms
+  ([#16489](https://github.com/google-gemini/gemini-cli/pull/16489) by
+  [@sehoon38](https://github.com/sehoon38)).
+- **Bug Fixes and Stability:** We've squashed numerous bugs across the CLI,
+  core, and workflows, addressing issues with subagent delegation, unicode
+  character crashes, and sticky header regressions.
+
+## Announcements: v0.24.0 - 2026-01-14
+
+- **Agent Skills:** We've introduced significant advancements in Agent Skills.
+  This includes initial documentation and tutorials to help you get started,
+  alongside enhanced support for remote agents, allowing for more distributed
+  and powerful automation within Gemini CLI.
+  ([#15869](https://github.com/google-gemini/gemini-cli/pull/15869) by
+  [@NTaylorMullen](https://github.com/NTaylorMullen)),
+  ([#16013](https://github.com/google-gemini/gemini-cli/pull/16013) by
+  [@adamweidman](https://github.com/adamweidman))
+- **Improved UI/UX:** The user interface has received several updates, featuring
+  visual indicators for hook execution, a more refined display for settings, and
+  the ability to use the Tab key to effortlessly switch focus between the shell
+  and input areas.
+  ([#15408](https://github.com/google-gemini/gemini-cli/pull/15408) by
+  [@abhipatel12](https://github.com/abhipatel12)),
+  ([#14332](https://github.com/google-gemini/gemini-cli/pull/14332) by
+  [@galz10](https://github.com/galz10))
+- **Enhanced Security:** Security has been a major focus, with default folder
+  trust now set to untrusted for increased safety. The Policy Engine has been
+  improved to allow specific modes in user and administrator policies, and
+  granular allowlisting for shell commands has been implemented, providing finer
+  control over tool execution.
+  ([#15943](https://github.com/google-gemini/gemini-cli/pull/15943) by
+  [@galz10](https://github.com/galz10)),
+  ([#15977](https://github.com/google-gemini/gemini-cli/pull/15977) by
+  [@NTaylorMullen](https://github.com/NTaylorMullen))
+- **Core Functionality:** This release includes a mandatory MessageBus
+  injection, marking Phase 3 of a hard migration to a more robust internal
+  communication system. We've also added support for built-in skills with the
+  CLI itself, and enhanced model routing to effectively utilize subagents.
+  ([#15776](https://github.com/google-gemini/gemini-cli/pull/15776) by
+  [@abhipatel12](https://github.com/abhipatel12)),
+  ([#16300](https://github.com/google-gemini/gemini-cli/pull/16300) by
+  [@NTaylorMullen](https://github.com/NTaylorMullen))
+- **Terminal Features:** Terminal interactions are more seamless with new
+  features like OSC 52 paste support, along with fixes for Windows clipboard
+  paste issues and general improvements to pasting in Windows terminals.
+  ([#15336](https://github.com/google-gemini/gemini-cli/pull/15336) by
+  [@scidomino](https://github.com/scidomino)),
+  ([#15932](https://github.com/google-gemini/gemini-cli/pull/15932) by
+  [@scidomino](https://github.com/scidomino))
+- **New Commands:** To manage the new features, we've added several new
+  commands: `/agents refresh` to update agent configurations, `/skills reload`
+  to refresh skill definitions, and `/skills install/uninstall` for easier
+  management of your Agent Skills.
+  ([#16204](https://github.com/google-gemini/gemini-cli/pull/16204) by
+  [@NTaylorMullen](https://github.com/NTaylorMullen)),
+  ([#15865](https://github.com/google-gemini/gemini-cli/pull/15865) by
+  [@NTaylorMullen](https://github.com/NTaylorMullen)),
+  ([#16377](https://github.com/google-gemini/gemini-cli/pull/16377) by
+  [@NTaylorMullen](https://github.com/NTaylorMullen))
+
 ## Announcements: v0.23.0 - 2026-01-07
 
 - 🎉 **Experimental Agent Skills Support in Preview:** Gemini CLI now supports

docs/changelogs/latest.md

@@ -1,6 +1,6 @@
-# Latest stable release: v0.23.0
+# Latest stable release: v0.25.0
 
-Released: January 6, 2026
+Released: January 20, 2026
 
 For most users, our latest stable release is the recommended release. Install
 the latest stable version with:
@@ -11,155 +11,360 @@ npm install -g @google/gemini-cli
 
 ## Highlights
 
-- **Gemini CLI wrapped:** Run `npx gemini-wrapped` to visualize your usage
-  stats, top models, languages, and more!
-- **Windows clipboard image support:** Windows users can now paste images
-  directly from their clipboard into the CLI using `Alt`+`V`.
-  ([pr](https://github.com/google-gemini/gemini-cli/pull/13997) by
-  [@sgeraldes](https://github.com/sgeraldes))
-- **Terminal background color detection:** Automatically optimizes your
-  terminal's background color to select compatible themes and provide
-  accessibility warnings.
-  ([pr](https://github.com/google-gemini/gemini-cli/pull/15132) by
-  [@jacob314](https://github.com/jacob314))
-- **Session logout:** Use the new `/logout` command to instantly clear
-  credentials and reset your authentication state for seamless account
-  switching. ([pr](https://github.com/google-gemini/gemini-cli/pull/13383) by
-  [@CN-Scars](https://github.com/CN-Scars))
+- **Skills and Agents Improvements:** Enhanced `activate_skill` tool, new
+  `pr-creator` skill, default enablement of skills, improved `cli_help` agent,
+  and a new `/agents refresh` command.
+- **UI/UX Refinements:** Transparent feedback for skills, ability to switch
+  focus between shell and input with Tab, and dynamic terminal tab titles.
+- **Core Functionality & Performance:** Support for built-in agent skills,
+  refined Gemini 3 system instructions, caching ignore instances for
+  performance, and improved retry mechanisms.
+- **Bug Fixes and Stability:** Numerous bug fixes across the CLI, core, and
+  workflows, including issues with subagent delegation, unicode character
+  crashes, and sticky header regressions.
 
-## What's changed
+## What's Changed
 
-- Code assist service metrics. by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/15024
-- chore/release: bump version to 0.21.0-nightly.20251216.bb0c0d8ee by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15121
-- Docs by @Roaimkhan in https://github.com/google-gemini/gemini-cli/pull/15103
-- Use official ACP SDK and support HTTP/SSE based MCP servers by @SteffenDE in
-  https://github.com/google-gemini/gemini-cli/pull/13856
-- Remove foreground for themes other than shades of purple and holiday. by
-  @jacob314 in https://github.com/google-gemini/gemini-cli/pull/14606
-- chore: remove repo specific tips by @jackwotherspoon in
-  https://github.com/google-gemini/gemini-cli/pull/15164
-- chore: remove user query from footer in debug mode by @jackwotherspoon in
-  https://github.com/google-gemini/gemini-cli/pull/15169
-- Disallow unnecessary awaits. by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/15172
-- Add one to the padding in settings dialog to avoid flicker. by @jacob314 in
-  https://github.com/google-gemini/gemini-cli/pull/15173
-- feat(core): introduce remote agent infrastructure and rename local executor by
-  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15110
-- feat(cli): Add `/auth logout` command to clear credentials and auth state by
-  @CN-Scars in https://github.com/google-gemini/gemini-cli/pull/13383
-- (fix) Automated pr labeller by @DaanVersavel in
-  https://github.com/google-gemini/gemini-cli/pull/14885
-- feat: launch Gemini 3 Flash in Gemini CLI ⚡️⚡️⚡️ by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15196
-- Refactor: Migrate console.error in ripGrep.ts to debugLogger by @Adib234 in
-  https://github.com/google-gemini/gemini-cli/pull/15201
-- chore: update a2a-js to 0.3.7 by @adamfweidman in
-  https://github.com/google-gemini/gemini-cli/pull/15197
-- chore(core): remove redundant isModelAvailabilityServiceEnabled toggle and
-  clean up dead code by @adamfweidman in
-  https://github.com/google-gemini/gemini-cli/pull/15207
-- feat(core): Late resolve `GenerateContentConfig`s and reduce mutation. by
-  @joshualitt in https://github.com/google-gemini/gemini-cli/pull/14920
-- Respect previewFeatures value from the remote flag if undefined by @sehoon38
-  in https://github.com/google-gemini/gemini-cli/pull/15214
-- feat(ui): add Windows clipboard image support and Alt+V paste workaround by
-  @jacob314 in https://github.com/google-gemini/gemini-cli/pull/15218
-- chore(core): remove legacy fallback flags and migrate loop detection by
-  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15213
-- fix(ui): Prevent eager slash command completion hiding sibling commands by
-  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15224
-- Docs: Update Changelog for Dec 17, 2025 by @jkcinouye in
-  https://github.com/google-gemini/gemini-cli/pull/15204
-- Code Assist backend telemetry for user accept/reject of suggestions by
-  @gundermanc in https://github.com/google-gemini/gemini-cli/pull/15206
-- fix(cli): correct initial history length handling for chat commands by
-  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15223
-- chore/release: bump version to 0.21.0-nightly.20251218.739c02bd6 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15231
-- Change detailed model stats to use a new shared Table class to resolve
-  robustness issues. by @jacob314 in
-  https://github.com/google-gemini/gemini-cli/pull/15208
-- feat: add agent toml parser by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15112
-- Add core tool that adds all context from the core package. by @jacob314 in
-  https://github.com/google-gemini/gemini-cli/pull/15238
-- (docs): Add reference section to hooks documentation by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15159
-- feat(hooks): add support for friendly names and descriptions by @abhipatel12
-  in https://github.com/google-gemini/gemini-cli/pull/15174
-- feat: Detect background color by @jacob314 in
-  https://github.com/google-gemini/gemini-cli/pull/15132
-- add 3.0 to allowed sensitive keywords by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15276
-- feat: Pass additional environment variables to shell execution by @galz10 in
-  https://github.com/google-gemini/gemini-cli/pull/15160
-- Remove unused code by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15290
-- Handle all 429 as retryableQuotaError by @sehoon38 in
-  https://github.com/google-gemini/gemini-cli/pull/15288
-- Remove unnecessary dependencies by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15291
-- fix: prevent infinite loop in prompt completion on error by @galz10 in
-  https://github.com/google-gemini/gemini-cli/pull/14548
-- fix(ui): show command suggestions even on perfect match and sort them by
-  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15287
-- feat(hooks): reduce log verbosity and improve error reporting in UI by
-  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15297
-- feat: simplify tool confirmation labels for better UX by @NTaylorMullen in
-  https://github.com/google-gemini/gemini-cli/pull/15296
-- chore/release: bump version to 0.21.0-nightly.20251219.70696e364 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15301
-- feat(core): Implement JIT context memory loading and UI sync by @SandyTao520
-  in https://github.com/google-gemini/gemini-cli/pull/14469
-- feat(ui): Put "Allow for all future sessions" behind a setting off by default.
-  by @jacob314 in https://github.com/google-gemini/gemini-cli/pull/15322
-- fix(cli):change the placeholder of input during the shell mode by
-  @JayadityaGit in https://github.com/google-gemini/gemini-cli/pull/15135
-- Validate OAuth resource parameter matches MCP server URL by @galz10 in
-  https://github.com/google-gemini/gemini-cli/pull/15289
-- docs(cli): add System Prompt Override (GEMINI_SYSTEM_MD) by @ashmod in
-  https://github.com/google-gemini/gemini-cli/pull/9515
-- more robust command parsing logs by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15339
-- Introspection agent demo by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15232
-- fix(core): sanitize hook command expansion and prevent injection by
-  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15343
-- fix(folder trust): add validation for trusted folder level by @adamfweidman in
-  https://github.com/google-gemini/gemini-cli/pull/12215
-- fix(cli): fix right border overflow in trust dialogs by @galz10 in
-  https://github.com/google-gemini/gemini-cli/pull/15350
-- fix(policy): fix bug where accepting-edits continued after it was turned off
-  by @jacob314 in https://github.com/google-gemini/gemini-cli/pull/15351
-- fix: prevent infinite relaunch loop when --resume fails (#14941) by @Ying-xi
-  in https://github.com/google-gemini/gemini-cli/pull/14951
-- chore/release: bump version to 0.21.0-nightly.20251220.41a1a3eed by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15352
-- feat(telemetry): add clearcut logging for hooks by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15405
-- fix(core): Add `.geminiignore` support to SearchText tool by @xyrolle in
-  https://github.com/google-gemini/gemini-cli/pull/13763
-- fix(patch): cherry-pick 0843d9a to release/v0.23.0-preview.0-pr-15443 to patch
-  version v0.23.0-preview.0 and create version 0.23.0-preview.1 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15445
-- fix(patch): cherry-pick 9cdb267 to release/v0.23.0-preview.1-pr-15494 to patch
-  version v0.23.0-preview.1 and create version 0.23.0-preview.2 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15592
-- fix(patch): cherry-pick 37be162 to release/v0.23.0-preview.2-pr-15601 to patch
-  version v0.23.0-preview.2 and create version 0.23.0-preview.3 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15603
-- fix(patch): cherry-pick 07e597d to release/v0.23.0-preview.3-pr-15684
-  [CONFLICTS] by @gemini-cli-robot in
-  https://github.com/google-gemini/gemini-cli/pull/15734
-- fix(patch): cherry-pick c31f053 to release/v0.23.0-preview.4-pr-16004 to patch
-  version v0.23.0-preview.4 and create version 0.23.0-preview.5 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/16027
-- fix(patch): cherry-pick 788bb04 to release/v0.23.0-preview.5-pr-15817
-  [CONFLICTS] by @gemini-cli-robot in
-  https://github.com/google-gemini/gemini-cli/pull/16038
+- feat(core): improve activate_skill tool and use lowercase XML tags by
+  @NTaylorMullen in
+  [#16009](https://github.com/google-gemini/gemini-cli/pull/16009)
+- Add initiation method telemetry property by @gundermanc in
+  [#15818](https://github.com/google-gemini/gemini-cli/pull/15818)
+- chore(release): bump version to 0.25.0-nightly.20260107.59a18e710 by
+  @gemini-cli-robot in
+  [#16048](https://github.com/google-gemini/gemini-cli/pull/16048)
+- Hx support by @kevinfjiang in
+  [#16032](https://github.com/google-gemini/gemini-cli/pull/16032)
+- [Skills] Foundation: Centralize management logic and feedback rendering by
+  @NTaylorMullen in
+  [#15952](https://github.com/google-gemini/gemini-cli/pull/15952)
+- Introduce GEMINI_CLI_HOME for strict test isolation by @NTaylorMullen in
+  [#15907](https://github.com/google-gemini/gemini-cli/pull/15907)
+- [Skills] Multi-scope skill enablement and shadowing fix by @NTaylorMullen in
+  [#15953](https://github.com/google-gemini/gemini-cli/pull/15953)
+- policy: extract legacy policy from core tool scheduler to policy engine by
+  @abhipatel12 in
+  [#15902](https://github.com/google-gemini/gemini-cli/pull/15902)
+- Enhance TestRig with process management and timeouts by @NTaylorMullen in
+  [#15908](https://github.com/google-gemini/gemini-cli/pull/15908)
+- Update troubleshooting doc for UNABLE_TO_GET_ISSUER_CERT_LOCALLY by @sehoon38
+  in [#16069](https://github.com/google-gemini/gemini-cli/pull/16069)
+- Add keytar to dependencies by @chrstnb in
+  [#15928](https://github.com/google-gemini/gemini-cli/pull/15928)
+- Simplify extension settings command by @chrstnb in
+  [#16001](https://github.com/google-gemini/gemini-cli/pull/16001)
+- feat(admin): implement extensions disabled by @skeshive in
+  [#16024](https://github.com/google-gemini/gemini-cli/pull/16024)
+- Core data structure updates for Rewind functionality by @Adib234 in
+  [#15714](https://github.com/google-gemini/gemini-cli/pull/15714)
+- feat(hooks): simplify hook firing with HookSystem wrapper methods by @ved015
+  in [#15982](https://github.com/google-gemini/gemini-cli/pull/15982)
+- Add exp.gws_experiment field to LogEventEntry by @gsquared94 in
+  [#16062](https://github.com/google-gemini/gemini-cli/pull/16062)
+- Revert "feat(admin): implement extensions disabled" by @chrstnb in
+  [#16082](https://github.com/google-gemini/gemini-cli/pull/16082)
+- feat(core): Decouple enabling hooks UI from subsystem. by @joshualitt in
+  [#16074](https://github.com/google-gemini/gemini-cli/pull/16074)
+- docs: add docs for hooks + extensions by @abhipatel12 in
+  [#16073](https://github.com/google-gemini/gemini-cli/pull/16073)
+- feat(core): Preliminary changes for subagent model routing. by @joshualitt in
+  [#16035](https://github.com/google-gemini/gemini-cli/pull/16035)
+- Optimize CI workflow: Parallelize jobs and cache linters by @NTaylorMullen in
+  [#16054](https://github.com/google-gemini/gemini-cli/pull/16054)
+- Add option to fallback for capacity errors in ProQuotaDi… by @sehoon38 in
+  [#16050](https://github.com/google-gemini/gemini-cli/pull/16050)
+- feat: add confirmation details support + jsonrpc vs http rest support by
+  @adamfweidman in
+  [#16079](https://github.com/google-gemini/gemini-cli/pull/16079)
+- fix(workflows): fix and limit labels for pr-triage.sh script by @jacob314 in
+  [#16096](https://github.com/google-gemini/gemini-cli/pull/16096)
+- Fix and rename introspection agent -> cli help agent by @scidomino in
+  [#16097](https://github.com/google-gemini/gemini-cli/pull/16097)
+- Docs: Changelogs update 20260105 by @jkcinouye in
+  [#15937](https://github.com/google-gemini/gemini-cli/pull/15937)
+- enable cli_help agent by default by @scidomino in
+  [#16100](https://github.com/google-gemini/gemini-cli/pull/16100)
+- Optimize json-output tests with mock responses by @NTaylorMullen in
+  [#16102](https://github.com/google-gemini/gemini-cli/pull/16102)
+- Fix CI for forks by @scidomino in
+  [#16113](https://github.com/google-gemini/gemini-cli/pull/16113)
+- Reduce nags about PRs that reference issues but don't fix them. by @jacob314
+  in [#16112](https://github.com/google-gemini/gemini-cli/pull/16112)
+- feat(cli): add filepath autosuggestion after slash commands by @jasmeetsb in
+  [#14738](https://github.com/google-gemini/gemini-cli/pull/14738)
+- Add upgrade option for paid users by @cayden-google in
+  [#15978](https://github.com/google-gemini/gemini-cli/pull/15978)
+- [Skills] UX Polishing: Transparent feedback and CLI refinements by
+  @NTaylorMullen in
+  [#15954](https://github.com/google-gemini/gemini-cli/pull/15954)
+- Polish: Move 'Failed to load skills' warning to debug logs by @NTaylorMullen
+  in [#16142](https://github.com/google-gemini/gemini-cli/pull/16142)
+- feat(cli): export chat history in /bug and prefill GitHub issue by
+  @NTaylorMullen in
+  [#16115](https://github.com/google-gemini/gemini-cli/pull/16115)
+- bug(core): fix issue with overrides to bases. by @joshualitt in
+  [#15255](https://github.com/google-gemini/gemini-cli/pull/15255)
+- enableInteractiveShell for external tooling relying on a2a server by
+  @DavidAPierce in
+  [#16080](https://github.com/google-gemini/gemini-cli/pull/16080)
+- Reapply "feat(admin): implement extensions disabled" (#16082) by @skeshive in
+  [#16109](https://github.com/google-gemini/gemini-cli/pull/16109)
+- bug(core): Fix spewie getter in hookTranslator.ts by @joshualitt in
+  [#16108](https://github.com/google-gemini/gemini-cli/pull/16108)
+- feat(hooks): add mcp_context to BeforeTool and AfterTool hook inputs by @vrv
+  in [#15656](https://github.com/google-gemini/gemini-cli/pull/15656)
+- Add extension linking capabilities in cli by @kevinjwang1 in
+  [#16040](https://github.com/google-gemini/gemini-cli/pull/16040)
+- Update the page's title to be consistent and show in site. by @kschaab in
+  [#16174](https://github.com/google-gemini/gemini-cli/pull/16174)
+- docs: correct typo in bufferFastReturn JSDoc ("accomodate" → "accommodate") by
+  @minglu7 in [#16056](https://github.com/google-gemini/gemini-cli/pull/16056)
+- fix: typo in MCP servers settings description by @alphanota in
+  [#15929](https://github.com/google-gemini/gemini-cli/pull/15929)
+- fix: yolo should auto allow redirection by @abhipatel12 in
+  [#16183](https://github.com/google-gemini/gemini-cli/pull/16183)
+- fix(cli): disableYoloMode shouldn't enforce default approval mode against args
+  by @psinha40898 in
+  [#16155](https://github.com/google-gemini/gemini-cli/pull/16155)
+- feat: add native Sublime Text support to IDE detection by @phreakocious in
+  [#16083](https://github.com/google-gemini/gemini-cli/pull/16083)
+- refactor(core): extract ToolModificationHandler from scheduler by @abhipatel12
+  in [#16118](https://github.com/google-gemini/gemini-cli/pull/16118)
+- Add support for Antigravity terminal in terminal setup utility by @raky291 in
+  [#16051](https://github.com/google-gemini/gemini-cli/pull/16051)
+- feat(core): Wire up model routing to subagents. by @joshualitt in
+  [#16043](https://github.com/google-gemini/gemini-cli/pull/16043)
+- feat(cli): add /agents slash command to list available agents by @adamfweidman
+  in [#16182](https://github.com/google-gemini/gemini-cli/pull/16182)
+- docs(cli): fix includeDirectories nesting in configuration.md by @maru0804 in
+  [#15067](https://github.com/google-gemini/gemini-cli/pull/15067)
+- feat: implement file system reversion utilities for rewind by @Adib234 in
+  [#15715](https://github.com/google-gemini/gemini-cli/pull/15715)
+- Always enable redaction in GitHub actions. by @gundermanc in
+  [#16200](https://github.com/google-gemini/gemini-cli/pull/16200)
+- fix: remove unsupported 'enabled' key from workflow config by @Han5991 in
+  [#15611](https://github.com/google-gemini/gemini-cli/pull/15611)
+- docs: Remove redundant and duplicate documentation files by @liqzheng in
+  [#14699](https://github.com/google-gemini/gemini-cli/pull/14699)
+- docs: shorten run command and use published version by @dsherret in
+  [#16172](https://github.com/google-gemini/gemini-cli/pull/16172)
+- test(command-registry): increase initialization test timeout by @wszqkzqk in
+  [#15979](https://github.com/google-gemini/gemini-cli/pull/15979)
+- Ensure TERM is set to xterm-256color by @falouu in
+  [#15828](https://github.com/google-gemini/gemini-cli/pull/15828)
+- The telemetry.js script should handle paths that contain spaces by @JohnJAS in
+  [#12078](https://github.com/google-gemini/gemini-cli/pull/12078)
+- ci: guard links workflow from running on forks by @wtanaka in
+  [#15461](https://github.com/google-gemini/gemini-cli/pull/15461)
+- ci: guard nightly release workflow from running on forks by @wtanaka in
+  [#15463](https://github.com/google-gemini/gemini-cli/pull/15463)
+- Support @ suggestions for subagenets by @sehoon38 in
+  [#16201](https://github.com/google-gemini/gemini-cli/pull/16201)
+- feat(hooks): Support explicit stop and block execution control in model hooks
+  by @SandyTao520 in
+  [#15947](https://github.com/google-gemini/gemini-cli/pull/15947)
+- Refine Gemini 3 system instructions to reduce model verbosity by
+  @NTaylorMullen in
+  [#16139](https://github.com/google-gemini/gemini-cli/pull/16139)
+- chore: clean up unused models and use consts by @sehoon38 in
+  [#16246](https://github.com/google-gemini/gemini-cli/pull/16246)
+- Always enable bracketed paste by @scidomino in
+  [#16179](https://github.com/google-gemini/gemini-cli/pull/16179)
+- refactor: migrate clearCommand hook calls to HookSystem by @ved015 in
+  [#16157](https://github.com/google-gemini/gemini-cli/pull/16157)
+- refactor: migrate app containter hook calls to hook system by @ishaanxgupta in
+  [#16161](https://github.com/google-gemini/gemini-cli/pull/16161)
+- Show settings source in extensions lists by @chrstnb in
+  [#16207](https://github.com/google-gemini/gemini-cli/pull/16207)
+- feat(skills): add pr-creator skill and enable skills by @NTaylorMullen in
+  [#16232](https://github.com/google-gemini/gemini-cli/pull/16232)
+- fix: handle Shift+Space in Kitty keyboard protocol terminals by @tt-a1i in
+  [#15767](https://github.com/google-gemini/gemini-cli/pull/15767)
+- feat(core, ui): Add /agents refresh command. by @joshualitt in
+  [#16204](https://github.com/google-gemini/gemini-cli/pull/16204)
+- feat(core): add local experiments override via GEMINI_EXP by @kevin-ramdass in
+  [#16181](https://github.com/google-gemini/gemini-cli/pull/16181)
+- feat(ui): reduce home directory warning noise and add opt-out setting by
+  @NTaylorMullen in
+  [#16229](https://github.com/google-gemini/gemini-cli/pull/16229)
+- refactor: migrate chatCompressionService to use HookSystem by @ved015 in
+  [#16259](https://github.com/google-gemini/gemini-cli/pull/16259)
+- fix: properly use systemMessage for hooks in UI by @jackwotherspoon in
+  [#16250](https://github.com/google-gemini/gemini-cli/pull/16250)
+- Infer modifyOtherKeys support by @scidomino in
+  [#16270](https://github.com/google-gemini/gemini-cli/pull/16270)
+- feat(core): Cache ignore instances for performance by @EricRahm in
+  [#16185](https://github.com/google-gemini/gemini-cli/pull/16185)
+- feat: apply remote admin settings (no-op) by @skeshive in
+  [#16106](https://github.com/google-gemini/gemini-cli/pull/16106)
+- Autogenerate docs/cli/settings.md docs/getting-started/configuration.md was
+  already autogenerated but settings.md was not. by @jacob314 in
+  [#14408](https://github.com/google-gemini/gemini-cli/pull/14408)
+- refactor(config): remove legacy V1 settings migration logic by @galz10 in
+  [#16252](https://github.com/google-gemini/gemini-cli/pull/16252)
+- Fix an issue where the agent stops prematurely by @gundermanc in
+  [#16269](https://github.com/google-gemini/gemini-cli/pull/16269)
+- Update system prompt to prefer non-interactive commands by @NTaylorMullen in
+  [#16117](https://github.com/google-gemini/gemini-cli/pull/16117)
+- Update ink version to 6.4.7 by @jacob314 in
+  [#16284](https://github.com/google-gemini/gemini-cli/pull/16284)
+- Support for Built-in Agent Skills by @NTaylorMullen in
+  [#16045](https://github.com/google-gemini/gemini-cli/pull/16045)
+- fix(skills): remove "Restart required" message from non-interactive commands
+  by @NTaylorMullen in
+  [#16307](https://github.com/google-gemini/gemini-cli/pull/16307)
+- remove unused sessionHookTriggers and exports by @ved015 in
+  [#16324](https://github.com/google-gemini/gemini-cli/pull/16324)
+- Triage action cleanup by @bdmorgan in
+  [#16319](https://github.com/google-gemini/gemini-cli/pull/16319)
+- fix: Add event-driven trigger to issue triage workflow by @bdmorgan in
+  [#16334](https://github.com/google-gemini/gemini-cli/pull/16334)
+- fix(workflows): resolve triage workflow failures and actionlint errors by
+  @bdmorgan in [#16338](https://github.com/google-gemini/gemini-cli/pull/16338)
+- docs: add note about experimental hooks by @abhipatel12 in
+  [#16337](https://github.com/google-gemini/gemini-cli/pull/16337)
+- feat(cli): implement passive activity logger for session analysis by
+  @SandyTao520 in
+  [#15829](https://github.com/google-gemini/gemini-cli/pull/15829)
+- feat(cli): add /chat debug command for nightly builds by @abhipatel12 in
+  [#16339](https://github.com/google-gemini/gemini-cli/pull/16339)
+- style: format pr-creator skill by @NTaylorMullen in
+  [#16381](https://github.com/google-gemini/gemini-cli/pull/16381)
+- feat(cli): Hooks enable-all/disable-all feature with dynamic status by
+  @AbdulTawabJuly in
+  [#15552](https://github.com/google-gemini/gemini-cli/pull/15552)
+- fix(core): ensure silent local subagent delegation while allowing remote
+  confirmation by @adamfweidman in
+  [#16395](https://github.com/google-gemini/gemini-cli/pull/16395)
+- Markdown w/ Frontmatter Agent Parser by @sehoon38 in
+  [#16094](https://github.com/google-gemini/gemini-cli/pull/16094)
+- Fix crash on unicode character by @chrstnb in
+  [#16420](https://github.com/google-gemini/gemini-cli/pull/16420)
+- Attempt to resolve OOM w/ useMemo on history items by @chrstnb in
+  [#16424](https://github.com/google-gemini/gemini-cli/pull/16424)
+- fix(core): ensure sub-agent schema and prompt refresh during runtime by
+  @adamfweidman in
+  [#16409](https://github.com/google-gemini/gemini-cli/pull/16409)
+- Update extension examples by @chrstnb in
+  [#16274](https://github.com/google-gemini/gemini-cli/pull/16274)
+- revert the change that was recently added from a fix by @sehoon38 in
+  [#16390](https://github.com/google-gemini/gemini-cli/pull/16390)
+- Add other hook wrapper methods to hooksystem by @ved015 in
+  [#16361](https://github.com/google-gemini/gemini-cli/pull/16361)
+- feat: introduce useRewindLogic hook for conversation history navigation by
+  @Adib234 in [#15716](https://github.com/google-gemini/gemini-cli/pull/15716)
+- docs: Fix formatting issue in memport documentation by @wanglc02 in
+  [#14774](https://github.com/google-gemini/gemini-cli/pull/14774)
+- fix(policy): enhance shell command safety and parsing by @allenhutchison in
+  [#15034](https://github.com/google-gemini/gemini-cli/pull/15034)
+- fix(core): avoid 'activate_skill' re-registration warning by @NTaylorMullen in
+  [#16398](https://github.com/google-gemini/gemini-cli/pull/16398)
+- perf(workflows): optimize PR triage script for faster execution by @bdmorgan
+  in [#16355](https://github.com/google-gemini/gemini-cli/pull/16355)
+- feat(admin): prompt user to restart the CLI if they change auth to oauth
+  mid-session or don't have auth type selected at start of session by @skeshive
+  in [#16426](https://github.com/google-gemini/gemini-cli/pull/16426)
+- Update cli-help agent's system prompt in sub-agents section by @sehoon38 in
+  [#16441](https://github.com/google-gemini/gemini-cli/pull/16441)
+- Revert "Update extension examples" by @chrstnb in
+  [#16442](https://github.com/google-gemini/gemini-cli/pull/16442)
+- Fix: add back fastreturn support by @scidomino in
+  [#16440](https://github.com/google-gemini/gemini-cli/pull/16440)
+- feat(a2a): Introduce /memory command for a2a server by @cocosheng-g in
+  [#14456](https://github.com/google-gemini/gemini-cli/pull/14456)
+- docs: fix broken internal link by using relative path by @Gong-Mi in
+  [#15371](https://github.com/google-gemini/gemini-cli/pull/15371)
+- migrate yolo/auto-edit keybindings by @scidomino in
+  [#16457](https://github.com/google-gemini/gemini-cli/pull/16457)
+- feat(cli): add install and uninstall commands for skills by @NTaylorMullen in
+  [#16377](https://github.com/google-gemini/gemini-cli/pull/16377)
+- feat(ui): use Tab to switch focus between shell and input by @jacob314 in
+  [#14332](https://github.com/google-gemini/gemini-cli/pull/14332)
+- feat(core): support shipping built-in skills with the CLI by @NTaylorMullen in
+  [#16300](https://github.com/google-gemini/gemini-cli/pull/16300)
+- Collect hardware details telemetry. by @gundermanc in
+  [#16119](https://github.com/google-gemini/gemini-cli/pull/16119)
+- feat(agents): improve UI feedback and parser reliability by @NTaylorMullen in
+  [#16459](https://github.com/google-gemini/gemini-cli/pull/16459)
+- Migrate keybindings by @scidomino in
+  [#16460](https://github.com/google-gemini/gemini-cli/pull/16460)
+- feat(cli): cleanup activity logs alongside session files by @SandyTao520 in
+  [#16399](https://github.com/google-gemini/gemini-cli/pull/16399)
+- feat(cli): implement dynamic terminal tab titles for CLI status by
+  @NTaylorMullen in
+  [#16378](https://github.com/google-gemini/gemini-cli/pull/16378)
+- feat(core): add disableLLMCorrection setting to skip auto-correction in edit
+  tools by @SandyTao520 in
+  [#16000](https://github.com/google-gemini/gemini-cli/pull/16000)
+- fix: Set both tab and window title instead of just window title by
+  @NTaylorMullen in
+  [#16464](https://github.com/google-gemini/gemini-cli/pull/16464)
+- fix(policy): ensure MCP policies match unqualified names in non-interactive
+  mode by @NTaylorMullen in
+  [#16490](https://github.com/google-gemini/gemini-cli/pull/16490)
+- fix(cli): refine 'Action Required' indicator and focus hints by @NTaylorMullen
+  in [#16497](https://github.com/google-gemini/gemini-cli/pull/16497)
+- Refactor beforeAgent and afterAgent hookEvents to follow desired output by
+  @ved015 in [#16495](https://github.com/google-gemini/gemini-cli/pull/16495)
+- feat(agents): clarify mandatory YAML frontmatter for sub-agents by
+  @NTaylorMullen in
+  [#16515](https://github.com/google-gemini/gemini-cli/pull/16515)
+- docs(telemetry): add Google Cloud Monitoring dashboard documentation by @jerop
+  in [#16520](https://github.com/google-gemini/gemini-cli/pull/16520)
+- Implement support for subagents as extensions. by @gundermanc in
+  [#16473](https://github.com/google-gemini/gemini-cli/pull/16473)
+- refactor: make baseTimestamp optional in addItem and remove redundant calls by
+  @sehoon38 in [#16471](https://github.com/google-gemini/gemini-cli/pull/16471)
+- Improve key binding names and descriptions by @scidomino in
+  [#16529](https://github.com/google-gemini/gemini-cli/pull/16529)
+- feat(core, cli): Add support for agents in settings.json. by @joshualitt in
+  [#16433](https://github.com/google-gemini/gemini-cli/pull/16433)
+- fix(cli): fix 'gemini skills install' unknown argument error by @NTaylorMullen
+  in [#16537](https://github.com/google-gemini/gemini-cli/pull/16537)
+- chore(ui): optimize AgentsStatus layout with dense list style and group
+  separation by @adamfweidman in
+  [#16545](https://github.com/google-gemini/gemini-cli/pull/16545)
+- fix(cli): allow @ file selector on slash command lines by @galz10 in
+  [#16370](https://github.com/google-gemini/gemini-cli/pull/16370)
+- fix(ui): resolve sticky header regression in tool messages by @jacob314 in
+  [#16514](https://github.com/google-gemini/gemini-cli/pull/16514)
+- feat(core): Align internal agent settings with configs exposed through
+  settings.json by @joshualitt in
+  [#16458](https://github.com/google-gemini/gemini-cli/pull/16458)
+- fix(cli): copy uses OSC52 only in SSH/WSL by @assagman in
+  [#16554](https://github.com/google-gemini/gemini-cli/pull/16554)
+- docs(skills): clarify skill directory structure and file location by
+  @NTaylorMullen in
+  [#16532](https://github.com/google-gemini/gemini-cli/pull/16532)
+- Fix: make ctrl+x use preferred editor by @scidomino in
+  [#16556](https://github.com/google-gemini/gemini-cli/pull/16556)
+- fix(core): Resolve race condition in tool response reporting by @abhipatel12
+  in [#16557](https://github.com/google-gemini/gemini-cli/pull/16557)
+- feat(ui): highlight persist mode status in ModelDialog by @sehoon38 in
+  [#16483](https://github.com/google-gemini/gemini-cli/pull/16483)
+- refactor: clean up A2A task output for users and LLMs by @adamfweidman in
+  [#16561](https://github.com/google-gemini/gemini-cli/pull/16561)
+- feat(core/ui): enhance retry mechanism and UX by @sehoon38 in
+  [#16489](https://github.com/google-gemini/gemini-cli/pull/16489)
+- Modernize MaxSizedBox to use and ResizeObservers by @jacob314 in
+  [#16565](https://github.com/google-gemini/gemini-cli/pull/16565)
+- Behavioral evals framework. by @gundermanc in
+  [#16047](https://github.com/google-gemini/gemini-cli/pull/16047)
+- Aggregate test results. by @gundermanc in
+  [#16581](https://github.com/google-gemini/gemini-cli/pull/16581)
+- feat(admin): support admin-enforced settings for Agent Skills by
+  @NTaylorMullen in
+  [#16406](https://github.com/google-gemini/gemini-cli/pull/16406)
+- fix(patch): cherry-pick cfdc4cf to release/v0.25.0-preview.0-pr-16759 to patch
+  version v0.25.0-preview.0 and create version 0.25.0-preview.1 by
+  @gemini-cli-robot in
+  [#16866](https://github.com/google-gemini/gemini-cli/pull/16866)
+- Patch #16730 into v0.25.0 preview by @chrstnb in
+  [#16882](https://github.com/google-gemini/gemini-cli/pull/16882)
+- fix(patch): cherry-pick 3b55581 to release/v0.25.0-preview.2-pr-16506 to patch
+  version v0.25.0-preview.2 and create version 0.25.0-preview.3 by
+  @gemini-cli-robot in
+  [#17098](https://github.com/google-gemini/gemini-cli/pull/17098)
 
 **Full changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.22.5...v0.23.0
+https://github.com/google-gemini/gemini-cli/compare/v0.24.5...v0.25.0

docs/changelogs/preview.md

@@ -1,6 +1,6 @@
-# Preview release: Release v0.24.0-preview.0
+# Preview release: Release v0.26.0-preview.0
 
-Released: January 6, 2026
+Released: January 21, 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).
@@ -11,214 +11,322 @@ To install the preview release:
 npm install -g @google/gemini-cli@preview
 ```
 
-## What's changed
+## Highlights
 
-- chore(core): refactor model resolution and cleanup fallback logic by
-  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15228
-- Add Folder Trust Support To Hooks by @sehoon38 in
-  https://github.com/google-gemini/gemini-cli/pull/15325
-- Record timestamp with code assist metrics. by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/15439
-- feat(policy): implement dynamic mode-aware policy evaluation by @abhipatel12
-  in https://github.com/google-gemini/gemini-cli/pull/15307
-- fix(core): use debugLogger.debug for startup profiler logs by @NTaylorMullen
-  in https://github.com/google-gemini/gemini-cli/pull/15443
-- feat(ui): Add security warning and improve layout for Hooks list by
-  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15440
-- fix #15369, prevent crash on unhandled EIO error in readStdin cleanup by
-  @ElecTwix in https://github.com/google-gemini/gemini-cli/pull/15410
-- chore: improve error messages for --resume by @jackwotherspoon in
-  https://github.com/google-gemini/gemini-cli/pull/15360
-- chore: remove clipboard file by @jackwotherspoon in
-  https://github.com/google-gemini/gemini-cli/pull/15447
-- Implemented unified secrets sanitization and env. redaction options by
-  @gundermanc in https://github.com/google-gemini/gemini-cli/pull/15348
-- feat: automatic `/model` persistence across Gemini CLI sessions by @niyasrad
-  in https://github.com/google-gemini/gemini-cli/pull/13199
-- refactor(core): remove deprecated permission aliases from BeforeToolHookOutput
-  by @StoyanD in https://github.com/google-gemini/gemini-cli/pull/14855
-- fix: add missing `type` field to MCPServerConfig by @jackwotherspoon in
-  https://github.com/google-gemini/gemini-cli/pull/15465
-- Make schema validation errors non-fatal by @jacob314 in
-  https://github.com/google-gemini/gemini-cli/pull/15487
-- chore: limit MCP resources display to 10 by default by @jackwotherspoon in
-  https://github.com/google-gemini/gemini-cli/pull/15489
-- Add experimental in-CLI extension install and uninstall subcommands by
-  @chrstnb in https://github.com/google-gemini/gemini-cli/pull/15178
-- feat: Add A2A Client Manager and tests by @adamfweidman in
-  https://github.com/google-gemini/gemini-cli/pull/15485
-- feat: terse transformations of image paths in text buffer by @psinha40898 in
-  https://github.com/google-gemini/gemini-cli/pull/4924
-- Security: Project-level hook warnings by @sehoon38 in
-  https://github.com/google-gemini/gemini-cli/pull/15470
-- Added modifyOtherKeys protocol support for tmux by @ved015 in
-  https://github.com/google-gemini/gemini-cli/pull/15524
-- chore(core): fix comment typo by @Mapleeeeeeeeeee in
-  https://github.com/google-gemini/gemini-cli/pull/15558
-- feat: Show snowfall animation for holiday theme by @sehoon38 in
-  https://github.com/google-gemini/gemini-cli/pull/15494
-- do not persist the fallback model by @sehoon38 in
-  https://github.com/google-gemini/gemini-cli/pull/15483
-- Resolve unhandled promise rejection in ide-client.ts by @Adib234 in
-  https://github.com/google-gemini/gemini-cli/pull/15587
-- fix(core): handle checkIsRepo failure in GitService.initialize by
-  @Mapleeeeeeeeeee in https://github.com/google-gemini/gemini-cli/pull/15574
-- fix(cli): add enableShellOutputEfficiency to settings schema by
-  @Mapleeeeeeeeeee in https://github.com/google-gemini/gemini-cli/pull/15560
-- Manual nightly version bump to 0.24.0-nightly.20251226.546baf993 by @galz10 in
-  https://github.com/google-gemini/gemini-cli/pull/15594
-- refactor(core): extract static concerns from CoreToolScheduler by @abhipatel12
-  in https://github.com/google-gemini/gemini-cli/pull/15589
-- fix(core): enable granular shell command allowlisting in policy engine by
-  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15601
-- chore/release: bump version to 0.24.0-nightly.20251227.37be16243 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15612
-- refactor: deprecate legacy confirmation settings and enforce Policy Engine by
-  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15626
-- Migrate console to coreEvents.emitFeedback or debugLogger by @Adib234 in
-  https://github.com/google-gemini/gemini-cli/pull/15219
-- Exponential back-off retries for retryable error without a specified … by
-  @sehoon38 in https://github.com/google-gemini/gemini-cli/pull/15684
-- feat(agents): add support for remote agents and multi-agent TOML files by
-  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15437
-- Update wittyPhrases.ts by @segyges in
-  https://github.com/google-gemini/gemini-cli/pull/15697
-- refactor(auth): Refactor non-interactive mode auth validation & refresh by
-  @skeshive in https://github.com/google-gemini/gemini-cli/pull/15679
-- Revert "Update wittyPhrases.ts (#15697)" by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15719
-- fix(hooks): deduplicate agent hooks and add cross-platform integration tests
-  by @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15701
-- Implement support for tool input modification by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/15492
-- Add instructions to the extensions update info notification by @chrstnb in
-  https://github.com/google-gemini/gemini-cli/pull/14907
-- Add extension settings info to /extensions list by @chrstnb in
-  https://github.com/google-gemini/gemini-cli/pull/14905
-- Agent Skills: Implement Core Skill Infrastructure & Tiered Discovery by
-  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15698
-- chore: remove cot style comments by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15735
-- feat(agents): Add remote agents to agent registry by @sehoon38 in
-  https://github.com/google-gemini/gemini-cli/pull/15711
-- feat(hooks): implement STOP_EXECUTION and enhance hook decision handling by
-  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15685
-- Fix build issues caused by year-specific linter rule by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/15780
-- fix(core): handle unhandled promise rejection in mcp-client-manager by
-  @kamja44 in https://github.com/google-gemini/gemini-cli/pull/14701
-- log fallback mode by @sehoon38 in
-  https://github.com/google-gemini/gemini-cli/pull/15817
-- Agent Skills: Implement Autonomous Activation Tool & Context Injection by
-  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15725
-- fix(core): improve shell command with redirection detection by @galz10 in
-  https://github.com/google-gemini/gemini-cli/pull/15683
-- Add security docs by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15739
-- feat: add folder suggestions to `/dir add` command by @jackwotherspoon in
-  https://github.com/google-gemini/gemini-cli/pull/15724
-- Agent Skills: Implement Agent Integration and System Prompt Awareness by
-  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15728
-- chore: cleanup old smart edit settings by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15832
-- Agent Skills: Status Bar Integration for Skill Counts by @NTaylorMullen in
-  https://github.com/google-gemini/gemini-cli/pull/15741
-- fix(core): mock powershell output in shell-utils test by @galz10 in
-  https://github.com/google-gemini/gemini-cli/pull/15831
-- Agent Skills: Unify Representation & Centralize Loading by @NTaylorMullen in
-  https://github.com/google-gemini/gemini-cli/pull/15833
-- Unify shell security policy and remove legacy logic by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15770
-- feat(core): restore MessageBus optionality for soft migration (Phase 1) by
-  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15774
-- feat(core): Standardize Tool and Agent Invocation constructors (Phase 2) by
-  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15775
-- feat(core,cli): enforce mandatory MessageBus injection (Phase 3 Hard
-  Migration) by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15776
-- Agent Skills: Extension Support & Security Disclosure by @NTaylorMullen in
-  https://github.com/google-gemini/gemini-cli/pull/15834
-- feat(hooks): implement granular stop and block behavior for agent hooks by
-  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15824
-- Agent Skills: Add gemini skills CLI management command by @NTaylorMullen in
-  https://github.com/google-gemini/gemini-cli/pull/15837
-- refactor: consolidate EditTool and SmartEditTool by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15857
-- fix(cli): mock fs.readdir in consent tests for Windows compatibility by
-  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15904
-- refactor(core): Extract and integrate ToolExecutor by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15900
-- Fix terminal hang when user exits browser without logging in by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/15748
-- fix: avoid SDK warning by not accessing .text getter in logging by @ved015 in
-  https://github.com/google-gemini/gemini-cli/pull/15706
-- Make default settings apply by @devr0306 in
-  https://github.com/google-gemini/gemini-cli/pull/15354
-- chore: rename smart-edit to edit by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15923
-- Opt-in to persist model from /model by @sehoon38 in
-  https://github.com/google-gemini/gemini-cli/pull/15820
-- fix: prevent /copy crash on Windows by skipping /dev/tty by @ManojINaik in
-  https://github.com/google-gemini/gemini-cli/pull/15657
-- Support context injection via SessionStart hook. by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/15746
-- Fix order of preflight by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15941
-- Fix failing unit tests by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/15940
-- fix(cli): resolve paste issue on Windows terminals. by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15932
-- Agent Skills: Implement /skills reload by @NTaylorMullen in
-  https://github.com/google-gemini/gemini-cli/pull/15865
-- Add setting to support OSC 52 paste by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15336
-- remove manual string when displaying manual model in the footer by @sehoon38
-  in https://github.com/google-gemini/gemini-cli/pull/15967
-- fix(core): use correct interactive check for system prompt by @ppergame in
-  https://github.com/google-gemini/gemini-cli/pull/15020
-- Inform user of missing settings on extensions update by @chrstnb in
-  https://github.com/google-gemini/gemini-cli/pull/15944
-- feat(policy): allow 'modes' in user and admin policies by @NTaylorMullen in
-  https://github.com/google-gemini/gemini-cli/pull/15977
-- fix: default folder trust to untrusted for enhanced security by @galz10 in
-  https://github.com/google-gemini/gemini-cli/pull/15943
-- Add description for each settings item in /settings by @sehoon38 in
-  https://github.com/google-gemini/gemini-cli/pull/15936
-- Use GetOperation to poll for OnboardUser completion by @ishaanxgupta in
-  https://github.com/google-gemini/gemini-cli/pull/15827
-- Agent Skills: Add skill directory to WorkspaceContext upon activation by
-  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15870
-- Fix settings command fallback by @chrstnb in
-  https://github.com/google-gemini/gemini-cli/pull/15926
-- fix: writeTodo construction by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/16014
-- properly disable keyboard modes on exit by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/16006
-- Add workflow to label child issues for rollup by @bdmorgan in
-  https://github.com/google-gemini/gemini-cli/pull/16002
-- feat(ui): add visual indicators for hook execution by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15408
-- fix: image token estimation by @jackwotherspoon in
-  https://github.com/google-gemini/gemini-cli/pull/16004
-- feat(hooks): Add a hooks.enabled setting. by @joshualitt in
-  https://github.com/google-gemini/gemini-cli/pull/15933
-- feat(admin): Introduce remote admin settings & implement
-  secureModeEnabled/mcpEnabled by @skeshive in
-  https://github.com/google-gemini/gemini-cli/pull/15935
-- Remove trailing whitespace in yaml. by @joshualitt in
-  https://github.com/google-gemini/gemini-cli/pull/16036
-- feat(agents): add support for remote agents by @adamfweidman in
-  https://github.com/google-gemini/gemini-cli/pull/16013
-- fix: limit scheduled issue triage queries to prevent argument list too long
-  error by @jerop in https://github.com/google-gemini/gemini-cli/pull/16021
-- ci(github-actions): triage all new issues automatically by @jerop in
-  https://github.com/google-gemini/gemini-cli/pull/16018
-- Fix test. by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/16011
-- fix: hide broken skills object from settings dialog by @korade-krushna in
-  https://github.com/google-gemini/gemini-cli/pull/15766
-- Agent Skills: Initial Documentation & Tutorial by @NTaylorMullen in
-  https://github.com/google-gemini/gemini-cli/pull/15869
+- **Skills and Agents:** Improvements to the `activate_skill` tool and skill
+  management. Experimental Agent Skills support.
+- **UI/UX:** Addition of a Rewind Confirmation dialog and Viewer component.
+- **Extensions:** Experimental setting for extension configuration.
+- **Bug Fixes and Stability:** PDF token estimation fix and improvements to
+  scheduled issue triage.
+
+## What's Changed
+
+- fix: PDF token estimation
+  ([#16494](https://github.com/google-gemini/gemini-cli/pull/16494)) by
+  @korade-krushna in
+  [#16527](https://github.com/google-gemini/gemini-cli/pull/16527)
+- chore(release): bump version to 0.26.0-nightly.20260114.bb6c57414 by
+  @gemini-cli-robot in
+  [#16604](https://github.com/google-gemini/gemini-cli/pull/16604)
+- docs: clarify F12 to open debug console by @jackwotherspoon in
+  [#16570](https://github.com/google-gemini/gemini-cli/pull/16570)
+- docs: Remove .md extension from internal links in architecture.md by
+  @medic-code in
+  [#12899](https://github.com/google-gemini/gemini-cli/pull/12899)
+- Add an experimental setting for extension config by @chrstnb in
+  [#16506](https://github.com/google-gemini/gemini-cli/pull/16506)
+- feat: add Rewind Confirmation dialog and Rewind Viewer component by @Adib234
+  in [#15717](https://github.com/google-gemini/gemini-cli/pull/15717)
+- fix(a2a): Don't throw errors for GeminiEventType Retry and InvalidStream. by
+  @ehedlund in [#16541](https://github.com/google-gemini/gemini-cli/pull/16541)
+- prefactor: add rootCommands as array so it can be used for policy parsing by
+  @abhipatel12 in
+  [#16640](https://github.com/google-gemini/gemini-cli/pull/16640)
+- remove unnecessary \x7f key bindings by @scidomino in
+  [#16646](https://github.com/google-gemini/gemini-cli/pull/16646)
+- docs(skills): use body-file in pr-creator skill for better reliability by
+  @abhipatel12 in
+  [#16642](https://github.com/google-gemini/gemini-cli/pull/16642)
+- chore(automation): recursive labeling for workstream descendants by @bdmorgan
+  in [#16609](https://github.com/google-gemini/gemini-cli/pull/16609)
+- feat: introduce 'skill-creator' built-in skill and CJS management tools by
+  @NTaylorMullen in
+  [#16394](https://github.com/google-gemini/gemini-cli/pull/16394)
+- chore(automation): remove automated PR size and complexity labeler by
+  @bdmorgan in [#16648](https://github.com/google-gemini/gemini-cli/pull/16648)
+- refactor(skills): replace 'project' with 'workspace' scope by @NTaylorMullen
+  in [#16380](https://github.com/google-gemini/gemini-cli/pull/16380)
+- Docs: Update release notes for 1/13/2026 by @jkcinouye in
+  [#16583](https://github.com/google-gemini/gemini-cli/pull/16583)
+- Simplify paste handling by @scidomino in
+  [#16654](https://github.com/google-gemini/gemini-cli/pull/16654)
+- chore(automation): improve scheduled issue triage discovery and throughput by
+  @bdmorgan in [#16652](https://github.com/google-gemini/gemini-cli/pull/16652)
+- fix(acp): run exit cleanup when stdin closes by @codefromthecrypt in
+  [#14953](https://github.com/google-gemini/gemini-cli/pull/14953)
+- feat(scheduler): add types needed for event driven scheduler by @abhipatel12
+  in [#16641](https://github.com/google-gemini/gemini-cli/pull/16641)
+- Remove unused rewind key binding by @scidomino in
+  [#16659](https://github.com/google-gemini/gemini-cli/pull/16659)
+- Remove sequence binding by @scidomino in
+  [#16664](https://github.com/google-gemini/gemini-cli/pull/16664)
+- feat(cli): undeprecate the --prompt flag by @alexaustin007 in
+  [#13981](https://github.com/google-gemini/gemini-cli/pull/13981)
+- chore: update dependabot configuration by @cosmopax in
+  [#13507](https://github.com/google-gemini/gemini-cli/pull/13507)
+- feat(config): add 'auto' alias for default model selection by @sehoon38 in
+  [#16661](https://github.com/google-gemini/gemini-cli/pull/16661)
+- Enable & disable agents by @sehoon38 in
+  [#16225](https://github.com/google-gemini/gemini-cli/pull/16225)
+- cleanup: Improve keybindings by @scidomino in
+  [#16672](https://github.com/google-gemini/gemini-cli/pull/16672)
+- Add timeout for shell-utils to prevent hangs. by @jacob314 in
+  [#16667](https://github.com/google-gemini/gemini-cli/pull/16667)
+- feat(plan): add experimental plan flag by @jerop in
+  [#16650](https://github.com/google-gemini/gemini-cli/pull/16650)
+- feat(cli): add security consent prompts for skill installation by
+  @NTaylorMullen in
+  [#16549](https://github.com/google-gemini/gemini-cli/pull/16549)
+- fix: replace 3 consecutive periods with ellipsis character by @Vist233 in
+  [#16587](https://github.com/google-gemini/gemini-cli/pull/16587)
+- chore(automation): ensure status/need-triage is applied and never cleared
+  automatically by @bdmorgan in
+  [#16657](https://github.com/google-gemini/gemini-cli/pull/16657)
+- fix: Handle colons in skill description frontmatter by @maru0804 in
+  [#16345](https://github.com/google-gemini/gemini-cli/pull/16345)
+- refactor(core): harden skill frontmatter parsing by @NTaylorMullen in
+  [#16705](https://github.com/google-gemini/gemini-cli/pull/16705)
+- feat(skills): add conflict detection and warnings for skill overrides by
+  @NTaylorMullen in
+  [#16709](https://github.com/google-gemini/gemini-cli/pull/16709)
+- feat(scheduler): add SchedulerStateManager for reactive tool state by
+  @abhipatel12 in
+  [#16651](https://github.com/google-gemini/gemini-cli/pull/16651)
+- chore(automation): enforce 'help wanted' label permissions and update
+  guidelines by @bdmorgan in
+  [#16707](https://github.com/google-gemini/gemini-cli/pull/16707)
+- fix(core): resolve circular dependency via tsconfig paths by @sehoon38 in
+  [#16730](https://github.com/google-gemini/gemini-cli/pull/16730)
+- chore/release: bump version to 0.26.0-nightly.20260115.6cb3ae4e0 by
+  @gemini-cli-robot in
+  [#16738](https://github.com/google-gemini/gemini-cli/pull/16738)
+- fix(automation): correct status/need-issue label matching wildcard by
+  @bdmorgan in [#16727](https://github.com/google-gemini/gemini-cli/pull/16727)
+- fix(automation): prevent label-enforcer loop by ignoring all bots by @bdmorgan
+  in [#16746](https://github.com/google-gemini/gemini-cli/pull/16746)
+- Add links to supported locations and minor fixes by @g-samroberts in
+  [#16476](https://github.com/google-gemini/gemini-cli/pull/16476)
+- feat(policy): add source tracking to policy rules by @allenhutchison in
+  [#16670](https://github.com/google-gemini/gemini-cli/pull/16670)
+- feat(automation): enforce '🔒 maintainer only' and fix bot loop by @bdmorgan
+  in [#16751](https://github.com/google-gemini/gemini-cli/pull/16751)
+- Make merged settings non-nullable and fix all lints related to that. by
+  @jacob314 in [#16647](https://github.com/google-gemini/gemini-cli/pull/16647)
+- fix(core): prevent ModelInfo event emission on aborted signal by @sehoon38 in
+  [#16752](https://github.com/google-gemini/gemini-cli/pull/16752)
+- Replace relative paths to fix website build by @chrstnb in
+  [#16755](https://github.com/google-gemini/gemini-cli/pull/16755)
+- Restricting to localhost by @cocosheng-g in
+  [#16548](https://github.com/google-gemini/gemini-cli/pull/16548)
+- fix(cli): add explicit dependency on color-convert by @sehoon38 in
+  [#16757](https://github.com/google-gemini/gemini-cli/pull/16757)
+- fix(automation): robust label enforcement with permission checks by @bdmorgan
+  in [#16762](https://github.com/google-gemini/gemini-cli/pull/16762)
+- fix(cli): prevent OOM crash by limiting file search traversal and adding
+  timeout by @galz10 in
+  [#16696](https://github.com/google-gemini/gemini-cli/pull/16696)
+- fix(cli): safely handle /dev/tty access on macOS by @korade-krushna in
+  [#16531](https://github.com/google-gemini/gemini-cli/pull/16531)
+- docs: clarify workspace test execution in GEMINI.md by @mattKorwel in
+  [#16764](https://github.com/google-gemini/gemini-cli/pull/16764)
+- Add support for running available commands prior to MCP servers loading by
+  @Adib234 in [#15596](https://github.com/google-gemini/gemini-cli/pull/15596)
+- feat(plan): add experimental 'plan' approval mode by @jerop in
+  [#16753](https://github.com/google-gemini/gemini-cli/pull/16753)
+- feat(scheduler): add functional awaitConfirmation utility by @abhipatel12 in
+  [#16721](https://github.com/google-gemini/gemini-cli/pull/16721)
+- fix(infra): update maintainer rollup label to 'workstream-rollup' by @bdmorgan
+  in [#16809](https://github.com/google-gemini/gemini-cli/pull/16809)
+- fix(infra): use GraphQL to detect direct parents in rollup workflow by
+  @bdmorgan in [#16811](https://github.com/google-gemini/gemini-cli/pull/16811)
+- chore(workflows): rename label-workstream-rollup workflow by @bdmorgan in
+  [#16818](https://github.com/google-gemini/gemini-cli/pull/16818)
+- skip simple-mcp-server.test.ts by @scidomino in
+  [#16842](https://github.com/google-gemini/gemini-cli/pull/16842)
+- Steer outer agent to use expert subagents when present by @gundermanc in
+  [#16763](https://github.com/google-gemini/gemini-cli/pull/16763)
+- Fix race condition by awaiting scheduleToolCalls by @chrstnb in
+  [#16759](https://github.com/google-gemini/gemini-cli/pull/16759)
+- cleanup: Organize key bindings by @scidomino in
+  [#16798](https://github.com/google-gemini/gemini-cli/pull/16798)
+- feat(core): Add generalist agent. by @joshualitt in
+  [#16638](https://github.com/google-gemini/gemini-cli/pull/16638)
+- perf(ui): optimize text buffer and highlighting for large inputs by
+  @NTaylorMullen in
+  [#16782](https://github.com/google-gemini/gemini-cli/pull/16782)
+- fix(core): fix PTY descriptor shell leak by @galz10 in
+  [#16773](https://github.com/google-gemini/gemini-cli/pull/16773)
+- feat(plan): enforce strict read-only policy and halt execution on violation by
+  @jerop in [#16849](https://github.com/google-gemini/gemini-cli/pull/16849)
+- remove need-triage label from bug_report template by @sehoon38 in
+  [#16864](https://github.com/google-gemini/gemini-cli/pull/16864)
+- fix(core): truncate large telemetry log entries by @sehoon38 in
+  [#16769](https://github.com/google-gemini/gemini-cli/pull/16769)
+- docs(extensions): add Agent Skills support and mark feature as experimental by
+  @NTaylorMullen in
+  [#16859](https://github.com/google-gemini/gemini-cli/pull/16859)
+- fix(core): surface warnings for invalid hook event names in configuration
+  ([#16788](https://github.com/google-gemini/gemini-cli/pull/16788)) by
+  @sehoon38 in [#16873](https://github.com/google-gemini/gemini-cli/pull/16873)
+- feat(plan): remove read_many_files from approval mode policies by @jerop in
+  [#16876](https://github.com/google-gemini/gemini-cli/pull/16876)
+- feat(admin): implement admin controls polling and restart prompt by @skeshive
+  in [#16627](https://github.com/google-gemini/gemini-cli/pull/16627)
+- Remove LRUCache class migrating to mnemoist by @jacob314 in
+  [#16872](https://github.com/google-gemini/gemini-cli/pull/16872)
+- feat(settings): rename negative settings to positive naming (disable* ->
+  enable*) by @afarber in
+  [#14142](https://github.com/google-gemini/gemini-cli/pull/14142)
+- refactor(cli): unify shell confirmation dialogs by @NTaylorMullen in
+  [#16828](https://github.com/google-gemini/gemini-cli/pull/16828)
+- feat(agent): enable agent skills by default by @NTaylorMullen in
+  [#16736](https://github.com/google-gemini/gemini-cli/pull/16736)
+- refactor(core): foundational truncation refactoring and token estimation
+  optimization by @NTaylorMullen in
+  [#16824](https://github.com/google-gemini/gemini-cli/pull/16824)
+- fix(hooks): enable /hooks disable to reliably stop single hooks by
+  @abhipatel12 in
+  [#16804](https://github.com/google-gemini/gemini-cli/pull/16804)
+- Don't commit unless user asks us to. by @gundermanc in
+  [#16902](https://github.com/google-gemini/gemini-cli/pull/16902)
+- chore: remove a2a-adapter and bump @a2a-js/sdk to 0.3.8 by @adamfweidman in
+  [#16800](https://github.com/google-gemini/gemini-cli/pull/16800)
+- fix: Show experiment values in settings UI for compressionThreshold by
+  @ishaanxgupta in
+  [#16267](https://github.com/google-gemini/gemini-cli/pull/16267)
+- feat(cli): replace relative keyboard shortcuts link with web URL by
+  @imaliabbas in
+  [#16479](https://github.com/google-gemini/gemini-cli/pull/16479)
+- fix(core): resolve PKCE length issue and stabilize OAuth redirect port by
+  @sehoon38 in [#16815](https://github.com/google-gemini/gemini-cli/pull/16815)
+- Delete rewind documentation for now by @Adib234 in
+  [#16932](https://github.com/google-gemini/gemini-cli/pull/16932)
+- Stabilize skill-creator CI and package format by @NTaylorMullen in
+  [#17001](https://github.com/google-gemini/gemini-cli/pull/17001)
+- Stabilize the git evals by @gundermanc in
+  [#16989](https://github.com/google-gemini/gemini-cli/pull/16989)
+- fix(core): attempt compression before context overflow check by @NTaylorMullen
+  in [#16914](https://github.com/google-gemini/gemini-cli/pull/16914)
+- Fix inverted logic. by @gundermanc in
+  [#17007](https://github.com/google-gemini/gemini-cli/pull/17007)
+- chore(scripts): add duplicate issue closer script and fix lint errors by
+  @bdmorgan in [#16997](https://github.com/google-gemini/gemini-cli/pull/16997)
+- docs: update README and config guide to reference Gemini 3 by @JayadityaGit in
+  [#15806](https://github.com/google-gemini/gemini-cli/pull/15806)
+- fix(cli): correct Homebrew installation detection by @kij in
+  [#14727](https://github.com/google-gemini/gemini-cli/pull/14727)
+- Demote git evals to nightly run. by @gundermanc in
+  [#17030](https://github.com/google-gemini/gemini-cli/pull/17030)
+- fix(cli): use OSC-52 clipboard copy in Windows Terminal by @Thomas-Shephard in
+  [#16920](https://github.com/google-gemini/gemini-cli/pull/16920)
+- Fix: Process all parts in response chunks when thought is first by @pyrytakala
+  in [#13539](https://github.com/google-gemini/gemini-cli/pull/13539)
+- fix(automation): fix jq quoting error in pr-triage.sh by @Kimsoo0119 in
+  [#16958](https://github.com/google-gemini/gemini-cli/pull/16958)
+- refactor(core): decouple scheduler into orchestration, policy, and
+  confirmation by @abhipatel12 in
+  [#16895](https://github.com/google-gemini/gemini-cli/pull/16895)
+- feat: add /introspect slash command by @NTaylorMullen in
+  [#17048](https://github.com/google-gemini/gemini-cli/pull/17048)
+- refactor(cli): centralize tool mapping and decouple legacy scheduler by
+  @abhipatel12 in
+  [#17044](https://github.com/google-gemini/gemini-cli/pull/17044)
+- fix(ui): ensure rationale renders before tool calls by @NTaylorMullen in
+  [#17043](https://github.com/google-gemini/gemini-cli/pull/17043)
+- fix(workflows): use author_association for maintainer check by @bdmorgan in
+  [#17060](https://github.com/google-gemini/gemini-cli/pull/17060)
+- fix return type of fireSessionStartEvent to defaultHookOutput by @ved015 in
+  [#16833](https://github.com/google-gemini/gemini-cli/pull/16833)
+- feat(cli): add experiment gate for event-driven scheduler by @abhipatel12 in
+  [#17055](https://github.com/google-gemini/gemini-cli/pull/17055)
+- feat(core): improve shell redirection transparency and security by
+  @NTaylorMullen in
+  [#16486](https://github.com/google-gemini/gemini-cli/pull/16486)
+- fix(core): deduplicate ModelInfo emission in GeminiClient by @NTaylorMullen in
+  [#17075](https://github.com/google-gemini/gemini-cli/pull/17075)
+- docs(themes): remove unsupported DiffModified color key by @jw409 in
+  [#17073](https://github.com/google-gemini/gemini-cli/pull/17073)
+- fix: update currentSequenceModel when modelChanged by @adamfweidman in
+  [#17051](https://github.com/google-gemini/gemini-cli/pull/17051)
+- feat(core): enhanced anchored iterative context compression with
+  self-verification by @rmedranollamas in
+  [#15710](https://github.com/google-gemini/gemini-cli/pull/15710)
+- Fix mcp instructions by @chrstnb in
+  [#16439](https://github.com/google-gemini/gemini-cli/pull/16439)
+- [A2A] Disable checkpointing if git is not installed by @cocosheng-g in
+  [#16896](https://github.com/google-gemini/gemini-cli/pull/16896)
+- feat(admin): set admin.skills.enabled based on advancedFeaturesEnabled setting
+  by @skeshive in
+  [#17095](https://github.com/google-gemini/gemini-cli/pull/17095)
+- Test coverage for hook exit code cases by @gundermanc in
+  [#17041](https://github.com/google-gemini/gemini-cli/pull/17041)
+- Revert "Revert "Update extension examples"" by @chrstnb in
+  [#16445](https://github.com/google-gemini/gemini-cli/pull/16445)
+- fix(core): Provide compact, actionable errors for agent delegation failures by
+  @SandyTao520 in
+  [#16493](https://github.com/google-gemini/gemini-cli/pull/16493)
+- fix: migrate BeforeModel and AfterModel hooks to HookSystem by @ved015 in
+  [#16599](https://github.com/google-gemini/gemini-cli/pull/16599)
+- feat(admin): apply admin settings to gemini skills/mcp/extensions commands by
+  @skeshive in [#17102](https://github.com/google-gemini/gemini-cli/pull/17102)
+- fix(core): update telemetry token count after session resume by @psinha40898
+  in [#15491](https://github.com/google-gemini/gemini-cli/pull/15491)
+- Demote the subagent test to nightly by @gundermanc in
+  [#17105](https://github.com/google-gemini/gemini-cli/pull/17105)
+- feat(plan): telemetry to track adoption and usage of plan mode by @Adib234 in
+  [#16863](https://github.com/google-gemini/gemini-cli/pull/16863)
+- feat: Add flash lite utility fallback chain by @adamfweidman in
+  [#17056](https://github.com/google-gemini/gemini-cli/pull/17056)
+- Fixes Windows crash: "Cannot resize a pty that has already exited" by @dzammit
+  in [#15757](https://github.com/google-gemini/gemini-cli/pull/15757)
+- feat(core): Add initial eval for generalist agent. by @joshualitt in
+  [#16856](https://github.com/google-gemini/gemini-cli/pull/16856)
+- feat(core): unify agent enabled and disabled flags by @SandyTao520 in
+  [#17127](https://github.com/google-gemini/gemini-cli/pull/17127)
+- fix(core): resolve auto model in default strategy by @sehoon38 in
+  [#17116](https://github.com/google-gemini/gemini-cli/pull/17116)
+- docs: update project context and pr-creator workflow by @NTaylorMullen in
+  [#17119](https://github.com/google-gemini/gemini-cli/pull/17119)
+- fix(cli): send gemini-cli version as mcp client version by @dsp in
+  [#13407](https://github.com/google-gemini/gemini-cli/pull/13407)
+- fix(cli): resolve Ctrl+Enter and Ctrl+J newline issues by @imadraude in
+  [#17021](https://github.com/google-gemini/gemini-cli/pull/17021)
+- Remove missing sidebar item by @chrstnb in
+  [#17145](https://github.com/google-gemini/gemini-cli/pull/17145)
+- feat(core): Ensure all properties in hooks object are event names. by
+  @joshualitt in
+  [#16870](https://github.com/google-gemini/gemini-cli/pull/16870)
+- fix(cli): fix newline support broken in previous PR by @scidomino in
+  [#17159](https://github.com/google-gemini/gemini-cli/pull/17159)
+- Add interactive ValidationDialog for handling 403 VALIDATION_REQUIRED errors.
+  by @gsquared94 in
+  [#16231](https://github.com/google-gemini/gemini-cli/pull/16231)
+- Add Esc-Esc to clear prompt when it's not empty by @Adib234 in
+  [#17131](https://github.com/google-gemini/gemini-cli/pull/17131)
+- Avoid spurious warnings about unexpected renders triggered by appEvents and
+  coreEvents. by @jacob314 in
+  [#17160](https://github.com/google-gemini/gemini-cli/pull/17160)
+- fix(cli): resolve home/end keybinding conflict by @scidomino in
+  [#17124](https://github.com/google-gemini/gemini-cli/pull/17124)
+- fix(cli): display 'http' type on mcp list by @pamanta in
+  [#16915](https://github.com/google-gemini/gemini-cli/pull/16915)
+- fix bad fallback logic external editor logic by @scidomino in
+  [#17166](https://github.com/google-gemini/gemini-cli/pull/17166)
+- Fix bug where System scopes weren't migrated. by @jacob314 in
+  [#17174](https://github.com/google-gemini/gemini-cli/pull/17174)
+- Fix mcp tool lookup in tool registry by @werdnum in
+  [#17054](https://github.com/google-gemini/gemini-cli/pull/17054)
 
 **Full changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.23.0-preview.6...v0.24.0-preview.0
+https://github.com/google-gemini/gemini-cli/compare/v0.25.0-preview.4...v0.26.0-preview.0

docs/cli/commands.md

@@ -168,12 +168,6 @@ Slash commands provide meta-level control over the CLI itself.
     [settings](../get-started/configuration.md). See
     [Checkpointing documentation](../cli/checkpointing.md) for more details.
 
-- [**`/rewind`**](./rewind.md)
-  - **Description:** Browse and rewind previous interactions. Allows you to
-    rewind the conversation, revert file changes, or both. Provides an
-    interactive interface to select the exact point to rewind to.
-  - **Keyboard shortcut:** Press **Esc** twice.
-
 - **`/resume`**
   - **Description:** Browse and resume previous conversation sessions. Opens an
     interactive session browser where you can search, filter, and select from

docs/cli/keyboard-shortcuts.md

@@ -19,14 +19,14 @@ available combinations.
 
 | Action                                      | Keys                                                         |
 | ------------------------------------------- | ------------------------------------------------------------ |
-| Move the cursor to the start of the line.   | `Ctrl + A`<br />`Home`                                       |
-| Move the cursor to the end of the line.     | `Ctrl + E`<br />`End`                                        |
-| Move the cursor up one line.                | `Up Arrow (no Ctrl, no Cmd)`                                 |
-| Move the cursor down one line.              | `Down Arrow (no Ctrl, no Cmd)`                               |
-| Move the cursor one character to the left.  | `Left Arrow (no Ctrl, no Cmd)`<br />`Ctrl + B`               |
-| Move the cursor one character to the right. | `Right Arrow (no Ctrl, no Cmd)`<br />`Ctrl + F`              |
-| Move the cursor one word to the left.       | `Ctrl + Left Arrow`<br />`Cmd + Left Arrow`<br />`Cmd + B`   |
-| Move the cursor one word to the right.      | `Ctrl + Right Arrow`<br />`Cmd + Right Arrow`<br />`Cmd + F` |
+| Move the cursor to the start of the line.   | `Ctrl + A`<br />`Home (no Shift, Ctrl)`                      |
+| Move the cursor to the end of the line.     | `Ctrl + E`<br />`End (no Shift, Ctrl)`                       |
+| Move the cursor up one line.                | `Up Arrow (no Shift, Alt, Ctrl, Cmd)`                        |
+| Move the cursor down one line.              | `Down Arrow (no Shift, Alt, Ctrl, Cmd)`                      |
+| Move the cursor one character to the left.  | `Left Arrow (no Shift, Alt, Ctrl, Cmd)`<br />`Ctrl + B`      |
+| Move the cursor one character to the right. | `Right Arrow (no Shift, Alt, Ctrl, Cmd)`<br />`Ctrl + F`     |
+| Move the cursor one word to the left.       | `Ctrl + Left Arrow`<br />`Alt + Left Arrow`<br />`Alt + B`   |
+| Move the cursor one word to the right.      | `Ctrl + Right Arrow`<br />`Alt + Right Arrow`<br />`Alt + F` |
 
 #### Editing
 
@@ -35,23 +35,23 @@ available combinations.
 | Delete from the cursor to the end of the line.   | `Ctrl + K`                                                |
 | 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 />`Cmd + Backspace`<br />`Ctrl + W` |
-| Delete the next word.                            | `Ctrl + Delete`<br />`Cmd + Delete`                       |
+| Delete the previous word.                        | `Ctrl + Backspace`<br />`Alt + Backspace`<br />`Ctrl + W` |
+| Delete the next word.                            | `Ctrl + Delete`<br />`Alt + Delete`                       |
 | 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.                  | `Ctrl + Z (no Shift)`                                     |
-| Redo the most recent undone text edit.           | `Ctrl + Shift + Z`                                        |
+| Redo the most recent undone text edit.           | `Shift + Ctrl + Z`                                        |
 
 #### Scrolling
 
-| Action                   | Keys                 |
-| ------------------------ | -------------------- |
-| Scroll content up.       | `Shift + Up Arrow`   |
-| Scroll content down.     | `Shift + Down Arrow` |
-| Scroll to the top.       | `Home`               |
-| Scroll to the bottom.    | `End`                |
-| Scroll up by one page.   | `Page Up`            |
-| Scroll down by one page. | `Page Down`          |
+| Action                   | Keys                              |
+| ------------------------ | --------------------------------- |
+| Scroll content up.       | `Shift + Up Arrow`                |
+| Scroll content down.     | `Shift + Down Arrow`              |
+| Scroll to the top.       | `Ctrl + Home`<br />`Shift + Home` |
+| Scroll to the bottom.    | `Ctrl + End`<br />`Shift + End`   |
+| Scroll up by one page.   | `Page Up`                         |
+| Scroll down by one page. | `Page Down`                       |
 
 #### History & Search
 
@@ -62,6 +62,7 @@ available combinations.
 | Start reverse search through history.        | `Ctrl + R`            |
 | Submit the selected reverse-search match.    | `Enter (no Ctrl)`     |
 | Accept a suggestion while reverse searching. | `Tab`                 |
+| Browse and rewind previous interactions.     | `Double Esc`          |
 
 #### Navigation
 
@@ -84,29 +85,29 @@ available combinations.
 
 #### Text Input
 
-| Action                                         | Keys                                                                   |
-| ---------------------------------------------- | ---------------------------------------------------------------------- |
-| Submit the current prompt.                     | `Enter (no Ctrl, no Shift, no Cmd)`                                    |
-| Insert a newline without submitting.           | `Ctrl + Enter`<br />`Cmd + Enter`<br />`Shift + Enter`<br />`Ctrl + J` |
-| Open the current prompt in an external editor. | `Ctrl + X`                                                             |
-| Paste from the clipboard.                      | `Ctrl + V`<br />`Cmd + V`                                              |
+| Action                                         | Keys                                                                                      |
+| ---------------------------------------------- | ----------------------------------------------------------------------------------------- |
+| Submit the current prompt.                     | `Enter (no Shift, Alt, Ctrl, Cmd)`                                                        |
+| Insert a newline without submitting.           | `Ctrl + Enter`<br />`Cmd + Enter`<br />`Alt + Enter`<br />`Shift + Enter`<br />`Ctrl + J` |
+| Open the current prompt in an external editor. | `Ctrl + X`                                                                                |
+| Paste from the clipboard.                      | `Ctrl + V`<br />`Cmd + V`<br />`Alt + V`                                                  |
 
 #### 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.                                                                       | `Cmd + M`        |
-| Toggle copy mode when in alternate buffer mode.                                                  | `Ctrl + S`       |
-| Toggle YOLO (auto-approval) mode for tool calls.                                                 | `Ctrl + Y`       |
-| Toggle Auto Edit (auto-accept edits) mode.                                                       | `Shift + Tab`    |
-| Expand a height-constrained response to show additional lines when not in alternate buffer mode. | `Ctrl + S`       |
-| Focus the shell input from the gemini input.                                                     | `Tab (no Shift)` |
-| Focus the Gemini input from the shell input.                                                     | `Tab`            |
-| Clear the terminal screen and redraw the UI.                                                     | `Ctrl + L`       |
-| Restart the application.                                                                         | `R`              |
+| 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 a height-constrained response to show additional lines when not in alternate buffer mode.      | `Ctrl + S`       |
+| Focus the shell input from the gemini input.                                                          | `Tab (no Shift)` |
+| Focus the Gemini input from the shell input.                                                          | `Tab`            |
+| Clear the terminal screen and redraw the UI.                                                          | `Ctrl + L`       |
+| Restart the application.                                                                              | `R`              |
 
 <!-- KEYBINDINGS-AUTOGEN:END -->
 
@@ -117,7 +118,8 @@ available combinations.
 - `!` on an empty prompt: Enter or exit shell mode.
 - `\` (at end of a line) + `Enter`: Insert a newline without leaving single-line
   mode.
-- `Esc` pressed twice quickly: Browse and rewind previous interactions.
+- `Esc` pressed twice quickly: Clear the input prompt if it is not empty,
+  otherwise browse and rewind previous interactions.
 - `Up Arrow` / `Down Arrow`: When the cursor is at the top or bottom of a
   single-line input, navigate backward or forward through prompt history.
 - `Number keys (1-9, multi-digit)` inside selection dialogs: Jump directly to

docs/cli/model-routing.md

@@ -17,6 +17,11 @@ policies.
     may prompt you to switch to a fallback model (by default always prompts
     you).
 
+    Some internal utility calls (such as prompt completion and classification)
+    use a silent fallback chain for `gemini-2.5-flash-lite` and will fall back
+    to `gemini-2.5-flash` and `gemini-2.5-pro` without prompting or changing the
+    configured model.
+
 3.  **Model switch:** If approved, or if the policy allows for silent fallback,
     the CLI will use an available fallback model for the current turn or the
     remainder of the session.

docs/cli/settings.md

@@ -99,7 +99,7 @@ they appear in the UI.
 | Enable Tool Output Truncation    | `tools.enableToolOutputTruncation`   | Enable truncation of large tool outputs.                                                                                                                                   | `true`    |
 | Tool Output Truncation Threshold | `tools.truncateToolOutputThreshold`  | Truncate tool output if it is larger than this many characters. Set to -1 to disable.                                                                                      | `4000000` |
 | Tool Output Truncation Lines     | `tools.truncateToolOutputLines`      | The number of lines to keep when truncating tool output.                                                                                                                   | `1000`    |
-| Disable LLM Correction           | `tools.disableLLMCorrection`         | Disable LLM-based error correction for edit tools. When enabled, tools will fail immediately if exact string matches are not found, instead of attempting to self-correct. | `false`   |
+| Disable LLM Correction           | `tools.disableLLMCorrection`         | Disable LLM-based error correction for edit tools. When enabled, tools will fail immediately if exact string matches are not found, instead of attempting to self-correct. | `true`    |
 
 ### Security
 
@@ -113,19 +113,16 @@ they appear in the UI.
 
 ### Experimental
 
-| UI Label                            | Setting                                                 | Description                                                                         | Default |
-| ----------------------------------- | ------------------------------------------------------- | ----------------------------------------------------------------------------------- | ------- |
-| Agent Skills                        | `experimental.skills`                                   | Enable Agent Skills (experimental).                                                 | `false` |
-| Enable Codebase Investigator        | `experimental.codebaseInvestigatorSettings.enabled`     | Enable the Codebase Investigator agent.                                             | `true`  |
-| Codebase Investigator Max Num Turns | `experimental.codebaseInvestigatorSettings.maxNumTurns` | Maximum number of turns for the Codebase Investigator agent.                        | `10`    |
-| Use OSC 52 Paste                    | `experimental.useOSC52Paste`                            | Use OSC 52 sequence for pasting instead of clipboardy (useful for remote sessions). | `false` |
-| Enable CLI Help Agent               | `experimental.cliHelpAgentSettings.enabled`             | Enable the CLI Help Agent.                                                          | `true`  |
-| Plan                                | `experimental.plan`                                     | Enable planning features (Plan Mode and tools).                                     | `false` |
+| UI Label         | Setting                      | Description                                                                         | Default |
+| ---------------- | ---------------------------- | ----------------------------------------------------------------------------------- | ------- |
+| Agent Skills     | `experimental.skills`        | Enable Agent Skills (experimental).                                                 | `false` |
+| 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` |
 
-### Hooks
+### HooksConfig
 
-| UI Label           | Setting               | Description                                      | Default |
-| ------------------ | --------------------- | ------------------------------------------------ | ------- |
-| Hook Notifications | `hooks.notifications` | Show visual indicators when hooks are executing. | `true`  |
+| UI Label           | Setting                     | Description                                      | Default |
+| ------------------ | --------------------------- | ------------------------------------------------ | ------- |
+| Hook Notifications | `hooksConfig.notifications` | Show visual indicators when hooks are executing. | `true`  |
 
 <!-- SETTINGS-AUTOGEN:END -->

docs/cli/system-prompt.md

@@ -56,6 +56,38 @@ error with: `missing system prompt file '<path>'`.
 When `GEMINI_SYSTEM_MD` is active, the CLI shows a `|⌐■_■|` indicator in the UI
 to signal custom system‑prompt mode.
 
+## Variable Substitution
+
+When using a custom system prompt file, you can use the following variables to
+dynamically include built-in content:
+
+- `${AgentSkills}`: Injects a complete section (including header) of all
+  available agent skills.
+- `${SubAgents}`: Injects a complete section (including header) of available
+  sub-agents.
+- `${AvailableTools}`: Injects a bulleted list of all currently enabled tool
+  names.
+- Tool Name Variables: Injects the actual name of a tool using the pattern:
+  `${toolName}_ToolName` (e.g., `${write_file_ToolName}`,
+  `${run_shell_command_ToolName}`).
+
+  This pattern is generated dynamically for all available tools.
+
+### Example
+
+```markdown
+# Custom System Prompt
+
+You are a helpful assistant. ${AgentSkills}
+${SubAgents}
+
+## Tooling
+
+The following tools are available to you: ${AvailableTools}
+
+You can use ${write_file_ToolName} to save logs.
+```
+
 ## Export the default prompt (recommended)
 
 Before overriding, export the current default prompt so you can review required

docs/cli/telemetry.md

@@ -18,6 +18,7 @@ Learn how to enable and setup OpenTelemetry for Gemini CLI.
   - [Logs and metrics](#logs-and-metrics)
     - [Logs](#logs)
       - [Sessions](#sessions)
+      - [Approval Mode](#approval-mode)
       - [Tools](#tools)
       - [Files](#files)
       - [API](#api)
@@ -315,6 +316,20 @@ Captures startup configuration and user prompt submissions.
     - `prompt` (string; excluded if `telemetry.logPrompts` is `false`)
     - `auth_type` (string)
 
+#### Approval Mode
+
+Tracks changes and duration of approval modes.
+
+- `approval_mode_switch`: Approval mode was changed.
+  - **Attributes**:
+    - `from_mode` (string)
+    - `to_mode` (string)
+
+- `approval_mode_duration`: Duration spent in an approval mode.
+  - **Attributes**:
+    - `mode` (string)
+    - `duration_ms` (int)
+
 #### Tools
 
 Captures tool executions, output truncation, and Edit behavior.

docs/core/index.md

@@ -68,6 +68,10 @@ If you are using the default "pro" model and the CLI detects that you are being
 rate-limited, it automatically switches to the "flash" model for the current
 session. This allows you to continue working without interruption.
 
+Internal utility calls that use `gemini-2.5-flash-lite` (for example, prompt
+completion and classification) silently fall back to `gemini-2.5-flash` and
+`gemini-2.5-pro` when quota is exhausted, without changing the configured model.
+
 ## File discovery service
 
 The file discovery service is responsible for finding files in the project that

docs/get-started/configuration.md

@@ -707,7 +707,7 @@ their corresponding top-level category object in your `settings.json` file.
   - **Description:** Disable LLM-based error correction for edit tools. When
     enabled, tools will fail immediately if exact string matches are not found,
     instead of attempting to self-correct.
-  - **Default:** `false`
+  - **Default:** `true`
   - **Requires restart:** Yes
 
 - **`tools.enableHooks`** (boolean):
@@ -837,7 +837,7 @@ their corresponding top-level category object in your `settings.json` file.
 
 - **`experimental.enableEventDrivenScheduler`** (boolean):
   - **Description:** Enables event-driven scheduler within the CLI session.
-  - **Default:** `false`
+  - **Default:** `true`
   - **Requires restart:** Yes
 
 - **`experimental.extensionReloading`** (boolean):
@@ -855,43 +855,11 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `false`
   - **Requires restart:** Yes
 
-- **`experimental.codebaseInvestigatorSettings.enabled`** (boolean):
-  - **Description:** Enable the Codebase Investigator agent.
-  - **Default:** `true`
-  - **Requires restart:** Yes
-
-- **`experimental.codebaseInvestigatorSettings.maxNumTurns`** (number):
-  - **Description:** Maximum number of turns for the Codebase Investigator
-    agent.
-  - **Default:** `10`
-  - **Requires restart:** Yes
-
-- **`experimental.codebaseInvestigatorSettings.maxTimeMinutes`** (number):
-  - **Description:** Maximum time for the Codebase Investigator agent (in
-    minutes).
-  - **Default:** `3`
-  - **Requires restart:** Yes
-
-- **`experimental.codebaseInvestigatorSettings.thinkingBudget`** (number):
-  - **Description:** The thinking budget for the Codebase Investigator agent.
-  - **Default:** `8192`
-  - **Requires restart:** Yes
-
-- **`experimental.codebaseInvestigatorSettings.model`** (string):
-  - **Description:** The model to use for the Codebase Investigator agent.
-  - **Default:** `"auto"`
-  - **Requires restart:** Yes
-
 - **`experimental.useOSC52Paste`** (boolean):
   - **Description:** Use OSC 52 sequence for pasting instead of clipboardy
     (useful for remote sessions).
   - **Default:** `false`
 
-- **`experimental.cliHelpAgentSettings.enabled`** (boolean):
-  - **Description:** Enable the CLI Help Agent.
-  - **Default:** `true`
-  - **Requires restart:** Yes
-
 - **`experimental.plan`** (boolean):
   - **Description:** Enable planning features (Plan Mode and tools).
   - **Default:** `false`
@@ -904,22 +872,24 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `[]`
   - **Requires restart:** Yes
 
-#### `hooks`
+#### `hooksConfig`
 
-- **`hooks.enabled`** (boolean):
+- **`hooksConfig.enabled`** (boolean):
   - **Description:** Canonical toggle for the hooks system. When disabled, no
     hooks will be executed.
-  - **Default:** `false`
+  - **Default:** `true`
 
-- **`hooks.disabled`** (array):
+- **`hooksConfig.disabled`** (array):
   - **Description:** List of hook names (commands) that should be disabled.
     Hooks in this list will not execute even if configured.
   - **Default:** `[]`
 
-- **`hooks.notifications`** (boolean):
+- **`hooksConfig.notifications`** (boolean):
   - **Description:** Show visual indicators when hooks are executing.
   - **Default:** `true`
 
+#### `hooks`
+
 - **`hooks.BeforeTool`** (array):
   - **Description:** Hooks that execute before tool execution. Can intercept,
     validate, or modify tool calls.

docs/hooks/best-practices.md

@@ -1,4 +1,4 @@
-# Hooks on Gemini CLI: Best practices
+# Hooks Best Practices
 
 This guide covers security considerations, performance optimization, debugging
 techniques, and privacy considerations for developing and deploying hooks in
@@ -15,21 +15,20 @@ using parallel operations:
 // Sequential operations are slower
 const data1 = await fetch(url1).then((r) => r.json());
 const data2 = await fetch(url2).then((r) => r.json());
-const data3 = await fetch(url3).then((r) => r.json());
 
 // Prefer parallel operations for better performance
 // Start requests concurrently
 const p1 = fetch(url1).then((r) => r.json());
 const p2 = fetch(url2).then((r) => r.json());
-const p3 = fetch(url3).then((r) => r.json());
 
 // Wait for all results
-const [data1, data2, data3] = await Promise.all([p1, p2, p3]);
+const [data1, data2] = await Promise.all([p1, p2]);
 ```
 
 ### Cache expensive operations
 
-Store results between invocations to avoid repeated computation:
+Store results between invocations to avoid repeated computation, especially for
+hooks that run frequently (like `BeforeTool` or `AfterModel`).
 
 ```javascript
 const fs = require('fs');
@@ -54,6 +53,7 @@ async function main() {
   const cacheKey = `tool-list-${(Date.now() / 3600000) | 0}`; // Hourly cache
 
   if (cache[cacheKey]) {
+    // Write JSON to stdout
     console.log(JSON.stringify(cache[cacheKey]));
     return;
   }
@@ -70,32 +70,20 @@ async function main() {
 ### Use appropriate events
 
 Choose hook events that match your use case to avoid unnecessary execution.
-`AfterAgent` fires once per agent loop completion, while `AfterModel` fires
-after every LLM call (potentially multiple times per loop):
 
-```json
-// If checking final completion, use AfterAgent instead of AfterModel
-{
-  "hooks": {
-    "AfterAgent": [
-      {
-        "matcher": "*",
-        "hooks": [
-          {
-            "name": "final-checker",
-            "command": "./check-completion.sh"
-          }
-        ]
-      }
-    ]
-  }
-}
-```
+- **`AfterAgent`**: Fires **once** per turn after the model finishes its final
+  response. Use this for quality validation (Retries) or final logging.
+- **`AfterModel`**: Fires after **every chunk** of LLM output. Use this for
+  real-time redaction, PII filtering, or monitoring output as it streams.
+
+If you only need to check the final completion, use `AfterAgent` to save
+performance.
 
 ### Filter with matchers
 
 Use specific matchers to avoid unnecessary hook execution. Instead of matching
-all tools with `*`, specify only the tools you need:
+all tools with `*`, specify only the tools you need. This saves the overhead of
+spawning a process for irrelevant events.
 
 ```json
 {
@@ -111,30 +99,32 @@ all tools with `*`, specify only the tools you need:
 
 ### Optimize JSON parsing
 
-For large inputs, use streaming JSON parsers to avoid loading everything into
-memory:
-
-```javascript
-// Standard approach: parse entire input
-const input = JSON.parse(await readStdin());
-const content = input.tool_input.content;
-
-// For very large inputs: stream and extract only needed fields
-const { createReadStream } = require('fs');
-const JSONStream = require('JSONStream');
-
-const stream = createReadStream(0).pipe(JSONStream.parse('tool_input.content'));
-let content = '';
-stream.on('data', (chunk) => {
-  content += chunk;
-});
-```
+For large inputs (like `AfterModel` receiving a large context), standard JSON
+parsing can be slow. If you only need one field, consider streaming parsers or
+lightweight extraction logic, though for most shell scripts `jq` is sufficient.
 
 ## Debugging
 
+### The "Strict JSON" rule
+
+The most common cause of hook failure is "polluting" the standard output.
+
+- **stdout** is for **JSON only**.
+- **stderr** is for **logs and text**.
+
+**Good:**
+
+```bash
+#!/bin/bash
+echo "Starting check..." >&2  # <--- Redirect to stderr
+echo '{"decision": "allow"}'
+
+```
+
 ### Log to files
 
-Write debug information to dedicated log files:
+Since hooks run in the background, writing to a dedicated log file is often the
+easiest way to debug complex logic.
 
 ```bash
 #!/usr/bin/env bash
@@ -151,6 +141,9 @@ log "Received input: ${input:0:100}..."
 # Hook logic here
 
 log "Hook completed successfully"
+# Always output valid JSON to stdout at the end, even if just empty
+echo "{}"
+
 ```
 
 ### Use stderr for errors
@@ -162,6 +155,7 @@ try {
   const result = dangerousOperation();
   console.log(JSON.stringify({ result }));
 } catch (error) {
+  // Write the error description to stderr so the user/agent sees it
   console.error(`Hook error: ${error.message}`);
   process.exit(2); // Blocking error
 }
@@ -169,7 +163,8 @@ try {
 
 ### Test hooks independently
 
-Run hook scripts manually with sample JSON input:
+Run hook scripts manually with sample JSON input to verify they behave as
+expected before hooking them up to the CLI.
 
 ```bash
 # Create test input
@@ -191,33 +186,46 @@ cat test-input.json | .gemini/hooks/my-hook.sh
 
 # Check exit code
 echo "Exit code: $?"
+
 ```
 
 ### Check exit codes
 
-Ensure your script returns the correct exit code:
+Gemini CLI uses exit codes for high-level flow control:
+
+- **Exit 0 (Success)**: The hook ran successfully. The CLI parses `stdout` for
+  JSON decisions.
+- **Exit 2 (System Block)**: A critical block occurred. `stderr` is used as the
+  reason.
+  - For **Agent/Model** events, this aborts the turn.
+  - For **Tool** events, this blocks the tool but allows the agent to continue.
+  - For **AfterAgent**, this triggers an automatic retry turn.
+
+> **TIP**
+>
+> **Blocking vs. Stopping**: Use `decision: "deny"` (or Exit Code 2) to block a
+> **specific action**. Use `{"continue": false}` in your JSON output to **kill
+> the entire agent loop** immediately.
 
 ```bash
 #!/usr/bin/env bash
-set -e  # Exit on error
+set -e
 
 # Hook logic
-process_input() {
-  # ...
-}
-
 if process_input; then
-  echo "Success message"
+  echo '{"decision": "allow"}'
   exit 0
 else
-  echo "Error message" >&2
+  echo "Critical validation failure" >&2
   exit 2
 fi
+
 ```
 
 ### Enable telemetry
 
-Hook execution is logged when `telemetry.logPrompts` is enabled:
+Hook execution is logged when `telemetry.logPrompts` is enabled. You can view
+these logs to debug execution flow.
 
 ```json
 {
@@ -227,11 +235,10 @@ Hook execution is logged when `telemetry.logPrompts` is enabled:
 }
 ```
 
-View hook telemetry in logs to debug execution issues.
-
 ### Use hook panel
 
-The `/hooks panel` command shows execution status and recent output:
+The `/hooks panel` command inside the CLI shows execution status and recent
+output:
 
 ```bash
 /hooks panel
@@ -255,18 +262,64 @@ Begin with basic logging hooks before implementing complex logic:
 # Simple logging hook to understand input structure
 input=$(cat)
 echo "$input" >> .gemini/hook-inputs.log
-echo "Logged input"
+# Always return valid JSON
+echo "{}"
+
+```
+
+### Documenting your hooks
+
+Maintainability is critical for complex hook systems. Use descriptions and
+comments to help yourself and others understand why a hook exists.
+
+**Use the `description` field**: This text is displayed in the `/hooks panel` UI
+and helps diagnose issues.
+
+```json
+{
+  "hooks": {
+    "BeforeTool": [
+      {
+        "matcher": "write_file|replace",
+        "hooks": [
+          {
+            "name": "secret-scanner",
+            "type": "command",
+            "command": "$GEMINI_PROJECT_DIR/.gemini/hooks/block-secrets.sh",
+            "description": "Scans code changes for API keys and secrets before writing"
+          }
+        ]
+      }
+    ]
+  }
+}
+```
+
+**Add comments in hook scripts**: Explain performance expectations and
+dependencies.
+
+```javascript
+#!/usr/bin/env node
+/**
+ * RAG Tool Filter Hook
+ *
+ * Reduces the tool space by extracting keywords from the user's request.
+ *
+ * Performance: ~500ms average
+ * Dependencies: @google/generative-ai
+ */
 ```
 
 ### Use JSON libraries
 
-Parse JSON with proper libraries instead of text processing:
+Parse JSON with proper libraries instead of text processing.
 
 **Bad:**
 
 ```bash
 # Fragile text parsing
 tool_name=$(echo "$input" | grep -oP '"tool_name":\s*"\K[^"]+')
+
 ```
 
 **Good:**
@@ -274,6 +327,7 @@ tool_name=$(echo "$input" | grep -oP '"tool_name":\s*"\K[^"]+')
 ```bash
 # Robust JSON parsing
 tool_name=$(echo "$input" | jq -r '.tool_name')
+
 ```
 
 ### Make scripts executable
@@ -283,6 +337,7 @@ Always make hook scripts executable:
 ```bash
 chmod +x .gemini/hooks/*.sh
 chmod +x .gemini/hooks/*.js
+
 ```
 
 ### Version control
@@ -292,7 +347,7 @@ Commit hooks to share with your team:
 ```bash
 git add .gemini/hooks/
 git add .gemini/settings.json
-git commit -m "Add project hooks for security and testing"
+
 ```
 
 **`.gitignore` considerations:**
@@ -306,295 +361,10 @@ git commit -m "Add project hooks for security and testing"
 # Keep hook scripts
 !.gemini/hooks/*.sh
 !.gemini/hooks/*.js
+
 ```
 
-### Document behavior
-
-Add descriptions to help others understand your hooks:
-
-```json
-{
-  "hooks": {
-    "BeforeTool": [
-      {
-        "matcher": "write_file|replace",
-        "hooks": [
-          {
-            "name": "secret-scanner",
-            "type": "command",
-            "command": "$GEMINI_PROJECT_DIR/.gemini/hooks/block-secrets.sh",
-            "description": "Scans code changes for API keys, passwords, and other secrets before writing"
-          }
-        ]
-      }
-    ]
-  }
-}
-```
-
-Add comments in hook scripts:
-
-```javascript
-#!/usr/bin/env node
-/**
- * RAG Tool Filter Hook
- *
- * This hook reduces the tool space from 100+ tools to ~15 relevant ones
- * by extracting keywords from the user's request and filtering tools
- * based on semantic similarity.
- *
- * Performance: ~500ms average, cached tool embeddings
- * Dependencies: @google/generative-ai
- */
-```
-
-## Troubleshooting
-
-### Hook not executing
-
-**Check hook name in `/hooks panel`:**
-
-```bash
-/hooks panel
-```
-
-Verify the hook appears in the list and is enabled.
-
-**Verify matcher pattern:**
-
-```bash
-# Test regex pattern
-echo "write_file|replace" | grep -E "write_.*|replace"
-```
-
-**Check disabled list:**
-
-```json
-{
-  "hooks": {
-    "disabled": ["my-hook-name"]
-  }
-}
-```
-
-**Ensure script is executable:**
-
-```bash
-ls -la .gemini/hooks/my-hook.sh
-chmod +x .gemini/hooks/my-hook.sh
-```
-
-**Verify script path:**
-
-```bash
-# Check path expansion
-echo "$GEMINI_PROJECT_DIR/.gemini/hooks/my-hook.sh"
-
-# Verify file exists
-test -f "$GEMINI_PROJECT_DIR/.gemini/hooks/my-hook.sh" && echo "File exists"
-```
-
-### Hook timing out
-
-**Check configured timeout:**
-
-```json
-{
-  "name": "slow-hook",
-  "timeout": 60000
-}
-```
-
-**Optimize slow operations:**
-
-```javascript
-// Before: Sequential operations (slow)
-for (const item of items) {
-  await processItem(item);
-}
-
-// After: Parallel operations (fast)
-await Promise.all(items.map((item) => processItem(item)));
-```
-
-**Use caching:**
-
-```javascript
-const cache = new Map();
-
-async function getCachedData(key) {
-  if (cache.has(key)) {
-    return cache.get(key);
-  }
-  const data = await fetchData(key);
-  cache.set(key, data);
-  return data;
-}
-```
-
-**Consider splitting into multiple faster hooks:**
-
-```json
-{
-  "hooks": {
-    "BeforeTool": [
-      {
-        "matcher": "write_file",
-        "hooks": [
-          {
-            "name": "quick-check",
-            "command": "./quick-validation.sh",
-            "timeout": 1000
-          }
-        ]
-      },
-      {
-        "matcher": "write_file",
-        "hooks": [
-          {
-            "name": "deep-check",
-            "command": "./deep-analysis.sh",
-            "timeout": 30000
-          }
-        ]
-      }
-    ]
-  }
-}
-```
-
-### Invalid JSON output
-
-**Validate JSON before outputting:**
-
-```bash
-#!/usr/bin/env bash
-output='{"decision": "allow"}'
-
-# Validate JSON
-if echo "$output" | jq empty 2>/dev/null; then
-  echo "$output"
-else
-  echo "Invalid JSON generated" >&2
-  exit 1
-fi
-```
-
-**Ensure proper quoting and escaping:**
-
-```javascript
-// Bad: Unescaped string interpolation
-const message = `User said: ${userInput}`;
-console.log(JSON.stringify({ message }));
-
-// Good: Automatic escaping
-console.log(JSON.stringify({ message: `User said: ${userInput}` }));
-```
-
-**Check for binary data or control characters:**
-
-```javascript
-function sanitizeForJSON(str) {
-  return str.replace(/[\x00-\x1F\x7F-\x9F]/g, ''); // Remove control chars
-}
-
-const cleanContent = sanitizeForJSON(content);
-console.log(JSON.stringify({ content: cleanContent }));
-```
-
-### Exit code issues
-
-**Verify script returns correct codes:**
-
-```bash
-#!/usr/bin/env bash
-set -e  # Exit on error
-
-# Processing logic
-if validate_input; then
-  echo "Success"
-  exit 0
-else
-  echo "Validation failed" >&2
-  exit 2
-fi
-```
-
-**Check for unintended errors:**
-
-```bash
-#!/usr/bin/env bash
-# Don't use 'set -e' if you want to handle errors explicitly
-# set -e
-
-if ! command_that_might_fail; then
-  # Handle error
-  echo "Command failed but continuing" >&2
-fi
-
-# Always exit explicitly
-exit 0
-```
-
-**Use trap for cleanup:**
-
-```bash
-#!/usr/bin/env bash
-
-cleanup() {
-  # Cleanup logic
-  rm -f /tmp/hook-temp-*
-}
-
-trap cleanup EXIT
-
-# Hook logic here
-```
-
-### Environment variables not available
-
-**Check if variable is set:**
-
-```bash
-#!/usr/bin/env bash
-
-if [ -z "$GEMINI_PROJECT_DIR" ]; then
-  echo "GEMINI_PROJECT_DIR not set" >&2
-  exit 1
-fi
-
-if [ -z "$CUSTOM_VAR" ]; then
-  echo "Warning: CUSTOM_VAR not set, using default" >&2
-  CUSTOM_VAR="default-value"
-fi
-```
-
-**Debug available variables:**
-
-```bash
-#!/usr/bin/env bash
-
-# List all environment variables
-env > .gemini/hook-env.log
-
-# Check specific variables
-echo "GEMINI_PROJECT_DIR: $GEMINI_PROJECT_DIR" >> .gemini/hook-env.log
-echo "GEMINI_SESSION_ID: $GEMINI_SESSION_ID" >> .gemini/hook-env.log
-echo "GEMINI_API_KEY: ${GEMINI_API_KEY:+<set>}" >> .gemini/hook-env.log
-```
-
-**Use .env files:**
-
-```bash
-#!/usr/bin/env bash
-
-# Load .env file if it exists
-if [ -f "$GEMINI_PROJECT_DIR/.env" ]; then
-  source "$GEMINI_PROJECT_DIR/.env"
-fi
-```
-
-## Using Hooks Securely
+## Hook security
 
 ### Threat Model
 
@@ -621,11 +391,10 @@ When you open a project with hooks defined in `.gemini/settings.json`:
    it).
 5. **Trust**: The hook is marked as "trusted" for this project.
 
-> [!IMPORTANT] **Modification Detection**: If the `command` string of a project
-> hook is changed (e.g., by a `git pull`), its identity changes. Gemini CLI will
-> treat it as a **new, untrusted hook** and warn you again. This prevents
-> malicious actors from silently swapping a verified command for a malicious
-> one.
+> **Modification detection**: If the `command` string of a project hook is
+> changed (e.g., by a `git pull`), its identity changes. Gemini CLI will treat
+> it as a **new, untrusted hook** and warn you again. This prevents malicious
+> actors from silently swapping a verified command for a malicious one.
 
 ### Risks
 
@@ -646,32 +415,134 @@ When you open a project with hooks defined in `.gemini/settings.json`:
   publishers, well-known community members).
 - Be cautious with obfuscated scripts or compiled binaries from unknown sources.
 
-#### Sanitize Environment
+#### Sanitize environment
 
 Hooks inherit the environment of the Gemini CLI process, which may include
-sensitive API keys. Gemini CLI attempts to sanitize sensitive variables, but you
-should be cautious.
+sensitive API keys. Gemini CLI provides a
+[redaction system](/docs/get-started/configuration#environment-variable-redaction)
+that automatically filters variables matching sensitive patterns (e.g., `KEY`,
+`TOKEN`).
 
-- **Avoid printing environment variables** to stdout/stderr unless necessary.
-- **Use `.env` files** to securely manage sensitive variables, ensuring they are
-  excluded from version control.
+> **Disabled by Default**: Environment redaction is currently **OFF by
+> default**. We strongly recommend enabling it if you are running third-party
+> hooks or working in sensitive environments.
 
-**System Administrators:** You can enforce environment variable redaction by
-default in the system configuration (e.g., `/etc/gemini-cli/settings.json`):
+**Impact on hooks:**
+
+- **Security**: Prevents your hook scripts from accidentally leaking secrets.
+- **Troubleshooting**: If your hook depends on a specific environment variable
+  that is being blocked, you must explicitly allow it in `settings.json`.
 
 ```json
 {
   "security": {
     "environmentVariableRedaction": {
       "enabled": true,
-      "blocked": ["MY_SECRET_KEY"],
-      "allowed": ["SAFE_VAR"]
+      "allowed": ["MY_REQUIRED_TOOL_KEY"]
     }
   }
 }
 ```
 
-## Authoring Secure Hooks
+**System administrators:** You can enforce redaction for all users in the system
+configuration.
+
+## Troubleshooting
+
+### Hook not executing
+
+**Check hook name in `/hooks panel`:** Verify the hook appears in the list and
+is enabled.
+
+**Verify matcher pattern:**
+
+```bash
+# Test regex pattern
+echo "write_file|replace" | grep -E "write_.*|replace"
+
+```
+
+**Check disabled list:** Verify the hook is not listed in your `settings.json`:
+
+```json
+{
+  "hooks": {
+    "disabled": ["my-hook-name"]
+  }
+}
+```
+
+**Ensure script is executable**: For macOS and Linux users, verify the script
+has execution permissions:
+
+```bash
+ls -la .gemini/hooks/my-hook.sh
+chmod +x .gemini/hooks/my-hook.sh
+```
+
+**Verify script path:** Ensure the path in `settings.json` resolves correctly.
+
+```bash
+# Check path expansion
+echo "$GEMINI_PROJECT_DIR/.gemini/hooks/my-hook.sh"
+
+# Verify file exists
+test -f "$GEMINI_PROJECT_DIR/.gemini/hooks/my-hook.sh" && echo "File exists"
+```
+
+### Hook timing out
+
+**Check configured timeout:** The default is 60000ms (1 minute). You can
+increase this in `settings.json`:
+
+```json
+{
+  "name": "slow-hook",
+  "timeout": 120000
+}
+```
+
+**Optimize slow operations:** Move heavy processing to background tasks or use
+caching.
+
+### Invalid JSON output
+
+**Validate JSON before outputting:**
+
+```bash
+#!/usr/bin/env bash
+output='{"decision": "allow"}'
+
+# Validate JSON
+if echo "$output" | jq empty 2>/dev/null; then
+  echo "$output"
+else
+  echo "Invalid JSON generated" >&2
+  exit 1
+fi
+
+```
+
+### Environment variables not available
+
+**Check if variable is set:**
+
+```bash
+#!/usr/bin/env bash
+if [ -z "$GEMINI_PROJECT_DIR" ]; then
+  echo "GEMINI_PROJECT_DIR not set" >&2
+  exit 1
+fi
+
+```
+
+**Debug available variables:**
+
+```bash
+env > .gemini/hook-env.log
+```
+
+## Authoring secure hooks
 
 When writing your own hooks, follow these practices to ensure they are robust
 and secure.
@@ -766,40 +637,17 @@ function containsSecret(content) {
 
 ## Privacy considerations
 
-Hook inputs and outputs may contain sensitive information. Gemini CLI respects
-the `telemetry.logPrompts` setting for hook data logging.
+Hook inputs and outputs may contain sensitive information.
 
 ### What data is collected
 
-Hook telemetry may include:
-
-- **Hook inputs:** User prompts, tool arguments, file contents
-- **Hook outputs:** Hook responses, decision reasons, added context
-- **Standard streams:** stdout and stderr from hook processes
-- **Execution metadata:** Hook name, event type, duration, success/failure
+Hook telemetry may include inputs (prompts, code) and outputs (decisions,
+reasons) unless disabled.
 
 ### Privacy settings
 
-**Enabled (default):**
-
-Full hook I/O is logged to telemetry. Use this when:
-
-- Developing and debugging hooks
-- Telemetry is redirected to a trusted enterprise system
-- You understand and accept the privacy implications
-
-**Disabled:**
-
-Only metadata is logged (event name, duration, success/failure). Hook inputs and
-outputs are excluded. Use this when:
-
-- Sending telemetry to third-party systems
-- Working with sensitive data
-- Privacy regulations require minimizing data collection
-
-### Configuration
-
-**Disable PII logging in settings:**
+**Disable PII logging:** If you are working with sensitive data, disable prompt
+logging in your settings:
 
 ```json
 {
@@ -809,48 +657,19 @@ outputs are excluded. Use this when:
 }
 ```
 
-**Disable via environment variable:**
+**Suppress Output:** Individual hooks can request their metadata be hidden from
+logs and telemetry by returning `"suppressOutput": true` in their JSON response.
 
-```bash
-export GEMINI_TELEMETRY_LOG_PROMPTS=false
-```
+> **Note**
+
+> `suppressOutput` only affects background logging. Any `systemMessage` or
+> `reason` included in the JSON will still be displayed to the user in the
+> terminal.
 
 ### Sensitive data in hooks
 
 If your hooks process sensitive data:
 
-1. **Minimize logging:** Don't write sensitive data to log files
-2. **Sanitize outputs:** Remove sensitive data before outputting
-3. **Use secure storage:** Encrypt sensitive data at rest
-4. **Limit access:** Restrict hook script permissions
-
-**Example sanitization:**
-
-```javascript
-function sanitizeOutput(data) {
-  const sanitized = { ...data };
-
-  // Remove sensitive fields
-  delete sanitized.apiKey;
-  delete sanitized.password;
-
-  // Redact sensitive strings
-  if (sanitized.content) {
-    sanitized.content = sanitized.content.replace(
-      /api[_-]?key\s*[:=]\s*['"]?[a-zA-Z0-9_-]{20,}['"]?/gi,
-      '[REDACTED]',
-    );
-  }
-
-  return sanitized;
-}
-
-console.log(JSON.stringify(sanitizeOutput(hookOutput)));
-```
-
-## Learn more
-
-- [Hooks Reference](index.md) - Complete API reference
-- [Writing Hooks](writing-hooks.md) - Tutorial and examples
-- [Configuration](../get-started/configuration.md) - Gemini CLI settings
-- [Hooks Design Document](../hooks-design.md) - Technical architecture
+1. **Minimize logging:** Don't write sensitive data to log files.
+2. **Sanitize outputs:** Remove sensitive data before outputting JSON or writing
+   to stderr.

docs/hooks/index.md

@@ -1,112 +1,119 @@
-# Gemini CLI hooks
+# Gemini CLI hooks (experimental)
 
 Hooks are scripts or programs that Gemini CLI executes at specific points in the
 agentic loop, allowing you to intercept and customize behavior without modifying
 the CLI's source code.
 
-> **Note: Hooks are currently an experimental feature.**
->
-> To use hooks, you must explicitly enable them in your `settings.json`:
->
-> ```json
-> {
->   "tools": { "enableHooks": true },
->   "hooks": { "enabled": true }
-> }
-> ```
->
-> Both of these are needed in this experimental phase.
+## Availability
 
-See [writing hooks guide](writing-hooks.md) for a tutorial on creating your
-first hook and a comprehensive example.
+> **Experimental Feature**: Hooks are currently enabled by default only in the
+> **Preview** and **Nightly** release channels.
 
-See [hooks reference](reference.md) for the technical specification of the I/O
-schemas.
+If you are on the Stable channel, you must explicitly enable the hooks system in
+your `settings.json`:
 
-See [best practices](best-practices.md) for guidelines on security, performance,
-and debugging.
+```json
+{
+  "hooksConfig": {
+    "enabled": true
+  }
+}
+```
+
+- **[Writing hooks guide](/docs/hooks/writing-hooks)**: A tutorial on creating
+  your first hook with comprehensive examples.
+- **[Hooks reference](/docs/hooks/reference)**: The definitive technical
+  specification of I/O schemas and exit codes.
+- **[Best practices](/docs/hooks/best-practices)**: Guidelines on security,
+  performance, and debugging.
 
 ## What are hooks?
 
-With hooks, you can:
-
-- **Add context:** Inject relevant information before the model processes a
-  request
-- **Validate actions:** Review and block potentially dangerous operations
-- **Enforce policies:** Implement security and compliance requirements
-- **Log interactions:** Track tool usage and model responses
-- **Optimize behavior:** Dynamically adjust tool selection or model parameters
-
 Hooks run synchronously as part of the agent loop—when a hook event fires,
 Gemini CLI waits for all matching hooks to complete before continuing.
 
-## Security and Risks
+With hooks, you can:
 
-> **Warning: Hooks execute arbitrary code with your user privileges.**
->
-> By configuring hooks, you are explicitly allowing Gemini CLI to run shell
-> commands on your machine. Malicious or poorly configured hooks can:
-
-- **Exfiltrate data**: Read sensitive files (`.env`, ssh keys) and send them to
-  remote servers.
-- **Modify system**: Delete files, install malware, or change system settings.
-- **Consume resources**: Run infinite loops or crash your system.
-
-**Project-level hooks** (in `.gemini/settings.json`) and **Extension hooks** are
-particularly risky when opening third-party projects or extensions from
-untrusted authors. Gemini CLI will **warn you** the first time it detects a new
-project hook (identified by its name and command), but it is **your
-responsibility** to review these hooks (and any installed extensions) before
-trusting them.
-
-> **Note:** Extension hooks are subject to a mandatory security warning and
-> consent flow during extension installation or update if hooks are detected.
-> You must explicitly approve the installation or update of any extension that
-> contains hooks.
-
-See [Security Considerations](best-practices.md#using-hooks-securely) for a
-detailed threat model and mitigation strategies.
+- **Add context:** Inject relevant information (like git history) before the
+  model processes a request.
+- **Validate actions:** Review tool arguments and block potentially dangerous
+  operations.
+- **Enforce policies:** Implement security scanners and compliance checks.
+- **Log interactions:** Track tool usage and model responses for auditing.
+- **Optimize behavior:** Dynamically filter available tools or adjust model
+  parameters.
 
 ## Core concepts
 
 ### Hook events
 
-Hooks are triggered by specific events in Gemini CLI's lifecycle. The following
-table lists all available hook events:
+Hooks are triggered by specific events in Gemini CLI's lifecycle.
 
-| Event                 | When It Fires                                 | Common Use Cases                           |
-| --------------------- | --------------------------------------------- | ------------------------------------------ |
-| `SessionStart`        | When a session begins                         | Initialize resources, load context         |
-| `SessionEnd`          | When a session ends                           | Clean up, save state                       |
-| `BeforeAgent`         | After user submits prompt, before planning    | Add context, validate prompts              |
-| `AfterAgent`          | When agent loop ends                          | Review output, force continuation          |
-| `BeforeModel`         | Before sending request to LLM                 | Modify prompts, add instructions           |
-| `AfterModel`          | After receiving LLM response                  | Filter responses, log interactions         |
-| `BeforeToolSelection` | Before LLM selects tools (after BeforeModel)  | Filter available tools, optimize selection |
-| `BeforeTool`          | Before a tool executes                        | Validate arguments, block dangerous ops    |
-| `AfterTool`           | After a tool executes                         | Process results, run tests                 |
-| `PreCompress`         | Before context compression                    | Save state, notify user                    |
-| `Notification`        | When a notification occurs (e.g., permission) | Auto-approve, log decisions                |
+| Event                 | When It Fires                                  | Impact                 | Common Use Cases                             |
+| --------------------- | ---------------------------------------------- | ---------------------- | -------------------------------------------- |
+| `SessionStart`        | When a session begins (startup, resume, clear) | Inject Context         | Initialize resources, load context           |
+| `SessionEnd`          | When a session ends (exit, clear)              | Advisory               | Clean up, save state                         |
+| `BeforeAgent`         | After user submits prompt, before planning     | Block Turn / Context   | Add context, validate prompts, block turns   |
+| `AfterAgent`          | When agent loop ends                           | Retry / Halt           | Review output, force retry or halt execution |
+| `BeforeModel`         | Before sending request to LLM                  | Block Turn / Mock      | Modify prompts, swap models, mock responses  |
+| `AfterModel`          | After receiving LLM response                   | Block Turn / Redact    | Filter/redact responses, log interactions    |
+| `BeforeToolSelection` | Before LLM selects tools                       | Filter Tools           | Filter available tools, optimize selection   |
+| `BeforeTool`          | Before a tool executes                         | Block Tool / Rewrite   | Validate arguments, block dangerous ops      |
+| `AfterTool`           | After a tool executes                          | Block Result / Context | Process results, run tests, hide results     |
+| `PreCompress`         | Before context compression                     | Advisory               | Save state, notify user                      |
+| `Notification`        | When a system notification occurs              | Advisory               | Forward to desktop alerts, logging           |
 
-### Hook types
+### Global mechanics
 
-Gemini CLI currently supports **command hooks** that run shell commands or
-scripts:
+Understanding these core principles is essential for building robust hooks.
 
-```json
-{
-  "type": "command",
-  "command": "$GEMINI_PROJECT_DIR/.gemini/hooks/my-hook.sh",
-  "timeout": 30000
-}
-```
+#### Strict JSON requirements (The "Golden Rule")
 
-**Note:** Plugin hooks (npm packages) are planned for a future release.
+Hooks communicate via `stdin` (Input) and `stdout` (Output).
 
-### Matchers
+1. **Silence is Mandatory**: Your script **must not** print any plain text to
+   `stdout` other than the final JSON object. **Even a single `echo` or `print`
+   call before the JSON will break parsing.**
+2. **Pollution = Failure**: If `stdout` contains non-JSON text, parsing will
+   fail. The CLI will default to "Allow" and treat the entire output as a
+   `systemMessage`.
+3. **Debug via Stderr**: Use `stderr` for **all** logging and debugging (e.g.,
+   `echo "debug" >&2`). Gemini CLI captures `stderr` but never attempts to parse
+   it as JSON.
 
-For tool-related events (`BeforeTool`, `AfterTool`), you can filter which tools
-trigger the hook:
+#### Exit codes
+
+Gemini CLI uses exit codes to determine the high-level outcome of a hook
+execution:
+
+| Exit Code | Label            | Behavioral Impact                                                                                                                                                            |
+| --------- | ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **0**     | **Success**      | The `stdout` is parsed as JSON. **Preferred code** for all logic, including intentional blocks (e.g., `{"decision": "deny"}`).                                               |
+| **2**     | **System Block** | **Critical Block**. The target action (tool, turn, or stop) is aborted. `stderr` is used as the rejection reason. High severity; used for security stops or script failures. |
+| **Other** | **Warning**      | Non-fatal failure. A warning is shown, but the interaction proceeds using original parameters.                                                                               |
+
+#### Matchers
+
+You can filter which specific tools or triggers fire your hook using the
+`matcher` field.
+
+- **Tool events** (`BeforeTool`, `AfterTool`): Matchers are **Regular
+  Expressions**. (e.g., `"write_.*"`).
+- **Lifecycle events**: Matchers are **Exact Strings**. (e.g., `"startup"`).
+- **Wildcards**: `"*"` or `""` (empty string) matches all occurrences.
+
+## Configuration
+
+Hook definitions are configured in `settings.json`. Gemini CLI merges
+configurations from multiple layers in the following order of precedence
+(highest to lowest):
+
+1.  **Project settings**: `.gemini/settings.json` in the current directory.
+2.  **User settings**: `~/.gemini/settings.json`.
+3.  **System settings**: `/etc/gemini-cli/settings.json`.
+4.  **Extensions**: Hooks defined by installed extensions.
+
+### Configuration schema
 
 ```json
 {
@@ -114,382 +121,13 @@ trigger the hook:
     "BeforeTool": [
       {
         "matcher": "write_file|replace",
-        "hooks": [
-          /* hooks for write operations */
-        ]
-      }
-    ]
-  }
-}
-```
-
-**Matcher patterns:**
-
-- **Exact match:** `"read_file"` matches only `read_file`
-- **Regex:** `"write_.*|replace"` matches `write_file`, `replace`
-- **Wildcard:** `"*"` or `""` matches all tools
-
-**Session event matchers:**
-
-- **SessionStart:** `startup`, `resume`, `clear`
-- **SessionEnd:** `exit`, `clear`, `logout`, `prompt_input_exit`
-- **PreCompress:** `manual`, `auto`
-- **Notification:** `ToolPermission`
-
-## Hook input/output contract
-
-### Command hook communication
-
-Hooks communicate via:
-
-- **Input:** JSON on stdin
-- **Output:** Exit code + stdout/stderr
-
-### Exit codes
-
-- **0:** Success - stdout shown to user (or injected as context for some events)
-- **2:** Blocking error - stderr shown to agent/user, operation may be blocked
-- **Other:** Non-blocking warning - logged but execution continues
-
-### Common input fields
-
-Every hook receives these base fields:
-
-```json
-{
-  "session_id": "abc123",
-  "transcript_path": "/path/to/transcript.jsonl",
-  "cwd": "/path/to/project",
-  "hook_event_name": "BeforeTool",
-  "timestamp": "2025-12-01T10:30:00Z"
-  // ... event-specific fields
-}
-```
-
-### Event-specific fields
-
-#### BeforeTool
-
-**Input:**
-
-```json
-{
-  "tool_name": "write_file",
-  "tool_input": {
-    "file_path": "/path/to/file.ts",
-    "content": "..."
-  }
-}
-```
-
-**Output (JSON on stdout):**
-
-```json
-{
-  "decision": "allow|deny|ask|block",
-  "reason": "Explanation shown to agent",
-  "systemMessage": "Message shown to user"
-}
-```
-
-Or simple exit codes:
-
-- Exit 0 = allow (stdout shown to user)
-- Exit 2 = deny (stderr shown to agent)
-
-#### AfterTool
-
-**Input:**
-
-```json
-{
-  "tool_name": "read_file",
-  "tool_input": { "file_path": "..." },
-  "tool_response": "file contents..."
-}
-```
-
-**Output:**
-
-```json
-{
-  "decision": "allow|deny",
-  "hookSpecificOutput": {
-    "hookEventName": "AfterTool",
-    "additionalContext": "Extra context for agent"
-  }
-}
-```
-
-#### BeforeAgent
-
-**Input:**
-
-```json
-{
-  "prompt": "Fix the authentication bug"
-}
-```
-
-**Output:**
-
-```json
-{
-  "decision": "allow|deny",
-  "hookSpecificOutput": {
-    "hookEventName": "BeforeAgent",
-    "additionalContext": "Recent project decisions: ..."
-  }
-}
-```
-
-#### BeforeModel
-
-**Input:**
-
-```json
-{
-  "llm_request": {
-    "model": "gemini-2.0-flash-exp",
-    "messages": [{ "role": "user", "content": "Hello" }],
-    "config": { "temperature": 0.7 },
-    "toolConfig": {
-      "functionCallingConfig": {
-        "mode": "AUTO",
-        "allowedFunctionNames": ["read_file", "write_file"]
-      }
-    }
-  }
-}
-```
-
-**Output:**
-
-```json
-{
-  "decision": "allow",
-  "hookSpecificOutput": {
-    "hookEventName": "BeforeModel",
-    "llm_request": {
-      "messages": [
-        { "role": "system", "content": "Additional instructions..." },
-        { "role": "user", "content": "Hello" }
-      ]
-    }
-  }
-}
-```
-
-#### AfterModel
-
-**Input:**
-
-```json
-{
-  "llm_request": {
-    "model": "gemini-2.0-flash-exp",
-    "messages": [
-      /* ... */
-    ],
-    "config": {
-      /* ... */
-    },
-    "toolConfig": {
-      /* ... */
-    }
-  },
-  "llm_response": {
-    "text": "string",
-    "candidates": [
-      {
-        "content": {
-          "role": "model",
-          "parts": ["array of content parts"]
-        },
-        "finishReason": "STOP"
-      }
-    ]
-  }
-}
-```
-
-**Output:**
-
-```json
-{
-  "hookSpecificOutput": {
-    "hookEventName": "AfterModel",
-    "llm_response": {
-      "candidate": {
-        /* modified response */
-      }
-    }
-  }
-}
-```
-
-#### BeforeToolSelection
-
-**Input:**
-
-```json
-{
-  "llm_request": {
-    "model": "gemini-2.0-flash-exp",
-    "messages": [
-      /* ... */
-    ],
-    "toolConfig": {
-      "functionCallingConfig": {
-        "mode": "AUTO",
-        "allowedFunctionNames": [
-          /* 100+ tools */
-        ]
-      }
-    }
-  }
-}
-```
-
-**Output:**
-
-```json
-{
-  "hookSpecificOutput": {
-    "hookEventName": "BeforeToolSelection",
-    "toolConfig": {
-      "functionCallingConfig": {
-        "mode": "ANY",
-        "allowedFunctionNames": ["read_file", "write_file", "replace"]
-      }
-    }
-  }
-}
-```
-
-Or simple output (comma-separated tool names sets mode to ANY):
-
-```bash
-echo "read_file,write_file,replace"
-```
-
-#### SessionStart
-
-**Input:**
-
-```json
-{
-  "source": "startup|resume|clear"
-}
-```
-
-**Output:**
-
-```json
-{
-  "hookSpecificOutput": {
-    "hookEventName": "SessionStart",
-    "additionalContext": "Loaded 5 project memories"
-  }
-}
-```
-
-#### SessionEnd
-
-**Input:**
-
-```json
-{
-  "reason": "exit|clear|logout|prompt_input_exit|other"
-}
-```
-
-No structured output expected (but stdout/stderr logged).
-
-#### PreCompress
-
-**Input:**
-
-```json
-{
-  "trigger": "manual|auto"
-}
-```
-
-**Output:**
-
-```json
-{
-  "systemMessage": "Compression starting..."
-}
-```
-
-#### Notification
-
-**Input:**
-
-```json
-{
-  "notification_type": "ToolPermission",
-  "message": "string",
-  "details": {
-    /* notification details */
-  }
-}
-```
-
-**Output:**
-
-```json
-{
-  "systemMessage": "Notification logged"
-}
-```
-
-## Configuration
-
-Hook definitions are configured in `settings.json` files using the `hooks`
-object. Configuration can be specified at multiple levels with defined
-precedence rules.
-
-### Configuration layers
-
-Hook configurations are applied in the following order of execution (lower
-numbers run first):
-
-1.  **Project settings:** `.gemini/settings.json` in your project directory
-    (highest priority)
-2.  **User settings:** `~/.gemini/settings.json`
-3.  **System settings:** `/etc/gemini-cli/settings.json`
-4.  **Extensions:** Internal hooks defined by installed extensions (lowest
-    priority). See [Extensions documentation](../extensions/index.md#hooks) for
-    details on how extensions define and configure hooks.
-
-#### Deduplication and shadowing
-
-If multiple hooks with the identical **name** and **command** are discovered
-across different configuration layers, Gemini CLI deduplicates them. The hook
-from the higher-priority layer (e.g., Project) will be kept, and others will be
-ignored.
-
-Within each level, hooks run in the order they are declared in the
-configuration.
-
-### Configuration schema
-
-```json
-{
-  "hooks": {
-    "EventName": [
-      {
-        "matcher": "pattern",
         "hooks": [
           {
-            "name": "hook-identifier",
+            "name": "security-check",
             "type": "command",
-            "command": "./path/to/script.sh",
-            "description": "What this hook does",
-            "timeout": 30000
+            "command": "$GEMINI_PROJECT_DIR/.gemini/hooks/security.sh",
+            "timeout": 5000,
+            "sequential": false
           }
         ]
       }
@@ -498,226 +136,33 @@ configuration.
 }
 ```
 
-**Configuration properties:**
-
-- **`name`** (string, recommended): Unique identifier for the hook used in
-  `/hooks enable/disable` commands. If omitted, the `command` path is used as
-  the identifier.
-- **`type`** (string, required): Hook type - currently only `"command"` is
-  supported
-- **`command`** (string, required): Path to the script or command to execute
-- **`description`** (string, optional): Human-readable description shown in
-  `/hooks panel`
-- **`timeout`** (number, optional): Timeout in milliseconds (default: 60000)
-- **`matcher`** (string, optional): Pattern to filter when hook runs (event
-  matchers only)
-
 ### Environment variables
 
-Hooks have access to:
+Hooks are executed with a sanitized environment.
 
-- `GEMINI_PROJECT_DIR`: Project root directory
-- `GEMINI_SESSION_ID`: Current session ID
-- `GEMINI_API_KEY`: Gemini API key (if configured)
-- All other environment variables from the parent process
+- `GEMINI_PROJECT_DIR`: The absolute path to the project root.
+- `GEMINI_SESSION_ID`: The unique ID for the current session.
+- `GEMINI_CWD`: The current working directory.
+- `CLAUDE_PROJECT_DIR`: (Alias) Provided for compatibility.
+
+## Security and risks
+
+> **Warning: Hooks execute arbitrary code with your user privileges.** By
+> configuring hooks, you are allowing scripts to run shell commands on your
+> machine.
+
+**Project-level hooks** are particularly risky when opening untrusted projects.
+Gemini CLI **fingerprints** project hooks. If a hook's name or command changes
+(e.g., via `git pull`), it is treated as a **new, untrusted hook** and you will
+be warned before it executes.
+
+See [Security Considerations](/docs/hooks/best-practices#using-hooks-securely)
+for a detailed threat model.
 
 ## Managing hooks
 
-### View registered hooks
+Use the CLI commands to manage hooks without editing JSON manually:
 
-Use the `/hooks panel` command to view all registered hooks:
-
-```bash
-/hooks panel
-```
-
-This command displays:
-
-- All configured hooks organized by event
-- Hook source (user, project, system)
-- Hook type (command or plugin)
-- Individual hook status (enabled/disabled)
-
-### Enable and disable all hooks at once
-
-You can enable or disable all hooks at once using commands:
-
-```bash
-/hooks enable-all
-/hooks disable-all
-```
-
-These commands provide a shortcut to enable or disable all configured hooks
-without managing them individually. The `enable-all` command removes all hooks
-from the `hooks.disabled` array, while `disable-all` adds all configured hooks
-to the disabled list. Changes take effect immediately without requiring a
-restart.
-
-### Enable and disable individual hooks
-
-You can enable or disable individual hooks using commands:
-
-```bash
-/hooks enable hook-name
-/hooks disable hook-name
-```
-
-These commands allow you to control hook execution without editing configuration
-files. The hook name should match the `name` field in your hook configuration.
-Changes made via these commands are persisted to your settings. The settings are
-saved to workspace scope if available, otherwise to your global user settings
-(`~/.gemini/settings.json`).
-
-### Disabled hooks configuration
-
-To permanently disable hooks, add them to the `hooks.disabled` array in your
-`settings.json`:
-
-```json
-{
-  "hooks": {
-    "disabled": ["secret-scanner", "auto-test"]
-  }
-}
-```
-
-**Note:** The `hooks.disabled` array uses a UNION merge strategy. Disabled hooks
-from all configuration levels (user, project, system) are combined and
-deduplicated, meaning a hook disabled at any level remains disabled.
-
-## Migration from Claude Code
-
-If you have hooks configured for Claude Code, you can migrate them:
-
-```bash
-gemini hooks migrate --from-claude
-```
-
-This command:
-
-- Reads `.claude/settings.json`
-- Converts event names (`PreToolUse` → `BeforeTool`, etc.)
-- Translates tool names (`Bash` → `run_shell_command`, `replace` → `replace`)
-- Updates matcher patterns
-- Writes to `.gemini/settings.json`
-
-### Event name mapping
-
-| Claude Code        | Gemini CLI     |
-| ------------------ | -------------- |
-| `PreToolUse`       | `BeforeTool`   |
-| `PostToolUse`      | `AfterTool`    |
-| `UserPromptSubmit` | `BeforeAgent`  |
-| `Stop`             | `AfterAgent`   |
-| `Notification`     | `Notification` |
-| `SessionStart`     | `SessionStart` |
-| `SessionEnd`       | `SessionEnd`   |
-| `PreCompact`       | `PreCompress`  |
-
-### Tool name mapping
-
-| Claude Code | Gemini CLI            |
-| ----------- | --------------------- |
-| `Bash`      | `run_shell_command`   |
-| `Edit`      | `replace`             |
-| `Read`      | `read_file`           |
-| `Write`     | `write_file`          |
-| `Glob`      | `glob`                |
-| `Grep`      | `search_file_content` |
-| `LS`        | `list_directory`      |
-
-## Tool and Event Matchers Reference
-
-### Available tool names for matchers
-
-The following built-in tools can be used in `BeforeTool` and `AfterTool` hook
-matchers:
-
-#### File operations
-
-- `read_file` - Read a single file
-- `read_many_files` - Read multiple files at once
-- `write_file` - Create or overwrite a file
-- `replace` - Edit file content with find/replace
-
-#### File system
-
-- `list_directory` - List directory contents
-- `glob` - Find files matching a pattern
-- `search_file_content` - Search within file contents
-
-#### Execution
-
-- `run_shell_command` - Execute shell commands
-
-#### Web and external
-
-- `google_web_search` - Google Search with grounding
-- `web_fetch` - Fetch web page content
-
-#### Agent features
-
-- `write_todos` - Manage TODO items
-- `save_memory` - Save information to memory
-- `delegate_to_agent` - Delegate tasks to sub-agents
-
-#### Example matchers
-
-```json
-{
-  "matcher": "write_file|replace" // File editing tools
-}
-```
-
-```json
-{
-  "matcher": "read_.*" // All read operations
-}
-```
-
-```json
-{
-  "matcher": "run_shell_command" // Only shell commands
-}
-```
-
-```json
-{
-  "matcher": "*" // All tools
-}
-```
-
-### Event-specific matchers
-
-#### SessionStart event matchers
-
-- `startup` - Fresh session start
-- `resume` - Resuming a previous session
-- `clear` - Session cleared
-
-#### SessionEnd event matchers
-
-- `exit` - Normal exit
-- `clear` - Session cleared
-- `logout` - User logged out
-- `prompt_input_exit` - Exit from prompt input
-- `other` - Other reasons
-
-#### PreCompress event matchers
-
-- `manual` - Manually triggered compression
-- `auto` - Automatically triggered compression
-
-#### Notification event matchers
-
-- `ToolPermission` - Tool permission notifications
-
-## Learn more
-
-- [Writing Hooks](writing-hooks.md) - Tutorial and comprehensive example
-- [Best Practices](best-practices.md) - Security, performance, and debugging
-- [Custom Commands](../cli/custom-commands.md) - Create reusable prompt
-  shortcuts
-- [Configuration](../get-started/configuration.md) - Gemini CLI configuration
-  options
-- [Hooks Design Document](../hooks-design.md) - Technical architecture details
+- **View hooks:** `/hooks panel`
+- **Enable/Disable all:** `/hooks enable-all` or `/hooks disable-all`
+- **Toggle individual:** `/hooks enable <name>` or `/hooks disable <name>`

docs/hooks/reference.md

@@ -1,178 +1,295 @@
-# Hooks Reference
+# Hooks reference
 
 This document provides the technical specification for Gemini CLI hooks,
-including the JSON schemas for input and output, exit code behaviors, and the
-stable model API.
+including JSON schemas and API details.
 
-## Communication Protocol
+## Global hook mechanics
 
-Hooks communicate with Gemini CLI via standard streams and exit codes:
-
-- **Input**: Gemini CLI sends a JSON object to the hook's `stdin`.
-- **Output**: The hook sends a JSON object (or plain text) to `stdout`.
-- **Exit Codes**: Used to signal success or blocking errors.
-
-### Exit Code Behavior
-
-| Exit Code | Meaning            | Behavior                                                                                        |
-| :-------- | :----------------- | :---------------------------------------------------------------------------------------------- |
-| `0`       | **Success**        | `stdout` is parsed as JSON. If parsing fails, it's treated as a `systemMessage`.                |
-| `2`       | **Blocking Error** | Interrupts the current operation. `stderr` is shown to the agent (for tool events) or the user. |
-| Other     | **Warning**        | Execution continues. `stderr` is logged as a non-blocking warning.                              |
+- **Communication**: `stdin` for Input (JSON), `stdout` for Output (JSON), and
+  `stderr` for logs and feedback.
+- **Exit codes**:
+  - `0`: Success. `stdout` is parsed as JSON. **Preferred for all logic.**
+  - `2`: System Block. The action is blocked; `stderr` is used as the rejection
+    reason.
+  - `Other`: Warning. A non-fatal failure occurred; the CLI continues with a
+    warning.
+- **Silence is Mandatory**: Your script **must not** print any plain text to
+  `stdout` other than the final JSON.
 
 ---
 
-## Input Schema (`stdin`)
+## Base input schema
 
-Every hook receives a base JSON object. Extra fields are added depending on the
-specific event.
+All hooks receive these common fields via `stdin`:
 
-### Base Fields (All Events)
-
-| Field             | Type     | Description                                           |
-| :---------------- | :------- | :---------------------------------------------------- |
-| `session_id`      | `string` | Unique identifier for the current CLI session.        |
-| `transcript_path` | `string` | Path to the session's JSON transcript (if available). |
-| `cwd`             | `string` | The current working directory.                        |
-| `hook_event_name` | `string` | The name of the firing event (e.g., `BeforeTool`).    |
-| `timestamp`       | `string` | ISO 8601 timestamp of the event.                      |
-
-### Event-Specific Fields
-
-#### Tool Events (`BeforeTool`, `AfterTool`)
-
-- `tool_name`: (`string`) The internal name of the tool (e.g., `write_file`,
-  `run_shell_command`).
-- `tool_input`: (`object`) The arguments passed to the tool.
-- `tool_response`: (`object`, **AfterTool only**) The raw output from the tool
-  execution.
-- `mcp_context`: (`object`, **optional**) Present only for MCP tool invocations.
-  Contains server identity information:
-  - `server_name`: (`string`) The configured name of the MCP server.
-  - `tool_name`: (`string`) The original tool name from the MCP server.
-  - `command`: (`string`, optional) For stdio transport, the command used to
-    start the server.
-  - `args`: (`string[]`, optional) For stdio transport, the command arguments.
-  - `cwd`: (`string`, optional) For stdio transport, the working directory.
-  - `url`: (`string`, optional) For SSE/HTTP transport, the server URL.
-  - `tcp`: (`string`, optional) For WebSocket transport, the TCP address.
-
-#### Agent Events (`BeforeAgent`, `AfterAgent`)
-
-- `prompt`: (`string`) The user's submitted prompt.
-- `prompt_response`: (`string`, **AfterAgent only**) The final response text
-  from the model.
-- `stop_hook_active`: (`boolean`, **AfterAgent only**) Indicates if a stop hook
-  is already handling a continuation.
-
-#### Model Events (`BeforeModel`, `AfterModel`, `BeforeToolSelection`)
-
-- `llm_request`: (`LLMRequest`) A stable representation of the outgoing request.
-  See [Stable Model API](#stable-model-api).
-- `llm_response`: (`LLMResponse`, **AfterModel only**) A stable representation
-  of the incoming response.
-
-#### Session & Notification Events
-
-- `source`: (`startup` | `resume` | `clear`, **SessionStart only**) The trigger
-  source.
-- `reason`: (`exit` | `clear` | `logout` | `prompt_input_exit` | `other`,
-  **SessionEnd only**) The reason for session end.
-- `trigger`: (`manual` | `auto`, **PreCompress only**) What triggered the
-  compression event.
-- `notification_type`: (`ToolPermission`, **Notification only**) The type of
-  notification being fired.
-- `message`: (`string`, **Notification only**) The notification message.
-- `details`: (`object`, **Notification only**) Payload-specific details for the
-  notification.
+```typescript
+{
+  "session_id": string,      // Unique ID for the current session
+  "transcript_path": string, // Absolute path to session transcript JSON
+  "cwd": string,             // Current working directory
+  "hook_event_name": string, // The firing event (e.g. "BeforeTool")
+  "timestamp": string        // ISO 8601 execution time
+}
+```
 
 ---
 
-## Output Schema (`stdout`)
+## Common output fields
 
-If the hook exits with `0`, the CLI attempts to parse `stdout` as JSON.
+Most hooks support these fields in their `stdout` JSON:
 
-### Common Output Fields
+| Field            | Type      | Description                                                                    |
+| :--------------- | :-------- | :----------------------------------------------------------------------------- |
+| `systemMessage`  | `string`  | Displayed immediately to the user in the terminal.                             |
+| `suppressOutput` | `boolean` | If `true`, hides internal hook metadata from logs/telemetry.                   |
+| `continue`       | `boolean` | If `false`, stops the entire agent loop immediately.                           |
+| `stopReason`     | `string`  | Displayed to the user when `continue` is `false`.                              |
+| `decision`       | `string`  | `"allow"` or `"deny"` (alias `"block"`). Specific impact depends on the event. |
+| `reason`         | `string`  | The feedback/error message provided when a `decision` is `"deny"`.             |
 
-| Field                | Type      | Description                                                                            |
-| :------------------- | :-------- | :------------------------------------------------------------------------------------- |
-| `decision`           | `string`  | One of: `allow`, `deny`, `block`, `ask`, `approve`.                                    |
-| `reason`             | `string`  | Explanation shown to the **agent** when a decision is `deny` or `block`.               |
-| `systemMessage`      | `string`  | Message displayed in Gemini CLI terminal to provide warning or context to the **user** |
-| `continue`           | `boolean` | If `false`, immediately terminates the agent loop for this turn.                       |
-| `stopReason`         | `string`  | Message shown to the user when `continue` is `false`.                                  |
-| `suppressOutput`     | `boolean` | If `true`, the hook execution is hidden from the CLI transcript.                       |
-| `hookSpecificOutput` | `object`  | Container for event-specific data (see below).                                         |
+---
 
-### `hookSpecificOutput` Reference
+## Tool hooks
 
-| Field               | Supported Events                           | Description                                                                       |
-| :------------------ | :----------------------------------------- | :-------------------------------------------------------------------------------- |
-| `additionalContext` | `SessionStart`, `BeforeAgent`, `AfterTool` | Appends text directly to the agent's context.                                     |
-| `llm_request`       | `BeforeModel`                              | A `Partial<LLMRequest>` to override parameters of the outgoing call.              |
-| `llm_response`      | `BeforeModel`                              | A **full** `LLMResponse` to bypass the model and provide a synthetic result.      |
-| `llm_response`      | `AfterModel`                               | A `Partial<LLMResponse>` to modify the model's response before the agent sees it. |
-| `toolConfig`        | `BeforeToolSelection`                      | Object containing `mode` (`AUTO`/`ANY`/`NONE`) and `allowedFunctionNames`.        |
+### Matchers and tool names
+
+For `BeforeTool` and `AfterTool` events, the `matcher` field in your settings is
+compared against the name of the tool being executed.
+
+- **Built-in Tools**: You can match any built-in tool (e.g., `read_file`,
+  `run_shell_command`). See the [Tools Reference](/docs/tools) for a full list
+  of available tool names.
+- **MCP Tools**: Tools from MCP servers follow the naming pattern
+  `mcp__<server_name>__<tool_name>`.
+- **Regex Support**: Matchers support regular expressions (e.g.,
+  `matcher: "read_.*"` matches all file reading tools).
+
+### `BeforeTool`
+
+Fires before a tool is invoked. Used for argument validation, security checks,
+and parameter rewriting.
+
+- **Input Fields**:
+  - `tool_name`: (`string`) The name of the tool being called.
+  - `tool_input`: (`object`) The raw arguments generated by the model.
+  - `mcp_context`: (`object`) Optional metadata for MCP-based tools.
+- **Relevant Output Fields**:
+  - `decision`: Set to `"deny"` (or `"block"`) to prevent the tool from
+    executing.
+  - `reason`: Required if denied. This text is sent **to the agent** as a tool
+    error, allowing it to respond or retry.
+  - `hookSpecificOutput.tool_input`: An object that **merges with and
+    overrides** the model's arguments before execution.
+  - `continue`: Set to `false` to **kill the entire agent loop** immediately.
+- **Exit Code 2 (Block Tool)**: Prevents execution. Uses `stderr` as the
+  `reason` sent to the agent. **The turn continues.**
+
+### `AfterTool`
+
+Fires after a tool executes. Used for result auditing, context injection, or
+hiding sensitive output from the agent.
+
+- **Input Fields**:
+  - `tool_name`: (`string`)
+  - `tool_input`: (`object`) The original arguments.
+  - `tool_response`: (`object`) The result containing `llmContent`,
+    `returnDisplay`, and optional `error`.
+  - `mcp_context`: (`object`)
+- **Relevant Output Fields**:
+  - `decision`: Set to `"deny"` to hide the real tool output from the agent.
+  - `reason`: Required if denied. This text **replaces** the tool result sent
+    back to the model.
+  - `hookSpecificOutput.additionalContext`: Text that is **appended** to the
+    tool result for the agent.
+  - `continue`: Set to `false` to **kill the entire agent loop** immediately.
+- **Exit Code 2 (Block Result)**: Hides the tool result. Uses `stderr` as the
+  replacement content sent to the agent. **The turn continues.**
+
+---
+
+## Agent hooks
+
+### `BeforeAgent`
+
+Fires after a user submits a prompt, but before the agent begins planning. Used
+for prompt validation or injecting dynamic context.
+
+- **Input Fields**:
+  - `prompt`: (`string`) The original text submitted by the user.
+- **Relevant Output Fields**:
+  - `hookSpecificOutput.additionalContext`: Text that is **appended** to the
+    prompt for this turn only.
+  - `decision`: Set to `"deny"` to block the turn and **discard the user's
+    message** (it will not appear in history).
+  - `continue`: Set to `false` to block the turn but **save the message to
+    history**.
+  - `reason`: Required if denied or stopped.
+- **Exit Code 2 (Block Turn)**: Aborts the turn and erases the prompt from
+  context. Same as `decision: "deny"`.
+
+### `AfterAgent`
+
+Fires once per turn after the model generates its final response. Primary use
+case is response validation and automatic retries.
+
+- **Input Fields**:
+  - `prompt`: (`string`) The user's original request.
+  - `prompt_response`: (`string`) The final text generated by the agent.
+  - `stop_hook_active`: (`boolean`) Indicates if this hook is already running as
+    part of a retry sequence.
+- **Relevant Output Fields**:
+  - `decision`: Set to `"deny"` to **reject the response** and force a retry.
+  - `reason`: Required if denied. This text is sent **to the agent as a new
+    prompt** to request a correction.
+  - `continue`: Set to `false` to **stop the session** without retrying.
+- **Exit Code 2 (Retry)**: Rejects the response and triggers an automatic retry
+  turn using `stderr` as the feedback prompt.
+
+---
+
+## Model hooks
+
+### `BeforeModel`
+
+Fires before sending a request to the LLM. Operates on a stable, SDK-agnostic
+request format.
+
+- **Input Fields**:
+  - `llm_request`: (`object`) Contains `model`, `messages`, and `config`
+    (generation params).
+- **Relevant Output Fields**:
+  - `hookSpecificOutput.llm_request`: An object that **overrides** parts of the
+    outgoing request (e.g., changing models or temperature).
+  - `hookSpecificOutput.llm_response`: A **Synthetic Response** object. If
+    provided, the CLI skips the LLM call entirely and uses this as the response.
+  - `decision`: Set to `"deny"` to block the request and abort the turn.
+- **Exit Code 2 (Block Turn)**: Aborts the turn and skips the LLM call. Uses
+  `stderr` as the error message.
+
+### `BeforeToolSelection`
+
+Fires before the LLM decides which tools to call. Used to filter the available
+toolset or force specific tool modes.
+
+- **Input Fields**:
+  - `llm_request`: (`object`) Same format as `BeforeModel`.
+- **Relevant Output Fields**:
+  - `hookSpecificOutput.toolConfig.mode`: (`"AUTO" | "ANY" | "NONE"`)
+    - `"NONE"`: Disables all tools (Wins over other hooks).
+    - `"ANY"`: Forces at least one tool call.
+  - `hookSpecificOutput.toolConfig.allowedFunctionNames`: (`string[]`) Whitelist
+    of tool names.
+- **Union Strategy**: Multiple hooks' whitelists are **combined**.
+- **Limitations**: Does **not** support `decision`, `continue`, or
+  `systemMessage`.
+
+### `AfterModel`
+
+Fires immediately after an LLM response chunk is received. Used for real-time
+redaction or PII filtering.
+
+- **Input Fields**:
+  - `llm_request`: (`object`) The original request.
+  - `llm_response`: (`object`) The model's response (or a single chunk during
+    streaming).
+- **Relevant Output Fields**:
+  - `hookSpecificOutput.llm_response`: An object that **replaces** the model's
+    response chunk.
+  - `decision`: Set to `"deny"` to discard the response chunk and block the
+    turn.
+  - `continue`: Set to `false` to **kill the entire agent loop** immediately.
+- **Note on Streaming**: Fired for **every chunk** generated by the model.
+  Modifying the response only affects the current chunk.
+- **Exit Code 2 (Block Response)**: Aborts the turn and discards the model's
+  output. Uses `stderr` as the error message.
+
+---
+
+## Lifecycle & system hooks
+
+### `SessionStart`
+
+Fires on application startup, resuming a session, or after a `/clear` command.
+Used for loading initial context.
+
+- **Input fields**:
+  - `source`: (`"startup" | "resume" | "clear"`)
+- **Relevant output fields**:
+  - `hookSpecificOutput.additionalContext`: (`string`)
+    - **Interactive**: Injected as the first turn in history.
+    - **Non-interactive**: Prepended to the user's prompt.
+  - `systemMessage`: Shown at the start of the session.
+- **Advisory only**: `continue` and `decision` fields are **ignored**. Startup
+  is never blocked.
+
+### `SessionEnd`
+
+Fires when the CLI exits or a session is cleared. Used for cleanup or final
+telemetry.
+
+- **Input Fields**:
+  - `reason`: (`"exit" | "clear" | "logout" | "prompt_input_exit" | "other"`)
+- **Relevant Output Fields**:
+  - `systemMessage`: Displayed to the user during shutdown.
+- **Best Effort**: The CLI **will not wait** for this hook to complete and
+  ignores all flow-control fields (`continue`, `decision`).
+
+### `Notification`
+
+Fires when the CLI emits a system alert (e.g., Tool Permissions). Used for
+external logging or cross-platform alerts.
+
+- **Input Fields**:
+  - `notification_type`: (`"ToolPermission"`)
+  - `message`: Summary of the alert.
+  - `details`: JSON object with alert-specific metadata (e.g., tool name, file
+    path).
+- **Relevant Output Fields**:
+  - `systemMessage`: Displayed alongside the system alert.
+- **Observability Only**: This hook **cannot** block alerts or grant permissions
+  automatically. Flow-control fields are ignored.
+
+### `PreCompress`
+
+Fires before the CLI summarizes history to save tokens. Used for logging or
+state saving.
+
+- **Input Fields**:
+  - `trigger`: (`"auto" | "manual"`)
+- **Relevant Output Fields**:
+  - `systemMessage`: Displayed to the user before compression.
+- **Advisory Only**: Fired asynchronously. It **cannot** block or modify the
+  compression process. Flow-control fields are ignored.
 
 ---
 
 ## Stable Model API
 
-Gemini CLI uses a decoupled format for model interactions to ensure hooks remain
-stable even if the underlying Gemini SDK changes.
+Gemini CLI uses these structures to ensure hooks don't break across SDK updates.
 
-### `LLMRequest` Object
-
-Used in `BeforeModel` and `BeforeToolSelection`.
-
-> 💡 **Note**: In v1, model hooks are primarily text-focused. Non-text parts
-> (like images or function calls) provided in the `content` array will be
-> simplified to their string representation by the translator.
+**LLMRequest**:
 
 ```typescript
 {
   "model": string,
   "messages": Array<{
     "role": "user" | "model" | "system",
-    "content": string | Array<{ "type": string, [key: string]: any }>
+    "content": string // Non-text parts are filtered out for hooks
   }>,
-  "config"?: {
-    "temperature"?: number,
-    "maxOutputTokens"?: number,
-    "topP"?: number,
-    "topK"?: number
-  },
-  "toolConfig"?: {
-    "mode"?: "AUTO" | "ANY" | "NONE",
-    "allowedFunctionNames"?: string[]
-  }
+  "config": { "temperature": number, ... },
+  "toolConfig": { "mode": string, "allowedFunctionNames": string[] }
 }
+
 ```
 
-### `LLMResponse` Object
-
-Used in `AfterModel` and as a synthetic response in `BeforeModel`.
+**LLMResponse**:
 
 ```typescript
 {
-  "text"?: string,
   "candidates": Array<{
-    "content": {
-      "role": "model",
-      "parts": string[]
-    },
-    "finishReason"?: "STOP" | "MAX_TOKENS" | "SAFETY" | "RECITATION" | "OTHER",
-    "index"?: number,
-    "safetyRatings"?: Array<{
-      "category": string,
-      "probability": string,
-      "blocked"?: boolean
-    }>
+    "content": { "role": "model", "parts": string[] },
+    "finishReason": string
   }>,
-  "usageMetadata"?: {
-    "promptTokenCount"?: number,
-    "candidatesTokenCount"?: number,
-    "totalTokenCount"?: number
-  }
+  "usageMetadata": { "totalTokenCount": number }
 }
 ```

docs/sidebar.json

@@ -80,10 +80,6 @@
         "label": "Model selection",
         "slug": "docs/cli/model"
       },
-      {
-        "label": "Rewind",
-        "slug": "docs/cli/rewind"
-      },
       {
         "label": "Sandbox",
         "slug": "docs/cli/sandbox"
@@ -206,7 +202,7 @@
     ]
   },
   {
-    "label": "Hooks",
+    "label": "Hooks (experimental)",
     "items": [
       {
         "label": "Introduction",
@@ -274,10 +270,6 @@
       {
         "label": "Preview release",
         "slug": "docs/changelogs/preview"
-      },
-      {
-        "label": "Changelog",
-        "slug": "docs/changelogs/releases"
       }
     ]
   },

docs/tools/mcp-server.md

@@ -733,7 +733,7 @@ The MCP integration tracks several states:
 
 ## Important notes
 
-### Security sonsiderations
+### Security considerations
 
 - **Trust settings:** The `trust` option bypasses all confirmation dialogs. Use
   cautiously and only for servers you completely control

eslint.config.js

@@ -304,6 +304,16 @@ export default tseslint.config(
       '@typescript-eslint/no-require-imports': 'off',
     },
   },
+  // Examples should have access to standard globals like fetch
+  {
+    files: ['packages/cli/src/commands/extensions/examples/**/*.js'],
+    languageOptions: {
+      globals: {
+        ...globals.node,
+        fetch: 'readonly',
+      },
+    },
+  },
   // extra settings for scripts that we run directly with node
   {
     files: ['packages/vscode-ide-companion/scripts/**/*.js'],

evals/generalist_agent.eval.ts

@@ -0,0 +1,48 @@
+/**
+ * @license
+ * Copyright 2025 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/promises';
+
+describe('generalist_agent', () => {
+  evalTest('ALWAYS_PASSES', {
+    name: 'should be able to use generalist agent by explicitly asking the main agent to invoke it',
+    params: {
+      settings: {
+        agents: {
+          overrides: {
+            generalist: { enabled: true },
+          },
+        },
+      },
+    },
+    prompt:
+      'Please use the generalist agent to create a file called "generalist_test_file.txt" containing exactly the following text: success',
+    assert: async (rig) => {
+      // 1) Verify the generalist agent was invoked via delegate_to_agent
+      const foundToolCall = await rig.waitForToolCall(
+        'delegate_to_agent',
+        undefined,
+        (args) => {
+          const parsed = JSON.parse(args);
+          return parsed.agent_name === 'generalist';
+        },
+      );
+      expect(
+        foundToolCall,
+        'Expected to find a delegate_to_agent tool call for generalist agent',
+      ).toBeTruthy();
+
+      // 2) Verify the file was created as expected
+      const filePath = path.join(rig.testDir!, 'generalist_test_file.txt');
+
+      const content = await fs.readFile(filePath, 'utf-8');
+      expect(content.trim()).toBe('success');
+    },
+  });
+});

evals/subagents.eval.ts

@@ -31,7 +31,7 @@ describe('subagent eval test cases', () => {
    *
    * This tests the system prompt's subagent specific clauses.
    */
-  evalTest('ALWAYS_PASSES', {
+  evalTest('USUALLY_PASSES', {
     name: 'should delegate to user provided agent with relevant expertise',
     params: {
       settings: {

evals/test-helper.ts

@@ -59,7 +59,10 @@ export function evalTest(policy: EvalPolicy, evalCase: EvalCase) {
         execSync('git commit --allow-empty -m "Initial commit"', execOptions);
       }
 
-      const result = await rig.run({ args: evalCase.prompt });
+      const result = await rig.run({
+        args: evalCase.prompt,
+        approvalMode: evalCase.approvalMode ?? 'yolo',
+      });
 
       const unauthorizedErrorPrefix =
         createUnauthorizedToolError('').split("'")[0];
@@ -91,6 +94,7 @@ export interface EvalCase {
   params?: Record<string, any>;
   prompt: string;
   files?: Record<string, string>;
+  approvalMode?: 'default' | 'auto_edit' | 'yolo' | 'plan';
   assert: (rig: TestRig, result: string) => Promise<void>;
 }
 

integration-tests/clipboard-linux.test.ts

@@ -0,0 +1,110 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, beforeEach, afterEach } from 'vitest';
+import { TestRig } from './test-helper.js';
+import { execSync, spawnSync } from 'node:child_process';
+import * as os from 'node:os';
+import * as fs from 'node:fs';
+import * as path from 'node:path';
+
+// Minimal 1x1 PNG image base64
+const DUMMY_PNG_BASE64 =
+  'iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8z8BQDwAEhQGAhKmMIQAAAABJRU5ErkJggg==';
+
+describe('Linux Clipboard Integration', () => {
+  let rig: TestRig;
+  let dummyImagePath: string;
+
+  beforeEach(() => {
+    rig = new TestRig();
+    // Create a dummy image file for testing
+    dummyImagePath = path.join(
+      os.tmpdir(),
+      `gemini-test-clipboard-${Date.now()}.png`,
+    );
+    fs.writeFileSync(dummyImagePath, Buffer.from(DUMMY_PNG_BASE64, 'base64'));
+  });
+
+  afterEach(async () => {
+    await rig.cleanup();
+    try {
+      if (fs.existsSync(dummyImagePath)) {
+        fs.unlinkSync(dummyImagePath);
+      }
+    } catch {
+      // Ignore cleanup errors
+    }
+  });
+
+  // Only run this test on Linux
+  const runIfLinux = os.platform() === 'linux' ? it : it.skip;
+
+  runIfLinux(
+    'should paste image from system clipboard when Ctrl+V is pressed',
+    async () => {
+      // 1. Setup rig
+      await rig.setup('linux-clipboard-paste');
+
+      // 2. Inject image into system clipboard
+      // We attempt both Wayland and X11 tools.
+      let clipboardSet = false;
+
+      // Try wl-copy (Wayland)
+      let sessionType = '';
+      const wlCopy = spawnSync('wl-copy', ['--type', 'image/png'], {
+        input: fs.readFileSync(dummyImagePath),
+      });
+      if (wlCopy.status === 0) {
+        clipboardSet = true;
+        sessionType = 'wayland';
+      } else {
+        // Try xclip (X11)
+        try {
+          execSync(
+            `xclip -selection clipboard -t image/png -i "${dummyImagePath}"`,
+            { stdio: 'ignore' },
+          );
+          clipboardSet = true;
+          sessionType = 'x11';
+        } catch {
+          // Both failed
+        }
+      }
+
+      if (!clipboardSet) {
+        console.warn(
+          'Skipping test: Could not access system clipboard (wl-copy or xclip required)',
+        );
+        return;
+      }
+
+      // 3. Launch CLI and simulate Ctrl+V
+      // We send the control character \u0016 (SYN) which corresponds to Ctrl+V
+      // Note: The CLI must be running and accepting input.
+      // The TestRig usually sends args/stdin and waits for exit or output.
+      // To properly test "interactive" pasting, we need the rig to support sending input *while* running.
+      // Assuming rig.run with 'stdin' sends it immediately.
+      // The CLI treats stdin as typed input if it's interactive.
+
+      // We append a small delay or a newline to ensure processing?
+      // Ctrl+V (\u0016) followed by a newline (\r) to submit?
+      // Or just Ctrl+V and check if the buffer updates (which we can't easily see in non-verbose rig output).
+      // If we send Ctrl+V then Enter, the CLI should submit the prompt containing the image path.
+
+      const result = await rig.run({
+        stdin: '\u0016\r', // Ctrl+V then Enter
+        env: { XDG_SESSION_TYPE: sessionType },
+      });
+
+      // 4. Verify Output
+      // Expect the CLI to have processed the image and echoed back the path (or the prompt containing it)
+      // The output usually contains the user's input echoed back + model response.
+      // The pasted image path should look like @.../clipboard-....png
+      expect(result).toMatch(/@\/.*\.gemini-clipboard\/clipboard-.*\.png/);
+    },
+  );
+});

integration-tests/hooks-agent-flow.test.ts

@@ -53,8 +53,10 @@ describe('Hooks Agent Flow', () => {
 
       await rig.setup('should inject additional context via BeforeAgent hook', {
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             BeforeAgent: [
               {
                 hooks: [
@@ -116,8 +118,10 @@ describe('Hooks Agent Flow', () => {
 
       await rig.setup('should receive prompt and response in AfterAgent hook', {
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             AfterAgent: [
               {
                 hooks: [
@@ -163,8 +167,10 @@ describe('Hooks Agent Flow', () => {
             'hooks-agent-flow-multistep.responses',
           ),
           settings: {
-            hooks: {
+            hooksConfig: {
               enabled: true,
+            },
+            hooks: {
               BeforeAgent: [
                 {
                   hooks: [

integration-tests/hooks-system.test.ts

@@ -24,7 +24,7 @@ describe('Hooks System Integration', () => {
 
   describe('Command Hooks - Blocking Behavior', () => {
     it('should block tool execution when hook returns block decision', async () => {
-      await rig.setup(
+      rig.setup(
         'should block tool execution when hook returns block decision',
         {
           fakeResponsesPath: join(
@@ -32,8 +32,10 @@ describe('Hooks System Integration', () => {
             'hooks-system.block-tool.responses',
           ),
           settings: {
-            hooks: {
+            hooksConfig: {
               enabled: true,
+            },
+            hooks: {
               BeforeTool: [
                 {
                   matcher: 'write_file',
@@ -75,8 +77,67 @@ describe('Hooks System Integration', () => {
       expect(hookTelemetryFound).toBeTruthy();
     });
 
+    it('should block tool execution and use stderr as reason when hook exits with code 2', async () => {
+      rig.setup(
+        'should block tool execution and use stderr as reason when hook exits with code 2',
+        {
+          fakeResponsesPath: join(
+            import.meta.dirname,
+            'hooks-system.block-tool.responses',
+          ),
+          settings: {
+            hooksConfig: {
+              enabled: true,
+            },
+            hooks: {
+              BeforeTool: [
+                {
+                  matcher: 'write_file',
+                  hooks: [
+                    {
+                      type: 'command',
+                      // Exit with code 2 and write reason to stderr
+                      command:
+                        'node -e "process.stderr.write(\'File writing blocked by security policy\'); process.exit(2)"',
+                      timeout: 5000,
+                    },
+                  ],
+                },
+              ],
+            },
+          },
+        },
+      );
+
+      const result = await rig.run({
+        args: 'Create a file called test.txt with content "Hello World"',
+      });
+
+      // The hook should block the write_file tool
+      const toolLogs = rig.readToolLogs();
+      const writeFileCalls = toolLogs.filter(
+        (t) =>
+          t.toolRequest.name === 'write_file' && t.toolRequest.success === true,
+      );
+
+      // Tool should not be called due to blocking hook
+      expect(writeFileCalls).toHaveLength(0);
+
+      // Result should mention the blocking reason from stderr
+      expect(result).toContain('File writing blocked by security policy');
+
+      // Verify hook telemetry shows exit code 2 and stderr
+      const hookLogs = rig.readHookLogs();
+      const blockHook = hookLogs.find((log) => log.hookCall.exit_code === 2);
+      expect(blockHook).toBeDefined();
+      expect(blockHook?.hookCall.stderr).toContain(
+        'File writing blocked by security policy',
+      );
+      expect(blockHook?.hookCall.success).toBe(false);
+    });
+
     it('should allow tool execution when hook returns allow decision', async () => {
-      await rig.setup(
+      rig.setup(
         'should allow tool execution when hook returns allow decision',
         {
           fakeResponsesPath: join(
@@ -84,8 +145,10 @@ describe('Hooks System Integration', () => {
             'hooks-system.allow-tool.responses',
           ),
           settings: {
-            hooks: {
+            hooksConfig: {
               enabled: true,
+            },
+            hooks: {
               BeforeTool: [
                 {
                   matcher: 'write_file',
@@ -126,14 +189,16 @@ describe('Hooks System Integration', () => {
     it('should add additional context from AfterTool hooks', async () => {
       const command =
         "node -e \"console.log(JSON.stringify({hookSpecificOutput: {hookEventName: 'AfterTool', additionalContext: 'Security scan: File content appears safe'}}))\"";
-      await rig.setup('should add additional context from AfterTool hooks', {
+      rig.setup('should add additional context from AfterTool hooks', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.after-tool-context.responses',
         ),
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             AfterTool: [
               {
                 matcher: 'read_file',
@@ -178,7 +243,7 @@ describe('Hooks System Integration', () => {
     it('should modify LLM requests with BeforeModel hooks', async () => {
       // Create a hook script that replaces the LLM request with a modified version
       // Note: Providing messages in the hook output REPLACES the entire conversation
-      await rig.setup('should modify LLM requests with BeforeModel hooks', {
+      rig.setup('should modify LLM requests with BeforeModel hooks', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.before-model.responses',
@@ -203,10 +268,12 @@ console.log(JSON.stringify({
       const scriptPath = join(rig.testDir!, 'before_model_hook.cjs');
       writeFileSync(scriptPath, hookScript);
 
-      await rig.setup('should modify LLM requests with BeforeModel hooks', {
+      rig.setup('should modify LLM requests with BeforeModel hooks', {
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             BeforeModel: [
               {
                 hooks: [
@@ -248,13 +315,103 @@ console.log(JSON.stringify({
       expect(hookTelemetryFound[0].hookCall.stdout).toBeDefined();
       expect(hookTelemetryFound[0].hookCall.stderr).toBeDefined();
     });
+
+    it('should block model execution when BeforeModel hook returns deny decision', async () => {
+      rig.setup(
+        'should block model execution when BeforeModel hook returns deny decision',
+      );
+      const hookScript = `console.log(JSON.stringify({
+  decision: "deny",
+  reason: "Model execution blocked by security policy"
+}));`;
+      const scriptPath = join(rig.testDir!, 'before_model_deny_hook.cjs');
+      writeFileSync(scriptPath, hookScript);
+
+      rig.setup(
+        'should block model execution when BeforeModel hook returns deny decision',
+        {
+          settings: {
+            hooksConfig: {
+              enabled: true,
+            },
+            hooks: {
+              BeforeModel: [
+                {
+                  hooks: [
+                    {
+                      type: 'command',
+                      command: `node "${scriptPath}"`,
+                      timeout: 5000,
+                    },
+                  ],
+                },
+              ],
+            },
+          },
+        },
+      );
+
+      const result = await rig.run({ args: 'Hello' });
+
+      // The hook should have blocked the request
+      expect(result).toContain('Model execution blocked by security policy');
+
+      // Verify no API requests were made to the LLM
+      const apiRequests = rig.readAllApiRequest();
+      expect(apiRequests).toHaveLength(0);
+    });
+
+    it('should block model execution when BeforeModel hook returns block decision', async () => {
+      rig.setup(
+        'should block model execution when BeforeModel hook returns block decision',
+      );
+      const hookScript = `console.log(JSON.stringify({
+  decision: "block",
+  reason: "Model execution blocked by security policy"
+}));`;
+      const scriptPath = join(rig.testDir!, 'before_model_block_hook.cjs');
+      writeFileSync(scriptPath, hookScript);
+
+      rig.setup(
+        'should block model execution when BeforeModel hook returns block decision',
+        {
+          settings: {
+            hooksConfig: {
+              enabled: true,
+            },
+            hooks: {
+              BeforeModel: [
+                {
+                  hooks: [
+                    {
+                      type: 'command',
+                      command: `node "${scriptPath}"`,
+                      timeout: 5000,
+                    },
+                  ],
+                },
+              ],
+            },
+          },
+        },
+      );
+
+      const result = await rig.run({ args: 'Hello' });
+
+      // The hook should have blocked the request
+      expect(result).toContain('Model execution blocked by security policy');
+
+      // Verify no API requests were made to the LLM
+      const apiRequests = rig.readAllApiRequest();
+      expect(apiRequests).toHaveLength(0);
+    });
   });
 
   describe('AfterModel Hooks - LLM Response Modification', () => {
     it.skipIf(process.platform === 'win32')(
       'should modify LLM responses with AfterModel hooks',
       async () => {
-        await rig.setup('should modify LLM responses with AfterModel hooks', {
+        rig.setup('should modify LLM responses with AfterModel hooks', {
           fakeResponsesPath: join(
             import.meta.dirname,
             'hooks-system.after-model.responses',
@@ -284,10 +441,12 @@ console.log(JSON.stringify({
         const scriptPath = join(rig.testDir!, 'after_model_hook.cjs');
         writeFileSync(scriptPath, hookScript);
 
-        await rig.setup('should modify LLM responses with AfterModel hooks', {
+        rig.setup('should modify LLM responses with AfterModel hooks', {
           settings: {
-            hooks: {
+            hooksConfig: {
               enabled: true,
+            },
+            hooks: {
               AfterModel: [
                 {
                   hooks: [
@@ -319,41 +478,37 @@ console.log(JSON.stringify({
 
   describe('BeforeToolSelection Hooks - Tool Configuration', () => {
     it('should modify tool selection with BeforeToolSelection hooks', async () => {
-      await rig.setup(
-        'should modify tool selection with BeforeToolSelection hooks',
-        {
-          fakeResponsesPath: join(
-            import.meta.dirname,
-            'hooks-system.before-tool-selection.responses',
-          ),
-        },
-      );
+      rig.setup('should modify tool selection with BeforeToolSelection hooks', {
+        fakeResponsesPath: join(
+          import.meta.dirname,
+          'hooks-system.before-tool-selection.responses',
+        ),
+      });
       // Create inline hook command (works on both Unix and Windows)
       const hookCommand =
         "node -e \"console.log(JSON.stringify({hookSpecificOutput: {hookEventName: 'BeforeToolSelection', toolConfig: {mode: 'ANY', allowedFunctionNames: ['read_file', 'run_shell_command']}}}))\"";
 
-      await rig.setup(
-        'should modify tool selection with BeforeToolSelection hooks',
-        {
-          settings: {
-            debugMode: true,
-            hooks: {
-              enabled: true,
-              BeforeToolSelection: [
-                {
-                  hooks: [
-                    {
-                      type: 'command',
-                      command: hookCommand,
-                      timeout: 5000,
-                    },
-                  ],
-                },
-              ],
-            },
+      rig.setup('should modify tool selection with BeforeToolSelection hooks', {
+        settings: {
+          debugMode: true,
+          hooksConfig: {
+            enabled: true,
+          },
+          hooks: {
+            BeforeToolSelection: [
+              {
+                hooks: [
+                  {
+                    type: 'command',
+                    command: hookCommand,
+                    timeout: 5000,
+                  },
+                ],
+              },
+            ],
           },
         },
-      );
+      });
 
       // Create a test file
       rig.createFile('new_file_data.txt', 'test data');
@@ -382,7 +537,7 @@ console.log(JSON.stringify({
 
   describe('BeforeAgent Hooks - Prompt Augmentation', () => {
     it('should augment prompts with BeforeAgent hooks', async () => {
-      await rig.setup('should augment prompts with BeforeAgent hooks', {
+      rig.setup('should augment prompts with BeforeAgent hooks', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.before-agent.responses',
@@ -401,10 +556,12 @@ console.log(JSON.stringify({
       const scriptPath = join(rig.testDir!, 'before_agent_hook.cjs');
       writeFileSync(scriptPath, hookScript);
 
-      await rig.setup('should augment prompts with BeforeAgent hooks', {
+      rig.setup('should augment prompts with BeforeAgent hooks', {
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             BeforeAgent: [
               {
                 hooks: [
@@ -438,7 +595,7 @@ console.log(JSON.stringify({
       const hookCommand =
         'node -e "console.log(JSON.stringify({suppressOutput: false, systemMessage: \'Permission request logged by security hook\'}))"';
 
-      await rig.setup('should handle notification hooks for tool permissions', {
+      rig.setup('should handle notification hooks for tool permissions', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.notification.responses',
@@ -449,8 +606,10 @@ console.log(JSON.stringify({
             approval: 'ASK', // Disable YOLO mode to show permission prompts
             confirmationRequired: ['run_shell_command'],
           },
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             Notification: [
               {
                 matcher: 'ToolPermission',
@@ -467,7 +626,7 @@ console.log(JSON.stringify({
         },
       });
 
-      const run = await rig.runInteractive({ yolo: false });
+      const run = await rig.runInteractive({ approvalMode: 'default' });
 
       // Send prompt that will trigger a permission request
       await run.type('Run the command "echo test"');
@@ -534,14 +693,16 @@ console.log(JSON.stringify({
       const hook2Command =
         "node -e \"console.log(JSON.stringify({decision: 'allow', hookSpecificOutput: {hookEventName: 'BeforeAgent', additionalContext: 'Step 2: Security check completed.'}}))\"";
 
-      await rig.setup('should execute hooks sequentially when configured', {
+      rig.setup('should execute hooks sequentially when configured', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.sequential-execution.responses',
         ),
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             BeforeAgent: [
               {
                 sequential: true,
@@ -594,7 +755,7 @@ console.log(JSON.stringify({
 
   describe('Hook Input/Output Validation', () => {
     it('should provide correct input format to hooks', async () => {
-      await rig.setup('should provide correct input format to hooks', {
+      rig.setup('should provide correct input format to hooks', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.input-validation.responses',
@@ -618,10 +779,12 @@ try {
       const scriptPath = join(rig.testDir!, 'input_validation_hook.cjs');
       writeFileSync(scriptPath, hookScript);
 
-      await rig.setup('should provide correct input format to hooks', {
+      rig.setup('should provide correct input format to hooks', {
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             BeforeTool: [
               {
                 hooks: [
@@ -653,6 +816,52 @@ try {
       const hookTelemetryFound = await rig.waitForTelemetryEvent('hook_call');
       expect(hookTelemetryFound).toBeTruthy();
     });
+
+    it('should treat mixed stdout (text + JSON) as system message and allow execution when exit code is 0', async () => {
+      rig.setup(
+        'should treat mixed stdout (text + JSON) as system message and allow execution when exit code is 0',
+        {
+          fakeResponsesPath: join(
+            import.meta.dirname,
+            'hooks-system.allow-tool.responses',
+          ),
+          settings: {
+            hooksConfig: {
+              enabled: true,
+            },
+            hooks: {
+              BeforeTool: [
+                {
+                  matcher: 'write_file',
+                  hooks: [
+                    {
+                      type: 'command',
+                      // Output plain text then JSON.
+                      // This breaks JSON parsing, so it falls back to 'allow' with the whole stdout as systemMessage.
+                      command:
+                        "node -e \"console.log('Pollution'); console.log(JSON.stringify({decision: 'deny', reason: 'Should be ignored'}))\"",
+                      timeout: 5000,
+                    },
+                  ],
+                },
+              ],
+            },
+          },
+        },
+      );
+
+      const result = await rig.run({
+        args: 'Create a file called approved.txt with content "Approved content"',
+      });
+
+      // The hook logic fails to parse JSON, so it allows the tool.
+      const foundWriteFile = await rig.waitForToolCall('write_file');
+      expect(foundWriteFile).toBeTruthy();
+
+      // The entire stdout (including the JSON part) becomes the systemMessage
+      expect(result).toContain('Pollution');
+      expect(result).toContain('Should be ignored');
+    });
   });
 
   describe('Multiple Event Types', () => {
@@ -665,14 +874,16 @@ try {
       const beforeAgentCommand =
         "node -e \"console.log(JSON.stringify({decision: 'allow', hookSpecificOutput: {hookEventName: 'BeforeAgent', additionalContext: 'BeforeAgent: User request processed'}}))\"";
 
-      await rig.setup('should handle hooks for all major event types', {
+      rig.setup('should handle hooks for all major event types', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.multiple-events.responses',
         ),
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             BeforeAgent: [
               {
                 hooks: [
@@ -768,7 +979,7 @@ try {
 
   describe('Hook Error Handling', () => {
     it('should handle hook failures gracefully', async () => {
-      await rig.setup('should handle hook failures gracefully', {
+      rig.setup('should handle hook failures gracefully', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.error-handling.responses',
@@ -782,10 +993,12 @@ try {
       const workingCommand =
         "node -e \"console.log(JSON.stringify({decision: 'allow', reason: 'Working hook succeeded'}))\"";
 
-      await rig.setup('should handle hook failures gracefully', {
+      rig.setup('should handle hook failures gracefully', {
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             BeforeTool: [
               {
                 hooks: [
@@ -830,14 +1043,16 @@ try {
       const hookCommand =
         "node -e \"console.log(JSON.stringify({decision: 'allow', reason: 'Telemetry test hook'}))\"";
 
-      await rig.setup('should generate telemetry events for hook executions', {
+      rig.setup('should generate telemetry events for hook executions', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.telemetry.responses',
         ),
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             BeforeTool: [
               {
                 hooks: [
@@ -871,14 +1086,16 @@ try {
       const sessionStartCommand =
         "node -e \"console.log(JSON.stringify({decision: 'allow', systemMessage: 'Session starting on startup'}))\"";
 
-      await rig.setup('should fire SessionStart hook on app startup', {
+      rig.setup('should fire SessionStart hook on app startup', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.session-startup.responses',
         ),
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             SessionStart: [
               {
                 matcher: 'startup',
@@ -936,7 +1153,7 @@ console.log(JSON.stringify({
   }
 }));`;
 
-      await rig.setup('should fire SessionStart hook and inject context', {
+      rig.setup('should fire SessionStart hook and inject context', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.session-startup.responses',
@@ -946,10 +1163,12 @@ console.log(JSON.stringify({
       const scriptPath = join(rig.testDir!, 'session_start_context_hook.cjs');
       writeFileSync(scriptPath, hookScript);
 
-      await rig.setup('should fire SessionStart hook and inject context', {
+      rig.setup('should fire SessionStart hook and inject context', {
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             SessionStart: [
               {
                 matcher: 'startup',
@@ -1011,7 +1230,7 @@ console.log(JSON.stringify({
   }
 }));`;
 
-      await rig.setup(
+      rig.setup(
         'should fire SessionStart hook and display systemMessage in interactive mode',
         {
           fakeResponsesPath: join(
@@ -1027,12 +1246,14 @@ console.log(JSON.stringify({
       );
       writeFileSync(scriptPath, hookScript);
 
-      await rig.setup(
+      rig.setup(
         'should fire SessionStart hook and display systemMessage in interactive mode',
         {
           settings: {
-            hooks: {
+            hooksConfig: {
               enabled: true,
+            },
+            hooks: {
               SessionStart: [
                 {
                   matcher: 'startup',
@@ -1091,7 +1312,7 @@ console.log(JSON.stringify({
       const sessionStartCommand =
         "node -e \"console.log(JSON.stringify({decision: 'allow', systemMessage: 'Session starting after clear'}))\"";
 
-      await rig.setup(
+      rig.setup(
         'should fire SessionEnd and SessionStart hooks on /clear command',
         {
           fakeResponsesPath: join(
@@ -1099,8 +1320,10 @@ console.log(JSON.stringify({
             'hooks-system.session-clear.responses',
           ),
           settings: {
-            hooks: {
+            hooksConfig: {
               enabled: true,
+            },
+            hooks: {
               SessionEnd: [
                 {
                   matcher: '*',
@@ -1265,14 +1488,16 @@ console.log(JSON.stringify({
       const preCompressCommand =
         "node -e \"console.log(JSON.stringify({decision: 'allow', systemMessage: 'PreCompress hook executed for automatic compression'}))\"";
 
-      await rig.setup('should fire PreCompress hook on automatic compression', {
+      rig.setup('should fire PreCompress hook on automatic compression', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.compress-auto.responses',
         ),
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             PreCompress: [
               {
                 matcher: 'auto',
@@ -1330,14 +1555,16 @@ console.log(JSON.stringify({
       const sessionEndCommand =
         "node -e \"console.log(JSON.stringify({decision: 'allow', systemMessage: 'SessionEnd hook executed on exit'}))\"";
 
-      await rig.setup('should fire SessionEnd hook on graceful exit', {
+      rig.setup('should fire SessionEnd hook on graceful exit', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.session-startup.responses',
         ),
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             SessionEnd: [
               {
                 matcher: 'exit',
@@ -1412,7 +1639,7 @@ console.log(JSON.stringify({
 
   describe('Hook Disabling', () => {
     it('should not execute hooks disabled in settings file', async () => {
-      await rig.setup('should not execute hooks disabled in settings file', {
+      rig.setup('should not execute hooks disabled in settings file', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.disabled-via-settings.responses',
@@ -1432,10 +1659,13 @@ console.log(JSON.stringify({decision: "block", systemMessage: "Disabled hook sho
       writeFileSync(enabledPath, enabledHookScript);
       writeFileSync(disabledPath, disabledHookScript);
 
-      await rig.setup('should not execute hooks disabled in settings file', {
+      rig.setup('should not execute hooks disabled in settings file', {
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+            disabled: [`node "${disabledPath}"`], // Disable the second hook
+          },
+          hooks: {
             BeforeTool: [
               {
                 hooks: [
@@ -1452,7 +1682,6 @@ console.log(JSON.stringify({decision: "block", systemMessage: "Disabled hook sho
                 ],
               },
             ],
-            disabled: [`node "${disabledPath}"`], // Disable the second hook
           },
         },
       });
@@ -1487,15 +1716,12 @@ console.log(JSON.stringify({decision: "block", systemMessage: "Disabled hook sho
     });
 
     it('should respect disabled hooks across multiple operations', async () => {
-      await rig.setup(
-        'should respect disabled hooks across multiple operations',
-        {
-          fakeResponsesPath: join(
-            import.meta.dirname,
-            'hooks-system.disabled-via-command.responses',
-          ),
-        },
-      );
+      rig.setup('should respect disabled hooks across multiple operations', {
+        fakeResponsesPath: join(
+          import.meta.dirname,
+          'hooks-system.disabled-via-command.responses',
+        ),
+      });
 
       // Create two hook scripts - one that will be disabled, one that won't
       const activeHookScript = `const fs = require('fs');
@@ -1510,33 +1736,32 @@ console.log(JSON.stringify({decision: "block", systemMessage: "Disabled hook sho
       writeFileSync(activePath, activeHookScript);
       writeFileSync(disabledPath, disabledHookScript);
 
-      await rig.setup(
-        'should respect disabled hooks across multiple operations',
-        {
-          settings: {
-            hooks: {
-              enabled: true,
-              BeforeTool: [
-                {
-                  hooks: [
-                    {
-                      type: 'command',
-                      command: `node "${activePath}"`,
-                      timeout: 5000,
-                    },
-                    {
-                      type: 'command',
-                      command: `node "${disabledPath}"`,
-                      timeout: 5000,
-                    },
-                  ],
-                },
-              ],
-              disabled: [`node "${disabledPath}"`], // Disable the second hook
-            },
+      rig.setup('should respect disabled hooks across multiple operations', {
+        settings: {
+          hooksConfig: {
+            enabled: true,
+            disabled: [`node "${disabledPath}"`], // Disable the second hook,
+          },
+          hooks: {
+            BeforeTool: [
+              {
+                hooks: [
+                  {
+                    type: 'command',
+                    command: `node "${activePath}"`,
+                    timeout: 5000,
+                  },
+                  {
+                    type: 'command',
+                    command: `node "${disabledPath}"`,
+                    timeout: 5000,
+                  },
+                ],
+              },
+            ],
           },
         },
-      );
+      });
 
       // First run - only active hook should execute
       const result1 = await rig.run({
@@ -1587,9 +1812,7 @@ console.log(JSON.stringify({decision: "block", systemMessage: "Disabled hook sho
   describe('BeforeTool Hooks - Input Override', () => {
     it('should override tool input parameters via BeforeTool hook', async () => {
       // 1. First setup to get the test directory and prepare the hook script
-      await rig.setup(
-        'should override tool input parameters via BeforeTool hook',
-      );
+      rig.setup('should override tool input parameters via BeforeTool hook');
 
       // Create a hook script that overrides the tool input
       const hookOutput = {
@@ -1616,32 +1839,31 @@ console.log(JSON.stringify({decision: "block", systemMessage: "Disabled hook sho
       const commandPath = scriptPath.replace(/\\/g, '/');
 
       // 2. Full setup with settings and fake responses
-      await rig.setup(
-        'should override tool input parameters via BeforeTool hook',
-        {
-          fakeResponsesPath: join(
-            import.meta.dirname,
-            'hooks-system.input-modification.responses',
-          ),
-          settings: {
-            hooks: {
-              enabled: true,
-              BeforeTool: [
-                {
-                  matcher: 'write_file',
-                  hooks: [
-                    {
-                      type: 'command',
-                      command: `node "${commandPath}"`,
-                      timeout: 5000,
-                    },
-                  ],
-                },
-              ],
-            },
+      rig.setup('should override tool input parameters via BeforeTool hook', {
+        fakeResponsesPath: join(
+          import.meta.dirname,
+          'hooks-system.input-modification.responses',
+        ),
+        settings: {
+          hooksConfig: {
+            enabled: true,
+          },
+          hooks: {
+            BeforeTool: [
+              {
+                matcher: 'write_file',
+                hooks: [
+                  {
+                    type: 'command',
+                    command: `node "${commandPath}"`,
+                    timeout: 5000,
+                  },
+                ],
+              },
+            ],
           },
         },
-      );
+      });
 
       // Run the agent. The fake response will attempt to call write_file with
       // file_path="original.txt" and content="original content"
@@ -1698,19 +1920,21 @@ console.log(JSON.stringify({decision: "block", systemMessage: "Disabled hook sho
         hookOutput,
       )}));`;
 
-      await rig.setup('should stop agent execution via BeforeTool hook');
+      rig.setup('should stop agent execution via BeforeTool hook');
       const scriptPath = join(rig.testDir!, 'before_tool_stop_hook.js');
       writeFileSync(scriptPath, hookScript);
       const commandPath = scriptPath.replace(/\\/g, '/');
 
-      await rig.setup('should stop agent execution via BeforeTool hook', {
+      rig.setup('should stop agent execution via BeforeTool hook', {
         fakeResponsesPath: join(
           import.meta.dirname,
           'hooks-system.before-tool-stop.responses',
         ),
         settings: {
-          hooks: {
+          hooksConfig: {
             enabled: true,
+          },
+          hooks: {
             BeforeTool: [
               {
                 matcher: 'write_file',

integration-tests/run_shell_command.test.ts

@@ -164,7 +164,7 @@ describe('run_shell_command', () => {
     const result = await rig.run({
       args: [`--allowed-tools=run_shell_command(${tool})`],
       stdin: prompt,
-      yolo: false,
+      approvalMode: 'default',
     });
 
     const foundToolCall = await rig.waitForToolCall('run_shell_command', 15000);
@@ -207,7 +207,7 @@ describe('run_shell_command', () => {
     const result = await rig.run({
       args: '--allowed-tools=run_shell_command',
       stdin: prompt,
-      yolo: false,
+      approvalMode: 'default',
     });
 
     const foundToolCall = await rig.waitForToolCall('run_shell_command', 15000);
@@ -231,8 +231,8 @@ describe('run_shell_command', () => {
     expect(toolCall.toolRequest.success).toBe(true);
   });
 
-  it('should succeed with --yolo mode', async () => {
-    await rig.setup('should succeed with --yolo mode', {
+  it('should succeed in yolo mode', async () => {
+    await rig.setup('should succeed in yolo mode', {
       settings: { tools: { core: ['run_shell_command'] } },
     });
 
@@ -242,7 +242,7 @@ describe('run_shell_command', () => {
 
     const result = await rig.run({
       args: prompt,
-      yolo: true,
+      approvalMode: 'yolo',
     });
 
     const foundToolCall = await rig.waitForToolCall('run_shell_command', 15000);
@@ -276,7 +276,7 @@ describe('run_shell_command', () => {
     const result = await rig.run({
       args: `--allowed-tools=ShellTool(${tool})`,
       stdin: prompt,
-      yolo: false,
+      approvalMode: 'default',
     });
 
     const foundToolCall = await rig.waitForToolCall('run_shell_command', 15000);
@@ -325,7 +325,7 @@ describe('run_shell_command', () => {
         '--allowed-tools=run_shell_command(ls)',
       ],
       stdin: prompt,
-      yolo: false,
+      approvalMode: 'default',
     });
 
     for (const expected in ['ls', tool]) {
@@ -377,7 +377,7 @@ describe('run_shell_command', () => {
     const result = await rig.run({
       args: `--allowed-tools=run_shell_command(${allowedCommand})`,
       stdin: prompt,
-      yolo: false,
+      approvalMode: 'default',
     });
 
     if (!result.toLowerCase().includes('fail')) {
@@ -438,7 +438,7 @@ describe('run_shell_command', () => {
     await rig.run({
       args: `--allowed-tools=ShellTool(${chained.allowPattern})`,
       stdin: `${shellInjection}\n`,
-      yolo: false,
+      approvalMode: 'default',
     });
 
     // CLI should refuse to execute the chained command without scheduling run_shell_command.
@@ -470,7 +470,7 @@ describe('run_shell_command', () => {
         '--allowed-tools=run_shell_command',
       ],
       stdin: prompt,
-      yolo: false,
+      approvalMode: 'default',
     });
 
     const foundToolCall = await rig.waitForToolCall('run_shell_command', 15000);

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@google/gemini-cli",
-  "version": "0.26.0-nightly.20260115.6cb3ae4e0",
+  "version": "0.27.0-nightly.20260121.97aac696f",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@google/gemini-cli",
-      "version": "0.26.0-nightly.20260115.6cb3ae4e0",
+      "version": "0.27.0-nightly.20260121.97aac696f",
       "workspaces": [
         "packages/*"
       ],
@@ -2474,7 +2474,6 @@
       "integrity": "sha512-t54CUOsFMappY1Jbzb7fetWeO0n6K0k/4+/ZpkS+3Joz8I4VcvY9OiEBFRYISqaI2fq5sCiPtAjRDOzVYG8m+Q==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@octokit/auth-token": "^6.0.0",
         "@octokit/graphql": "^9.0.2",
@@ -2655,7 +2654,6 @@
       "resolved": "https://registry.npmjs.org/@opentelemetry/api/-/api-1.9.0.tgz",
       "integrity": "sha512-3giAOQvZiH5F9bMlMiv8+GSPMeqg0dbaeo58/0SlA9sxSqZhnUtxzX9/2FzyhS9sWQf5S0GJE0AKBrFqjpeYcg==",
       "license": "Apache-2.0",
-      "peer": true,
       "engines": {
         "node": ">=8.0.0"
       }
@@ -2689,7 +2687,6 @@
       "resolved": "https://registry.npmjs.org/@opentelemetry/core/-/core-2.0.1.tgz",
       "integrity": "sha512-MaZk9SJIDgo1peKevlbhP6+IwIiNPNmswNL4AF0WaQJLbHXjr9SrZMgS12+iqr9ToV4ZVosCcc0f8Rg67LXjxw==",
       "license": "Apache-2.0",
-      "peer": true,
       "dependencies": {
         "@opentelemetry/semantic-conventions": "^1.29.0"
       },
@@ -3058,7 +3055,6 @@
       "resolved": "https://registry.npmjs.org/@opentelemetry/resources/-/resources-2.0.1.tgz",
       "integrity": "sha512-dZOB3R6zvBwDKnHDTB4X1xtMArB/d324VsbiPkX/Yu0Q8T2xceRthoIVFhJdvgVM2QhGVUyX9tzwiNxGtoBJUw==",
       "license": "Apache-2.0",
-      "peer": true,
       "dependencies": {
         "@opentelemetry/core": "2.0.1",
         "@opentelemetry/semantic-conventions": "^1.29.0"
@@ -3092,7 +3088,6 @@
       "resolved": "https://registry.npmjs.org/@opentelemetry/sdk-metrics/-/sdk-metrics-2.0.1.tgz",
       "integrity": "sha512-wf8OaJoSnujMAHWR3g+/hGvNcsC16rf9s1So4JlMiFaFHiE4HpIA3oUh+uWZQ7CNuK8gVW/pQSkgoa5HkkOl0g==",
       "license": "Apache-2.0",
-      "peer": true,
       "dependencies": {
         "@opentelemetry/core": "2.0.1",
         "@opentelemetry/resources": "2.0.1"
@@ -3145,7 +3140,6 @@
       "resolved": "https://registry.npmjs.org/@opentelemetry/sdk-trace-base/-/sdk-trace-base-2.0.1.tgz",
       "integrity": "sha512-xYLlvk/xdScGx1aEqvxLwf6sXQLXCjk3/1SQT9X9AoN5rXRhkdvIFShuNNmtTEPRBqcsMbS4p/gJLNI2wXaDuQ==",
       "license": "Apache-2.0",
-      "peer": true,
       "dependencies": {
         "@opentelemetry/core": "2.0.1",
         "@opentelemetry/resources": "2.0.1",
@@ -4358,7 +4352,6 @@
       "integrity": "sha512-6mDvHUFSjyT2B2yeNx2nUgMxh9LtOWvkhIU3uePn2I2oyNymUAX1NIsdgviM4CH+JSrp2D2hsMvJOkxY+0wNRA==",
       "devOptional": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "csstype": "^3.0.2"
       }
@@ -4636,7 +4629,6 @@
       "integrity": "sha512-6sMvZePQrnZH2/cJkwRpkT7DxoAWh+g6+GFRK6bV3YQo7ogi3SX5rgF6099r5Q53Ma5qeT7LGmOmuIutF4t3lA==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@typescript-eslint/scope-manager": "8.35.0",
         "@typescript-eslint/types": "8.35.0",
@@ -5641,7 +5633,6 @@
       "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.15.0.tgz",
       "integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
       "license": "MIT",
-      "peer": true,
       "bin": {
         "acorn": "bin/acorn"
       },
@@ -6086,7 +6077,8 @@
       "version": "1.1.1",
       "resolved": "https://registry.npmjs.org/array-flatten/-/array-flatten-1.1.1.tgz",
       "integrity": "sha512-PCVAQswWemu6UdxsDFFX/+gVeYqKAod3D3UVm91jHwynguOwAvYPhx8nNlM++NqRcK6CxxpUafjmhIdKiHibqg==",
-      "license": "MIT"
+      "license": "MIT",
+      "peer": true
     },
     "node_modules/array-includes": {
       "version": "3.1.9",
@@ -7370,6 +7362,7 @@
       "resolved": "https://registry.npmjs.org/content-disposition/-/content-disposition-0.5.4.tgz",
       "integrity": "sha512-FveZTNuGw04cxlAiWbzi6zTAL/lhehaWbTtgluJh4/E95DqMwTmha3KZN1aAWA8cFIhHzMZUvLevkw5Rqk+tSQ==",
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "safe-buffer": "5.2.1"
       },
@@ -8689,7 +8682,6 @@
       "integrity": "sha512-GsGizj2Y1rCWDu6XoEekL3RLilp0voSePurjZIkxL3wlm5o5EC9VpgaP7lrCvjnkuLvzFBQWB3vWB3K5KQTveQ==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@eslint-community/eslint-utils": "^4.2.0",
         "@eslint-community/regexpp": "^4.12.1",
@@ -9292,6 +9284,7 @@
       "resolved": "https://registry.npmjs.org/cookie/-/cookie-0.7.1.tgz",
       "integrity": "sha512-6DnInpx7SJ2AK3+CTUE/ZM0vWTUboZCegxhC2xiIydHR9jNuTAASBrfEpHhiGOZw/nX51bHt6YQl8jsGo4y/0w==",
       "license": "MIT",
+      "peer": true,
       "engines": {
         "node": ">= 0.6"
       }
@@ -9301,6 +9294,7 @@
       "resolved": "https://registry.npmjs.org/debug/-/debug-2.6.9.tgz",
       "integrity": "sha512-bC7ElrdJaJnPbAP+1EotYvqZsb3ecl5wi6Bfi6BJTUcNowp6cvspg0jXznRTKDjm/E7AdgFBVeAPVMNcKGsHMA==",
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "ms": "2.0.0"
       }
@@ -9310,6 +9304,7 @@
       "resolved": "https://registry.npmjs.org/statuses/-/statuses-2.0.1.tgz",
       "integrity": "sha512-RwNA9Z/7PrK06rYLIzFMlaF+l73iwpzsqRIFgbMLbTcLD6cOao82TaWefPXQvB2fOC4AjuYSEndS7N/mTCbkdQ==",
       "license": "MIT",
+      "peer": true,
       "engines": {
         "node": ">= 0.8"
       }
@@ -9563,6 +9558,7 @@
       "resolved": "https://registry.npmjs.org/finalhandler/-/finalhandler-1.3.1.tgz",
       "integrity": "sha512-6BN9trH7bp3qvnrRyzsBz+g3lZxTNZTbVO2EV1CS0WIcDbawYVdYvGflME/9QP0h0pYlCDBCTjYa9nZzMDpyxQ==",
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "debug": "2.6.9",
         "encodeurl": "~2.0.0",
@@ -9581,6 +9577,7 @@
       "resolved": "https://registry.npmjs.org/debug/-/debug-2.6.9.tgz",
       "integrity": "sha512-bC7ElrdJaJnPbAP+1EotYvqZsb3ecl5wi6Bfi6BJTUcNowp6cvspg0jXznRTKDjm/E7AdgFBVeAPVMNcKGsHMA==",
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "ms": "2.0.0"
       }
@@ -9589,13 +9586,15 @@
       "version": "2.0.0",
       "resolved": "https://registry.npmjs.org/ms/-/ms-2.0.0.tgz",
       "integrity": "sha512-Tpp60P6IUJDTuOq/5Z8cdskzJujfwqfOTkrwIwj7IRISpnkJnT6SyJ4PCPnGMoFjC9ddhal5KVIYtAt97ix05A==",
-      "license": "MIT"
+      "license": "MIT",
+      "peer": true
     },
     "node_modules/finalhandler/node_modules/statuses": {
       "version": "2.0.1",
       "resolved": "https://registry.npmjs.org/statuses/-/statuses-2.0.1.tgz",
       "integrity": "sha512-RwNA9Z/7PrK06rYLIzFMlaF+l73iwpzsqRIFgbMLbTcLD6cOao82TaWefPXQvB2fOC4AjuYSEndS7N/mTCbkdQ==",
       "license": "MIT",
+      "peer": true,
       "engines": {
         "node": ">= 0.8"
       }
@@ -10878,7 +10877,6 @@
       "resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.4.7.tgz",
       "integrity": "sha512-QHyxhNF5VonF5cRmdAJD/UPucB9nRx3FozWMjQrDGfBxfAL9lpyu72/MlFPgloS1TMTGsOt7YN6dTPPA6mh0Aw==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@alcalzone/ansi-tokenize": "^0.2.1",
         "ansi-escapes": "^7.0.0",
@@ -14063,7 +14061,8 @@
       "version": "0.1.12",
       "resolved": "https://registry.npmjs.org/path-to-regexp/-/path-to-regexp-0.1.12.tgz",
       "integrity": "sha512-RA1GjUVMnvYFxuqovrEqZoxxW5NUZqbwKtYz/Tt7nXerk0LbLblQmrsgdeOxV5SFHf0UDggjS/bSeOZwt1pmEQ==",
-      "license": "MIT"
+      "license": "MIT",
+      "peer": true
     },
     "node_modules/path-type": {
       "version": "3.0.0",
@@ -14640,7 +14639,6 @@
       "resolved": "https://registry.npmjs.org/react/-/react-19.2.0.tgz",
       "integrity": "sha512-tmbWg6W31tQLeB5cdIBOicJDJRR2KzXsV7uSK9iNfLWQ5bIZfxuPEHp7M8wiHyHnn0DD1i7w3Zmin0FtkrwoCQ==",
       "license": "MIT",
-      "peer": true,
       "engines": {
         "node": ">=0.10.0"
       }
@@ -14651,7 +14649,6 @@
       "integrity": "sha512-ePrwPfxAnB+7hgnEr8vpKxL9cmnp7F322t8oqcPshbIQQhDKgFDW4tjhF2wjVbdXF9O/nyuy3sQWd9JGpiLPvA==",
       "devOptional": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "shell-quote": "^1.6.1",
         "ws": "^7"
@@ -16911,7 +16908,6 @@
       "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
       "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
       "license": "MIT",
-      "peer": true,
       "engines": {
         "node": ">=12"
       },
@@ -17135,8 +17131,7 @@
       "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.8.1.tgz",
       "integrity": "sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w==",
       "dev": true,
-      "license": "0BSD",
-      "peer": true
+      "license": "0BSD"
     },
     "node_modules/tsx": {
       "version": "4.20.3",
@@ -17144,7 +17139,6 @@
       "integrity": "sha512-qjbnuR9Tr+FJOMBqJCW5ehvIo/buZq7vH7qD7JziU98h6l3qGy0a/yPFjwO+y0/T7GFpNgNAvEcPPVfyT8rrPQ==",
       "devOptional": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "esbuild": "~0.25.0",
         "get-tsconfig": "^4.7.5"
@@ -17328,7 +17322,6 @@
       "integrity": "sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ==",
       "devOptional": true,
       "license": "Apache-2.0",
-      "peer": true,
       "bin": {
         "tsc": "bin/tsc",
         "tsserver": "bin/tsserver"
@@ -17491,6 +17484,7 @@
       "resolved": "https://registry.npmjs.org/utils-merge/-/utils-merge-1.0.1.tgz",
       "integrity": "sha512-pMZTvIkT1d+TFGvDOqodOclx0QWkkgi6Tdoa8gC8ffGAAqz9pzPTZWAybbsHHoED/ztMtkv/VoYTYyShUn81hA==",
       "license": "MIT",
+      "peer": true,
       "engines": {
         "node": ">= 0.4.0"
       }
@@ -17545,7 +17539,6 @@
       "resolved": "https://registry.npmjs.org/vite/-/vite-7.2.2.tgz",
       "integrity": "sha512-BxAKBWmIbrDgrokdGZH1IgkIk/5mMHDreLDmCJ0qpyJaAteP8NvMhkwr/ZCQNqNH97bw/dANTE9PDzqwJghfMQ==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "esbuild": "^0.25.0",
         "fdir": "^6.5.0",
@@ -17659,7 +17652,6 @@
       "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
       "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
       "license": "MIT",
-      "peer": true,
       "engines": {
         "node": ">=12"
       },
@@ -17672,7 +17664,6 @@
       "resolved": "https://registry.npmjs.org/vitest/-/vitest-3.2.4.tgz",
       "integrity": "sha512-LUCP5ev3GURDysTWiP47wRRUpLKMOfPh+yKTx3kVIEiu5KOMeqzpnYNsKyOoVrULivR8tLcks4+lga33Whn90A==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@types/chai": "^5.2.2",
         "@vitest/expect": "3.2.4",
@@ -18377,7 +18368,6 @@
       "resolved": "https://registry.npmjs.org/zod/-/zod-3.25.76.tgz",
       "integrity": "sha512-gzUt/qt81nXsFGKIFcC3YnfEAx5NkunCfnDlvuBSSFS02bcXu4Lmea0AFIUwbLWxWPx3d9p8S5QoaujKcNQxcQ==",
       "license": "MIT",
-      "peer": true,
       "funding": {
         "url": "https://github.com/sponsors/colinhacks"
       }
@@ -18393,7 +18383,7 @@
     },
     "packages/a2a-server": {
       "name": "@google/gemini-cli-a2a-server",
-      "version": "0.26.0-nightly.20260115.6cb3ae4e0",
+      "version": "0.27.0-nightly.20260121.97aac696f",
       "dependencies": {
         "@a2a-js/sdk": "^0.3.8",
         "@google-cloud/storage": "^7.16.0",
@@ -18703,7 +18693,7 @@
     },
     "packages/cli": {
       "name": "@google/gemini-cli",
-      "version": "0.26.0-nightly.20260115.6cb3ae4e0",
+      "version": "0.27.0-nightly.20260121.97aac696f",
       "license": "Apache-2.0",
       "dependencies": {
         "@agentclientprotocol/sdk": "^0.12.0",
@@ -18807,7 +18797,7 @@
     },
     "packages/core": {
       "name": "@google/gemini-cli-core",
-      "version": "0.26.0-nightly.20260115.6cb3ae4e0",
+      "version": "0.27.0-nightly.20260121.97aac696f",
       "license": "Apache-2.0",
       "dependencies": {
         "@a2a-js/sdk": "^0.3.8",
@@ -18944,7 +18934,6 @@
       "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
       "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
       "license": "MIT",
-      "peer": true,
       "engines": {
         "node": ">=12"
       },
@@ -18967,7 +18956,7 @@
     },
     "packages/test-utils": {
       "name": "@google/gemini-cli-test-utils",
-      "version": "0.26.0-nightly.20260115.6cb3ae4e0",
+      "version": "0.27.0-nightly.20260121.97aac696f",
       "license": "Apache-2.0",
       "dependencies": {
         "@google/gemini-cli-core": "file:../core",
@@ -18984,7 +18973,7 @@
     },
     "packages/vscode-ide-companion": {
       "name": "gemini-cli-vscode-ide-companion",
-      "version": "0.26.0-nightly.20260115.6cb3ae4e0",
+      "version": "0.27.0-nightly.20260121.97aac696f",
       "license": "LICENSE",
       "dependencies": {
         "@modelcontextprotocol/sdk": "^1.23.0",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@google/gemini-cli",
-  "version": "0.26.0-nightly.20260115.6cb3ae4e0",
+  "version": "0.27.0-nightly.20260121.97aac696f",
   "engines": {
     "node": ">=20.0.0"
   },
@@ -14,7 +14,7 @@
     "url": "git+https://github.com/google-gemini/gemini-cli.git"
   },
   "config": {
-    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.26.0-nightly.20260115.6cb3ae4e0"
+    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.27.0-nightly.20260121.97aac696f"
   },
   "scripts": {
     "start": "cross-env NODE_ENV=development node scripts/start.js",

packages/a2a-server/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@google/gemini-cli-a2a-server",
-  "version": "0.26.0-nightly.20260115.6cb3ae4e0",
+  "version": "0.27.0-nightly.20260121.97aac696f",
   "description": "Gemini CLI A2A Server",
   "repository": {
     "type": "git",

packages/a2a-server/src/agent/task.ts

@@ -575,7 +575,10 @@ export class Task {
       EDIT_TOOL_NAMES.has(request.name),
     );
 
-    if (restorableToolCalls.length > 0) {
+    if (
+      restorableToolCalls.length > 0 &&
+      this.config.getCheckpointingEnabled()
+    ) {
       const gitService = await this.config.getGitService();
       if (gitService) {
         const { checkpointsToWrite, toolCallToCheckpointMap, errors } =

packages/a2a-server/src/config/config.test.ts

@@ -0,0 +1,110 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
+import { loadConfig } from './config.js';
+import type { ExtensionLoader } from '@google/gemini-cli-core';
+import type { Settings } from './settings.js';
+
+const {
+  mockLoadServerHierarchicalMemory,
+  mockConfigConstructor,
+  mockVerifyGitAvailability,
+} = vi.hoisted(() => ({
+  mockLoadServerHierarchicalMemory: vi.fn().mockResolvedValue({
+    memoryContent: '',
+    fileCount: 0,
+    filePaths: [],
+  }),
+  mockConfigConstructor: vi.fn(),
+  mockVerifyGitAvailability: vi.fn(),
+}));
+
+vi.mock('@google/gemini-cli-core', async () => ({
+  Config: class MockConfig {
+    constructor(params: unknown) {
+      mockConfigConstructor(params);
+    }
+    initialize = vi.fn();
+    refreshAuth = vi.fn();
+  },
+  loadServerHierarchicalMemory: mockLoadServerHierarchicalMemory,
+  startupProfiler: {
+    flush: vi.fn(),
+  },
+  FileDiscoveryService: vi.fn(),
+  ApprovalMode: { DEFAULT: 'default', YOLO: 'yolo' },
+  AuthType: {
+    LOGIN_WITH_GOOGLE: 'login_with_google',
+    USE_GEMINI: 'use_gemini',
+  },
+  GEMINI_DIR: '.gemini',
+  DEFAULT_GEMINI_EMBEDDING_MODEL: 'models/embedding-001',
+  DEFAULT_GEMINI_MODEL: 'models/gemini-1.5-flash',
+  PREVIEW_GEMINI_MODEL: 'models/gemini-1.5-pro-latest',
+  homedir: () => '/tmp',
+  GitService: {
+    verifyGitAvailability: mockVerifyGitAvailability,
+  },
+}));
+
+describe('loadConfig', () => {
+  const mockSettings = {
+    checkpointing: { enabled: true },
+  };
+  const mockExtensionLoader = {
+    start: vi.fn(),
+    getExtensions: vi.fn().mockReturnValue([]),
+  } as unknown as ExtensionLoader;
+
+  beforeEach(() => {
+    vi.resetAllMocks();
+    process.env['GEMINI_API_KEY'] = 'test-key';
+    // Reset the mock return value just in case
+    mockLoadServerHierarchicalMemory.mockResolvedValue({
+      memoryContent: '',
+      fileCount: 0,
+      filePaths: [],
+    });
+  });
+
+  afterEach(() => {
+    delete process.env['GEMINI_API_KEY'];
+    delete process.env['CHECKPOINTING'];
+  });
+
+  it('should disable checkpointing if git is not installed', async () => {
+    mockVerifyGitAvailability.mockResolvedValue(false);
+
+    await loadConfig(
+      mockSettings as unknown as Settings,
+      mockExtensionLoader,
+      'test-task',
+    );
+
+    expect(mockConfigConstructor).toHaveBeenCalledWith(
+      expect.objectContaining({
+        checkpointing: false,
+      }),
+    );
+  });
+
+  it('should enable checkpointing if git is installed', async () => {
+    mockVerifyGitAvailability.mockResolvedValue(true);
+
+    await loadConfig(
+      mockSettings as unknown as Settings,
+      mockExtensionLoader,
+      'test-task',
+    );
+
+    expect(mockConfigConstructor).toHaveBeenCalledWith(
+      expect.objectContaining({
+        checkpointing: true,
+      }),
+    );
+  });
+});

packages/a2a-server/src/config/config.ts

@@ -23,6 +23,7 @@ import {
   startupProfiler,
   PREVIEW_GEMINI_MODEL,
   homedir,
+  GitService,
 } from '@google/gemini-cli-core';
 
 import { logger } from '../utils/logger.js';
@@ -41,6 +42,19 @@ export async function loadConfig(
     settings.folderTrust === true ||
     process.env['GEMINI_FOLDER_TRUST'] === 'true';
 
+  let checkpointing = process.env['CHECKPOINTING']
+    ? process.env['CHECKPOINTING'] === 'true'
+    : settings.checkpointing?.enabled;
+
+  if (checkpointing) {
+    if (!(await GitService.verifyGitAvailability())) {
+      logger.warn(
+        '[Config] Checkpointing is enabled but git is not installed. Disabling checkpointing.',
+      );
+      checkpointing = false;
+    }
+  }
+
   const configParams: ConfigParameters = {
     sessionId: taskId,
     model: settings.general?.previewFeatures
@@ -79,9 +93,7 @@ export async function loadConfig(
     folderTrust,
     trustedFolder: true,
     extensionLoader,
-    checkpointing: process.env['CHECKPOINTING']
-      ? process.env['CHECKPOINTING'] === 'true'
-      : settings.checkpointing?.enabled,
+    checkpointing,
     previewFeatures: settings.general?.previewFeatures,
     interactive: true,
     enableInteractiveShell: true,

packages/cli/index.ts

@@ -11,6 +11,30 @@ import { FatalError, writeToStderr } from '@google/gemini-cli-core';
 import { runExitCleanup } from './src/utils/cleanup.js';
 
 // --- Global Entry Point ---
+
+// Suppress known race condition error in node-pty on Windows
+// Tracking bug: https://github.com/microsoft/node-pty/issues/827
+process.on('uncaughtException', (error) => {
+  if (
+    process.platform === 'win32' &&
+    error instanceof Error &&
+    error.message === 'Cannot resize a pty that has already exited'
+  ) {
+    // This error happens on Windows with node-pty when resizing a pty that has just exited.
+    // It is a race condition in node-pty that we cannot prevent, so we silence it.
+    return;
+  }
+
+  // For other errors, we rely on the default behavior, but since we attached a listener,
+  // we must manually replicate it.
+  if (error instanceof Error) {
+    writeToStderr(error.stack + '\n');
+  } else {
+    writeToStderr(String(error) + '\n');
+  }
+  process.exit(1);
+});
+
 main().catch(async (error) => {
   await runExitCleanup();
 

packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@google/gemini-cli",
-  "version": "0.26.0-nightly.20260115.6cb3ae4e0",
+  "version": "0.27.0-nightly.20260121.97aac696f",
   "description": "Gemini CLI",
   "license": "Apache-2.0",
   "repository": {
@@ -26,7 +26,7 @@
     "dist"
   ],
   "config": {
-    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.26.0-nightly.20260115.6cb3ae4e0"
+    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.27.0-nightly.20260121.97aac696f"
   },
   "dependencies": {
     "@agentclientprotocol/sdk": "^0.12.0",

packages/cli/src/commands/extensions.test.tsx

@@ -54,15 +54,33 @@ describe('extensionsCommand', () => {
     extensionsCommand.builder(mockYargs);
 
     expect(mockYargs.middleware).toHaveBeenCalled();
-    expect(mockYargs.command).toHaveBeenCalledWith({ command: 'install' });
-    expect(mockYargs.command).toHaveBeenCalledWith({ command: 'uninstall' });
-    expect(mockYargs.command).toHaveBeenCalledWith({ command: 'list' });
-    expect(mockYargs.command).toHaveBeenCalledWith({ command: 'update' });
-    expect(mockYargs.command).toHaveBeenCalledWith({ command: 'disable' });
-    expect(mockYargs.command).toHaveBeenCalledWith({ command: 'enable' });
-    expect(mockYargs.command).toHaveBeenCalledWith({ command: 'link' });
-    expect(mockYargs.command).toHaveBeenCalledWith({ command: 'new' });
-    expect(mockYargs.command).toHaveBeenCalledWith({ command: 'validate' });
+    expect(mockYargs.command).toHaveBeenCalledWith(
+      expect.objectContaining({ command: 'install' }),
+    );
+    expect(mockYargs.command).toHaveBeenCalledWith(
+      expect.objectContaining({ command: 'uninstall' }),
+    );
+    expect(mockYargs.command).toHaveBeenCalledWith(
+      expect.objectContaining({ command: 'list' }),
+    );
+    expect(mockYargs.command).toHaveBeenCalledWith(
+      expect.objectContaining({ command: 'update' }),
+    );
+    expect(mockYargs.command).toHaveBeenCalledWith(
+      expect.objectContaining({ command: 'disable' }),
+    );
+    expect(mockYargs.command).toHaveBeenCalledWith(
+      expect.objectContaining({ command: 'enable' }),
+    );
+    expect(mockYargs.command).toHaveBeenCalledWith(
+      expect.objectContaining({ command: 'link' }),
+    );
+    expect(mockYargs.command).toHaveBeenCalledWith(
+      expect.objectContaining({ command: 'new' }),
+    );
+    expect(mockYargs.command).toHaveBeenCalledWith(
+      expect.objectContaining({ command: 'validate' }),
+    );
     expect(mockYargs.demandCommand).toHaveBeenCalledWith(1, expect.any(String));
     expect(mockYargs.version).toHaveBeenCalledWith(false);
   });

packages/cli/src/commands/extensions.tsx

@@ -16,6 +16,7 @@ import { newCommand } from './extensions/new.js';
 import { validateCommand } from './extensions/validate.js';
 import { configureCommand } from './extensions/configure.js';
 import { initializeOutputListenersAndFlush } from '../gemini.js';
+import { defer } from '../deferred.js';
 
 export const extensionsCommand: CommandModule = {
   command: 'extensions <command>',
@@ -23,17 +24,20 @@ export const extensionsCommand: CommandModule = {
   describe: 'Manage Gemini CLI extensions.',
   builder: (yargs) =>
     yargs
-      .middleware(() => initializeOutputListenersAndFlush())
-      .command(installCommand)
-      .command(uninstallCommand)
-      .command(listCommand)
-      .command(updateCommand)
-      .command(disableCommand)
-      .command(enableCommand)
-      .command(linkCommand)
-      .command(newCommand)
-      .command(validateCommand)
-      .command(configureCommand)
+      .middleware((argv) => {
+        initializeOutputListenersAndFlush();
+        argv['isCommand'] = true;
+      })
+      .command(defer(installCommand, 'extensions'))
+      .command(defer(uninstallCommand, 'extensions'))
+      .command(defer(listCommand, 'extensions'))
+      .command(defer(updateCommand, 'extensions'))
+      .command(defer(disableCommand, 'extensions'))
+      .command(defer(enableCommand, 'extensions'))
+      .command(defer(linkCommand, 'extensions'))
+      .command(defer(newCommand, 'extensions'))
+      .command(defer(validateCommand, 'extensions'))
+      .command(defer(configureCommand, 'extensions'))
       .demandCommand(1, 'You need at least one command before continuing.')
       .version(false),
   handler: () => {

packages/cli/src/commands/extensions/examples/hooks/gemini-extension.json

@@ -0,0 +1,4 @@
+{
+  "name": "hooks-example",
+  "version": "1.0.0"
+}

packages/cli/src/commands/extensions/examples/hooks/hooks/hooks.json

@@ -0,0 +1,14 @@
+{
+  "hooks": {
+    "SessionStart": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node ${extensionPath}/scripts/on-start.js"
+          }
+        ]
+      }
+    ]
+  }
+}

packages/cli/src/commands/extensions/examples/hooks/scripts/on-start.js

@@ -0,0 +1,8 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+console.log(
+  'Session Started! This is running from a script in the hooks-example extension.',
+);

packages/cli/src/commands/extensions/examples/mcp-server/README.md

@@ -0,0 +1,35 @@
+# MCP Server Example
+
+This is a basic example of an MCP (Model Context Protocol) server used as a
+Gemini CLI extension. It demonstrates how to expose tools and prompts to the
+Gemini CLI.
+
+## Description
+
+The contents of this directory are a valid MCP server implementation using the
+`@modelcontextprotocol/sdk`. It exposes:
+
+- A tool `fetch_posts` that mock-fetches posts.
+- A prompt `poem-writer`.
+
+## Structure
+
+- `example.js`: The main server entry point.
+- `gemini-extension.json`: The configuration file that tells Gemini CLI how to
+  use this extension.
+- `package.json`: Helper for dependencies.
+
+## How to Use
+
+1.  Navigate to this directory:
+
+    ```bash
+    cd packages/cli/src/commands/extensions/examples/mcp-server
+    ```
+
+2.  Install dependencies:
+    ```bash
+    npm install
+    ```
+
+This example is typically used by `gemini extensions new`.

packages/cli/src/commands/extensions/examples/mcp-server/example.test.ts

@@ -1,135 +0,0 @@
-/**
- * @license
- * Copyright 2025 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
-import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
-import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
-import { z } from 'zod';
-
-// Mock the MCP server and transport
-const mockRegisterTool = vi.fn();
-const mockRegisterPrompt = vi.fn();
-const mockConnect = vi.fn();
-
-vi.mock('@modelcontextprotocol/sdk/server/mcp.js', () => ({
-  McpServer: vi.fn().mockImplementation(() => ({
-    registerTool: mockRegisterTool,
-    registerPrompt: mockRegisterPrompt,
-    connect: mockConnect,
-  })),
-}));
-
-vi.mock('@modelcontextprotocol/sdk/server/stdio.js', () => ({
-  StdioServerTransport: vi.fn(),
-}));
-
-describe('MCP Server Example', () => {
-  beforeEach(async () => {
-    // Dynamically import the server setup after mocks are in place
-    await import('./example.js');
-  });
-
-  afterEach(() => {
-    vi.clearAllMocks();
-    vi.resetModules();
-  });
-
-  it('should create an McpServer with the correct name and version', () => {
-    expect(McpServer).toHaveBeenCalledWith({
-      name: 'prompt-server',
-      version: '1.0.0',
-    });
-  });
-
-  it('should register the "fetch_posts" tool', () => {
-    expect(mockRegisterTool).toHaveBeenCalledWith(
-      'fetch_posts',
-      {
-        description: 'Fetches a list of posts from a public API.',
-        inputSchema: z.object({}).shape,
-      },
-      expect.any(Function),
-    );
-  });
-
-  it('should register the "poem-writer" prompt', () => {
-    expect(mockRegisterPrompt).toHaveBeenCalledWith(
-      'poem-writer',
-      {
-        title: 'Poem Writer',
-        description: 'Write a nice haiku',
-        argsSchema: expect.any(Object),
-      },
-      expect.any(Function),
-    );
-  });
-
-  it('should connect the server to an StdioServerTransport', () => {
-    expect(StdioServerTransport).toHaveBeenCalled();
-    expect(mockConnect).toHaveBeenCalledWith(expect.any(StdioServerTransport));
-  });
-
-  describe('fetch_posts tool implementation', () => {
-    it('should fetch posts and return a formatted response', async () => {
-      const mockPosts = [
-        { id: 1, title: 'Post 1' },
-        { id: 2, title: 'Post 2' },
-      ];
-      global.fetch = vi.fn().mockResolvedValue({
-        json: vi.fn().mockResolvedValue(mockPosts),
-      });
-
-      const toolFn = mockRegisterTool.mock.calls[0][2];
-      const result = await toolFn();
-
-      expect(global.fetch).toHaveBeenCalledWith(
-        'https://jsonplaceholder.typicode.com/posts',
-      );
-      expect(result).toEqual({
-        content: [
-          {
-            type: 'text',
-            text: JSON.stringify({ posts: mockPosts }),
-          },
-        ],
-      });
-    });
-  });
-
-  describe('poem-writer prompt implementation', () => {
-    it('should generate a prompt with a title', () => {
-      const promptFn = mockRegisterPrompt.mock.calls[0][2];
-      const result = promptFn({ title: 'My Poem' });
-      expect(result).toEqual({
-        messages: [
-          {
-            role: 'user',
-            content: {
-              type: 'text',
-              text: 'Write a haiku called My Poem. Note that a haiku is 5 syllables followed by 7 syllables followed by 5 syllables ',
-            },
-          },
-        ],
-      });
-    });
-
-    it('should generate a prompt with a title and mood', () => {
-      const promptFn = mockRegisterPrompt.mock.calls[0][2];
-      const result = promptFn({ title: 'My Poem', mood: 'sad' });
-      expect(result).toEqual({
-        messages: [
-          {
-            role: 'user',
-            content: {
-              type: 'text',
-              text: 'Write a haiku with the mood sad called My Poem. Note that a haiku is 5 syllables followed by 7 syllables followed by 5 syllables ',
-            },
-          },
-        ],
-      });
-    });
-  });
-});

packages/cli/src/commands/extensions/examples/mcp-server/gemini-extension.json

@@ -4,7 +4,7 @@
   "mcpServers": {
     "nodeServer": {
       "command": "node",
-      "args": ["${extensionPath}${/}dist${/}example.js"],
+      "args": ["${extensionPath}${/}example.js"],
       "cwd": "${extensionPath}"
     }
   }

packages/cli/src/commands/extensions/examples/mcp-server/package.json

@@ -4,13 +4,6 @@
   "description": "Example MCP Server for Gemini CLI Extension",
   "type": "module",
   "main": "example.js",
-  "scripts": {
-    "build": "tsc"
-  },
-  "devDependencies": {
-    "typescript": "~5.4.5",
-    "@types/node": "^20.11.25"
-  },
   "dependencies": {
     "@modelcontextprotocol/sdk": "^1.23.0",
     "zod": "^3.22.4"

packages/cli/src/commands/extensions/examples/mcp-server/tsconfig.json

@@ -1,13 +0,0 @@
-{
-  "compilerOptions": {
-    "target": "ES2022",
-    "module": "NodeNext",
-    "moduleResolution": "NodeNext",
-    "strict": true,
-    "esModuleInterop": true,
-    "skipLibCheck": true,
-    "forceConsistentCasingInFileNames": true,
-    "outDir": "./dist"
-  },
-  "include": ["example.ts"]
-}

packages/cli/src/commands/extensions/examples/skills/gemini-extension.json

@@ -0,0 +1,4 @@
+{
+  "name": "skills-example",
+  "version": "1.0.0"
+}

packages/cli/src/commands/extensions/examples/skills/skills/greeter/SKILL.md

@@ -0,0 +1,7 @@
+---
+name: greeter
+description: A friendly greeter skill
+---
+
+You are a friendly greeter. When the user says "hello" or asks for a greeting,
+you should reply with: "Greetings from the skills-example extension! 👋"

packages/cli/src/commands/hooks.tsx

@@ -14,7 +14,10 @@ export const hooksCommand: CommandModule = {
   describe: 'Manage Gemini CLI hooks.',
   builder: (yargs) =>
     yargs
-      .middleware(() => initializeOutputListenersAndFlush())
+      .middleware((argv) => {
+        initializeOutputListenersAndFlush();
+        argv['isCommand'] = true;
+      })
       .command(migrateCommand)
       .demandCommand(1, 'You need at least one command before continuing.')
       .version(false),

packages/cli/src/commands/hooks/migrate.test.ts

@@ -511,8 +511,5 @@ describe('migrate command', () => {
     expect(debugLoggerLogSpy).toHaveBeenCalledWith(
       '\nMigration complete! Please review the migrated hooks in .gemini/settings.json',
     );
-    expect(debugLoggerLogSpy).toHaveBeenCalledWith(
-      'Note: Set hooks.enabled to true in your settings to enable the hook system.',
-    );
   });
 });

packages/cli/src/commands/hooks/migrate.ts

@@ -230,7 +230,10 @@ export async function handleMigrateFromClaude() {
   const settings = loadSettings(workingDir);
 
   // Merge migrated hooks with existing hooks
-  const existingHooks = settings.merged.hooks as Record<string, unknown>;
+  const existingHooks = (settings.merged?.hooks || {}) as Record<
+    string,
+    unknown
+  >;
   const mergedHooks = { ...existingHooks, ...migratedHooks };
 
   // Update settings (setValue automatically saves)
@@ -241,9 +244,6 @@ export async function handleMigrateFromClaude() {
     debugLogger.log(
       '\nMigration complete! Please review the migrated hooks in .gemini/settings.json',
     );
-    debugLogger.log(
-      'Note: Set hooks.enabled to true in your settings to enable the hook system.',
-    );
   } catch (error) {
     debugLogger.error(`Error saving migrated hooks: ${getErrorMessage(error)}`);
   }

packages/cli/src/commands/mcp.ts

@@ -10,16 +10,20 @@ import { addCommand } from './mcp/add.js';
 import { removeCommand } from './mcp/remove.js';
 import { listCommand } from './mcp/list.js';
 import { initializeOutputListenersAndFlush } from '../gemini.js';
+import { defer } from '../deferred.js';
 
 export const mcpCommand: CommandModule = {
   command: 'mcp',
   describe: 'Manage MCP servers',
   builder: (yargs: Argv) =>
     yargs
-      .middleware(() => initializeOutputListenersAndFlush())
-      .command(addCommand)
-      .command(removeCommand)
-      .command(listCommand)
+      .middleware((argv) => {
+        initializeOutputListenersAndFlush();
+        argv['isCommand'] = true;
+      })
+      .command(defer(addCommand, 'mcp'))
+      .command(defer(removeCommand, 'mcp'))
+      .command(defer(listCommand, 'mcp'))
       .demandCommand(1, 'You need at least one command before continuing.')
       .version(false),
   handler: () => {

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

@@ -123,8 +123,13 @@ describe('mcp list command', () => {
         ...defaultMergedSettings,
         mcpServers: {
           'stdio-server': { command: '/path/to/server', args: ['arg1'] },
-          'sse-server': { url: 'https://example.com/sse' },
+          'sse-server': { url: 'https://example.com/sse', type: 'sse' },
           'http-server': { httpUrl: 'https://example.com/http' },
+          'http-server-by-default': { url: 'https://example.com/http' },
+          'http-server-with-type': {
+            url: 'https://example.com/http',
+            type: 'http',
+          },
         },
       },
     });
@@ -150,6 +155,16 @@ describe('mcp list command', () => {
         'http-server: https://example.com/http (http) - Connected',
       ),
     );
+    expect(debugLogger.log).toHaveBeenCalledWith(
+      expect.stringContaining(
+        'http-server-by-default: https://example.com/http (http) - Connected',
+      ),
+    );
+    expect(debugLogger.log).toHaveBeenCalledWith(
+      expect.stringContaining(
+        'http-server-with-type: https://example.com/http (http) - Connected',
+      ),
+    );
   });
 
   it('should display disconnected status when connection fails', async () => {

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

@@ -144,7 +144,8 @@ export async function listMcpServers(): Promise<void> {
     if (server.httpUrl) {
       serverInfo += `${server.httpUrl} (http)`;
     } else if (server.url) {
-      serverInfo += `${server.url} (sse)`;
+      const type = server.type || 'http';
+      serverInfo += `${server.url} (${type})`;
     } else if (server.command) {
       serverInfo += `${server.command} ${server.args?.join(' ') || ''} (stdio)`;
     }

packages/cli/src/commands/skills.test.tsx

@@ -38,13 +38,19 @@ describe('skillsCommand', () => {
     skillsCommand.builder(mockYargs);
 
     expect(mockYargs.middleware).toHaveBeenCalled();
-    expect(mockYargs.command).toHaveBeenCalledWith({ command: 'list' });
-    expect(mockYargs.command).toHaveBeenCalledWith({
-      command: 'enable <name>',
-    });
-    expect(mockYargs.command).toHaveBeenCalledWith({
-      command: 'disable <name>',
-    });
+    expect(mockYargs.command).toHaveBeenCalledWith(
+      expect.objectContaining({ command: 'list' }),
+    );
+    expect(mockYargs.command).toHaveBeenCalledWith(
+      expect.objectContaining({
+        command: 'enable <name>',
+      }),
+    );
+    expect(mockYargs.command).toHaveBeenCalledWith(
+      expect.objectContaining({
+        command: 'disable <name>',
+      }),
+    );
     expect(mockYargs.demandCommand).toHaveBeenCalledWith(1, expect.any(String));
     expect(mockYargs.version).toHaveBeenCalledWith(false);
   });

packages/cli/src/commands/skills.tsx

@@ -11,6 +11,7 @@ import { disableCommand } from './skills/disable.js';
 import { installCommand } from './skills/install.js';
 import { uninstallCommand } from './skills/uninstall.js';
 import { initializeOutputListenersAndFlush } from '../gemini.js';
+import { defer } from '../deferred.js';
 
 export const skillsCommand: CommandModule = {
   command: 'skills <command>',
@@ -18,12 +19,15 @@ export const skillsCommand: CommandModule = {
   describe: 'Manage agent skills.',
   builder: (yargs) =>
     yargs
-      .middleware(() => initializeOutputListenersAndFlush())
-      .command(listCommand)
-      .command(enableCommand)
-      .command(disableCommand)
-      .command(installCommand)
-      .command(uninstallCommand)
+      .middleware((argv) => {
+        initializeOutputListenersAndFlush();
+        argv['isCommand'] = true;
+      })
+      .command(defer(listCommand, 'skills'))
+      .command(defer(enableCommand, 'skills'))
+      .command(defer(disableCommand, 'skills'))
+      .command(defer(installCommand, 'skills'))
+      .command(defer(uninstallCommand, 'skills'))
       .demandCommand(1, 'You need at least one command before continuing.')
       .version(false),
   handler: () => {

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

@@ -34,6 +34,10 @@ vi.mock('./sandboxConfig.js', () => ({
   loadSandboxConfig: vi.fn(async () => undefined),
 }));
 
+vi.mock('../commands/utils.js', () => ({
+  exitCli: vi.fn(),
+}));
+
 vi.mock('fs', async (importOriginal) => {
   const actualFs = await importOriginal<typeof import('fs')>();
   const pathMod = await import('node:path');
@@ -134,7 +138,12 @@ vi.mock('@google/gemini-cli-core', async () => {
   };
 });
 
-vi.mock('./extension-manager.js');
+vi.mock('./extension-manager.js', () => {
+  const ExtensionManager = vi.fn();
+  ExtensionManager.prototype.loadExtensions = vi.fn();
+  ExtensionManager.prototype.getExtensions = vi.fn().mockReturnValue([]);
+  return { ExtensionManager };
+});
 
 // Global setup to ensure clean environment for all tests in this file
 const originalArgv = process.argv;
@@ -142,6 +151,11 @@ const originalGeminiModel = process.env['GEMINI_MODEL'];
 
 beforeEach(() => {
   delete process.env['GEMINI_MODEL'];
+  // Restore ExtensionManager mocks by re-assigning them
+  ExtensionManager.prototype.getExtensions = vi.fn().mockReturnValue([]);
+  ExtensionManager.prototype.loadExtensions = vi
+    .fn()
+    .mockResolvedValue(undefined);
 });
 
 afterEach(() => {
@@ -534,6 +548,42 @@ describe('parseArguments', () => {
       'Use whoami to write a poem in file poem.md about my username in pig latin and use wc to tell me how many lines are in the poem you wrote.',
     );
   });
+
+  it('should set isCommand to true for mcp command', async () => {
+    process.argv = ['node', 'script.js', 'mcp', 'list'];
+    const argv = await parseArguments(createTestMergedSettings());
+    expect(argv.isCommand).toBe(true);
+  });
+
+  it('should set isCommand to true for extensions command', async () => {
+    process.argv = ['node', 'script.js', 'extensions', 'list'];
+    // Extensions command uses experimental settings
+    const settings = createTestMergedSettings({
+      experimental: { extensionManagement: true },
+    });
+    const argv = await parseArguments(settings);
+    expect(argv.isCommand).toBe(true);
+  });
+
+  it('should set isCommand to true for skills command', async () => {
+    process.argv = ['node', 'script.js', 'skills', 'list'];
+    // Skills command enabled by default or via experimental
+    const settings = createTestMergedSettings({
+      experimental: { skills: true },
+    });
+    const argv = await parseArguments(settings);
+    expect(argv.isCommand).toBe(true);
+  });
+
+  it('should set isCommand to true for hooks command', async () => {
+    process.argv = ['node', 'script.js', 'hooks', 'migrate'];
+    // Hooks command enabled via tools settings
+    const settings = createTestMergedSettings({
+      tools: { enableHooks: true },
+    });
+    const argv = await parseArguments(settings);
+    expect(argv.isCommand).toBe(true);
+  });
 });
 
 describe('loadCliConfig', () => {
@@ -639,11 +689,31 @@ describe('loadCliConfig', () => {
     );
     expect(config.getApprovalMode()).toBe(ApprovalMode.DEFAULT);
   });
+
+  it('should be non-interactive when isCommand is set', async () => {
+    process.argv = ['node', 'script.js', 'mcp', 'list'];
+    const argv = await parseArguments(createTestMergedSettings());
+    argv.isCommand = true; // explicitly set it as if middleware ran (it does in parseArguments but we want to be sure for this isolated test if we were mocking argv)
+
+    // reset tty for this test
+    process.stdin.isTTY = true;
+
+    const settings = createTestMergedSettings();
+    const config = await loadCliConfig(settings, 'test-session', argv);
+
+    expect(config.isInteractive()).toBe(false);
+  });
 });
 
 describe('Hierarchical Memory Loading (config.ts) - Placeholder Suite', () => {
   beforeEach(() => {
     vi.resetAllMocks();
+    // Restore ExtensionManager mocks that were reset
+    ExtensionManager.prototype.getExtensions = vi.fn().mockReturnValue([]);
+    ExtensionManager.prototype.loadExtensions = vi
+      .fn()
+      .mockResolvedValue(undefined);
+
     vi.mocked(os.homedir).mockReturnValue('/mock/home/user');
     // Other common mocks would be reset here.
   });
@@ -701,6 +771,63 @@ describe('Hierarchical Memory Loading (config.ts) - Placeholder Suite', () => {
       200, // maxDirs
     );
   });
+
+  it('should pass includeDirectories to loadServerHierarchicalMemory when loadMemoryFromIncludeDirectories is true', async () => {
+    process.argv = ['node', 'script.js'];
+    const includeDir = path.resolve(path.sep, 'path', 'to', 'include');
+    const settings = createTestMergedSettings({
+      context: {
+        includeDirectories: [includeDir],
+        loadMemoryFromIncludeDirectories: true,
+      },
+    });
+
+    const argv = await parseArguments(settings);
+    await loadCliConfig(settings, 'session-id', argv);
+
+    expect(ServerConfig.loadServerHierarchicalMemory).toHaveBeenCalledWith(
+      expect.any(String),
+      [includeDir],
+      false,
+      expect.any(Object),
+      expect.any(ExtensionManager),
+      true,
+      'tree',
+      expect.objectContaining({
+        respectGitIgnore: true,
+        respectGeminiIgnore: true,
+      }),
+      200,
+    );
+  });
+
+  it('should NOT pass includeDirectories to loadServerHierarchicalMemory when loadMemoryFromIncludeDirectories is false', async () => {
+    process.argv = ['node', 'script.js'];
+    const settings = createTestMergedSettings({
+      context: {
+        includeDirectories: ['/path/to/include'],
+        loadMemoryFromIncludeDirectories: false,
+      },
+    });
+
+    const argv = await parseArguments(settings);
+    await loadCliConfig(settings, 'session-id', argv);
+
+    expect(ServerConfig.loadServerHierarchicalMemory).toHaveBeenCalledWith(
+      expect.any(String),
+      [],
+      false,
+      expect.any(Object),
+      expect.any(ExtensionManager),
+      true,
+      'tree',
+      expect.objectContaining({
+        respectGitIgnore: true,
+        respectGeminiIgnore: true,
+      }),
+      200,
+    );
+  });
 });
 
 describe('mergeMcpServers', () => {

packages/cli/src/config/config.ts

@@ -83,6 +83,9 @@ export interface CliArgs {
   outputFormat: string | undefined;
   fakeResponses: string | undefined;
   recordResponses: string | undefined;
+  rawOutput: boolean | undefined;
+  acceptRawOutputRisk: boolean | undefined;
+  isCommand: boolean | undefined;
 }
 
 export async function parseArguments(
@@ -95,7 +98,6 @@ export async function parseArguments(
     .usage(
       'Usage: gemini [options] [command]\n\nGemini CLI - Launch an interactive CLI, use -p/--prompt for non-interactive mode',
     )
-
     .option('debug', {
       alias: 'd',
       type: 'boolean',
@@ -248,6 +250,15 @@ export async function parseArguments(
           type: 'string',
           description: 'Path to a file to record model responses for testing.',
           hidden: true,
+        })
+        .option('raw-output', {
+          type: 'boolean',
+          description:
+            'Disable sanitization of model output (e.g. allow ANSI escape sequences). WARNING: This can be a security risk if the model output is untrusted.',
+        })
+        .option('accept-raw-output-risk', {
+          type: 'boolean',
+          description: 'Suppress the security warning when using --raw-output.',
         }),
     )
     // Register MCP subcommands
@@ -451,6 +462,7 @@ export async function loadCliConfig(
     workspaceDir: cwd,
     enabledExtensionOverrides: argv.extensions,
     eventEmitter: appEvents as EventEmitter<ExtensionEvents>,
+    clientVersion: await getVersion(),
   });
   await extensionManager.loadExtensions();
 
@@ -464,7 +476,9 @@ export async function loadCliConfig(
     // Call the (now wrapper) loadHierarchicalGeminiMemory which calls the server's version
     const result = await loadServerHierarchicalMemory(
       cwd,
-      [],
+      settings.context?.loadMemoryFromIncludeDirectories || false
+        ? includeDirectories
+        : [],
       debugMode,
       fileService,
       extensionManager,
@@ -563,7 +577,7 @@ export async function loadCliConfig(
   const interactive =
     !!argv.promptInteractive ||
     !!argv.experimentalAcp ||
-    (process.stdin.isTTY && !hasQuery && !argv.prompt);
+    (process.stdin.isTTY && !hasQuery && !argv.prompt && !argv.isCommand);
 
   const allowedTools = argv.allowedTools || settings.tools?.allowed || [];
   const allowedToolsSet = new Set(allowedTools);
@@ -653,6 +667,7 @@ export async function loadCliConfig(
 
   return new Config({
     sessionId,
+    clientVersion: await getVersion(),
     embeddingModel: DEFAULT_GEMINI_EMBEDDING_MODEL,
     sandbox: sandboxConfig,
     targetDir: cwd,
@@ -749,21 +764,21 @@ export async function loadCliConfig(
     output: {
       format: (argv.outputFormat ?? settings.output?.format) as OutputFormat,
     },
-    codebaseInvestigatorSettings:
-      settings.experimental?.codebaseInvestigatorSettings,
-    cliHelpAgentSettings: settings.experimental?.cliHelpAgentSettings,
     fakeResponses: argv.fakeResponses,
     recordResponses: argv.recordResponses,
     retryFetchErrors: settings.general?.retryFetchErrors,
     ptyInfo: ptyInfo?.name,
     disableLLMCorrection: settings.tools?.disableLLMCorrection,
+    rawOutput: argv.rawOutput,
+    acceptRawOutputRisk: argv.acceptRawOutputRisk,
     modelConfigServiceConfig: settings.modelConfigs,
     // TODO: loading of hooks based on workspace trust
     enableHooks:
       (settings.tools?.enableHooks ?? true) &&
-      (settings.hooks?.enabled ?? false),
+      (settings.hooksConfig?.enabled ?? true),
     enableHooksUI: settings.tools?.enableHooks ?? true,
     hooks: settings.hooks || {},
+    disabledHooks: settings.hooksConfig?.disabled || [],
     projectHooks: projectHooks || {},
     onModelChange: (model: string) => saveModelChange(loadedSettings, model),
     onReload: async () => {

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

@@ -76,6 +76,7 @@ interface ExtensionManagerParams {
   requestSetting: ((setting: ExtensionSetting) => Promise<string>) | null;
   workspaceDir: string;
   eventEmitter?: EventEmitter<ExtensionEvents>;
+  clientVersion?: string;
 }
 
 /**
@@ -105,6 +106,7 @@ export class ExtensionManager extends ExtensionLoader {
       telemetry: options.settings.telemetry,
       interactive: false,
       sessionId: randomUUID(),
+      clientVersion: options.clientVersion ?? 'unknown',
       targetDir: options.workspaceDir,
       cwd: options.workspaceDir,
       model: '',
@@ -611,7 +613,10 @@ Would you like to attempt to install via "git clone" instead?`,
         .filter((contextFilePath) => fs.existsSync(contextFilePath));
 
       let hooks: { [K in HookEventName]?: HookDefinition[] } | undefined;
-      if (this.settings.tools.enableHooks && this.settings.hooks.enabled) {
+      if (
+        this.settings.tools.enableHooks &&
+        this.settings.hooksConfig.enabled
+      ) {
         hooks = await this.loadExtensionHooks(effectiveExtensionPath, {
           extensionPath: effectiveExtensionPath,
           workspacePath: this.workspaceDir,

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

@@ -815,6 +815,7 @@ describe('extension tests', () => {
         fs.mkdirSync(hooksDir);
 
         const hooksConfig = {
+          enabled: false,
           hooks: {
             BeforeTool: [
               {
@@ -836,7 +837,7 @@ describe('extension tests', () => {
         );
 
         const settings = loadSettings(tempWorkspaceDir).merged;
-        settings.hooks.enabled = true;
+        settings.hooksConfig.enabled = true;
 
         extensionManager = new ExtensionManager({
           workspaceDir: tempWorkspaceDir,
@@ -867,11 +868,11 @@ describe('extension tests', () => {
         fs.mkdirSync(hooksDir);
         fs.writeFileSync(
           path.join(hooksDir, 'hooks.json'),
-          JSON.stringify({ hooks: { BeforeTool: [] } }),
+          JSON.stringify({ hooks: { BeforeTool: [] }, enabled: false }),
         );
 
         const settings = loadSettings(tempWorkspaceDir).merged;
-        settings.hooks.enabled = false;
+        settings.hooksConfig.enabled = false;
 
         extensionManager = new ExtensionManager({
           workspaceDir: tempWorkspaceDir,

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

@@ -33,14 +33,17 @@ describe('keyBindings config', () => {
           expect(binding.key.length).toBeGreaterThan(0);
 
           // Modifier properties should be boolean or undefined
-          if (binding.ctrl !== undefined) {
-            expect(typeof binding.ctrl).toBe('boolean');
-          }
           if (binding.shift !== undefined) {
             expect(typeof binding.shift).toBe('boolean');
           }
-          if (binding.command !== undefined) {
-            expect(typeof binding.command).toBe('boolean');
+          if (binding.alt !== undefined) {
+            expect(typeof binding.alt).toBe('boolean');
+          }
+          if (binding.ctrl !== undefined) {
+            expect(typeof binding.ctrl).toBe('boolean');
+          }
+          if (binding.cmd !== undefined) {
+            expect(typeof binding.cmd).toBe('boolean');
           }
         }
       }
@@ -73,9 +76,27 @@ describe('keyBindings config', () => {
       expect(dialogNavDown).toContainEqual({ key: 'down', shift: false });
       expect(dialogNavDown).toContainEqual({ key: 'j', shift: false });
 
-      // Verify physical home/end keys
-      expect(defaultKeyBindings[Command.HOME]).toContainEqual({ key: 'home' });
-      expect(defaultKeyBindings[Command.END]).toContainEqual({ key: 'end' });
+      // Verify physical home/end keys for cursor movement
+      expect(defaultKeyBindings[Command.HOME]).toContainEqual({
+        key: 'home',
+        ctrl: false,
+        shift: false,
+      });
+      expect(defaultKeyBindings[Command.END]).toContainEqual({
+        key: 'end',
+        ctrl: false,
+        shift: false,
+      });
+
+      // Verify physical home/end keys for scrolling
+      expect(defaultKeyBindings[Command.SCROLL_HOME]).toContainEqual({
+        key: 'home',
+        ctrl: true,
+      });
+      expect(defaultKeyBindings[Command.SCROLL_END]).toContainEqual({
+        key: 'end',
+        ctrl: true,
+      });
     });
   });
 

packages/cli/src/config/keyBindings.ts

@@ -49,6 +49,7 @@ export enum Command {
   REVERSE_SEARCH = 'history.search.start',
   SUBMIT_REVERSE_SEARCH = 'history.search.submit',
   ACCEPT_SUGGESTION_REVERSE_SEARCH = 'history.search.accept',
+  REWIND = 'history.rewind',
 
   // Navigation
   NAVIGATION_UP = 'nav.up',
@@ -76,7 +77,7 @@ export enum Command {
   TOGGLE_MARKDOWN = 'app.toggleMarkdown',
   TOGGLE_COPY_MODE = 'app.toggleCopyMode',
   TOGGLE_YOLO = 'app.toggleYolo',
-  TOGGLE_AUTO_EDIT = 'app.toggleAutoEdit',
+  CYCLE_APPROVAL_MODE = 'app.cycleApprovalMode',
   SHOW_MORE_LINES = 'app.showMoreLines',
   FOCUS_SHELL_INPUT = 'app.focusShellInput',
   UNFOCUS_SHELL_INPUT = 'app.unfocusShellInput',
@@ -90,12 +91,14 @@ export enum Command {
 export interface KeyBinding {
   /** The key name (e.g., 'a', 'return', 'tab', 'escape') */
   key: string;
-  /** Control key requirement: true=must be pressed, false=must not be pressed, undefined=ignore */
-  ctrl?: boolean;
   /** Shift key requirement: true=must be pressed, false=must not be pressed, undefined=ignore */
   shift?: boolean;
-  /** Command/meta key requirement: true=must be pressed, false=must not be pressed, undefined=ignore */
-  command?: boolean;
+  /** Alt/Option key requirement: true=must be pressed, false=must not be pressed, undefined=ignore */
+  alt?: boolean;
+  /** Control key requirement: true=must be pressed, false=must not be pressed, undefined=ignore */
+  ctrl?: boolean;
+  /** Command/Windows/Super key requirement: true=must be pressed, false=must not be pressed, undefined=ignore */
+  cmd?: boolean;
 }
 
 /**
@@ -117,61 +120,76 @@ export const defaultKeyBindings: KeyBindingConfig = {
   [Command.EXIT]: [{ key: 'd', ctrl: true }],
 
   // Cursor Movement
-  [Command.HOME]: [{ key: 'a', ctrl: true }, { key: 'home' }],
-  [Command.END]: [{ key: 'e', ctrl: true }, { key: 'end' }],
-  [Command.MOVE_UP]: [{ key: 'up', ctrl: false, command: false }],
-  [Command.MOVE_DOWN]: [{ key: 'down', ctrl: false, command: false }],
+  [Command.HOME]: [
+    { key: 'a', ctrl: true },
+    { key: 'home', shift: false, ctrl: false },
+  ],
+  [Command.END]: [
+    { key: 'e', ctrl: true },
+    { key: 'end', shift: false, ctrl: false },
+  ],
+  [Command.MOVE_UP]: [
+    { key: 'up', shift: false, alt: false, ctrl: false, cmd: false },
+  ],
+  [Command.MOVE_DOWN]: [
+    { key: 'down', shift: false, alt: false, ctrl: false, cmd: false },
+  ],
   [Command.MOVE_LEFT]: [
-    { key: 'left', ctrl: false, command: false },
+    { key: 'left', shift: false, alt: false, ctrl: false, cmd: false },
     { key: 'b', ctrl: true },
   ],
   [Command.MOVE_RIGHT]: [
-    { key: 'right', ctrl: false, command: false },
+    { key: 'right', shift: false, alt: false, ctrl: false, cmd: false },
     { key: 'f', ctrl: true },
   ],
   [Command.MOVE_WORD_LEFT]: [
     { key: 'left', ctrl: true },
-    { key: 'left', command: true },
-    { key: 'b', command: true },
+    { key: 'left', alt: true },
+    { key: 'b', alt: true },
   ],
   [Command.MOVE_WORD_RIGHT]: [
     { key: 'right', ctrl: true },
-    { key: 'right', command: true },
-    { key: 'f', command: true },
+    { key: 'right', alt: true },
+    { key: 'f', alt: true },
   ],
 
   // Editing
   [Command.KILL_LINE_RIGHT]: [{ key: 'k', ctrl: true }],
   [Command.KILL_LINE_LEFT]: [{ key: 'u', ctrl: true }],
   [Command.CLEAR_INPUT]: [{ key: 'c', ctrl: true }],
-  // Added command (meta/alt/option) for mac compatibility
   [Command.DELETE_WORD_BACKWARD]: [
     { key: 'backspace', ctrl: true },
-    { key: 'backspace', command: true },
+    { key: 'backspace', alt: true },
     { key: 'w', ctrl: true },
   ],
   [Command.DELETE_WORD_FORWARD]: [
     { key: 'delete', ctrl: true },
-    { key: 'delete', command: true },
+    { key: 'delete', alt: true },
   ],
   [Command.DELETE_CHAR_LEFT]: [{ key: 'backspace' }, { key: 'h', ctrl: true }],
   [Command.DELETE_CHAR_RIGHT]: [{ key: 'delete' }, { key: 'd', ctrl: true }],
-  [Command.UNDO]: [{ key: 'z', ctrl: true, shift: false }],
-  [Command.REDO]: [{ key: 'z', ctrl: true, shift: true }],
+  [Command.UNDO]: [{ key: 'z', shift: false, ctrl: true }],
+  [Command.REDO]: [{ key: 'z', shift: true, ctrl: true }],
 
   // Scrolling
   [Command.SCROLL_UP]: [{ key: 'up', shift: true }],
   [Command.SCROLL_DOWN]: [{ key: 'down', shift: true }],
-  [Command.SCROLL_HOME]: [{ key: 'home' }],
-  [Command.SCROLL_END]: [{ key: 'end' }],
+  [Command.SCROLL_HOME]: [
+    { key: 'home', ctrl: true },
+    { key: 'home', shift: true },
+  ],
+  [Command.SCROLL_END]: [
+    { key: 'end', ctrl: true },
+    { key: 'end', shift: true },
+  ],
   [Command.PAGE_UP]: [{ key: 'pageup' }],
   [Command.PAGE_DOWN]: [{ key: 'pagedown' }],
 
   // History & Search
-  [Command.HISTORY_UP]: [{ key: 'p', ctrl: true, shift: false }],
-  [Command.HISTORY_DOWN]: [{ key: 'n', ctrl: true, shift: false }],
+  [Command.HISTORY_UP]: [{ key: 'p', shift: false, ctrl: true }],
+  [Command.HISTORY_DOWN]: [{ key: 'n', shift: false, ctrl: true }],
   [Command.REVERSE_SEARCH]: [{ key: 'r', ctrl: true }],
-  // Note: original logic ONLY checked ctrl=false, ignored meta/shift/paste
+  [Command.REWIND]: [{ key: 'double escape' }],
   [Command.SUBMIT_REVERSE_SEARCH]: [{ key: 'return', ctrl: false }],
   [Command.ACCEPT_SUGGESTION_REVERSE_SEARCH]: [{ key: 'tab' }],
 
@@ -191,14 +209,13 @@ export const defaultKeyBindings: KeyBindingConfig = {
 
   // Suggestions & Completions
   [Command.ACCEPT_SUGGESTION]: [{ key: 'tab' }, { key: 'return', ctrl: false }],
-  // Completion navigation (arrow or Ctrl+P/N)
   [Command.COMPLETION_UP]: [
     { key: 'up', shift: false },
-    { key: 'p', ctrl: true, shift: false },
+    { key: 'p', shift: false, ctrl: true },
   ],
   [Command.COMPLETION_DOWN]: [
     { key: 'down', shift: false },
-    { key: 'n', ctrl: true, shift: false },
+    { key: 'n', shift: false, ctrl: true },
   ],
   [Command.EXPAND_SUGGESTION]: [{ key: 'right' }],
   [Command.COLLAPSE_SUGGESTION]: [{ key: 'left' }],
@@ -208,33 +225,34 @@ export const defaultKeyBindings: KeyBindingConfig = {
   [Command.SUBMIT]: [
     {
       key: 'return',
-      ctrl: false,
-      command: false,
       shift: false,
+      alt: false,
+      ctrl: false,
+      cmd: false,
     },
   ],
-  // Split into multiple data-driven bindings
-  // Now also includes shift+enter for multi-line input
   [Command.NEWLINE]: [
     { key: 'return', ctrl: true },
-    { key: 'return', command: true },
+    { key: 'return', cmd: true },
+    { key: 'return', alt: true },
     { key: 'return', shift: true },
     { key: 'j', ctrl: true },
   ],
   [Command.OPEN_EXTERNAL_EDITOR]: [{ key: 'x', ctrl: true }],
   [Command.PASTE_CLIPBOARD]: [
     { key: 'v', ctrl: true },
-    { key: 'v', command: true },
+    { key: 'v', cmd: true },
+    { key: 'v', alt: true },
   ],
 
   // App Controls
   [Command.SHOW_ERROR_DETAILS]: [{ key: 'f12' }],
   [Command.SHOW_FULL_TODOS]: [{ key: 't', ctrl: true }],
   [Command.SHOW_IDE_CONTEXT_DETAIL]: [{ key: 'g', ctrl: true }],
-  [Command.TOGGLE_MARKDOWN]: [{ key: 'm', command: true }],
+  [Command.TOGGLE_MARKDOWN]: [{ key: 'm', alt: true }],
   [Command.TOGGLE_COPY_MODE]: [{ key: 's', ctrl: true }],
   [Command.TOGGLE_YOLO]: [{ key: 'y', ctrl: true }],
-  [Command.TOGGLE_AUTO_EDIT]: [{ key: 'tab', shift: true }],
+  [Command.CYCLE_APPROVAL_MODE]: [{ key: 'tab', shift: true }],
   [Command.SHOW_MORE_LINES]: [{ key: 's', ctrl: true }],
   [Command.FOCUS_SHELL_INPUT]: [{ key: 'tab', shift: false }],
   [Command.UNFOCUS_SHELL_INPUT]: [{ key: 'tab' }],
@@ -301,6 +319,7 @@ export const commandCategories: readonly CommandCategory[] = [
       Command.REVERSE_SEARCH,
       Command.SUBMIT_REVERSE_SEARCH,
       Command.ACCEPT_SUGGESTION_REVERSE_SEARCH,
+      Command.REWIND,
     ],
   },
   {
@@ -340,7 +359,7 @@ export const commandCategories: readonly CommandCategory[] = [
       Command.TOGGLE_MARKDOWN,
       Command.TOGGLE_COPY_MODE,
       Command.TOGGLE_YOLO,
-      Command.TOGGLE_AUTO_EDIT,
+      Command.CYCLE_APPROVAL_MODE,
       Command.SHOW_MORE_LINES,
       Command.FOCUS_SHELL_INPUT,
       Command.UNFOCUS_SHELL_INPUT,
@@ -397,6 +416,7 @@ export const commandDescriptions: Readonly<Record<Command, string>> = {
   [Command.SUBMIT_REVERSE_SEARCH]: 'Submit the selected reverse-search match.',
   [Command.ACCEPT_SUGGESTION_REVERSE_SEARCH]:
     'Accept a suggestion while reverse searching.',
+  [Command.REWIND]: 'Browse and rewind previous interactions.',
 
   // Navigation
   [Command.NAVIGATION_UP]: 'Move selection up in lists.',
@@ -425,7 +445,8 @@ export const commandDescriptions: Readonly<Record<Command, string>> = {
   [Command.TOGGLE_MARKDOWN]: 'Toggle Markdown rendering.',
   [Command.TOGGLE_COPY_MODE]: 'Toggle copy mode when in alternate buffer mode.',
   [Command.TOGGLE_YOLO]: 'Toggle YOLO (auto-approval) mode for tool calls.',
-  [Command.TOGGLE_AUTO_EDIT]: 'Toggle Auto Edit (auto-accept edits) mode.',
+  [Command.CYCLE_APPROVAL_MODE]:
+    'Cycle through approval modes: default (prompt), auto_edit (auto-approve edits), and plan (read-only).',
   [Command.SHOW_MORE_LINES]:
     'Expand a height-constrained response to show additional lines when not in alternate buffer mode.',
   [Command.FOCUS_SHELL_INPUT]: 'Focus the shell input from the gemini input.',

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

@@ -25,11 +25,15 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
   };
 });
 
-vi.mock('command-exists', () => ({
-  default: {
-    sync: vi.fn(),
-  },
-}));
+vi.mock('command-exists', () => {
+  const sync = vi.fn();
+  return {
+    sync,
+    default: {
+      sync,
+    },
+  };
+});
 
 vi.mock('node:os', async (importOriginal) => {
   const actual = await importOriginal();
@@ -49,6 +53,8 @@ describe('loadSandboxConfig', () => {
   beforeEach(() => {
     vi.resetAllMocks();
     process.env = { ...originalEnv };
+    delete process.env['SANDBOX'];
+    delete process.env['GEMINI_SANDBOX'];
     mockedGetPackageJson.mockResolvedValue({
       config: { sandboxImageUri: 'default/image' },
     });

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

@@ -1961,6 +1961,107 @@ describe('Settings Loading and Merging', () => {
         }),
       );
     });
+
+    it('should migrate disableUpdateNag to enableAutoUpdateNotification in system and system defaults settings', () => {
+      const systemSettingsContent = {
+        general: {
+          disableUpdateNag: true,
+        },
+      };
+      const systemDefaultsContent = {
+        general: {
+          disableUpdateNag: false,
+        },
+      };
+
+      vi.mocked(fs.existsSync).mockReturnValue(true);
+      (fs.readFileSync as Mock).mockImplementation(
+        (p: fs.PathOrFileDescriptor) => {
+          if (p === getSystemSettingsPath()) {
+            return JSON.stringify(systemSettingsContent);
+          }
+          if (p === getSystemDefaultsPath()) {
+            return JSON.stringify(systemDefaultsContent);
+          }
+          return '{}';
+        },
+      );
+
+      const settings = loadSettings(MOCK_WORKSPACE_DIR);
+
+      // Verify system settings were migrated
+      expect(settings.system.settings.general).toHaveProperty(
+        'enableAutoUpdateNotification',
+      );
+      expect(
+        (settings.system.settings.general as Record<string, unknown>)[
+          'enableAutoUpdateNotification'
+        ],
+      ).toBe(false);
+
+      // Verify system defaults settings were migrated
+      expect(settings.systemDefaults.settings.general).toHaveProperty(
+        'enableAutoUpdateNotification',
+      );
+      expect(
+        (settings.systemDefaults.settings.general as Record<string, unknown>)[
+          'enableAutoUpdateNotification'
+        ],
+      ).toBe(true);
+
+      // Merged should also reflect it (system overrides defaults, but both are migrated)
+      expect(settings.merged.general?.enableAutoUpdateNotification).toBe(false);
+    });
+
+    it('should migrate experimental agent settings to agents overrides', () => {
+      const userSettingsContent = {
+        experimental: {
+          codebaseInvestigatorSettings: {
+            enabled: true,
+            maxNumTurns: 15,
+            maxTimeMinutes: 5,
+            thinkingBudget: 16384,
+            model: 'gemini-1.5-pro',
+          },
+          cliHelpAgentSettings: {
+            enabled: false,
+          },
+        },
+      };
+
+      vi.mocked(fs.existsSync).mockReturnValue(true);
+      (fs.readFileSync as Mock).mockImplementation(
+        (p: fs.PathOrFileDescriptor) => {
+          if (p === USER_SETTINGS_PATH)
+            return JSON.stringify(userSettingsContent);
+          return '{}';
+        },
+      );
+
+      const settings = loadSettings(MOCK_WORKSPACE_DIR);
+
+      // Verify migration to agents.overrides
+      expect(settings.user.settings.agents?.overrides).toMatchObject({
+        codebase_investigator: {
+          enabled: true,
+          runConfig: {
+            maxTurns: 15,
+            maxTimeMinutes: 5,
+          },
+          modelConfig: {
+            model: 'gemini-1.5-pro',
+            generateContentConfig: {
+              thinkingConfig: {
+                thinkingBudget: 16384,
+              },
+            },
+          },
+        },
+        cli_help: {
+          enabled: false,
+        },
+      });
+    });
   });
 
   describe('saveSettings', () => {
@@ -2200,6 +2301,23 @@ describe('Settings Loading and Merging', () => {
       expect(loadedSettings.merged.admin?.mcp?.enabled).toBe(true);
       expect(loadedSettings.merged.admin?.extensions?.enabled).toBe(false);
     });
+
+    it('should set skills based on advancedFeaturesEnabled', () => {
+      const loadedSettings = loadSettings();
+      loadedSettings.setRemoteAdminSettings({
+        cliFeatureSetting: {
+          advancedFeaturesEnabled: true,
+        },
+      });
+      expect(loadedSettings.merged.admin.skills?.enabled).toBe(true);
+
+      loadedSettings.setRemoteAdminSettings({
+        cliFeatureSetting: {
+          advancedFeaturesEnabled: false,
+        },
+      });
+      expect(loadedSettings.merged.admin.skills?.enabled).toBe(false);
+    });
   });
 
   describe('getDefaultsFromSchema', () => {

packages/cli/src/config/settings.ts

@@ -363,6 +363,10 @@ export class LoadedSettings {
       admin.extensions = { enabled: extensionsSetting.extensionsEnabled };
     }
 
+    if (cliFeatureSetting?.advancedFeaturesEnabled !== undefined) {
+      admin.skills = { enabled: cliFeatureSetting.advancedFeaturesEnabled };
+    }
+
     this._remoteAdminSettings = { admin };
     this._merged = this.computeMergedSettings();
   }
@@ -800,10 +804,20 @@ export function migrateDeprecatedSettings(
         anyModified = true;
       }
     }
+
+    // Migrate experimental agent settings
+    anyModified ||= migrateExperimentalSettings(
+      settings,
+      loadedSettings,
+      scope,
+      removeDeprecated,
+    );
   };
 
   processScope(SettingScope.User);
   processScope(SettingScope.Workspace);
+  processScope(SettingScope.System);
+  processScope(SettingScope.SystemDefaults);
 
   return anyModified;
 }
@@ -846,3 +860,100 @@ export function saveModelChange(
     );
   }
 }
+
+function migrateExperimentalSettings(
+  settings: Settings,
+  loadedSettings: LoadedSettings,
+  scope: LoadableSettingScope,
+  removeDeprecated: boolean,
+): boolean {
+  const experimentalSettings = settings.experimental as
+    | Record<string, unknown>
+    | undefined;
+  if (experimentalSettings) {
+    const agentsSettings = {
+      ...(settings.agents as Record<string, unknown> | undefined),
+    };
+    const agentsOverrides = {
+      ...((agentsSettings['overrides'] as Record<string, unknown>) || {}),
+    };
+    let modified = false;
+
+    // Migrate codebaseInvestigatorSettings -> agents.overrides.codebase_investigator
+    if (experimentalSettings['codebaseInvestigatorSettings']) {
+      const old = experimentalSettings[
+        'codebaseInvestigatorSettings'
+      ] as Record<string, unknown>;
+      const override = {
+        ...(agentsOverrides['codebase_investigator'] as
+          | Record<string, unknown>
+          | undefined),
+      };
+
+      if (old['enabled'] !== undefined) override['enabled'] = old['enabled'];
+
+      const runConfig = {
+        ...(override['runConfig'] as Record<string, unknown> | undefined),
+      };
+      if (old['maxNumTurns'] !== undefined)
+        runConfig['maxTurns'] = old['maxNumTurns'];
+      if (old['maxTimeMinutes'] !== undefined)
+        runConfig['maxTimeMinutes'] = old['maxTimeMinutes'];
+      if (Object.keys(runConfig).length > 0) override['runConfig'] = runConfig;
+
+      if (old['model'] !== undefined || old['thinkingBudget'] !== undefined) {
+        const modelConfig = {
+          ...(override['modelConfig'] as Record<string, unknown> | undefined),
+        };
+        if (old['model'] !== undefined) modelConfig['model'] = old['model'];
+        if (old['thinkingBudget'] !== undefined) {
+          const generateContentConfig = {
+            ...(modelConfig['generateContentConfig'] as
+              | Record<string, unknown>
+              | undefined),
+          };
+          const thinkingConfig = {
+            ...(generateContentConfig['thinkingConfig'] as
+              | Record<string, unknown>
+              | undefined),
+          };
+          thinkingConfig['thinkingBudget'] = old['thinkingBudget'];
+          generateContentConfig['thinkingConfig'] = thinkingConfig;
+          modelConfig['generateContentConfig'] = generateContentConfig;
+        }
+        override['modelConfig'] = modelConfig;
+      }
+
+      agentsOverrides['codebase_investigator'] = override;
+      modified = true;
+    }
+
+    // Migrate cliHelpAgentSettings -> agents.overrides.cli_help
+    if (experimentalSettings['cliHelpAgentSettings']) {
+      const old = experimentalSettings['cliHelpAgentSettings'] as Record<
+        string,
+        unknown
+      >;
+      const override = {
+        ...(agentsOverrides['cli_help'] as Record<string, unknown> | undefined),
+      };
+      if (old['enabled'] !== undefined) override['enabled'] = old['enabled'];
+      agentsOverrides['cli_help'] = override;
+      modified = true;
+    }
+
+    if (modified) {
+      agentsSettings['overrides'] = agentsOverrides;
+      loadedSettings.setValue(scope, 'agents', agentsSettings);
+
+      if (removeDeprecated) {
+        const newExperimental = { ...experimentalSettings };
+        delete newExperimental['codebaseInvestigatorSettings'];
+        delete newExperimental['cliHelpAgentSettings'];
+        loadedSettings.setValue(scope, 'experimental', newExperimental);
+      }
+      return true;
+    }
+  }
+  return false;
+}

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

@@ -387,7 +387,7 @@ describe('SettingsSchema', () => {
       expect(setting).toBeDefined();
       expect(setting.type).toBe('boolean');
       expect(setting.category).toBe('Experimental');
-      expect(setting.default).toBe(false);
+      expect(setting.default).toBe(true);
       expect(setting.requiresRestart).toBe(true);
       expect(setting.showInDialog).toBe(false);
       expect(setting.description).toBe(
@@ -395,8 +395,8 @@ describe('SettingsSchema', () => {
       );
     });
 
-    it('should have hooks.notifications setting in schema', () => {
-      const setting = getSettingsSchema().hooks.properties.notifications;
+    it('should have hooksConfig.notifications setting in schema', () => {
+      const setting = getSettingsSchema().hooksConfig?.properties.notifications;
       expect(setting).toBeDefined();
       expect(setting.type).toBe('boolean');
       expect(setting.category).toBe('Advanced');

packages/cli/src/config/settingsSchema.ts

@@ -20,7 +20,6 @@ import {
   DEFAULT_TRUNCATE_TOOL_OUTPUT_LINES,
   DEFAULT_TRUNCATE_TOOL_OUTPUT_THRESHOLD,
   DEFAULT_MODEL_CONFIGS,
-  GEMINI_MODEL_ALIAS_AUTO,
 } from '@google/gemini-cli-core';
 import type { CustomTheme } from '../ui/themes/theme.js';
 import type { SessionRetentionSettings } from './settings.js';
@@ -1126,7 +1125,7 @@ const SETTINGS_SCHEMA = {
         label: 'Disable LLM Correction',
         category: 'Tools',
         requiresRestart: true,
-        default: false,
+        default: true,
         description: oneLine`
           Disable LLM-based error correction for edit tools.
           When enabled, tools will fail immediately if exact string matches are not found, instead of attempting to self-correct.
@@ -1429,7 +1428,7 @@ const SETTINGS_SCHEMA = {
         label: 'Event Driven Scheduler',
         category: 'Experimental',
         requiresRestart: true,
-        default: false,
+        default: true,
         description: 'Enables event-driven scheduler within the CLI session.',
         showInDialog: false,
       },
@@ -1461,66 +1460,6 @@ const SETTINGS_SCHEMA = {
         description: 'Enable Agent Skills (experimental).',
         showInDialog: true,
       },
-      codebaseInvestigatorSettings: {
-        type: 'object',
-        label: 'Codebase Investigator Settings',
-        category: 'Experimental',
-        requiresRestart: true,
-        default: {},
-        description: 'Configuration for Codebase Investigator.',
-        showInDialog: false,
-        properties: {
-          enabled: {
-            type: 'boolean',
-            label: 'Enable Codebase Investigator',
-            category: 'Experimental',
-            requiresRestart: true,
-            default: true,
-            description: 'Enable the Codebase Investigator agent.',
-            showInDialog: true,
-          },
-          maxNumTurns: {
-            type: 'number',
-            label: 'Codebase Investigator Max Num Turns',
-            category: 'Experimental',
-            requiresRestart: true,
-            default: 10,
-            description:
-              'Maximum number of turns for the Codebase Investigator agent.',
-            showInDialog: true,
-          },
-          maxTimeMinutes: {
-            type: 'number',
-            label: 'Max Time (Minutes)',
-            category: 'Experimental',
-            requiresRestart: true,
-            default: 3,
-            description:
-              'Maximum time for the Codebase Investigator agent (in minutes).',
-            showInDialog: false,
-          },
-          thinkingBudget: {
-            type: 'number',
-            label: 'Thinking Budget',
-            category: 'Experimental',
-            requiresRestart: true,
-            default: 8192,
-            description:
-              'The thinking budget for the Codebase Investigator agent.',
-            showInDialog: false,
-          },
-          model: {
-            type: 'string',
-            label: 'Model',
-            category: 'Experimental',
-            requiresRestart: true,
-            default: GEMINI_MODEL_ALIAS_AUTO,
-            description:
-              'The model to use for the Codebase Investigator agent.',
-            showInDialog: false,
-          },
-        },
-      },
       useOSC52Paste: {
         type: 'boolean',
         label: 'Use OSC 52 Paste',
@@ -1531,26 +1470,6 @@ const SETTINGS_SCHEMA = {
           'Use OSC 52 sequence for pasting instead of clipboardy (useful for remote sessions).',
         showInDialog: true,
       },
-      cliHelpAgentSettings: {
-        type: 'object',
-        label: 'CLI Help Agent Settings',
-        category: 'Experimental',
-        requiresRestart: true,
-        default: {},
-        description: 'Configuration for CLI Help Agent.',
-        showInDialog: false,
-        properties: {
-          enabled: {
-            type: 'boolean',
-            label: 'Enable CLI Help Agent',
-            category: 'Experimental',
-            requiresRestart: true,
-            default: true,
-            description: 'Enable the CLI Help Agent.',
-            showInDialog: true,
-          },
-        },
-      },
       plan: {
         type: 'boolean',
         label: 'Plan',
@@ -1631,9 +1550,9 @@ const SETTINGS_SCHEMA = {
     },
   },
 
-  hooks: {
+  hooksConfig: {
     type: 'object',
-    label: 'Hooks',
+    label: 'HooksConfig',
     category: 'Advanced',
     requiresRestart: false,
     default: {},
@@ -1646,7 +1565,7 @@ const SETTINGS_SCHEMA = {
         label: 'Enable Hooks',
         category: 'Advanced',
         requiresRestart: false,
-        default: false,
+        default: true,
         description:
           'Canonical toggle for the hooks system. When disabled, no hooks will be executed.',
         showInDialog: false,
@@ -1675,6 +1594,18 @@ const SETTINGS_SCHEMA = {
         description: 'Show visual indicators when hooks are executing.',
         showInDialog: true,
       },
+    },
+  },
+
+  hooks: {
+    type: 'object',
+    label: 'Hook Events',
+    category: 'Advanced',
+    requiresRestart: false,
+    default: {},
+    description: 'Event-specific hook configurations.',
+    showInDialog: false,
+    properties: {
       BeforeTool: {
         type: 'array',
         label: 'Before Tool Hooks',
@@ -2117,10 +2048,6 @@ export const SETTINGS_SCHEMA_DEFINITIONS: Record<
         type: 'boolean',
         description: 'Whether to enable the agent.',
       },
-      disabled: {
-        type: 'boolean',
-        description: 'Whether to disable the agent.',
-      },
     },
   },
   CustomTheme: {

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

@@ -155,8 +155,12 @@ describe('Settings Repro', () => {
       experimental: {
         useModelRouter: false,
         enableSubagents: false,
-        codebaseInvestigatorSettings: {
-          enabled: true,
+      },
+      agents: {
+        overrides: {
+          codebase_investigator: {
+            enabled: true,
+          },
         },
       },
       ui: {

packages/cli/src/deferred.test.ts

@@ -0,0 +1,217 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, vi, beforeEach } from 'vitest';
+import {
+  runDeferredCommand,
+  defer,
+  setDeferredCommand,
+  type DeferredCommand,
+} from './deferred.js';
+import { ExitCodes } from '@google/gemini-cli-core';
+import type { ArgumentsCamelCase, CommandModule } from 'yargs';
+import type { MergedSettings } from './config/settings.js';
+import type { MockInstance } from 'vitest';
+
+const { mockRunExitCleanup, mockDebugLogger } = vi.hoisted(() => ({
+  mockRunExitCleanup: vi.fn(),
+  mockDebugLogger: {
+    log: vi.fn(),
+    error: vi.fn(),
+  },
+}));
+
+vi.mock('@google/gemini-cli-core', async () => {
+  const actual = await vi.importActual('@google/gemini-cli-core');
+  return {
+    ...actual,
+    debugLogger: mockDebugLogger,
+  };
+});
+
+vi.mock('./utils/cleanup.js', () => ({
+  runExitCleanup: mockRunExitCleanup,
+}));
+
+let mockExit: MockInstance;
+
+describe('deferred', () => {
+  beforeEach(() => {
+    vi.clearAllMocks();
+    mockExit = vi
+      .spyOn(process, 'exit')
+      .mockImplementation(() => undefined as never);
+    setDeferredCommand(undefined as unknown as DeferredCommand); // Reset deferred command
+  });
+
+  const createMockSettings = (adminSettings: unknown = {}): MergedSettings =>
+    ({
+      admin: adminSettings,
+    }) as unknown as MergedSettings;
+
+  describe('runDeferredCommand', () => {
+    it('should do nothing if no deferred command is set', async () => {
+      await runDeferredCommand(createMockSettings());
+      expect(mockDebugLogger.log).not.toHaveBeenCalled();
+      expect(mockDebugLogger.error).not.toHaveBeenCalled();
+      expect(mockExit).not.toHaveBeenCalled();
+    });
+
+    it('should execute the deferred command if enabled', async () => {
+      const mockHandler = vi.fn();
+      setDeferredCommand({
+        handler: mockHandler,
+        argv: { _: [], $0: 'gemini' } as ArgumentsCamelCase,
+        commandName: 'mcp',
+      });
+
+      const settings = createMockSettings({ mcp: { enabled: true } });
+      await runDeferredCommand(settings);
+      expect(mockHandler).toHaveBeenCalled();
+      expect(mockRunExitCleanup).toHaveBeenCalled();
+      expect(mockExit).toHaveBeenCalledWith(ExitCodes.SUCCESS);
+    });
+
+    it('should exit with FATAL_CONFIG_ERROR if MCP is disabled', async () => {
+      setDeferredCommand({
+        handler: vi.fn(),
+        argv: {} as ArgumentsCamelCase,
+        commandName: 'mcp',
+      });
+
+      const settings = createMockSettings({ mcp: { enabled: false } });
+      await runDeferredCommand(settings);
+
+      expect(mockDebugLogger.error).toHaveBeenCalledWith(
+        'Error: MCP is disabled by your admin.',
+      );
+      expect(mockRunExitCleanup).toHaveBeenCalled();
+      expect(mockExit).toHaveBeenCalledWith(ExitCodes.FATAL_CONFIG_ERROR);
+    });
+
+    it('should exit with FATAL_CONFIG_ERROR if extensions are disabled', async () => {
+      setDeferredCommand({
+        handler: vi.fn(),
+        argv: {} as ArgumentsCamelCase,
+        commandName: 'extensions',
+      });
+
+      const settings = createMockSettings({ extensions: { enabled: false } });
+      await runDeferredCommand(settings);
+
+      expect(mockDebugLogger.error).toHaveBeenCalledWith(
+        'Error: Extensions are disabled by your admin.',
+      );
+      expect(mockRunExitCleanup).toHaveBeenCalled();
+      expect(mockExit).toHaveBeenCalledWith(ExitCodes.FATAL_CONFIG_ERROR);
+    });
+
+    it('should exit with FATAL_CONFIG_ERROR if skills are disabled', async () => {
+      setDeferredCommand({
+        handler: vi.fn(),
+        argv: {} as ArgumentsCamelCase,
+        commandName: 'skills',
+      });
+
+      const settings = createMockSettings({ skills: { enabled: false } });
+      await runDeferredCommand(settings);
+
+      expect(mockDebugLogger.error).toHaveBeenCalledWith(
+        'Error: Agent skills are disabled by your admin.',
+      );
+      expect(mockRunExitCleanup).toHaveBeenCalled();
+      expect(mockExit).toHaveBeenCalledWith(ExitCodes.FATAL_CONFIG_ERROR);
+    });
+
+    it('should execute if admin settings are undefined (default implicit enable)', async () => {
+      const mockHandler = vi.fn();
+      setDeferredCommand({
+        handler: mockHandler,
+        argv: {} as ArgumentsCamelCase,
+        commandName: 'mcp',
+      });
+
+      const settings = createMockSettings({}); // No admin settings
+      await runDeferredCommand(settings);
+
+      expect(mockHandler).toHaveBeenCalled();
+      expect(mockExit).toHaveBeenCalledWith(ExitCodes.SUCCESS);
+    });
+  });
+
+  describe('defer', () => {
+    it('should wrap a command module and defer execution', async () => {
+      const originalHandler = vi.fn();
+      const commandModule: CommandModule = {
+        command: 'test',
+        describe: 'test command',
+        handler: originalHandler,
+      };
+
+      const deferredModule = defer(commandModule);
+      expect(deferredModule.command).toBe(commandModule.command);
+
+      // Execute the wrapper handler
+      const argv = { _: [], $0: 'gemini' } as ArgumentsCamelCase;
+      await deferredModule.handler(argv);
+
+      // Should check that it set the deferred command, but didn't run original handler yet
+      expect(originalHandler).not.toHaveBeenCalled();
+
+      // Now manually run it to verify it captured correctly
+      await runDeferredCommand(createMockSettings());
+      expect(originalHandler).toHaveBeenCalledWith(argv);
+      expect(mockExit).toHaveBeenCalledWith(ExitCodes.SUCCESS);
+    });
+
+    it('should use parentCommandName if provided', async () => {
+      const commandModule: CommandModule = {
+        command: 'subcommand',
+        describe: 'sub command',
+        handler: vi.fn(),
+      };
+
+      const deferredModule = defer(commandModule, 'parent');
+      await deferredModule.handler({} as ArgumentsCamelCase);
+
+      const deferredMcp = defer(commandModule, 'mcp');
+      await deferredMcp.handler({} as ArgumentsCamelCase);
+
+      const mcpSettings = createMockSettings({ mcp: { enabled: false } });
+      await runDeferredCommand(mcpSettings);
+
+      expect(mockDebugLogger.error).toHaveBeenCalledWith(
+        'Error: MCP is disabled by your admin.',
+      );
+    });
+
+    it('should fallback to unknown if no parentCommandName is provided', async () => {
+      const mockHandler = vi.fn();
+      const commandModule: CommandModule = {
+        command: ['foo', 'infoo'],
+        describe: 'foo command',
+        handler: mockHandler,
+      };
+
+      const deferredModule = defer(commandModule);
+      await deferredModule.handler({} as ArgumentsCamelCase);
+
+      // Verify it runs even if all known commands are disabled,
+      // confirming it didn't capture 'mcp', 'extensions', or 'skills'
+      // and defaulted to 'unknown' (or something else safe).
+      const settings = createMockSettings({
+        mcp: { enabled: false },
+        extensions: { enabled: false },
+        skills: { enabled: false },
+      });
+
+      await runDeferredCommand(settings);
+
+      expect(mockHandler).toHaveBeenCalled();
+      expect(mockExit).toHaveBeenCalledWith(ExitCodes.SUCCESS);
+    });
+  });
+});

packages/cli/src/deferred.ts

@@ -0,0 +1,78 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+import type { ArgumentsCamelCase, CommandModule } from 'yargs';
+import { debugLogger, ExitCodes } from '@google/gemini-cli-core';
+import { runExitCleanup } from './utils/cleanup.js';
+import type { MergedSettings } from './config/settings.js';
+import process from 'node:process';
+
+export interface DeferredCommand {
+  handler: (argv: ArgumentsCamelCase) => void | Promise<void>;
+  argv: ArgumentsCamelCase;
+  commandName: string;
+}
+
+let deferredCommand: DeferredCommand | undefined;
+
+export function setDeferredCommand(command: DeferredCommand) {
+  deferredCommand = command;
+}
+
+export async function runDeferredCommand(settings: MergedSettings) {
+  if (!deferredCommand) {
+    return;
+  }
+
+  const adminSettings = settings.admin;
+  const commandName = deferredCommand.commandName;
+
+  if (commandName === 'mcp' && adminSettings?.mcp?.enabled === false) {
+    debugLogger.error('Error: MCP is disabled by your admin.');
+    await runExitCleanup();
+    process.exit(ExitCodes.FATAL_CONFIG_ERROR);
+  }
+
+  if (
+    commandName === 'extensions' &&
+    adminSettings?.extensions?.enabled === false
+  ) {
+    debugLogger.error('Error: Extensions are disabled by your admin.');
+    await runExitCleanup();
+    process.exit(ExitCodes.FATAL_CONFIG_ERROR);
+  }
+
+  if (commandName === 'skills' && adminSettings?.skills?.enabled === false) {
+    debugLogger.error('Error: Agent skills are disabled by your admin.');
+    await runExitCleanup();
+    process.exit(ExitCodes.FATAL_CONFIG_ERROR);
+  }
+
+  await deferredCommand.handler(deferredCommand.argv);
+  await runExitCleanup();
+  process.exit(ExitCodes.SUCCESS);
+}
+
+/**
+ * Wraps a command's handler to defer its execution.
+ * It stores the handler and arguments in a singleton `deferredCommand` variable.
+ */
+export function defer<T = object, U = object>(
+  commandModule: CommandModule<T, U>,
+  parentCommandName?: string,
+): CommandModule<T, U> {
+  return {
+    ...commandModule,
+    handler: (argv: ArgumentsCamelCase<U>) => {
+      setDeferredCommand({
+        handler: commandModule.handler as (
+          argv: ArgumentsCamelCase,
+        ) => void | Promise<void>,
+        argv: argv as unknown as ArgumentsCamelCase,
+        commandName: parentCommandName || 'unknown',
+      });
+    },
+  };
+}

packages/cli/src/gemini.test.tsx

@@ -205,10 +205,14 @@ vi.mock('./config/sandboxConfig.js', () => ({
 vi.mock('./ui/utils/mouse.js', () => ({
   enableMouseEvents: vi.fn(),
   disableMouseEvents: vi.fn(),
-  parseMouseEvent: vi.fn(),
   isIncompleteMouseSequence: vi.fn(),
 }));
 
+const runNonInteractiveSpy = vi.hoisted(() => vi.fn());
+vi.mock('./nonInteractiveCli.js', () => ({
+  runNonInteractive: runNonInteractiveSpy,
+}));
+
 describe('gemini.tsx main function', () => {
   let originalEnvGeminiSandbox: string | undefined;
   let originalEnvSandbox: string | undefined;
@@ -490,6 +494,9 @@ describe('gemini.tsx main function kitty protocol', () => {
       outputFormat: undefined,
       fakeResponses: undefined,
       recordResponses: undefined,
+      rawOutput: undefined,
+      acceptRawOutputRisk: undefined,
+      isCommand: undefined,
     });
 
     await act(async () => {
@@ -559,6 +566,7 @@ describe('gemini.tsx main function kitty protocol', () => {
       getProjectRoot: () => '/',
       getRemoteAdminSettings: () => undefined,
       setTerminalBackground: vi.fn(),
+      refreshAuth: vi.fn(),
     } as unknown as Config;
 
     vi.mocked(loadCliConfig).mockResolvedValue(mockConfig);
@@ -571,10 +579,13 @@ describe('gemini.tsx main function kitty protocol', () => {
       .spyOn(debugLogger, 'log')
       .mockImplementation(() => {});
 
+    process.env['GEMINI_API_KEY'] = 'test-key';
     try {
       await main();
     } catch (e) {
       if (!(e instanceof MockProcessExitError)) throw e;
+    } finally {
+      delete process.env['GEMINI_API_KEY'];
     }
 
     if (flag === 'listExtensions') {
@@ -646,18 +657,59 @@ describe('gemini.tsx main function kitty protocol', () => {
       refreshAuth: vi.fn(),
       getRemoteAdminSettings: () => undefined,
       setTerminalBackground: vi.fn(),
+      getToolRegistry: () => ({ getAllTools: () => [] }),
+      getModel: () => 'gemini-pro',
+      getEmbeddingModel: () => 'embedding-model',
+      getCoreTools: () => [],
+      getApprovalMode: () => 'default',
+      getPreviewFeatures: () => false,
+      getTargetDir: () => '/',
+      getUsageStatisticsEnabled: () => false,
+      getTelemetryEnabled: () => false,
+      getTelemetryTarget: () => 'none',
+      getTelemetryOtlpEndpoint: () => '',
+      getTelemetryOtlpProtocol: () => 'grpc',
+      getTelemetryLogPromptsEnabled: () => false,
+      getContinueOnFailedApiCall: () => false,
+      getShellToolInactivityTimeout: () => 0,
+      getTruncateToolOutputThreshold: () => 0,
+      getUseRipgrep: () => false,
+      getUseWriteTodos: () => false,
+      getHooks: () => undefined,
+      getExperiments: () => undefined,
+      getFileFilteringRespectGitIgnore: () => true,
+      getOutputFormat: () => 'text',
+      getFolderTrust: () => false,
+      getPendingIncludeDirectories: () => [],
+      getWorkspaceContext: () => ({ getDirectories: () => ['/'] }),
+      getModelAvailabilityService: () => ({
+        reset: vi.fn(),
+        resetTurn: vi.fn(),
+      }),
+      getBaseLlmClient: () => ({}),
+      getGeminiClient: () => ({}),
+      getContentGenerator: () => ({}),
+      isTrustedFolder: () => true,
+      isYoloModeDisabled: () => true,
+      isPlanEnabled: () => false,
+      isEventDrivenSchedulerEnabled: () => false,
     } as unknown as Config;
 
     vi.mocked(loadCliConfig).mockResolvedValue(mockConfig);
-    vi.mocked(loadSandboxConfig).mockResolvedValue({} as any); // eslint-disable-line @typescript-eslint/no-explicit-any
+    vi.mocked(loadSandboxConfig).mockResolvedValue({
+      command: 'docker',
+    } as any); // eslint-disable-line @typescript-eslint/no-explicit-any
     vi.mocked(relaunchOnExitCode).mockImplementation(async (fn) => {
       await fn();
     });
 
+    process.env['GEMINI_API_KEY'] = 'test-key';
     try {
       await main();
     } catch (e) {
       if (!(e instanceof MockProcessExitError)) throw e;
+    } finally {
+      delete process.env['GEMINI_API_KEY'];
     }
 
     expect(start_sandbox).toHaveBeenCalled();
@@ -735,10 +787,13 @@ describe('gemini.tsx main function kitty protocol', () => {
 
     vi.spyOn(themeManager, 'setActiveTheme').mockReturnValue(false);
 
+    process.env['GEMINI_API_KEY'] = 'test-key';
     try {
       await main();
     } catch (e) {
       if (!(e instanceof MockProcessExitError)) throw e;
+    } finally {
+      delete process.env['GEMINI_API_KEY'];
     }
 
     expect(debugLoggerWarnSpy).toHaveBeenCalledWith(
@@ -988,14 +1043,6 @@ describe('gemini.tsx main function kitty protocol', () => {
     vi.mock('./utils/readStdin.js', () => ({
       readStdin: vi.fn().mockResolvedValue('stdin-data'),
     }));
-    const runNonInteractiveSpy = vi.hoisted(() => vi.fn());
-    vi.mock('./nonInteractiveCli.js', () => ({
-      runNonInteractive: runNonInteractiveSpy,
-    }));
-    runNonInteractiveSpy.mockClear();
-    vi.mock('./validateNonInterActiveAuth.js', () => ({
-      validateNonInteractiveAuth: vi.fn().mockResolvedValue({}),
-    }));
 
     // Mock stdin to be non-TTY
     Object.defineProperty(process.stdin, 'isTTY', {
@@ -1003,10 +1050,13 @@ describe('gemini.tsx main function kitty protocol', () => {
       configurable: true,
     });
 
+    process.env['GEMINI_API_KEY'] = 'test-key';
     try {
       await main();
     } catch (e) {
       if (!(e instanceof MockProcessExitError)) throw e;
+    } finally {
+      delete process.env['GEMINI_API_KEY'];
     }
 
     expect(readStdin).toHaveBeenCalled();
@@ -1085,6 +1135,8 @@ describe('gemini.tsx main function exit codes', () => {
     vi.mocked(loadSandboxConfig).mockResolvedValue({} as any);
     vi.mocked(loadCliConfig).mockResolvedValue({
       refreshAuth: vi.fn().mockRejectedValue(new Error('Auth failed')),
+      getRemoteAdminSettings: vi.fn().mockReturnValue(undefined),
+      isInteractive: vi.fn().mockReturnValue(true),
     } as unknown as Config);
     vi.mocked(loadSettings).mockReturnValue(
       createMockSettings({
@@ -1149,6 +1201,7 @@ describe('gemini.tsx main function exit codes', () => {
       storage: {
         getProjectTempDir: vi.fn().mockReturnValue('/tmp/gemini-test'),
       },
+      refreshAuth: vi.fn(),
     } as unknown as Config);
     vi.mocked(loadSettings).mockReturnValue(
       createMockSettings({
@@ -1167,12 +1220,15 @@ describe('gemini.tsx main function exit codes', () => {
       })),
     }));
 
+    process.env['GEMINI_API_KEY'] = 'test-key';
     try {
       await main();
       expect.fail('Should have thrown MockProcessExitError');
     } catch (e) {
       expect(e).toBeInstanceOf(MockProcessExitError);
       expect((e as MockProcessExitError).code).toBe(42);
+    } finally {
+      delete process.env['GEMINI_API_KEY'];
     }
   });
 
@@ -1217,6 +1273,7 @@ describe('gemini.tsx main function exit codes', () => {
       storage: {
         getProjectTempDir: vi.fn().mockReturnValue('/tmp/gemini-test'),
       },
+      refreshAuth: vi.fn(),
       getRemoteAdminSettings: () => undefined,
     } as unknown as Config);
     vi.mocked(loadSettings).mockReturnValue(
@@ -1230,14 +1287,93 @@ describe('gemini.tsx main function exit codes', () => {
       configurable: true,
     });
 
+    process.env['GEMINI_API_KEY'] = 'test-key';
     try {
       await main();
       expect.fail('Should have thrown MockProcessExitError');
     } catch (e) {
       expect(e).toBeInstanceOf(MockProcessExitError);
       expect((e as MockProcessExitError).code).toBe(42);
+    } finally {
+      delete process.env['GEMINI_API_KEY'];
     }
   });
+
+  it('should validate and refresh auth in non-interactive mode when no auth type is selected but env var is present', async () => {
+    const { loadCliConfig, parseArguments } = await import(
+      './config/config.js'
+    );
+    const { loadSettings } = await import('./config/settings.js');
+    const { AuthType } = await import('@google/gemini-cli-core');
+
+    const refreshAuthSpy = vi.fn();
+
+    vi.mocked(loadCliConfig).mockResolvedValue({
+      isInteractive: () => false,
+      getQuestion: () => 'test prompt',
+      getSandbox: () => false,
+      getDebugMode: () => false,
+      getListExtensions: () => false,
+      getListSessions: () => false,
+      getDeleteSession: () => undefined,
+      getMcpServers: () => ({}),
+      getMcpClientManager: vi.fn(),
+      initialize: vi.fn(),
+      getIdeMode: () => false,
+      getExperimentalZedIntegration: () => false,
+      getScreenReader: () => false,
+      getGeminiMdFileCount: () => 0,
+      getPolicyEngine: vi.fn(),
+      getMessageBus: () => ({ subscribe: vi.fn() }),
+      getEnableHooks: () => false,
+      getHookSystem: () => undefined,
+      getToolRegistry: vi.fn(),
+      getContentGeneratorConfig: vi.fn(),
+      getModel: () => 'gemini-pro',
+      getEmbeddingModel: () => 'embedding-001',
+      getApprovalMode: () => 'default',
+      getCoreTools: () => [],
+      getTelemetryEnabled: () => false,
+      getTelemetryLogPromptsEnabled: () => false,
+      getFileFilteringRespectGitIgnore: () => true,
+      getOutputFormat: () => 'text',
+      getExtensions: () => [],
+      getUsageStatisticsEnabled: () => false,
+      setTerminalBackground: vi.fn(),
+      storage: {
+        getProjectTempDir: vi.fn().mockReturnValue('/tmp/gemini-test'),
+      },
+      refreshAuth: refreshAuthSpy,
+      getRemoteAdminSettings: () => undefined,
+    } as unknown as Config);
+
+    vi.mocked(loadSettings).mockReturnValue(
+      createMockSettings({
+        merged: { security: { auth: { selectedType: undefined } }, ui: {} },
+      }),
+    );
+    vi.mocked(parseArguments).mockResolvedValue({} as unknown as CliArgs);
+
+    runNonInteractiveSpy.mockImplementation(() => Promise.resolve());
+
+    const processExitSpy = vi
+      .spyOn(process, 'exit')
+      .mockImplementation((code) => {
+        throw new MockProcessExitError(code);
+      });
+
+    process.env['GEMINI_API_KEY'] = 'test-key';
+    try {
+      await main();
+    } catch (e) {
+      if (!(e instanceof MockProcessExitError)) throw e;
+    } finally {
+      delete process.env['GEMINI_API_KEY'];
+      processExitSpy.mockRestore();
+    }
+
+    expect(refreshAuthSpy).toHaveBeenCalledWith(AuthType.USE_GEMINI);
+  });
 });
 
 describe('validateDnsResolutionOrder', () => {

packages/cli/src/gemini.tsx

@@ -96,6 +96,7 @@ import { isAlternateBufferEnabled } from './ui/hooks/useAlternateBuffer.js';
 
 import { setupTerminalAndTheme } from './utils/terminalTheme.js';
 import { profiler } from './ui/components/DebugProfiler.js';
+import { runDeferredCommand } from './deferred.js';
 
 const SLOW_RENDER_MS = 200;
 
@@ -372,12 +373,13 @@ export async function main() {
   // Refresh auth to fetch remote admin settings from CCPA and before entering
   // the sandbox because the sandbox will interfere with the Oauth2 web
   // redirect.
-  if (
-    settings.merged.security.auth.selectedType &&
-    !settings.merged.security.auth.useExternal
-  ) {
+  let initialAuthFailed = false;
+  if (!settings.merged.security.auth.useExternal) {
     try {
-      if (partialConfig.isInteractive()) {
+      if (
+        partialConfig.isInteractive() &&
+        settings.merged.security.auth.selectedType
+      ) {
         const err = validateAuthMethod(
           settings.merged.security.auth.selectedType,
         );
@@ -388,7 +390,7 @@ export async function main() {
         await partialConfig.refreshAuth(
           settings.merged.security.auth.selectedType,
         );
-      } else {
+      } else if (!partialConfig.isInteractive()) {
         const authType = await validateNonInteractiveAuth(
           settings.merged.security.auth.selectedType,
           settings.merged.security.auth.useExternal,
@@ -399,8 +401,7 @@ export async function main() {
       }
     } catch (err) {
       debugLogger.error('Error authenticating:', err);
-      await runExitCleanup();
-      process.exit(ExitCodes.FATAL_AUTHENTICATION_ERROR);
+      initialAuthFailed = true;
     }
   }
 
@@ -410,6 +411,9 @@ export async function main() {
     settings.setRemoteAdminSettings(remoteAdminSettings);
   }
 
+  // Run deferred command now that we have admin settings.
+  await runDeferredCommand(settings.merged);
+
   // hop into sandbox if we are outside and sandboxing is enabled
   if (!process.env['SANDBOX']) {
     const memoryArgs = settings.merged.advanced.autoConfigureMemory
@@ -423,6 +427,10 @@ export async function main() {
     // another way to decouple refreshAuth from requiring a config.
 
     if (sandboxConfig) {
+      if (initialAuthFailed) {
+        await runExitCleanup();
+        process.exit(ExitCodes.FATAL_AUTHENTICATION_ERROR);
+      }
       let stdinData = '';
       if (!process.stdin.isTTY) {
         stdinData = await readStdin();
@@ -660,9 +668,8 @@ export async function main() {
         const additionalContext = result.getAdditionalContext();
         if (additionalContext) {
           // Prepend context to input (System Context -> Stdin -> Question)
-          input = input
-            ? `${additionalContext}\n\n${input}`
-            : additionalContext;
+          const wrappedContext = `<hook_context>${additionalContext}</hook_context>`;
+          input = input ? `${wrappedContext}\n\n${input}` : wrappedContext;
         }
       }
     }
@@ -724,6 +731,7 @@ function setWindowTitle(title: string, settings: LoadedSettings) {
     const windowTitle = computeTerminalTitle({
       streamingState: StreamingState.Idle,
       isConfirming: false,
+      isSilentWorking: false,
       folderName: title,
       showThoughts: !!settings.merged.ui.showStatusInTitle,
       useDynamicTitle: settings.merged.ui.dynamicWindowTitle,

packages/cli/src/nonInteractiveCli.test.ts

@@ -173,6 +173,8 @@ describe('runNonInteractive', () => {
       getModel: vi.fn().mockReturnValue('test-model'),
       getFolderTrust: vi.fn().mockReturnValue(false),
       isTrustedFolder: vi.fn().mockReturnValue(false),
+      getRawOutput: vi.fn().mockReturnValue(false),
+      getAcceptRawOutputRisk: vi.fn().mockReturnValue(false),
     } as unknown as Config;
 
     mockSettings = {
@@ -1745,6 +1747,121 @@ describe('runNonInteractive', () => {
 
     // The key assertion: sendMessageStream should have been called ONLY ONCE (initial user input).
     expect(mockGeminiClient.sendMessageStream).toHaveBeenCalledTimes(1);
+
+    expect(processStderrSpy).toHaveBeenCalledWith(
+      'Agent execution stopped: Stop reason from hook\n',
+    );
+  });
+
+  it('should write JSON output when a tool call returns STOP_EXECUTION error', async () => {
+    vi.mocked(mockConfig.getOutputFormat).mockReturnValue(OutputFormat.JSON);
+    vi.mocked(uiTelemetryService.getMetrics).mockReturnValue(
+      MOCK_SESSION_METRICS,
+    );
+
+    const toolCallEvent: ServerGeminiStreamEvent = {
+      type: GeminiEventType.ToolCallRequest,
+      value: {
+        callId: 'stop-call',
+        name: 'stopTool',
+        args: {},
+        isClientInitiated: false,
+        prompt_id: 'prompt-id-stop-json',
+      },
+    };
+
+    mockCoreExecuteToolCall.mockResolvedValue({
+      status: 'error',
+      request: toolCallEvent.value,
+      tool: {} as AnyDeclarativeTool,
+      invocation: {} as AnyToolInvocation,
+      response: {
+        callId: 'stop-call',
+        responseParts: [{ text: 'error occurred' }],
+        errorType: ToolErrorType.STOP_EXECUTION,
+        error: new Error('Stop reason'),
+        resultDisplay: undefined,
+      },
+    });
+
+    const firstCallEvents: ServerGeminiStreamEvent[] = [
+      { type: GeminiEventType.Content, value: 'Partial content' },
+      toolCallEvent,
+    ];
+
+    mockGeminiClient.sendMessageStream.mockReturnValue(
+      createStreamFromEvents(firstCallEvents),
+    );
+
+    await runNonInteractive({
+      config: mockConfig,
+      settings: mockSettings,
+      input: 'Run stop tool',
+      prompt_id: 'prompt-id-stop-json',
+    });
+
+    expect(processStdoutSpy).toHaveBeenCalledWith(
+      JSON.stringify(
+        {
+          session_id: 'test-session-id',
+          response: 'Partial content',
+          stats: MOCK_SESSION_METRICS,
+        },
+        null,
+        2,
+      ),
+    );
+  });
+
+  it('should emit result event when a tool call returns STOP_EXECUTION error in streaming JSON mode', async () => {
+    vi.mocked(mockConfig.getOutputFormat).mockReturnValue(
+      OutputFormat.STREAM_JSON,
+    );
+    vi.mocked(uiTelemetryService.getMetrics).mockReturnValue(
+      MOCK_SESSION_METRICS,
+    );
+
+    const toolCallEvent: ServerGeminiStreamEvent = {
+      type: GeminiEventType.ToolCallRequest,
+      value: {
+        callId: 'stop-call',
+        name: 'stopTool',
+        args: {},
+        isClientInitiated: false,
+        prompt_id: 'prompt-id-stop-stream',
+      },
+    };
+
+    mockCoreExecuteToolCall.mockResolvedValue({
+      status: 'error',
+      request: toolCallEvent.value,
+      tool: {} as AnyDeclarativeTool,
+      invocation: {} as AnyToolInvocation,
+      response: {
+        callId: 'stop-call',
+        responseParts: [{ text: 'error occurred' }],
+        errorType: ToolErrorType.STOP_EXECUTION,
+        error: new Error('Stop reason'),
+        resultDisplay: undefined,
+      },
+    });
+
+    const firstCallEvents: ServerGeminiStreamEvent[] = [toolCallEvent];
+
+    mockGeminiClient.sendMessageStream.mockReturnValue(
+      createStreamFromEvents(firstCallEvents),
+    );
+
+    await runNonInteractive({
+      config: mockConfig,
+      settings: mockSettings,
+      input: 'Run stop tool',
+      prompt_id: 'prompt-id-stop-stream',
+    });
+
+    const output = getWrittenOutput();
+    expect(output).toContain('"type":"result"');
+    expect(output).toContain('"status":"success"');
   });
 
   describe('Agent Execution Events', () => {
@@ -1805,4 +1922,142 @@ describe('runNonInteractive', () => {
       expect(getWrittenOutput()).toBe('Final answer\n');
     });
   });
+
+  describe('Output Sanitization', () => {
+    const ANSI_SEQUENCE = '\u001B[31mRed Text\u001B[0m';
+    const OSC_HYPERLINK =
+      '\u001B]8;;http://example.com\u001B\\Link\u001B]8;;\u001B\\';
+    const PLAIN_TEXT_RED = 'Red Text';
+    const PLAIN_TEXT_LINK = 'Link';
+
+    it('should sanitize ANSI output by default', async () => {
+      const events: ServerGeminiStreamEvent[] = [
+        { type: GeminiEventType.Content, value: ANSI_SEQUENCE },
+        { type: GeminiEventType.Content, value: ' ' },
+        { type: GeminiEventType.Content, value: OSC_HYPERLINK },
+        {
+          type: GeminiEventType.Finished,
+          value: { reason: undefined, usageMetadata: { totalTokenCount: 10 } },
+        },
+      ];
+      mockGeminiClient.sendMessageStream.mockReturnValue(
+        createStreamFromEvents(events),
+      );
+
+      vi.mocked(mockConfig.getRawOutput).mockReturnValue(false);
+
+      await runNonInteractive({
+        config: mockConfig,
+        settings: mockSettings,
+        input: 'Test input',
+        prompt_id: 'prompt-id-sanitization',
+      });
+
+      expect(getWrittenOutput()).toBe(`${PLAIN_TEXT_RED} ${PLAIN_TEXT_LINK}\n`);
+    });
+
+    it('should allow ANSI output when rawOutput is true', async () => {
+      const events: ServerGeminiStreamEvent[] = [
+        { type: GeminiEventType.Content, value: ANSI_SEQUENCE },
+        { type: GeminiEventType.Content, value: ' ' },
+        { type: GeminiEventType.Content, value: OSC_HYPERLINK },
+        {
+          type: GeminiEventType.Finished,
+          value: { reason: undefined, usageMetadata: { totalTokenCount: 10 } },
+        },
+      ];
+      mockGeminiClient.sendMessageStream.mockReturnValue(
+        createStreamFromEvents(events),
+      );
+
+      vi.mocked(mockConfig.getRawOutput).mockReturnValue(true);
+      vi.mocked(mockConfig.getAcceptRawOutputRisk).mockReturnValue(true);
+
+      await runNonInteractive({
+        config: mockConfig,
+        settings: mockSettings,
+        input: 'Test input',
+        prompt_id: 'prompt-id-raw',
+      });
+
+      expect(getWrittenOutput()).toBe(`${ANSI_SEQUENCE} ${OSC_HYPERLINK}\n`);
+    });
+
+    it('should allow ANSI output when only acceptRawOutputRisk is true', async () => {
+      const events: ServerGeminiStreamEvent[] = [
+        { type: GeminiEventType.Content, value: ANSI_SEQUENCE },
+        {
+          type: GeminiEventType.Finished,
+          value: { reason: undefined, usageMetadata: { totalTokenCount: 5 } },
+        },
+      ];
+      mockGeminiClient.sendMessageStream.mockReturnValue(
+        createStreamFromEvents(events),
+      );
+
+      vi.mocked(mockConfig.getRawOutput).mockReturnValue(false);
+      vi.mocked(mockConfig.getAcceptRawOutputRisk).mockReturnValue(true);
+
+      await runNonInteractive({
+        config: mockConfig,
+        settings: mockSettings,
+        input: 'Test input',
+        prompt_id: 'prompt-id-accept-only',
+      });
+
+      expect(getWrittenOutput()).toBe(`${ANSI_SEQUENCE}\n`);
+    });
+
+    it('should warn when rawOutput is true and acceptRisk is false', async () => {
+      const events: ServerGeminiStreamEvent[] = [
+        {
+          type: GeminiEventType.Finished,
+          value: { reason: undefined, usageMetadata: { totalTokenCount: 0 } },
+        },
+      ];
+      mockGeminiClient.sendMessageStream.mockReturnValue(
+        createStreamFromEvents(events),
+      );
+
+      vi.mocked(mockConfig.getRawOutput).mockReturnValue(true);
+      vi.mocked(mockConfig.getAcceptRawOutputRisk).mockReturnValue(false);
+
+      await runNonInteractive({
+        config: mockConfig,
+        settings: mockSettings,
+        input: 'Test input',
+        prompt_id: 'prompt-id-warn',
+      });
+
+      expect(processStderrSpy).toHaveBeenCalledWith(
+        expect.stringContaining('[WARNING] --raw-output is enabled'),
+      );
+    });
+
+    it('should not warn when rawOutput is true and acceptRisk is true', async () => {
+      const events: ServerGeminiStreamEvent[] = [
+        {
+          type: GeminiEventType.Finished,
+          value: { reason: undefined, usageMetadata: { totalTokenCount: 0 } },
+        },
+      ];
+      mockGeminiClient.sendMessageStream.mockReturnValue(
+        createStreamFromEvents(events),
+      );
+
+      vi.mocked(mockConfig.getRawOutput).mockReturnValue(true);
+      vi.mocked(mockConfig.getAcceptRawOutputRisk).mockReturnValue(true);
+
+      await runNonInteractive({
+        config: mockConfig,
+        settings: mockSettings,
+        input: 'Test input',
+        prompt_id: 'prompt-id-no-warn',
+      });
+
+      expect(processStderrSpy).not.toHaveBeenCalledWith(
+        expect.stringContaining('[WARNING] --raw-output is enabled'),
+      );
+    });
+  });
 });

packages/cli/src/nonInteractiveCli.ts

@@ -33,6 +33,7 @@ import {
 
 import type { Content, Part } from '@google/genai';
 import readline from 'node:readline';
+import stripAnsi from 'strip-ansi';
 
 import { convertSessionToHistoryFormats } from './ui/hooks/useSessionBrowser.js';
 import { handleSlashCommand } from './nonInteractiveCliCommands.js';
@@ -176,6 +177,16 @@ export async function runNonInteractive({
     try {
       consolePatcher.patch();
 
+      if (
+        config.getRawOutput() &&
+        !config.getAcceptRawOutputRisk() &&
+        config.getOutputFormat() === OutputFormat.TEXT
+      ) {
+        process.stderr.write(
+          '[WARNING] --raw-output is enabled. Model output is not sanitized and may contain harmful ANSI sequences (e.g. for phishing or command injection). Use --accept-raw-output-risk to suppress this warning.\n',
+        );
+      }
+
       // Setup stdin cancellation listener
       setupStdinCancellation();
 
@@ -285,19 +296,22 @@ export async function runNonInteractive({
           }
 
           if (event.type === GeminiEventType.Content) {
+            const isRaw =
+              config.getRawOutput() || config.getAcceptRawOutputRisk();
+            const output = isRaw ? event.value : stripAnsi(event.value);
             if (streamFormatter) {
               streamFormatter.emitEvent({
                 type: JsonStreamEventType.MESSAGE,
                 timestamp: new Date().toISOString(),
                 role: 'assistant',
-                content: event.value,
+                content: output,
                 delta: true,
               });
             } else if (config.getOutputFormat() === OutputFormat.JSON) {
-              responseText += event.value;
+              responseText += output;
             } else {
               if (event.value) {
-                textOutput.write(event.value);
+                textOutput.write(output);
               }
             }
           } else if (event.type === GeminiEventType.ToolCallRequest) {

packages/cli/src/services/BuiltinCommandLoader.ts

@@ -27,6 +27,7 @@ import { directoryCommand } from '../ui/commands/directoryCommand.js';
 import { editorCommand } from '../ui/commands/editorCommand.js';
 import { extensionsCommand } from '../ui/commands/extensionsCommand.js';
 import { helpCommand } from '../ui/commands/helpCommand.js';
+import { rewindCommand } from '../ui/commands/rewindCommand.js';
 import { hooksCommand } from '../ui/commands/hooksCommand.js';
 import { ideCommand } from '../ui/commands/ideCommand.js';
 import { initCommand } from '../ui/commands/initCommand.js';
@@ -106,6 +107,7 @@ export class BuiltinCommandLoader implements ICommandLoader {
         : [extensionsCommand(this.config?.getEnableExtensionReloading())]),
       helpCommand,
       ...(this.config?.getEnableHooksUI() ? [hooksCommand] : []),
+      rewindCommand,
       await ideCommand(),
       initCommand,
       ...(this.config?.getMcpEnabled() === false

packages/cli/src/services/FileCommandLoader.test.ts

@@ -1337,4 +1337,69 @@ describe('FileCommandLoader', () => {
       consoleErrorSpy.mockRestore();
     });
   });
+
+  describe('Sanitization', () => {
+    it('sanitizes command names from filenames containing control characters', async () => {
+      const userCommandsDir = Storage.getUserCommandsDir();
+      mock({
+        [userCommandsDir]: {
+          'test\twith\nnewlines.toml': 'prompt = "Test prompt"',
+        },
+      });
+
+      const loader = new FileCommandLoader(null);
+      const commands = await loader.loadCommands(signal);
+      expect(commands).toHaveLength(1);
+      // Non-alphanumeric characters (except - and .) become underscores
+      expect(commands[0].name).toBe('test_with_newlines');
+    });
+
+    it('truncates excessively long filenames', async () => {
+      const userCommandsDir = Storage.getUserCommandsDir();
+      const longName = 'a'.repeat(60) + '.toml';
+      mock({
+        [userCommandsDir]: {
+          [longName]: 'prompt = "Test prompt"',
+        },
+      });
+
+      const loader = new FileCommandLoader(null);
+      const commands = await loader.loadCommands(signal);
+      expect(commands).toHaveLength(1);
+      expect(commands[0].name.length).toBe(50);
+      expect(commands[0].name).toBe('a'.repeat(47) + '...');
+    });
+
+    it('sanitizes descriptions containing newlines and ANSI codes', async () => {
+      const userCommandsDir = Storage.getUserCommandsDir();
+      mock({
+        [userCommandsDir]: {
+          'test.toml':
+            'prompt = "Test"\ndescription = "Line 1\\nLine 2\\tTabbed\\r\\n\\u001B[31mRed text\\u001B[0m"',
+        },
+      });
+
+      const loader = new FileCommandLoader(null);
+      const commands = await loader.loadCommands(signal);
+      expect(commands).toHaveLength(1);
+      // Newlines and tabs become spaces, ANSI is stripped
+      expect(commands[0].description).toBe('Line 1 Line 2 Tabbed Red text');
+    });
+
+    it('truncates long descriptions', async () => {
+      const userCommandsDir = Storage.getUserCommandsDir();
+      const longDesc = 'd'.repeat(150);
+      mock({
+        [userCommandsDir]: {
+          'test.toml': `prompt = "Test"\ndescription = "${longDesc}"`,
+        },
+      });
+
+      const loader = new FileCommandLoader(null);
+      const commands = await loader.loadCommands(signal);
+      expect(commands).toHaveLength(1);
+      expect(commands[0].description.length).toBe(100);
+      expect(commands[0].description).toBe('d'.repeat(97) + '...');
+    });
+  });
 });

packages/cli/src/services/FileCommandLoader.ts

@@ -33,6 +33,7 @@ import {
   ShellProcessor,
 } from './prompt-processors/shellProcessor.js';
 import { AtFileProcessor } from './prompt-processors/atFileProcessor.js';
+import { sanitizeForListDisplay } from '../ui/utils/textUtils.js';
 
 interface CommandDirectory {
   path: string;
@@ -230,15 +231,25 @@ export class FileCommandLoader implements ICommandLoader {
     );
     const baseCommandName = relativePath
       .split(path.sep)
-      // Sanitize each path segment to prevent ambiguity. Since ':' is our
-      // namespace separator, we replace any literal colons in filenames
-      // with underscores to avoid naming conflicts.
-      .map((segment) => segment.replaceAll(':', '_'))
+      // Sanitize each path segment to prevent ambiguity, replacing non-allowlisted characters with underscores.
+      // Since ':' is our namespace separator, this ensures that colons do not cause naming conflicts.
+      .map((segment) => {
+        let sanitized = segment.replace(/[^a-zA-Z0-9_\-.]/g, '_');
+
+        // Truncate excessively long segments to prevent UI overflow
+        if (sanitized.length > 50) {
+          sanitized = sanitized.substring(0, 47) + '...';
+        }
+        return sanitized;
+      })
       .join(':');
 
     // Add extension name tag for extension commands
     const defaultDescription = `Custom command from ${path.basename(filePath)}`;
     let description = validDef.description || defaultDescription;
+
+    description = sanitizeForListDisplay(description, 100);
+
     if (extensionName) {
       description = `[${extensionName}] ${description}`;
     }

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

@@ -0,0 +1,45 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { vi } from 'vitest';
+
+/**
+ * A fake implementation of PersistentState for testing.
+ * It keeps state in memory and provides spies for get and set.
+ */
+export class FakePersistentState {
+  private data: Record<string, unknown> = {};
+
+  get = vi.fn().mockImplementation((key: string) => this.data[key]);
+
+  set = vi.fn().mockImplementation((key: string, value: unknown) => {
+    this.data[key] = value;
+  });
+
+  /**
+   * Helper to reset the fake state between tests.
+   */
+  reset() {
+    this.data = {};
+    this.get.mockClear();
+    this.set.mockClear();
+  }
+
+  /**
+   * Helper to clear mock call history without wiping data.
+   */
+  mockClear() {
+    this.get.mockClear();
+    this.set.mockClear();
+  }
+
+  /**
+   * Helper to set initial data for the fake.
+   */
+  setData(data: Record<string, unknown>) {
+    this.data = { ...data };
+  }
+}

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

@@ -14,7 +14,6 @@ import { KeypressProvider } from '../ui/contexts/KeypressContext.js';
 import { SettingsContext } from '../ui/contexts/SettingsContext.js';
 import { ShellFocusContext } from '../ui/contexts/ShellFocusContext.js';
 import { UIStateContext, type UIState } from '../ui/contexts/UIStateContext.js';
-import { StreamingState } from '../ui/types.js';
 import { ConfigContext } from '../ui/contexts/ConfigContext.js';
 import { calculateMainAreaWidth } from '../ui/utils/ui-sizing.js';
 import { VimModeProvider } from '../ui/contexts/VimModeContext.js';
@@ -25,8 +24,17 @@ import {
   type UIActions,
   UIActionsContext,
 } from '../ui/contexts/UIActionsContext.js';
+import { type HistoryItemToolGroup, StreamingState } from '../ui/types.js';
+import { ToolActionsProvider } from '../ui/contexts/ToolActionsContext.js';
 
 import { type Config } from '@google/gemini-cli-core';
+import { FakePersistentState } from './persistentStateFake.js';
+
+export const persistentStateMock = new FakePersistentState();
+
+vi.mock('../utils/persistentState.js', () => ({
+  persistentState: persistentStateMock,
+}));
 
 // Wrapper around ink-testing-library's render that ensures act() is called
 export const render = (
@@ -150,6 +158,8 @@ const mockUIActions: UIActions = {
   exitPrivacyNotice: vi.fn(),
   closeSettingsDialog: vi.fn(),
   closeModelDialog: vi.fn(),
+  openAgentConfigDialog: vi.fn(),
+  closeAgentConfigDialog: vi.fn(),
   openPermissionsDialog: vi.fn(),
   openSessionBrowser: vi.fn(),
   closeSessionBrowser: vi.fn(),
@@ -166,6 +176,7 @@ const mockUIActions: UIActions = {
   handleFinalSubmit: vi.fn(),
   handleClearScreen: vi.fn(),
   handleProQuotaChoice: vi.fn(),
+  handleValidationChoice: vi.fn(),
   setQueueErrorMessage: vi.fn(),
   popAllMessages: vi.fn(),
   handleApiKeySubmit: vi.fn(),
@@ -187,6 +198,7 @@ export const renderWithProviders = (
     config = configProxy as unknown as Config,
     useAlternateBuffer = true,
     uiActions,
+    persistentState,
   }: {
     shellFocus?: boolean;
     settings?: LoadedSettings;
@@ -196,6 +208,10 @@ export const renderWithProviders = (
     config?: Config;
     useAlternateBuffer?: boolean;
     uiActions?: Partial<UIActions>;
+    persistentState?: {
+      get?: typeof persistentStateMock.get;
+      set?: typeof persistentStateMock.set;
+    };
   } = {},
 ): ReturnType<typeof render> & { simulateClick: typeof simulateClick } => {
   const baseState: UIState = new Proxy(
@@ -216,6 +232,15 @@ export const renderWithProviders = (
     },
   ) as UIState;
 
+  if (persistentState?.get) {
+    persistentStateMock.get.mockImplementation(persistentState.get);
+  }
+  if (persistentState?.set) {
+    persistentStateMock.set.mockImplementation(persistentState.set);
+  }
+
+  persistentStateMock.mockClear();
+
   const terminalWidth = width ?? baseState.terminalWidth;
   let finalSettings = settings;
   if (useAlternateBuffer !== undefined) {
@@ -238,6 +263,10 @@ export const renderWithProviders = (
 
   const finalUIActions = { ...mockUIActions, ...uiActions };
 
+  const allToolCalls = (finalUiState.pendingHistoryItems || [])
+    .filter((item): item is HistoryItemToolGroup => item.type === 'tool_group')
+    .flatMap((item) => item.tools);
+
   const renderResult = render(
     <ConfigContext.Provider value={config}>
       <SettingsContext.Provider value={finalSettings}>
@@ -246,20 +275,22 @@ export const renderWithProviders = (
             <ShellFocusContext.Provider value={shellFocus}>
               <StreamingContext.Provider value={finalUiState.streamingState}>
                 <UIActionsContext.Provider value={finalUIActions}>
-                  <KeypressProvider>
-                    <MouseProvider mouseEventsEnabled={mouseEventsEnabled}>
-                      <ScrollProvider>
-                        <Box
-                          width={terminalWidth}
-                          flexShrink={0}
-                          flexGrow={0}
-                          flexDirection="column"
-                        >
-                          {component}
-                        </Box>
-                      </ScrollProvider>
-                    </MouseProvider>
-                  </KeypressProvider>
+                  <ToolActionsProvider config={config} toolCalls={allToolCalls}>
+                    <KeypressProvider>
+                      <MouseProvider mouseEventsEnabled={mouseEventsEnabled}>
+                        <ScrollProvider>
+                          <Box
+                            width={terminalWidth}
+                            flexShrink={0}
+                            flexGrow={0}
+                            flexDirection="column"
+                          >
+                            {component}
+                          </Box>
+                        </ScrollProvider>
+                      </MouseProvider>
+                    </KeypressProvider>
+                  </ToolActionsProvider>
                 </UIActionsContext.Provider>
               </StreamingContext.Provider>
             </ShellFocusContext.Provider>

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

@@ -20,6 +20,7 @@ import { cleanup } from 'ink-testing-library';
 import { act, useContext, type ReactElement } from 'react';
 import { AppContainer } from './AppContainer.js';
 import { SettingsContext } from './contexts/SettingsContext.js';
+import { type TrackedToolCall } from './hooks/useReactToolScheduler.js';
 import {
   type Config,
   makeFakeConfig,
@@ -27,6 +28,7 @@ import {
   type UserFeedbackPayload,
   type ResumedSessionData,
   AuthType,
+  type AgentDefinition,
 } from '@google/gemini-cli-core';
 
 // Mock coreEvents
@@ -136,7 +138,7 @@ vi.mock('./hooks/useLoadingIndicator.js');
 vi.mock('./hooks/useFolderTrust.js');
 vi.mock('./hooks/useIdeTrustListener.js');
 vi.mock('./hooks/useMessageQueue.js');
-vi.mock('./hooks/useAutoAcceptIndicator.js');
+vi.mock('./hooks/useApprovalModeIndicator.js');
 vi.mock('./hooks/useGitBranchName.js');
 vi.mock('./contexts/VimModeContext.js');
 vi.mock('./contexts/SessionContext.js');
@@ -164,7 +166,7 @@ import { useVim } from './hooks/vim.js';
 import { useFolderTrust } from './hooks/useFolderTrust.js';
 import { useIdeTrustListener } from './hooks/useIdeTrustListener.js';
 import { useMessageQueue } from './hooks/useMessageQueue.js';
-import { useAutoAcceptIndicator } from './hooks/useAutoAcceptIndicator.js';
+import { useApprovalModeIndicator } from './hooks/useApprovalModeIndicator.js';
 import { useGitBranchName } from './hooks/useGitBranchName.js';
 import { useVimMode } from './contexts/VimModeContext.js';
 import { useSessionStats } from './contexts/SessionContext.js';
@@ -236,7 +238,7 @@ describe('AppContainer State Management', () => {
   const mockedUseFolderTrust = useFolderTrust as Mock;
   const mockedUseIdeTrustListener = useIdeTrustListener as Mock;
   const mockedUseMessageQueue = useMessageQueue as Mock;
-  const mockedUseAutoAcceptIndicator = useAutoAcceptIndicator as Mock;
+  const mockedUseApprovalModeIndicator = useApprovalModeIndicator as Mock;
   const mockedUseGitBranchName = useGitBranchName as Mock;
   const mockedUseVimMode = useVimMode as Mock;
   const mockedUseSessionStats = useSessionStats as Mock;
@@ -335,7 +337,7 @@ describe('AppContainer State Management', () => {
       clearQueue: vi.fn(),
       getQueuedMessagesText: vi.fn().mockReturnValue(''),
     });
-    mockedUseAutoAcceptIndicator.mockReturnValue(false);
+    mockedUseApprovalModeIndicator.mockReturnValue(false);
     mockedUseGitBranchName.mockReturnValue('main');
     mockedUseVimMode.mockReturnValue({
       isVimEnabled: false,
@@ -1274,8 +1276,12 @@ describe('AppContainer State Management', () => {
           pendingHistoryItems: [],
           thought: { subject: 'Executing shell command' },
           cancelOngoingRequest: vi.fn(),
+          pendingToolCalls: [],
+          handleApprovalModeChange: vi.fn(),
           activePtyId: 'pty-1',
-          lastOutputTime: 0,
+          loopDetectionConfirmationRequest: null,
+          lastOutputTime: startTime + 100, // Trigger aggressive delay
+          retryStatus: null,
         });
 
         vi.spyOn(mockConfig, 'isInteractive').mockReturnValue(true);
@@ -1309,6 +1315,136 @@ describe('AppContainer State Management', () => {
         unmount();
       });
 
+      it('should show Working… in title for redirected commands after 2 mins', async () => {
+        const startTime = 1000000;
+        vi.setSystemTime(startTime);
+
+        // Arrange: Set up mock settings with showStatusInTitle enabled
+        const mockSettingsWithTitleEnabled = {
+          ...mockSettings,
+          merged: {
+            ...mockSettings.merged,
+            ui: {
+              ...mockSettings.merged.ui,
+              showStatusInTitle: true,
+              hideWindowTitle: false,
+            },
+          },
+        } as unknown as LoadedSettings;
+
+        // Mock an active shell pty with redirection active
+        mockedUseGeminiStream.mockReturnValue({
+          streamingState: 'responding',
+          submitQuery: vi.fn(),
+          initError: null,
+          pendingHistoryItems: [],
+          thought: { subject: 'Executing shell command' },
+          cancelOngoingRequest: vi.fn(),
+          pendingToolCalls: [
+            {
+              request: {
+                name: 'run_shell_command',
+                args: { command: 'ls > out' },
+              },
+              status: 'executing',
+            } as unknown as TrackedToolCall,
+          ],
+          handleApprovalModeChange: vi.fn(),
+          activePtyId: 'pty-1',
+          loopDetectionConfirmationRequest: null,
+          lastOutputTime: startTime,
+          retryStatus: null,
+        });
+
+        vi.spyOn(mockConfig, 'isInteractive').mockReturnValue(true);
+        vi.spyOn(mockConfig, 'isInteractiveShellEnabled').mockReturnValue(true);
+
+        const { unmount } = renderAppContainer({
+          settings: mockSettingsWithTitleEnabled,
+        });
+
+        // Fast-forward time by 65 seconds - should still NOT be Action Required
+        await act(async () => {
+          await vi.advanceTimersByTimeAsync(65000);
+        });
+
+        const titleWritesMid = mocks.mockStdout.write.mock.calls.filter(
+          (call) => call[0].includes('\x1b]0;'),
+        );
+        expect(titleWritesMid[titleWritesMid.length - 1][0]).not.toContain(
+          '✋  Action Required',
+        );
+
+        // Fast-forward to 2 minutes (120000ms)
+        await act(async () => {
+          await vi.advanceTimersByTimeAsync(60000);
+        });
+
+        const titleWritesEnd = mocks.mockStdout.write.mock.calls.filter(
+          (call) => call[0].includes('\x1b]0;'),
+        );
+        expect(titleWritesEnd[titleWritesEnd.length - 1][0]).toContain(
+          '⏲  Working…',
+        );
+
+        unmount();
+      });
+
+      it('should show Working… in title for silent non-redirected commands after 1 min', async () => {
+        const startTime = 1000000;
+        vi.setSystemTime(startTime);
+
+        // Arrange: Set up mock settings with showStatusInTitle enabled
+        const mockSettingsWithTitleEnabled = {
+          ...mockSettings,
+          merged: {
+            ...mockSettings.merged,
+            ui: {
+              ...mockSettings.merged.ui,
+              showStatusInTitle: true,
+              hideWindowTitle: false,
+            },
+          },
+        } as unknown as LoadedSettings;
+
+        // Mock an active shell pty with NO output since operation started (silent)
+        mockedUseGeminiStream.mockReturnValue({
+          streamingState: 'responding',
+          submitQuery: vi.fn(),
+          initError: null,
+          pendingHistoryItems: [],
+          thought: { subject: 'Executing shell command' },
+          cancelOngoingRequest: vi.fn(),
+          pendingToolCalls: [],
+          handleApprovalModeChange: vi.fn(),
+          activePtyId: 'pty-1',
+          loopDetectionConfirmationRequest: null,
+          lastOutputTime: startTime, // lastOutputTime <= operationStartTime
+          retryStatus: null,
+        });
+
+        vi.spyOn(mockConfig, 'isInteractive').mockReturnValue(true);
+        vi.spyOn(mockConfig, 'isInteractiveShellEnabled').mockReturnValue(true);
+
+        const { unmount } = renderAppContainer({
+          settings: mockSettingsWithTitleEnabled,
+        });
+
+        // Fast-forward time by 65 seconds
+        await act(async () => {
+          await vi.advanceTimersByTimeAsync(65000);
+        });
+
+        const titleWrites = mocks.mockStdout.write.mock.calls.filter((call) =>
+          call[0].includes('\x1b]0;'),
+        );
+        const lastTitle = titleWrites[titleWrites.length - 1][0];
+        // Should show Working… (⏲) instead of Action Required (✋)
+        expect(lastTitle).toContain('⏲  Working…');
+
+        unmount();
+      });
+
       it('should NOT show Action Required in title if shell is streaming output', async () => {
         const startTime = 1000000;
         vi.setSystemTime(startTime);
@@ -1327,7 +1463,7 @@ describe('AppContainer State Management', () => {
         } as unknown as LoadedSettings;
 
         // Mock an active shell pty but not focused
-        let lastOutputTime = 1000;
+        let lastOutputTime = startTime + 1000;
         mockedUseGeminiStream.mockImplementation(() => ({
           streamingState: 'responding',
           submitQuery: vi.fn(),
@@ -1353,7 +1489,7 @@ describe('AppContainer State Management', () => {
         });
 
         // Update lastOutputTime to simulate new output
-        lastOutputTime = 21000;
+        lastOutputTime = startTime + 21000;
         mockedUseGeminiStream.mockImplementation(() => ({
           streamingState: 'responding',
           submitQuery: vi.fn(),
@@ -1660,9 +1796,10 @@ describe('AppContainer State Management', () => {
         act(() => {
           handleGlobalKeypress({
             name: 'c',
-            ctrl: false,
-            meta: false,
             shift: false,
+            alt: false,
+            ctrl: false,
+            cmd: false,
             ...key,
           } as Key);
         });
@@ -1870,9 +2007,10 @@ describe('AppContainer State Management', () => {
         act(() => {
           handleGlobalKeypress({
             name: 's',
-            ctrl: true,
-            meta: false,
             shift: false,
+            alt: false,
+            ctrl: true,
+            cmd: false,
             insertable: false,
             sequence: '\x13',
           });
@@ -1896,9 +2034,10 @@ describe('AppContainer State Management', () => {
           act(() => {
             handleGlobalKeypress({
               name: 's',
-              ctrl: true,
-              meta: false,
               shift: false,
+              alt: false,
+              ctrl: true,
+              cmd: false,
               insertable: false,
               sequence: '\x13',
             });
@@ -1910,9 +2049,10 @@ describe('AppContainer State Management', () => {
           act(() => {
             handleGlobalKeypress({
               name: 'any', // Any key should exit copy mode
-              ctrl: false,
-              meta: false,
               shift: false,
+              alt: false,
+              ctrl: false,
+              cmd: false,
               insertable: true,
               sequence: 'a',
             });
@@ -1930,9 +2070,10 @@ describe('AppContainer State Management', () => {
           act(() => {
             handleGlobalKeypress({
               name: 's',
-              ctrl: true,
-              meta: false,
               shift: false,
+              alt: false,
+              ctrl: true,
+              cmd: false,
               insertable: false,
               sequence: '\x13',
             });
@@ -1945,9 +2086,10 @@ describe('AppContainer State Management', () => {
           act(() => {
             handleGlobalKeypress({
               name: 'a',
-              ctrl: false,
-              meta: false,
               shift: false,
+              alt: false,
+              ctrl: false,
+              cmd: false,
               insertable: true,
               sequence: 'a',
             });
@@ -2006,6 +2148,77 @@ describe('AppContainer State Management', () => {
     });
   });
 
+  describe('Agent Configuration Dialog Integration', () => {
+    it('should initialize with dialog closed and no agent selected', async () => {
+      let unmount: () => void;
+      await act(async () => {
+        const result = renderAppContainer();
+        unmount = result.unmount;
+      });
+      await waitFor(() => expect(capturedUIState).toBeTruthy());
+
+      expect(capturedUIState.isAgentConfigDialogOpen).toBe(false);
+      expect(capturedUIState.selectedAgentName).toBeUndefined();
+      expect(capturedUIState.selectedAgentDisplayName).toBeUndefined();
+      expect(capturedUIState.selectedAgentDefinition).toBeUndefined();
+      unmount!();
+    });
+
+    it('should update state when openAgentConfigDialog is called', async () => {
+      let unmount: () => void;
+      await act(async () => {
+        const result = renderAppContainer();
+        unmount = result.unmount;
+      });
+      await waitFor(() => expect(capturedUIState).toBeTruthy());
+
+      const agentDefinition = { name: 'test-agent' };
+      act(() => {
+        capturedUIActions.openAgentConfigDialog(
+          'test-agent',
+          'Test Agent',
+          agentDefinition as unknown as AgentDefinition,
+        );
+      });
+
+      expect(capturedUIState.isAgentConfigDialogOpen).toBe(true);
+      expect(capturedUIState.selectedAgentName).toBe('test-agent');
+      expect(capturedUIState.selectedAgentDisplayName).toBe('Test Agent');
+      expect(capturedUIState.selectedAgentDefinition).toEqual(agentDefinition);
+      unmount!();
+    });
+
+    it('should clear state when closeAgentConfigDialog is called', async () => {
+      let unmount: () => void;
+      await act(async () => {
+        const result = renderAppContainer();
+        unmount = result.unmount;
+      });
+      await waitFor(() => expect(capturedUIState).toBeTruthy());
+
+      const agentDefinition = { name: 'test-agent' };
+      act(() => {
+        capturedUIActions.openAgentConfigDialog(
+          'test-agent',
+          'Test Agent',
+          agentDefinition as unknown as AgentDefinition,
+        );
+      });
+
+      expect(capturedUIState.isAgentConfigDialogOpen).toBe(true);
+
+      act(() => {
+        capturedUIActions.closeAgentConfigDialog();
+      });
+
+      expect(capturedUIState.isAgentConfigDialogOpen).toBe(false);
+      expect(capturedUIState.selectedAgentName).toBeUndefined();
+      expect(capturedUIState.selectedAgentDisplayName).toBeUndefined();
+      expect(capturedUIState.selectedAgentDefinition).toBeUndefined();
+      unmount!();
+    });
+  });
+
   describe('CoreEvents Integration', () => {
     it('subscribes to UserFeedback and drains backlog on mount', async () => {
       let unmount: () => void;

packages/cli/src/ui/AppContainer.tsx

@@ -25,9 +25,11 @@ import {
   type HistoryItem,
   ToolCallStatus,
   type HistoryItemWithoutId,
+  type HistoryItemToolGroup,
   AuthState,
 } from './types.js';
 import { MessageType, StreamingState } from './types.js';
+import { ToolActionsProvider } from './contexts/ToolActionsContext.js';
 import {
   type EditorType,
   type Config,
@@ -35,6 +37,7 @@ import {
   type IdeContext,
   type UserTierId,
   type UserFeedbackPayload,
+  type AgentDefinition,
   IdeClient,
   ideContextStore,
   getErrorMessage,
@@ -92,6 +95,7 @@ import { useFocus } from './hooks/useFocus.js';
 import { useKeypress, type Key } from './hooks/useKeypress.js';
 import { keyMatchers, Command } from './keyMatchers.js';
 import { useLoadingIndicator } from './hooks/useLoadingIndicator.js';
+import { useShellInactivityStatus } from './hooks/useShellInactivityStatus.js';
 import { useFolderTrust } from './hooks/useFolderTrust.js';
 import { useIdeTrustListener } from './hooks/useIdeTrustListener.js';
 import { type IdeIntegrationNudgeResult } from './IdeIntegrationNudge.js';
@@ -102,7 +106,7 @@ import { registerCleanup, runExitCleanup } from '../utils/cleanup.js';
 import { RELAUNCH_EXIT_CODE } from '../utils/processUtils.js';
 import type { SessionInfo } from '../utils/sessionUtils.js';
 import { useMessageQueue } from './hooks/useMessageQueue.js';
-import { useAutoAcceptIndicator } from './hooks/useAutoAcceptIndicator.js';
+import { useApprovalModeIndicator } from './hooks/useApprovalModeIndicator.js';
 import { useSessionStats } from './contexts/SessionContext.js';
 import { useGitBranchName } from './hooks/useGitBranchName.js';
 import {
@@ -125,10 +129,8 @@ import { useHookDisplayState } from './hooks/useHookDisplayState.js';
 import {
   WARNING_PROMPT_DURATION_MS,
   QUEUE_ERROR_DISPLAY_DURATION_MS,
-  SHELL_ACTION_REQUIRED_TITLE_DELAY_MS,
 } from './constants.js';
 import { LoginWithGoogleRestartDialog } from './auth/LoginWithGoogleRestartDialog.js';
-import { useInactivityTimer } from './hooks/useInactivityTimer.js';
 
 function isToolExecuting(pendingHistoryItems: HistoryItemWithoutId[]) {
   return pendingHistoryItems.some((item) => {
@@ -252,6 +254,34 @@ export const AppContainer = (props: AppContainerProps) => {
     setPermissionsDialogProps(null);
   }, []);
 
+  const [isAgentConfigDialogOpen, setIsAgentConfigDialogOpen] = useState(false);
+  const [selectedAgentName, setSelectedAgentName] = useState<
+    string | undefined
+  >();
+  const [selectedAgentDisplayName, setSelectedAgentDisplayName] = useState<
+    string | undefined
+  >();
+  const [selectedAgentDefinition, setSelectedAgentDefinition] = useState<
+    AgentDefinition | undefined
+  >();
+
+  const openAgentConfigDialog = useCallback(
+    (name: string, displayName: string, definition: AgentDefinition) => {
+      setSelectedAgentName(name);
+      setSelectedAgentDisplayName(displayName);
+      setSelectedAgentDefinition(definition);
+      setIsAgentConfigDialogOpen(true);
+    },
+    [],
+  );
+
+  const closeAgentConfigDialog = useCallback(() => {
+    setIsAgentConfigDialogOpen(false);
+    setSelectedAgentName(undefined);
+    setSelectedAgentDisplayName(undefined);
+    setSelectedAgentDefinition(undefined);
+  }, []);
+
   const toggleDebugProfiler = useCallback(
     () => setShowDebugProfiler((prev) => !prev),
     [],
@@ -316,7 +346,9 @@ export const AppContainer = (props: AppContainerProps) => {
         if (additionalContext && geminiClient) {
           await geminiClient.addHistory({
             role: 'user',
-            parts: [{ text: additionalContext }],
+            parts: [
+              { text: `<hook_context>${additionalContext}</hook_context>` },
+            ],
           });
         }
       }
@@ -495,7 +527,12 @@ export const AppContainer = (props: AppContainerProps) => {
     }
   }, [authState, authContext, setAuthState]);
 
-  const { proQuotaRequest, handleProQuotaChoice } = useQuotaAndFallback({
+  const {
+    proQuotaRequest,
+    handleProQuotaChoice,
+    validationRequest,
+    handleValidationChoice,
+  } = useQuotaAndFallback({
     config,
     historyManager,
     userTier,
@@ -671,6 +708,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       openSettingsDialog,
       openSessionBrowser,
       openModelDialog,
+      openAgentConfigDialog,
       openPermissionsDialog,
       quit: (messages: HistoryItem[]) => {
         setQuittingMessages(messages);
@@ -684,6 +722,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       toggleDebugProfiler,
       dispatchExtensionStateUpdate,
       addConfirmUpdateExtensionRequest,
+      setText: (text: string) => buffer.setText(text),
     }),
     [
       setAuthState,
@@ -692,6 +731,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       openSettingsDialog,
       openSessionBrowser,
       openModelDialog,
+      openAgentConfigDialog,
       setQuittingMessages,
       setDebugMessage,
       setShowPrivacyNotice,
@@ -700,6 +740,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       openPermissionsDialog,
       addConfirmUpdateExtensionRequest,
       toggleDebugProfiler,
+      buffer,
     ],
   );
 
@@ -807,6 +848,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
     pendingHistoryItems: pendingGeminiHistoryItems,
     thought,
     cancelOngoingRequest,
+    pendingToolCalls,
     handleApprovalModeChange,
     activePtyId,
     loopDetectionConfirmationRequest,
@@ -838,18 +880,20 @@ Logging in with Google... Restarting Gemini CLI to continue.
     lastOutputTimeRef.current = lastOutputTime;
   }, [lastOutputTime]);
 
-  const isShellAwaitingFocus =
-    !!activePtyId &&
-    !embeddedShellFocused &&
-    config.isInteractiveShellEnabled();
-  const showShellActionRequired = useInactivityTimer(
-    isShellAwaitingFocus,
+  const { shouldShowFocusHint, inactivityStatus } = useShellInactivityStatus({
+    activePtyId,
     lastOutputTime,
-    SHELL_ACTION_REQUIRED_TITLE_DELAY_MS,
-  );
+    streamingState,
+    pendingToolCalls,
+    embeddedShellFocused,
+    isInteractiveShellEnabled: config.isInteractiveShellEnabled(),
+  });
+
+  const shouldShowActionRequiredTitle = inactivityStatus === 'action_required';
+  const shouldShowSilentWorkingTitle = inactivityStatus === 'silent_working';
 
   // Auto-accept indicator
-  const showAutoAcceptIndicator = useAutoAcceptIndicator({
+  const showApprovalModeIndicator = useApprovalModeIndicator({
     config,
     addItem: historyManager.addItem,
     onApprovalModeChange: handleApprovalModeChange,
@@ -1228,13 +1272,11 @@ Logging in with Google... Restarting Gemini CLI to continue.
     [handleSlashCommand, settings],
   );
 
-  const { elapsedTime, currentLoadingPhrase } = useLoadingIndicator(
+  const { elapsedTime, currentLoadingPhrase } = useLoadingIndicator({
     streamingState,
-    settings.merged.ui.customWittyPhrases,
-    !!activePtyId && !embeddedShellFocused,
-    lastOutputTime,
+    shouldShowFocusHint,
     retryStatus,
-  );
+  });
 
   const handleGlobalKeypress = useCallback(
     (key: Key) => {
@@ -1364,7 +1406,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
     const paddedTitle = computeTerminalTitle({
       streamingState,
       thoughtSubject: thought?.subject,
-      isConfirming: !!confirmationRequest || showShellActionRequired,
+      isConfirming: !!confirmationRequest || shouldShowActionRequiredTitle,
+      isSilentWorking: shouldShowSilentWorkingTitle,
       folderName: basename(config.getTargetDir()),
       showThoughts: !!settings.merged.ui.showStatusInTitle,
       useDynamicTitle: settings.merged.ui.dynamicWindowTitle,
@@ -1380,7 +1423,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
     streamingState,
     thought,
     confirmationRequest,
-    showShellActionRequired,
+    shouldShowActionRequiredTitle,
+    shouldShowSilentWorkingTitle,
     settings.merged.ui.showStatusInTitle,
     settings.merged.ui.dynamicWindowTitle,
     settings.merged.ui.hideWindowTitle,
@@ -1464,6 +1508,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
     isThemeDialogOpen ||
     isSettingsDialogOpen ||
     isModelDialogOpen ||
+    isAgentConfigDialogOpen ||
     isPermissionsDialogOpen ||
     isAuthenticating ||
     isAuthDialogOpen ||
@@ -1471,6 +1516,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
     showPrivacyNotice ||
     showIdeRestartPrompt ||
     !!proQuotaRequest ||
+    !!validationRequest ||
     isSessionBrowserOpen ||
     isAuthDialogOpen ||
     authState === AuthState.AwaitingApiKeyInput;
@@ -1480,6 +1526,16 @@ Logging in with Google... Restarting Gemini CLI to continue.
     [pendingSlashCommandHistoryItems, pendingGeminiHistoryItems],
   );
 
+  const allToolCalls = useMemo(
+    () =>
+      pendingHistoryItems
+        .filter(
+          (item): item is HistoryItemToolGroup => item.type === 'tool_group',
+        )
+        .flatMap((item) => item.tools),
+    [pendingHistoryItems],
+  );
+
   const [geminiMdFileCount, setGeminiMdFileCount] = useState<number>(
     config.getGeminiMdFileCount(),
   );
@@ -1546,6 +1602,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
       isSettingsDialogOpen,
       isSessionBrowserOpen,
       isModelDialogOpen,
+      isAgentConfigDialogOpen,
+      selectedAgentName,
+      selectedAgentDisplayName,
+      selectedAgentDefinition,
       isPermissionsDialogOpen,
       permissionsDialogProps,
       slashCommands,
@@ -1584,10 +1644,11 @@ Logging in with Google... Restarting Gemini CLI to continue.
       activeHooks,
       messageQueue,
       queueErrorMessage,
-      showAutoAcceptIndicator,
+      showApprovalModeIndicator,
       currentModel,
       userTier,
       proQuotaRequest,
+      validationRequest,
       contextFileNames,
       errorCount,
       availableTerminalHeight,
@@ -1637,6 +1698,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
       isSettingsDialogOpen,
       isSessionBrowserOpen,
       isModelDialogOpen,
+      isAgentConfigDialogOpen,
+      selectedAgentName,
+      selectedAgentDisplayName,
+      selectedAgentDefinition,
       isPermissionsDialogOpen,
       permissionsDialogProps,
       slashCommands,
@@ -1675,9 +1740,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
       activeHooks,
       messageQueue,
       queueErrorMessage,
-      showAutoAcceptIndicator,
+      showApprovalModeIndicator,
       userTier,
       proQuotaRequest,
+      validationRequest,
       contextFileNames,
       errorCount,
       availableTerminalHeight,
@@ -1735,6 +1801,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
       exitPrivacyNotice,
       closeSettingsDialog,
       closeModelDialog,
+      openAgentConfigDialog,
+      closeAgentConfigDialog,
       openPermissionsDialog,
       closePermissionsDialog,
       setShellModeActive,
@@ -1747,6 +1815,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       handleFinalSubmit,
       handleClearScreen,
       handleProQuotaChoice,
+      handleValidationChoice,
       openSessionBrowser,
       closeSessionBrowser,
       handleResumeSession,
@@ -1775,6 +1844,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
       exitPrivacyNotice,
       closeSettingsDialog,
       closeModelDialog,
+      openAgentConfigDialog,
+      closeAgentConfigDialog,
       openPermissionsDialog,
       closePermissionsDialog,
       setShellModeActive,
@@ -1787,6 +1858,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       handleFinalSubmit,
       handleClearScreen,
       handleProQuotaChoice,
+      handleValidationChoice,
       openSessionBrowser,
       closeSessionBrowser,
       handleResumeSession,
@@ -1822,9 +1894,11 @@ Logging in with Google... Restarting Gemini CLI to continue.
               startupWarnings: props.startupWarnings || [],
             }}
           >
-            <ShellFocusContext.Provider value={isFocused}>
-              <App />
-            </ShellFocusContext.Provider>
+            <ToolActionsProvider config={config} toolCalls={allToolCalls}>
+              <ShellFocusContext.Provider value={isFocused}>
+                <App />
+              </ShellFocusContext.Provider>
+            </ToolActionsProvider>
           </AppContext.Provider>
         </ConfigContext.Provider>
       </UIActionsContext.Provider>

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

@@ -108,10 +108,10 @@ describe('ApiAuthDialog', () => {
 
       keypressHandler({
         name: keyName,
-        sequence,
-        ctrl: false,
-        meta: false,
         shift: false,
+        ctrl: false,
+        cmd: false,
+        sequence,
       });
 
       expect(expectedCall).toHaveBeenCalledWith(...args);
@@ -137,9 +137,9 @@ describe('ApiAuthDialog', () => {
 
     await keypressHandler({
       name: 'c',
-      ctrl: true,
-      meta: false,
       shift: false,
+      ctrl: true,
+      cmd: false,
     });
 
     expect(clearApiKey).toHaveBeenCalled();

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

@@ -48,10 +48,10 @@ describe('LoginWithGoogleRestartDialog', () => {
 
     keypressHandler({
       name: 'escape',
-      sequence: '\u001b',
-      ctrl: false,
-      meta: false,
       shift: false,
+      ctrl: false,
+      cmd: false,
+      sequence: '\u001b',
     });
 
     expect(onDismiss).toHaveBeenCalledTimes(1);
@@ -67,10 +67,10 @@ describe('LoginWithGoogleRestartDialog', () => {
 
       keypressHandler({
         name: keyName,
-        sequence: keyName,
-        ctrl: false,
-        meta: false,
         shift: false,
+        ctrl: false,
+        cmd: false,
+        sequence: keyName,
       });
 
       // Advance timers to trigger the setTimeout callback

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

@@ -149,7 +149,7 @@ describe('agentsCommand', () => {
     });
     // Add agent to disabled overrides so validation passes
     mockContext.services.settings.merged.agents.overrides['test-agent'] = {
-      disabled: true,
+      enabled: false,
     };
 
     vi.mocked(enableAgent).mockReturnValue({
@@ -264,7 +264,7 @@ describe('agentsCommand', () => {
   it('should show info message if agent is already disabled', async () => {
     mockConfig.getAgentRegistry().getAllAgentNames.mockReturnValue([]);
     mockContext.services.settings.merged.agents.overrides['test-agent'] = {
-      disabled: true,
+      enabled: false,
     };
 
     const disableCommand = agentsCommand.subCommands?.find(

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

@@ -85,10 +85,10 @@ async function enableAction(
   const allAgents = agentRegistry.getAllAgentNames();
   const overrides = settings.merged.agents.overrides;
   const disabledAgents = Object.keys(overrides).filter(
-    (name) => overrides[name]?.disabled === true,
+    (name) => overrides[name]?.enabled === false,
   );
 
-  if (allAgents.includes(agentName)) {
+  if (allAgents.includes(agentName) && !disabledAgents.includes(agentName)) {
     return {
       type: 'message',
       messageType: 'info',
@@ -96,7 +96,7 @@ async function enableAction(
     };
   }
 
-  if (!disabledAgents.includes(agentName)) {
+  if (!disabledAgents.includes(agentName) && !allAgents.includes(agentName)) {
     return {
       type: 'message',
       messageType: 'error',
@@ -155,7 +155,7 @@ async function disableAction(
   const allAgents = agentRegistry.getAllAgentNames();
   const overrides = settings.merged.agents.overrides;
   const disabledAgents = Object.keys(overrides).filter(
-    (name) => overrides[name]?.disabled === true,
+    (name) => overrides[name]?.enabled === false,
   );
 
   if (disabledAgents.includes(agentName)) {
@@ -206,7 +206,7 @@ function completeAgentsToEnable(context: CommandContext, partialArg: string) {
 
   const overrides = settings.merged.agents.overrides;
   const disabledAgents = Object.entries(overrides)
-    .filter(([_, override]) => override?.disabled === true)
+    .filter(([_, override]) => override?.enabled === false)
     .map(([name]) => name);
 
   return disabledAgents.filter((name) => name.startsWith(partialArg));

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

@@ -43,6 +43,7 @@ describe('directoryCommand', () => {
   beforeEach(() => {
     mockWorkspaceContext = {
       addDirectory: vi.fn(),
+      addDirectories: vi.fn().mockReturnValue({ added: [], failed: [] }),
       getDirectories: vi
         .fn()
         .mockReturnValue([
@@ -125,9 +126,15 @@ describe('directoryCommand', () => {
 
     it('should call addDirectory and show a success message for a single path', async () => {
       const newPath = path.normalize('/home/user/new-project');
+      vi.mocked(mockWorkspaceContext.addDirectories).mockReturnValue({
+        added: [newPath],
+        failed: [],
+      });
       if (!addCommand?.action) throw new Error('No action');
       await addCommand.action(mockContext, newPath);
-      expect(mockWorkspaceContext.addDirectory).toHaveBeenCalledWith(newPath);
+      expect(mockWorkspaceContext.addDirectories).toHaveBeenCalledWith([
+        newPath,
+      ]);
       expect(mockContext.ui.addItem).toHaveBeenCalledWith(
         expect.objectContaining({
           type: MessageType.INFO,
@@ -139,10 +146,16 @@ describe('directoryCommand', () => {
     it('should call addDirectory for each path and show a success message for multiple paths', async () => {
       const newPath1 = path.normalize('/home/user/new-project1');
       const newPath2 = path.normalize('/home/user/new-project2');
+      vi.mocked(mockWorkspaceContext.addDirectories).mockReturnValue({
+        added: [newPath1, newPath2],
+        failed: [],
+      });
       if (!addCommand?.action) throw new Error('No action');
       await addCommand.action(mockContext, `${newPath1},${newPath2}`);
-      expect(mockWorkspaceContext.addDirectory).toHaveBeenCalledWith(newPath1);
-      expect(mockWorkspaceContext.addDirectory).toHaveBeenCalledWith(newPath2);
+      expect(mockWorkspaceContext.addDirectories).toHaveBeenCalledWith([
+        newPath1,
+        newPath2,
+      ]);
       expect(mockContext.ui.addItem).toHaveBeenCalledWith(
         expect.objectContaining({
           type: MessageType.INFO,
@@ -153,10 +166,11 @@ describe('directoryCommand', () => {
 
     it('should show an error if addDirectory throws an exception', async () => {
       const error = new Error('Directory does not exist');
-      vi.mocked(mockWorkspaceContext.addDirectory).mockImplementation(() => {
-        throw error;
-      });
       const newPath = path.normalize('/home/user/invalid-project');
+      vi.mocked(mockWorkspaceContext.addDirectories).mockReturnValue({
+        added: [],
+        failed: [{ path: newPath, error }],
+      });
       if (!addCommand?.action) throw new Error('No action');
       await addCommand.action(mockContext, newPath);
       expect(mockContext.ui.addItem).toHaveBeenCalledWith(
@@ -171,10 +185,16 @@ describe('directoryCommand', () => {
       if (!addCommand?.action) throw new Error('No action');
       vi.spyOn(trustedFolders, 'isFolderTrustEnabled').mockReturnValue(false);
       const newPath = path.normalize('/home/user/new-project');
+      vi.mocked(mockWorkspaceContext.addDirectories).mockReturnValue({
+        added: [newPath],
+        failed: [],
+      });
 
       await addCommand.action(mockContext, newPath);
 
-      expect(mockWorkspaceContext.addDirectory).toHaveBeenCalledWith(newPath);
+      expect(mockWorkspaceContext.addDirectories).toHaveBeenCalledWith([
+        newPath,
+      ]);
     });
 
     it('should show an info message for an already added directory', async () => {
@@ -196,13 +216,10 @@ describe('directoryCommand', () => {
       const validPath = path.normalize('/home/user/valid-project');
       const invalidPath = path.normalize('/home/user/invalid-project');
       const error = new Error('Directory does not exist');
-      vi.mocked(mockWorkspaceContext.addDirectory).mockImplementation(
-        (p: string) => {
-          if (p === invalidPath) {
-            throw error;
-          }
-        },
-      );
+      vi.mocked(mockWorkspaceContext.addDirectories).mockReturnValue({
+        added: [validPath],
+        failed: [{ path: invalidPath, error }],
+      });
 
       if (!addCommand?.action) throw new Error('No action');
       await addCommand.action(mockContext, `${validPath},${invalidPath}`);
@@ -290,10 +307,16 @@ describe('directoryCommand', () => {
       if (!addCommand?.action) throw new Error('No action');
       mockIsPathTrusted.mockReturnValue(true);
       const newPath = path.normalize('/home/user/trusted-project');
+      vi.mocked(mockWorkspaceContext.addDirectories).mockReturnValue({
+        added: [newPath],
+        failed: [],
+      });
 
       await addCommand.action(mockContext, newPath);
 
-      expect(mockWorkspaceContext.addDirectory).toHaveBeenCalledWith(newPath);
+      expect(mockWorkspaceContext.addDirectories).toHaveBeenCalledWith([
+        newPath,
+      ]);
     });
 
     it('should show an error for an untrusted directory', async () => {
@@ -303,7 +326,7 @@ describe('directoryCommand', () => {
 
       await addCommand.action(mockContext, newPath);
 
-      expect(mockWorkspaceContext.addDirectory).not.toHaveBeenCalled();
+      expect(mockWorkspaceContext.addDirectories).not.toHaveBeenCalled();
       expect(mockContext.ui.addItem).toHaveBeenCalledWith(
         expect.objectContaining({
           type: MessageType.ERROR,

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

@@ -17,6 +17,7 @@ import { refreshServerHierarchicalMemory } from '@google/gemini-cli-core';
 import {
   expandHomeDir,
   getDirectorySuggestions,
+  batchAddDirectories,
 } from '../utils/directoryUtils.js';
 import type { Config } from '@google/gemini-cli-core';
 
@@ -193,14 +194,10 @@ export const directoryCommand: SlashCommand = {
             );
           }
 
-          for (const pathToAdd of trustedDirs) {
-            try {
-              workspaceContext.addDirectory(expandHomeDir(pathToAdd));
-              added.push(pathToAdd);
-            } catch (e) {
-              const error = e as Error;
-              errors.push(`Error adding '${pathToAdd}': ${error.message}`);
-            }
+          if (trustedDirs.length > 0) {
+            const result = batchAddDirectories(workspaceContext, trustedDirs);
+            added.push(...result.added);
+            errors.push(...result.errors);
           }
 
           if (undefinedTrustDirs.length > 0) {
@@ -220,17 +217,9 @@ export const directoryCommand: SlashCommand = {
             };
           }
         } else {
-          for (const pathToAdd of pathsToProcess) {
-            try {
-              workspaceContext.addDirectory(expandHomeDir(pathToAdd.trim()));
-              added.push(pathToAdd.trim());
-            } catch (e) {
-              const error = e as Error;
-              errors.push(
-                `Error adding '${pathToAdd.trim()}': ${error.message}`,
-              );
-            }
-          }
+          const result = batchAddDirectories(workspaceContext, pathsToProcess);
+          added.push(...result.added);
+          errors.push(...result.errors);
         }
 
         await finishAddingDirectories(config, addItem, added, errors);

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

@@ -26,7 +26,7 @@ describe('hooksCommand', () => {
   };
   let mockSettings: {
     merged: {
-      hooks?: {
+      hooksConfig?: {
         disabled?: string[];
       };
       tools?: {
@@ -58,7 +58,7 @@ describe('hooksCommand', () => {
     // Create mock settings
     mockSettings = {
       merged: {
-        hooks: {
+        hooksConfig: {
           disabled: [],
         },
       },
@@ -273,7 +273,7 @@ describe('hooksCommand', () => {
 
     it('should enable a hook and update settings', async () => {
       // Update the context's settings with disabled hooks
-      mockContext.services.settings.merged.hooks.disabled = [
+      mockContext.services.settings.merged.hooksConfig.disabled = [
         'test-hook',
         'other-hook',
       ];
@@ -289,7 +289,7 @@ describe('hooksCommand', () => {
 
       expect(mockContext.services.settings.setValue).toHaveBeenCalledWith(
         expect.any(String),
-        'hooks.disabled',
+        'hooksConfig.disabled',
         ['other-hook'],
       );
       expect(mockHookSystem.setHookEnabled).toHaveBeenCalledWith(
@@ -404,7 +404,7 @@ describe('hooksCommand', () => {
     });
 
     it('should disable a hook and update settings', async () => {
-      mockContext.services.settings.merged.hooks.disabled = [];
+      mockContext.services.settings.merged.hooksConfig.disabled = [];
 
       const disableCmd = hooksCommand.subCommands!.find(
         (cmd) => cmd.name === 'disable',
@@ -417,7 +417,7 @@ describe('hooksCommand', () => {
 
       expect(mockContext.services.settings.setValue).toHaveBeenCalledWith(
         expect.any(String),
-        'hooks.disabled',
+        'hooksConfig.disabled',
         ['test-hook'],
       );
       expect(mockHookSystem.setHookEnabled).toHaveBeenCalledWith(
@@ -433,7 +433,7 @@ describe('hooksCommand', () => {
 
     it('should synchronize with hook system even if hook is already in disabled list', async () => {
       // Update the context's settings with the hook already disabled
-      mockContext.services.settings.merged.hooks.disabled = ['test-hook'];
+      mockContext.services.settings.merged.hooksConfig.disabled = ['test-hook'];
 
       const disableCmd = hooksCommand.subCommands!.find(
         (cmd) => cmd.name === 'disable',
@@ -458,7 +458,7 @@ describe('hooksCommand', () => {
     });
 
     it('should handle error when disabling hook fails', async () => {
-      mockContext.services.settings.merged.hooks.disabled = [];
+      mockContext.services.settings.merged.hooksConfig.disabled = [];
       mockSettings.setValue.mockImplementationOnce(() => {
         throw new Error('Failed to save settings');
       });
@@ -637,7 +637,7 @@ describe('hooksCommand', () => {
 
       expect(mockContext.services.settings.setValue).toHaveBeenCalledWith(
         expect.any(String),
-        'hooks.disabled',
+        'hooksConfig.disabled',
         [],
       );
       expect(mockHookSystem.setHookEnabled).toHaveBeenCalledWith(
@@ -761,7 +761,7 @@ describe('hooksCommand', () => {
 
       expect(mockContext.services.settings.setValue).toHaveBeenCalledWith(
         expect.any(String),
-        'hooks.disabled',
+        'hooksConfig.disabled',
         ['hook-1', 'hook-2', 'hook-3'],
       );
       expect(mockHookSystem.setHookEnabled).toHaveBeenCalledWith(

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

@@ -76,7 +76,7 @@ async function enableAction(
 
   // Get current disabled hooks from settings
   const settings = context.services.settings;
-  const disabledHooks = settings.merged.hooks.disabled;
+  const disabledHooks = settings.merged.hooksConfig.disabled;
   // Remove from disabled list if present
   const newDisabledHooks = disabledHooks.filter(
     (name: string) => name !== hookName,
@@ -87,10 +87,10 @@ async function enableAction(
     const scope = settings.workspace
       ? SettingScope.Workspace
       : SettingScope.User;
-    settings.setValue(scope, 'hooks.disabled', newDisabledHooks);
+    settings.setValue(scope, 'hooksConfig.disabled', newDisabledHooks);
 
     // Update core config so re-initialization (e.g. extension reload) respects the change
-    config.updateDisabledHooks(settings.merged.hooks.disabled);
+    config.updateDisabledHooks(settings.merged.hooksConfig.disabled);
 
     // Enable in hook system
     hookSystem.setHookEnabled(hookName, true);
@@ -145,7 +145,7 @@ async function disableAction(
 
   // Get current disabled hooks from settings
   const settings = context.services.settings;
-  const disabledHooks = settings.merged.hooks.disabled;
+  const disabledHooks = settings.merged.hooksConfig.disabled;
   // Add to disabled list if not already present
   try {
     if (!disabledHooks.includes(hookName)) {
@@ -154,11 +154,11 @@ async function disableAction(
       const scope = settings.workspace
         ? SettingScope.Workspace
         : SettingScope.User;
-      settings.setValue(scope, 'hooks.disabled', newDisabledHooks);
+      settings.setValue(scope, 'hooksConfig.disabled', newDisabledHooks);
     }
 
     // Update core config so re-initialization (e.g. extension reload) respects the change
-    config.updateDisabledHooks(settings.merged.hooks.disabled);
+    config.updateDisabledHooks(settings.merged.hooksConfig.disabled);
 
     // Always disable in hook system to ensure in-memory state matches settings
     hookSystem.setHookEnabled(hookName, false);
@@ -250,10 +250,10 @@ async function enableAllAction(
     const scope = settings.workspace
       ? SettingScope.Workspace
       : SettingScope.User;
-    settings.setValue(scope, 'hooks.disabled', []);
+    settings.setValue(scope, 'hooksConfig.disabled', []);
 
     // Update core config so re-initialization (e.g. extension reload) respects the change
-    config.updateDisabledHooks(settings.merged.hooks.disabled);
+    config.updateDisabledHooks(settings.merged.hooksConfig.disabled);
 
     for (const hook of disabledHooks) {
       const hookName = getHookDisplayName(hook);
@@ -323,10 +323,10 @@ async function disableAllAction(
     const scope = settings.workspace
       ? SettingScope.Workspace
       : SettingScope.User;
-    settings.setValue(scope, 'hooks.disabled', allHookNames);
+    settings.setValue(scope, 'hooksConfig.disabled', allHookNames);
 
     // Update core config so re-initialization (e.g. extension reload) respects the change
-    config.updateDisabledHooks(settings.merged.hooks.disabled);
+    config.updateDisabledHooks(settings.merged.hooksConfig.disabled);
 
     for (const hook of enabledHooks) {
       const hookName = getHookDisplayName(hook);

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

@@ -62,7 +62,7 @@ describe('policiesCommand', () => {
       );
     });
 
-    it('should list active policies in correct format', async () => {
+    it('should list policies grouped by mode', async () => {
       const mockRules = [
         {
           decision: PolicyDecision.DENY,
@@ -99,13 +99,18 @@ describe('policiesCommand', () => {
       const call = vi.mocked(mockContext.ui.addItem).mock.calls[0];
       const content = (call[0] as { text: string }).text;
 
+      expect(content).toContain('### Normal Mode Policies');
       expect(content).toContain(
-        '1. **DENY** tool: `dangerousTool` [Priority: 10]',
+        '### Auto Edit Mode Policies (combined with normal mode policies)',
       );
       expect(content).toContain(
-        '2. **ALLOW** all tools (args match: `safe`) [Source: `test.toml`]',
+        '### Yolo Mode Policies (combined with normal mode policies)',
       );
-      expect(content).toContain('3. **ASK_USER** all tools');
+      expect(content).toContain(
+        '**DENY** tool: `dangerousTool` [Priority: 10]',
+      );
+      expect(content).toContain('**ALLOW** all tools (args match: `safe`)');
+      expect(content).toContain('**ASK_USER** all tools');
     });
   });
 });

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

@@ -4,12 +4,46 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
+import { ApprovalMode, type PolicyRule } from '@google/gemini-cli-core';
 import { CommandKind, type SlashCommand } from './types.js';
 import { MessageType } from '../types.js';
 
+interface CategorizedRules {
+  normal: PolicyRule[];
+  autoEdit: PolicyRule[];
+  yolo: PolicyRule[];
+}
+
+const categorizeRulesByMode = (
+  rules: readonly PolicyRule[],
+): CategorizedRules => {
+  const result: CategorizedRules = {
+    normal: [],
+    autoEdit: [],
+    yolo: [],
+  };
+  const ALL_MODES = Object.values(ApprovalMode);
+  rules.forEach((rule) => {
+    const modes = rule.modes?.length ? rule.modes : ALL_MODES;
+    const modeSet = new Set(modes);
+    if (modeSet.has(ApprovalMode.DEFAULT)) result.normal.push(rule);
+    if (modeSet.has(ApprovalMode.AUTO_EDIT)) result.autoEdit.push(rule);
+    if (modeSet.has(ApprovalMode.YOLO)) result.yolo.push(rule);
+  });
+  return result;
+};
+
+const formatRule = (rule: PolicyRule, i: number) =>
+  `${i + 1}. **${rule.decision.toUpperCase()}** ${rule.toolName ? `tool: \`${rule.toolName}\`` : 'all tools'}` +
+  (rule.argsPattern ? ` (args match: \`${rule.argsPattern.source}\`)` : '') +
+  (rule.priority !== undefined ? ` [Priority: ${rule.priority}]` : '');
+
+const formatSection = (title: string, rules: PolicyRule[]) =>
+  `### ${title}\n${rules.length ? rules.map(formatRule).join('\n') : '_No policies._'}\n\n`;
+
 const listPoliciesCommand: SlashCommand = {
   name: 'list',
-  description: 'List all active policies',
+  description: 'List all active policies grouped by mode',
   kind: CommandKind.BUILT_IN,
   autoExecute: true,
   action: async (context) => {
@@ -39,25 +73,25 @@ const listPoliciesCommand: SlashCommand = {
       return;
     }
 
+    const categorized = categorizeRulesByMode(rules);
+    const normalRulesSet = new Set(categorized.normal);
+    const uniqueAutoEdit = categorized.autoEdit.filter(
+      (rule) => !normalRulesSet.has(rule),
+    );
+    const uniqueYolo = categorized.yolo.filter(
+      (rule) => !normalRulesSet.has(rule),
+    );
+
     let content = '**Active Policies**\n\n';
-    rules.forEach((rule, index) => {
-      content += `${index + 1}. **${rule.decision.toUpperCase()}**`;
-      if (rule.toolName) {
-        content += ` tool: \`${rule.toolName}\``;
-      } else {
-        content += ` all tools`;
-      }
-      if (rule.argsPattern) {
-        content += ` (args match: \`${rule.argsPattern.source}\`)`;
-      }
-      if (rule.priority !== undefined) {
-        content += ` [Priority: ${rule.priority}]`;
-      }
-      if (rule.source) {
-        content += ` [Source: \`${rule.source}\`]`;
-      }
-      content += '\n';
-    });
+    content += formatSection('Normal Mode Policies', categorized.normal);
+    content += formatSection(
+      'Auto Edit Mode Policies (combined with normal mode policies)',
+      uniqueAutoEdit,
+    );
+    content += formatSection(
+      'Yolo Mode Policies (combined with normal mode policies)',
+      uniqueYolo,
+    );
 
     context.ui.addItem(
       {

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

@@ -0,0 +1,351 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, beforeEach, vi } from 'vitest';
+import { rewindCommand } from './rewindCommand.js';
+import { createMockCommandContext } from '../../test-utils/mockCommandContext.js';
+import { waitFor } from '../../test-utils/async.js';
+import { RewindOutcome } from '../components/RewindConfirmation.js';
+import {
+  type OpenCustomDialogActionReturn,
+  type CommandContext,
+} from './types.js';
+import type { ReactElement } from 'react';
+import { coreEvents } from '@google/gemini-cli-core';
+
+// Mock dependencies
+const mockRewindTo = vi.fn();
+const mockRecordMessage = vi.fn();
+const mockSetHistory = vi.fn();
+const mockSendMessageStream = vi.fn();
+const mockGetChatRecordingService = vi.fn();
+const mockGetConversation = vi.fn();
+const mockRemoveComponent = vi.fn();
+const mockLoadHistory = vi.fn();
+const mockAddItem = vi.fn();
+const mockSetPendingItem = vi.fn();
+const mockResetContext = vi.fn();
+const mockSetInput = vi.fn();
+const mockRevertFileChanges = vi.fn();
+const mockGetProjectRoot = vi.fn().mockReturnValue('/mock/root');
+
+vi.mock('@google/gemini-cli-core', async (importOriginal) => {
+  const actual =
+    await importOriginal<typeof import('@google/gemini-cli-core')>();
+  return {
+    ...actual,
+    coreEvents: {
+      ...actual.coreEvents,
+      emitFeedback: vi.fn(),
+    },
+  };
+});
+
+vi.mock('../components/RewindViewer.js', () => ({
+  RewindViewer: () => null,
+}));
+
+vi.mock('../hooks/useSessionBrowser.js', () => ({
+  convertSessionToHistoryFormats: vi.fn().mockReturnValue({
+    uiHistory: [
+      { type: 'user', text: 'old user' },
+      { type: 'gemini', text: 'old gemini' },
+    ],
+    clientHistory: [{ role: 'user', parts: [{ text: 'old user' }] }],
+  }),
+}));
+
+vi.mock('../utils/rewindFileOps.js', () => ({
+  revertFileChanges: (...args: unknown[]) => mockRevertFileChanges(...args),
+}));
+
+interface RewindViewerProps {
+  onRewind: (
+    messageId: string,
+    newText: string,
+    outcome: RewindOutcome,
+  ) => Promise<void>;
+  conversation: unknown;
+  onExit: () => void;
+}
+
+describe('rewindCommand', () => {
+  let mockContext: CommandContext;
+
+  beforeEach(() => {
+    vi.clearAllMocks();
+
+    mockGetConversation.mockReturnValue({
+      messages: [{ id: 'msg-1', type: 'user', content: 'hello' }],
+      sessionId: 'test-session',
+    });
+
+    mockRewindTo.mockReturnValue({
+      messages: [], // Mocked rewound messages
+    });
+
+    mockGetChatRecordingService.mockReturnValue({
+      getConversation: mockGetConversation,
+      rewindTo: mockRewindTo,
+      recordMessage: mockRecordMessage,
+    });
+
+    mockContext = createMockCommandContext({
+      services: {
+        config: {
+          getGeminiClient: () => ({
+            getChatRecordingService: mockGetChatRecordingService,
+            setHistory: mockSetHistory,
+            sendMessageStream: mockSendMessageStream,
+          }),
+          getSessionId: () => 'test-session-id',
+          getContextManager: () => ({ refresh: mockResetContext }),
+          getProjectRoot: mockGetProjectRoot,
+        },
+      },
+      ui: {
+        removeComponent: mockRemoveComponent,
+        loadHistory: mockLoadHistory,
+        addItem: mockAddItem,
+        setPendingItem: mockSetPendingItem,
+      },
+    }) as unknown as CommandContext;
+  });
+
+  it('should initialize successfully', async () => {
+    const result = await rewindCommand.action!(mockContext, '');
+    expect(result).toHaveProperty('type', 'custom_dialog');
+  });
+
+  it('should handle RewindOnly correctly', async () => {
+    // 1. Run the command to get the component
+    const result = (await rewindCommand.action!(
+      mockContext,
+      '',
+    )) as OpenCustomDialogActionReturn;
+    const component = result.component as ReactElement<RewindViewerProps>;
+
+    // Access onRewind from props
+    const onRewind = component.props.onRewind;
+    expect(onRewind).toBeDefined();
+
+    await onRewind('msg-id-123', 'New Prompt', RewindOutcome.RewindOnly);
+
+    await waitFor(() => {
+      expect(mockRevertFileChanges).not.toHaveBeenCalled();
+      expect(mockRewindTo).toHaveBeenCalledWith('msg-id-123');
+      expect(mockSetHistory).toHaveBeenCalled();
+      expect(mockResetContext).toHaveBeenCalled();
+      expect(mockLoadHistory).toHaveBeenCalledWith(
+        [
+          expect.objectContaining({ text: 'old user', id: 1 }),
+          expect.objectContaining({ text: 'old gemini', id: 2 }),
+        ],
+        'New Prompt',
+      );
+      expect(mockRemoveComponent).toHaveBeenCalled();
+    });
+
+    // Verify setInput was NOT called directly (it's handled via loadHistory now)
+    expect(mockSetInput).not.toHaveBeenCalled();
+  });
+
+  it('should handle RewindAndRevert correctly', async () => {
+    const result = (await rewindCommand.action!(
+      mockContext,
+      '',
+    )) as OpenCustomDialogActionReturn;
+    const component = result.component as ReactElement<RewindViewerProps>;
+    const onRewind = component.props.onRewind;
+
+    await onRewind('msg-id-123', 'New Prompt', RewindOutcome.RewindAndRevert);
+
+    await waitFor(() => {
+      expect(mockRevertFileChanges).toHaveBeenCalledWith(
+        mockGetConversation(),
+        'msg-id-123',
+      );
+      expect(mockRewindTo).toHaveBeenCalledWith('msg-id-123');
+      expect(mockLoadHistory).toHaveBeenCalledWith(
+        expect.any(Array),
+        'New Prompt',
+      );
+    });
+    expect(mockSetInput).not.toHaveBeenCalled();
+  });
+
+  it('should handle RevertOnly correctly', async () => {
+    const result = (await rewindCommand.action!(
+      mockContext,
+      '',
+    )) as OpenCustomDialogActionReturn;
+    const component = result.component as ReactElement<RewindViewerProps>;
+    const onRewind = component.props.onRewind;
+
+    await onRewind('msg-id-123', 'New Prompt', RewindOutcome.RevertOnly);
+
+    await waitFor(() => {
+      expect(mockRevertFileChanges).toHaveBeenCalledWith(
+        mockGetConversation(),
+        'msg-id-123',
+      );
+      expect(mockRewindTo).not.toHaveBeenCalled();
+      expect(mockRemoveComponent).toHaveBeenCalled();
+      expect(coreEvents.emitFeedback).toHaveBeenCalledWith(
+        'info',
+        'File changes reverted.',
+      );
+    });
+    expect(mockSetInput).not.toHaveBeenCalled();
+  });
+
+  it('should handle Cancel correctly', async () => {
+    const result = (await rewindCommand.action!(
+      mockContext,
+      '',
+    )) as OpenCustomDialogActionReturn;
+    const component = result.component as ReactElement<RewindViewerProps>;
+    const onRewind = component.props.onRewind;
+
+    await onRewind('msg-id-123', 'New Prompt', RewindOutcome.Cancel);
+
+    await waitFor(() => {
+      expect(mockRevertFileChanges).not.toHaveBeenCalled();
+      expect(mockRewindTo).not.toHaveBeenCalled();
+      expect(mockRemoveComponent).toHaveBeenCalled();
+    });
+    expect(mockSetInput).not.toHaveBeenCalled();
+  });
+
+  it('should handle onExit correctly', async () => {
+    const result = (await rewindCommand.action!(
+      mockContext,
+      '',
+    )) as OpenCustomDialogActionReturn;
+    const component = result.component as ReactElement<RewindViewerProps>;
+    const onExit = component.props.onExit;
+
+    onExit();
+
+    expect(mockRemoveComponent).toHaveBeenCalled();
+  });
+
+  it('should handle rewind error correctly', async () => {
+    const result = (await rewindCommand.action!(
+      mockContext,
+      '',
+    )) as OpenCustomDialogActionReturn;
+    const component = result.component as ReactElement<RewindViewerProps>;
+    const onRewind = component.props.onRewind;
+
+    mockRewindTo.mockImplementation(() => {
+      throw new Error('Rewind Failed');
+    });
+
+    await onRewind('msg-1', 'Prompt', RewindOutcome.RewindOnly);
+
+    await waitFor(() => {
+      expect(coreEvents.emitFeedback).toHaveBeenCalledWith(
+        'error',
+        'Rewind Failed',
+      );
+    });
+  });
+
+  it('should handle null conversation from rewindTo', async () => {
+    const result = (await rewindCommand.action!(
+      mockContext,
+      '',
+    )) as OpenCustomDialogActionReturn;
+    const component = result.component as ReactElement<RewindViewerProps>;
+    const onRewind = component.props.onRewind;
+
+    mockRewindTo.mockReturnValue(null);
+
+    await onRewind('msg-1', 'Prompt', RewindOutcome.RewindOnly);
+
+    await waitFor(() => {
+      expect(coreEvents.emitFeedback).toHaveBeenCalledWith(
+        'error',
+        'Could not fetch conversation file',
+      );
+      expect(mockRemoveComponent).toHaveBeenCalled();
+    });
+  });
+
+  it('should fail if config is missing', () => {
+    const context = { services: {} } as CommandContext;
+
+    const result = rewindCommand.action!(context, '');
+
+    expect(result).toEqual({
+      type: 'message',
+      messageType: 'error',
+      content: 'Config not found',
+    });
+  });
+
+  it('should fail if client is not initialized', () => {
+    const context = createMockCommandContext({
+      services: {
+        config: { getGeminiClient: () => undefined },
+      },
+    }) as unknown as CommandContext;
+
+    const result = rewindCommand.action!(context, '');
+
+    expect(result).toEqual({
+      type: 'message',
+      messageType: 'error',
+      content: 'Client not initialized',
+    });
+  });
+
+  it('should fail if recording service is unavailable', () => {
+    const context = createMockCommandContext({
+      services: {
+        config: {
+          getGeminiClient: () => ({ getChatRecordingService: () => undefined }),
+        },
+      },
+    }) as unknown as CommandContext;
+
+    const result = rewindCommand.action!(context, '');
+
+    expect(result).toEqual({
+      type: 'message',
+      messageType: 'error',
+      content: 'Recording service unavailable',
+    });
+  });
+
+  it('should return info if no conversation found', () => {
+    mockGetConversation.mockReturnValue(null);
+
+    const result = rewindCommand.action!(mockContext, '');
+
+    expect(result).toEqual({
+      type: 'message',
+      messageType: 'info',
+      content: 'No conversation found.',
+    });
+  });
+
+  it('should return info if no user interactions found', () => {
+    mockGetConversation.mockReturnValue({
+      messages: [{ id: 'msg-1', type: 'gemini', content: 'hello' }],
+      sessionId: 'test-session',
+    });
+
+    const result = rewindCommand.action!(mockContext, '');
+
+    expect(result).toEqual({
+      type: 'message',
+      messageType: 'info',
+      content: 'Nothing to rewind to.',
+    });
+  });
+});

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

@@ -0,0 +1,191 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import {
+  CommandKind,
+  type CommandContext,
+  type SlashCommand,
+} from './types.js';
+import { RewindViewer } from '../components/RewindViewer.js';
+import { type HistoryItem } from '../types.js';
+import { convertSessionToHistoryFormats } from '../hooks/useSessionBrowser.js';
+import { revertFileChanges } from '../utils/rewindFileOps.js';
+import { RewindOutcome } from '../components/RewindConfirmation.js';
+import { checkExhaustive } from '../../utils/checks.js';
+
+import type { Content } from '@google/genai';
+import type {
+  ChatRecordingService,
+  GeminiClient,
+} from '@google/gemini-cli-core';
+import { coreEvents, debugLogger } from '@google/gemini-cli-core';
+
+/**
+ * Helper function to handle the core logic of rewinding a conversation.
+ * This function encapsulates the steps needed to rewind the conversation,
+ * update the client and UI history, and clear the component.
+ *
+ * @param context The command context.
+ * @param client Gemini client
+ * @param recordingService The chat recording service.
+ * @param messageId The ID of the message to rewind to.
+ * @param newText The new text for the input field after rewinding.
+ */
+async function rewindConversation(
+  context: CommandContext,
+  client: GeminiClient,
+  recordingService: ChatRecordingService,
+  messageId: string,
+  newText: string,
+) {
+  try {
+    const conversation = recordingService.rewindTo(messageId);
+    if (!conversation) {
+      const errorMsg = 'Could not fetch conversation file';
+      debugLogger.error(errorMsg);
+      context.ui.removeComponent();
+      coreEvents.emitFeedback('error', errorMsg);
+      return;
+    }
+
+    // Convert to UI and Client formats
+    const { uiHistory, clientHistory } = convertSessionToHistoryFormats(
+      conversation.messages,
+    );
+
+    client.setHistory(clientHistory as Content[]);
+
+    // Reset context manager as we are rewinding history
+    await context.services.config?.getContextManager()?.refresh();
+
+    // Update UI History
+    // We generate IDs based on index for the rewind history
+    const startId = 1;
+    const historyWithIds = uiHistory.map(
+      (item, idx) =>
+        ({
+          ...item,
+          id: startId + idx,
+        }) as HistoryItem,
+    );
+
+    // 1. Remove component FIRST to avoid flicker and clear the stage
+    context.ui.removeComponent();
+
+    // 2. Load the rewound history and set the input
+    context.ui.loadHistory(historyWithIds, newText);
+  } catch (error) {
+    // If an error occurs, we still want to remove the component if possible
+    context.ui.removeComponent();
+    coreEvents.emitFeedback(
+      'error',
+      error instanceof Error ? error.message : 'Unknown error during rewind',
+    );
+  }
+}
+
+export const rewindCommand: SlashCommand = {
+  name: 'rewind',
+  description: 'Jump back to a specific message and restart the conversation',
+  kind: CommandKind.BUILT_IN,
+  action: (context) => {
+    const config = context.services.config;
+    if (!config)
+      return {
+        type: 'message',
+        messageType: 'error',
+        content: 'Config not found',
+      };
+
+    const client = config.getGeminiClient();
+    if (!client)
+      return {
+        type: 'message',
+        messageType: 'error',
+        content: 'Client not initialized',
+      };
+
+    const recordingService = client.getChatRecordingService();
+    if (!recordingService)
+      return {
+        type: 'message',
+        messageType: 'error',
+        content: 'Recording service unavailable',
+      };
+
+    const conversation = recordingService.getConversation();
+    if (!conversation)
+      return {
+        type: 'message',
+        messageType: 'info',
+        content: 'No conversation found.',
+      };
+
+    const hasUserInteractions = conversation.messages.some(
+      (msg) => msg.type === 'user',
+    );
+    if (!hasUserInteractions) {
+      return {
+        type: 'message',
+        messageType: 'info',
+        content: 'Nothing to rewind to.',
+      };
+    }
+
+    return {
+      type: 'custom_dialog',
+      component: (
+        <RewindViewer
+          conversation={conversation}
+          onExit={() => {
+            context.ui.removeComponent();
+          }}
+          onRewind={async (messageId, newText, outcome) => {
+            switch (outcome) {
+              case RewindOutcome.Cancel:
+                context.ui.removeComponent();
+                return;
+
+              case RewindOutcome.RevertOnly:
+                if (conversation) {
+                  await revertFileChanges(conversation, messageId);
+                }
+                context.ui.removeComponent();
+                coreEvents.emitFeedback('info', 'File changes reverted.');
+                return;
+
+              case RewindOutcome.RewindAndRevert:
+                if (conversation) {
+                  await revertFileChanges(conversation, messageId);
+                }
+                await rewindConversation(
+                  context,
+                  client,
+                  recordingService,
+                  messageId,
+                  newText,
+                );
+                return;
+
+              case RewindOutcome.RewindOnly:
+                await rewindConversation(
+                  context,
+                  client,
+                  recordingService,
+                  messageId,
+                  newText,
+                );
+                return;
+
+              default:
+                checkExhaustive(outcome);
+            }
+          }}
+        />
+      ),
+    };
+  },
+};

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

@@ -234,7 +234,34 @@ describe('skillsCommand', () => {
       expect(context.ui.addItem).toHaveBeenCalledWith(
         expect.objectContaining({
           type: MessageType.INFO,
-          text: 'Skill "skill1" disabled by adding it to the disabled list in workspace (/workspace) settings. Use "/skills reload" for it to take effect.',
+          text: 'Skill "skill1" disabled by adding it to the disabled list in workspace (/workspace) settings. You can run "/skills reload" to refresh your current instance.',
+        }),
+      );
+    });
+
+    it('should show reload guidance even if skill is already disabled', async () => {
+      const disableCmd = skillsCommand.subCommands!.find(
+        (s) => s.name === 'disable',
+      )!;
+      (
+        context.services.settings as unknown as { merged: MergedSettings }
+      ).merged = createTestMergedSettings({
+        skills: { enabled: true, disabled: ['skill1'] },
+      });
+      (
+        context.services.settings as unknown as {
+          workspace: { settings: { skills: { disabled: string[] } } };
+        }
+      ).workspace.settings = {
+        skills: { disabled: ['skill1'] },
+      };
+
+      await disableCmd.action!(context, 'skill1');
+
+      expect(context.ui.addItem).toHaveBeenCalledWith(
+        expect.objectContaining({
+          type: MessageType.INFO,
+          text: 'Skill "skill1" is already disabled. You can run "/skills reload" to refresh your current instance.',
         }),
       );
     });
@@ -269,7 +296,7 @@ describe('skillsCommand', () => {
       expect(context.ui.addItem).toHaveBeenCalledWith(
         expect.objectContaining({
           type: MessageType.INFO,
-          text: 'Skill "skill1" enabled by removing it from the disabled list in workspace (/workspace) and user (/user/settings.json) settings. Use "/skills reload" for it to take effect.',
+          text: 'Skill "skill1" enabled by removing it from the disabled list in workspace (/workspace) and user (/user/settings.json) settings. You can run "/skills reload" to refresh your current instance.',
         }),
       );
     });
@@ -308,7 +335,7 @@ describe('skillsCommand', () => {
       expect(context.ui.addItem).toHaveBeenCalledWith(
         expect.objectContaining({
           type: MessageType.INFO,
-          text: 'Skill "skill1" enabled by removing it from the disabled list in workspace (/workspace) and user (/user/settings.json) settings. Use "/skills reload" for it to take effect.',
+          text: 'Skill "skill1" enabled by removing it from the disabled list in workspace (/workspace) and user (/user/settings.json) settings. You can run "/skills reload" to refresh your current instance.',
         }),
       );
     });

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

@@ -112,8 +112,9 @@ async function disableAction(
     result,
     (label, path) => `${label} (${path})`,
   );
-  if (result.status === 'success') {
-    feedback += ' Use "/skills reload" for it to take effect.';
+  if (result.status === 'success' || result.status === 'no-op') {
+    feedback +=
+      ' You can run "/skills reload" to refresh your current instance.';
   }
 
   context.ui.addItem({
@@ -153,8 +154,9 @@ async function enableAction(
     result,
     (label, path) => `${label} (${path})`,
   );
-  if (result.status === 'success') {
-    feedback += ' Use "/skills reload" for it to take effect.';
+  if (result.status === 'success' || result.status === 'no-op') {
+    feedback +=
+      ' You can run "/skills reload" to refresh your current instance.';
   }
 
   context.ui.addItem({