fix(cli)!: Default to interactive mode for positional arguments (#16329)

Co-authored-by: Allen Hutchison <adh@google.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
@@ -35,14 +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.  **Preflight Check**: Before creating the PR, run the workspace preflight
+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.
 
-5.  **Create PR**: Use the `gh` CLI to create the PR. To avoid shell escaping
+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}`);
             }

.gitignore

@@ -55,6 +55,7 @@ gha-creds-*.json
 
 # Log files
 patch_output.log
+gemini-debug.log
 
 .genkit
 .gemini-clipboard/

GEMINI.md

@@ -64,9 +64,7 @@ powerful tool for developers.
 
 ## Documentation
 
+- Suggest documentation updates when code changes render existing documentation
+  obsolete or incomplete.
 - Located in the `docs/` directory.
-- Architecture overview: `docs/architecture.md`.
-- Contribution guide: `CONTRIBUTING.md`.
-- Documentation is organized via `docs/sidebar.json`.
-- Follows the
-  [Google Developer Documentation Style Guide](https://developers.google.com/style).
+- 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 (no Ctrl, no Shift)`                   |
-| Move the cursor to the end of the line.     | `Ctrl + E`<br />`End (no Ctrl, no Shift)`                    |
-| 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
 
@@ -35,12 +35,12 @@ 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
 
@@ -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 -->
 

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
 
@@ -113,14 +113,11 @@ 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` |
 
 ### HooksConfig
 

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/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`

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

@@ -202,7 +202,7 @@
     ]
   },
   {
-    "label": "Hooks",
+    "label": "Hooks (experimental)",
     "items": [
       {
         "label": "Introduction",
@@ -270,10 +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
@@ -1038,6 +1038,29 @@ gemini mcp remove my-server
 This will find and delete the "my-server" entry from the `mcpServers` object in
 the appropriate `settings.json` file based on the scope (`-s, --scope`).
 
+### Enabling/disabling a server (`gemini mcp enable`, `gemini mcp disable`)
+
+Temporarily disable an MCP server without removing its configuration, or
+re-enable a previously disabled server.
+
+**Commands:**
+
+```bash
+gemini mcp enable <name> [--session]
+gemini mcp disable <name> [--session]
+```
+
+**Options (flags):**
+
+- `--session`: Apply change only for this session (not persisted to file).
+
+Disabled servers appear in `/mcp` status as "Disabled" but won't connect or
+provide tools. Enablement state is stored in
+`~/.gemini/mcp-server-enablement.json`.
+
+The same commands are available as slash commands during an active session:
+`/mcp enable <name>` and `/mcp disable <name>`.
+
 ## Instructions
 
 Gemini CLI supports

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-system.test.ts

@@ -626,7 +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"');

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-preview.2",
+  "version": "0.27.0-nightly.20260121.97aac696f",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@google/gemini-cli",
-      "version": "0.26.0-preview.2",
+      "version": "0.27.0-nightly.20260121.97aac696f",
       "workspaces": [
         "packages/*"
       ],
@@ -18383,7 +18383,7 @@
     },
     "packages/a2a-server": {
       "name": "@google/gemini-cli-a2a-server",
-      "version": "0.26.0-preview.2",
+      "version": "0.27.0-nightly.20260121.97aac696f",
       "dependencies": {
         "@a2a-js/sdk": "^0.3.8",
         "@google-cloud/storage": "^7.16.0",
@@ -18693,7 +18693,7 @@
     },
     "packages/cli": {
       "name": "@google/gemini-cli",
-      "version": "0.26.0-preview.2",
+      "version": "0.27.0-nightly.20260121.97aac696f",
       "license": "Apache-2.0",
       "dependencies": {
         "@agentclientprotocol/sdk": "^0.12.0",
@@ -18797,7 +18797,7 @@
     },
     "packages/core": {
       "name": "@google/gemini-cli-core",
-      "version": "0.26.0-preview.2",
+      "version": "0.27.0-nightly.20260121.97aac696f",
       "license": "Apache-2.0",
       "dependencies": {
         "@a2a-js/sdk": "^0.3.8",
@@ -18956,7 +18956,7 @@
     },
     "packages/test-utils": {
       "name": "@google/gemini-cli-test-utils",
-      "version": "0.26.0-preview.2",
+      "version": "0.27.0-nightly.20260121.97aac696f",
       "license": "Apache-2.0",
       "dependencies": {
         "@google/gemini-cli-core": "file:../core",
@@ -18973,7 +18973,7 @@
     },
     "packages/vscode-ide-companion": {
       "name": "gemini-cli-vscode-ide-companion",
-      "version": "0.26.0-preview.2",
+      "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-preview.2",
+  "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-preview.2"
+    "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-preview.2",
+  "version": "0.27.0-nightly.20260121.97aac696f",
   "description": "Gemini CLI A2A Server",
   "repository": {
     "type": "git",

packages/a2a-server/src/commands/init.test.ts

@@ -26,10 +26,14 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
   };
 });
 
-vi.mock('node:fs', () => ({
-  existsSync: vi.fn(),
-  writeFileSync: vi.fn(),
-}));
+vi.mock('node:fs', async (importOriginal) => {
+  const actual = await importOriginal<typeof import('node:fs')>();
+  return {
+    ...actual,
+    existsSync: vi.fn(),
+    writeFileSync: vi.fn(),
+  };
+});
 
 vi.mock('../agent/executor.js', () => ({
   CoderAgentExecutor: vi.fn().mockImplementation(() => ({

packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@google/gemini-cli",
-  "version": "0.26.0-preview.2",
+  "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-preview.2"
+    "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.tsx

@@ -24,7 +24,10 @@ export const extensionsCommand: CommandModule = {
   describe: 'Manage Gemini CLI extensions.',
   builder: (yargs) =>
     yargs
-      .middleware(() => initializeOutputListenersAndFlush())
+      .middleware((argv) => {
+        initializeOutputListenersAndFlush();
+        argv['isCommand'] = true;
+      })
       .command(defer(installCommand, 'extensions'))
       .command(defer(uninstallCommand, 'extensions'))
       .command(defer(listCommand, 'extensions'))

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/mcp.test.ts

@@ -61,7 +61,7 @@ describe('mcp command', () => {
 
     (mcpCommand.builder as (y: Argv) => Argv)(mockYargs as unknown as Argv);
 
-    expect(mockYargs.command).toHaveBeenCalledTimes(3);
+    expect(mockYargs.command).toHaveBeenCalledTimes(5);
 
     // Verify that the specific subcommands are registered
     const commandCalls = mockYargs.command.mock.calls;
@@ -70,6 +70,8 @@ describe('mcp command', () => {
     expect(commandNames).toContain('add <name> <commandOrUrl> [args...]');
     expect(commandNames).toContain('remove <name>');
     expect(commandNames).toContain('list');
+    expect(commandNames).toContain('enable <name>');
+    expect(commandNames).toContain('disable <name>');
 
     expect(mockYargs.demandCommand).toHaveBeenCalledWith(
       1,

packages/cli/src/commands/mcp.ts

@@ -9,6 +9,7 @@ import type { CommandModule, Argv } from 'yargs';
 import { addCommand } from './mcp/add.js';
 import { removeCommand } from './mcp/remove.js';
 import { listCommand } from './mcp/list.js';
+import { enableCommand, disableCommand } from './mcp/enableDisable.js';
 import { initializeOutputListenersAndFlush } from '../gemini.js';
 import { defer } from '../deferred.js';
 
@@ -17,10 +18,15 @@ export const mcpCommand: CommandModule = {
   describe: 'Manage MCP servers',
   builder: (yargs: Argv) =>
     yargs
-      .middleware(() => initializeOutputListenersAndFlush())
+      .middleware((argv) => {
+        initializeOutputListenersAndFlush();
+        argv['isCommand'] = true;
+      })
       .command(defer(addCommand, 'mcp'))
       .command(defer(removeCommand, 'mcp'))
       .command(defer(listCommand, 'mcp'))
+      .command(defer(enableCommand, 'mcp'))
+      .command(defer(disableCommand, 'mcp'))
       .demandCommand(1, 'You need at least one command before continuing.')
       .version(false),
   handler: () => {

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

@@ -0,0 +1,169 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import type { CommandModule } from 'yargs';
+import { debugLogger } from '@google/gemini-cli-core';
+import {
+  McpServerEnablementManager,
+  canLoadServer,
+  normalizeServerId,
+} from '../../config/mcp/mcpServerEnablement.js';
+import { loadSettings } from '../../config/settings.js';
+import { exitCli } from '../utils.js';
+import { getMcpServersFromConfig } from './list.js';
+
+const GREEN = '\x1b[32m';
+const YELLOW = '\x1b[33m';
+const RED = '\x1b[31m';
+const RESET = '\x1b[0m';
+
+interface Args {
+  name: string;
+  session?: boolean;
+}
+
+async function handleEnable(args: Args): Promise<void> {
+  const manager = McpServerEnablementManager.getInstance();
+  const name = normalizeServerId(args.name);
+
+  // Check settings blocks
+  const settings = loadSettings();
+
+  // Get all servers including extensions
+  const servers = await getMcpServersFromConfig();
+  const normalizedServerNames = Object.keys(servers).map(normalizeServerId);
+  if (!normalizedServerNames.includes(name)) {
+    debugLogger.log(
+      `${RED}Error:${RESET} Server '${args.name}' not found. Use 'gemini mcp' to see available servers.`,
+    );
+    return;
+  }
+
+  // Check if server is from an extension
+  const serverKey = Object.keys(servers).find(
+    (key) => normalizeServerId(key) === name,
+  );
+  const server = serverKey ? servers[serverKey] : undefined;
+  if (server?.extension) {
+    debugLogger.log(
+      `${RED}Error:${RESET} Server '${args.name}' is provided by extension '${server.extension.name}'.`,
+    );
+    debugLogger.log(
+      `Use 'gemini extensions enable ${server.extension.name}' to manage this extension.`,
+    );
+    return;
+  }
+
+  const result = await canLoadServer(name, {
+    adminMcpEnabled: settings.merged.admin?.mcp?.enabled ?? true,
+    allowedList: settings.merged.mcp?.allowed,
+    excludedList: settings.merged.mcp?.excluded,
+  });
+
+  if (
+    !result.allowed &&
+    (result.blockType === 'allowlist' || result.blockType === 'excludelist')
+  ) {
+    debugLogger.log(`${RED}Error:${RESET} ${result.reason}`);
+    return;
+  }
+
+  if (args.session) {
+    manager.clearSessionDisable(name);
+    debugLogger.log(`${GREEN}✓${RESET} Session disable cleared for '${name}'.`);
+  } else {
+    await manager.enable(name);
+    debugLogger.log(`${GREEN}✓${RESET} MCP server '${name}' enabled.`);
+  }
+
+  if (result.blockType === 'admin') {
+    debugLogger.log(
+      `${YELLOW}Warning:${RESET} MCP servers are disabled by administrator.`,
+    );
+  }
+}
+
+async function handleDisable(args: Args): Promise<void> {
+  const manager = McpServerEnablementManager.getInstance();
+  const name = normalizeServerId(args.name);
+
+  // Get all servers including extensions
+  const servers = await getMcpServersFromConfig();
+  const normalizedServerNames = Object.keys(servers).map(normalizeServerId);
+  if (!normalizedServerNames.includes(name)) {
+    debugLogger.log(
+      `${RED}Error:${RESET} Server '${args.name}' not found. Use 'gemini mcp' to see available servers.`,
+    );
+    return;
+  }
+
+  // Check if server is from an extension
+  const serverKey = Object.keys(servers).find(
+    (key) => normalizeServerId(key) === name,
+  );
+  const server = serverKey ? servers[serverKey] : undefined;
+  if (server?.extension) {
+    debugLogger.log(
+      `${RED}Error:${RESET} Server '${args.name}' is provided by extension '${server.extension.name}'.`,
+    );
+    debugLogger.log(
+      `Use 'gemini extensions disable ${server.extension.name}' to manage this extension.`,
+    );
+    return;
+  }
+
+  if (args.session) {
+    manager.disableForSession(name);
+    debugLogger.log(
+      `${GREEN}✓${RESET} MCP server '${name}' disabled for this session.`,
+    );
+  } else {
+    await manager.disable(name);
+    debugLogger.log(`${GREEN}✓${RESET} MCP server '${name}' disabled.`);
+  }
+}
+
+export const enableCommand: CommandModule<object, Args> = {
+  command: 'enable <name>',
+  describe: 'Enable an MCP server',
+  builder: (yargs) =>
+    yargs
+      .positional('name', {
+        describe: 'MCP server name to enable',
+        type: 'string',
+        demandOption: true,
+      })
+      .option('session', {
+        describe: 'Clear session-only disable',
+        type: 'boolean',
+        default: false,
+      }),
+  handler: async (argv) => {
+    await handleEnable(argv as Args);
+    await exitCli();
+  },
+};
+
+export const disableCommand: CommandModule<object, Args> = {
+  command: 'disable <name>',
+  describe: 'Disable an MCP server',
+  builder: (yargs) =>
+    yargs
+      .positional('name', {
+        describe: 'MCP server name to disable',
+        type: 'string',
+        demandOption: true,
+      })
+      .option('session', {
+        describe: 'Disable for current session only',
+        type: 'boolean',
+        default: false,
+      }),
+  handler: async (argv) => {
+    await handleDisable(argv as Args);
+    await exitCli();
+  },
+};

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

@@ -24,7 +24,7 @@ const COLOR_YELLOW = '\u001b[33m';
 const COLOR_RED = '\u001b[31m';
 const RESET_COLOR = '\u001b[0m';
 
-async function getMcpServersFromConfig(): Promise<
+export async function getMcpServersFromConfig(): Promise<
   Record<string, MCPServerConfig>
 > {
   const settings = loadSettings();

packages/cli/src/commands/skills.tsx

@@ -19,7 +19,10 @@ export const skillsCommand: CommandModule = {
   describe: 'Manage agent skills.',
   builder: (yargs) =>
     yargs
-      .middleware(() => initializeOutputListenersAndFlush())
+      .middleware((argv) => {
+        initializeOutputListenersAndFlush();
+        argv['isCommand'] = true;
+      })
       .command(defer(listCommand, 'skills'))
       .command(defer(enableCommand, 'skills'))
       .command(defer(disableCommand, 'skills'))

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(() => {
@@ -357,6 +371,21 @@ describe('parseArguments', () => {
         }
       },
     );
+
+    it('should include a startup message when converting positional query to interactive prompt', async () => {
+      const originalIsTTY = process.stdin.isTTY;
+      process.stdin.isTTY = true;
+      process.argv = ['node', 'script.js', 'hello'];
+
+      try {
+        const argv = await parseArguments(createTestMergedSettings());
+        expect(argv.startupMessages).toContain(
+          'Positional arguments now default to interactive mode. To run in non-interactive mode, use the --prompt (-p) flag.',
+        );
+      } finally {
+        process.stdin.isTTY = originalIsTTY;
+      }
+    });
   });
 
   it.each([
@@ -534,6 +563,42 @@ 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 +704,31 @@ 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 +786,63 @@ 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', () => {
@@ -1826,7 +1968,7 @@ describe('loadCliConfig interactive', () => {
     expect(config.isInteractive()).toBe(false);
   });
 
-  it('should not be interactive if positional prompt words are provided with other flags', async () => {
+  it('should be interactive if positional prompt words are provided with other flags', async () => {
     process.stdin.isTTY = true;
     process.argv = ['node', 'script.js', '--model', 'gemini-2.5-pro', 'Hello'];
     const argv = await parseArguments(createTestMergedSettings());
@@ -1835,10 +1977,10 @@ describe('loadCliConfig interactive', () => {
       'test-session',
       argv,
     );
-    expect(config.isInteractive()).toBe(false);
+    expect(config.isInteractive()).toBe(true);
   });
 
-  it('should not be interactive if positional prompt words are provided with multiple flags', async () => {
+  it('should be interactive if positional prompt words are provided with multiple flags', async () => {
     process.stdin.isTTY = true;
     process.argv = [
       'node',
@@ -1854,13 +1996,13 @@ describe('loadCliConfig interactive', () => {
       'test-session',
       argv,
     );
-    expect(config.isInteractive()).toBe(false);
+    expect(config.isInteractive()).toBe(true);
     // Verify the question is preserved for one-shot execution
-    expect(argv.prompt).toBe('Hello world');
-    expect(argv.promptInteractive).toBeUndefined();
+    expect(argv.prompt).toBeUndefined();
+    expect(argv.promptInteractive).toBe('Hello world');
   });
 
-  it('should not be interactive if positional prompt words are provided with extensions flag', async () => {
+  it('should be interactive if positional prompt words are provided with extensions flag', async () => {
     process.stdin.isTTY = true;
     process.argv = ['node', 'script.js', '-e', 'none', 'hello'];
     const argv = await parseArguments(createTestMergedSettings());
@@ -1869,8 +2011,9 @@ describe('loadCliConfig interactive', () => {
       'test-session',
       argv,
     );
-    expect(config.isInteractive()).toBe(false);
+    expect(config.isInteractive()).toBe(true);
     expect(argv.query).toBe('hello');
+    expect(argv.promptInteractive).toBe('hello');
     expect(argv.extensions).toEqual(['none']);
   });
 
@@ -1883,9 +2026,9 @@ describe('loadCliConfig interactive', () => {
       'test-session',
       argv,
     );
-    expect(config.isInteractive()).toBe(false);
+    expect(config.isInteractive()).toBe(true);
     expect(argv.query).toBe('hello world how are you');
-    expect(argv.prompt).toBe('hello world how are you');
+    expect(argv.promptInteractive).toBe('hello world how are you');
   });
 
   it('should handle multiple positional words with flags', async () => {
@@ -1908,8 +2051,9 @@ describe('loadCliConfig interactive', () => {
       'test-session',
       argv,
     );
-    expect(config.isInteractive()).toBe(false);
+    expect(config.isInteractive()).toBe(true);
     expect(argv.query).toBe('write a function to sort array');
+    expect(argv.promptInteractive).toBe('write a function to sort array');
     expect(argv.model).toBe('gemini-2.5-pro');
   });
 
@@ -1945,8 +2089,9 @@ describe('loadCliConfig interactive', () => {
       'test-session',
       argv,
     );
-    expect(config.isInteractive()).toBe(false);
+    expect(config.isInteractive()).toBe(true);
     expect(argv.query).toBe('hello world how are you');
+    expect(argv.promptInteractive).toBe('hello world how are you');
     expect(argv.extensions).toEqual(['none']);
   });
 
@@ -2581,9 +2726,9 @@ describe('PolicyEngine nonInteractive wiring', () => {
     vi.restoreAllMocks();
   });
 
-  it('should set nonInteractive to true in one-shot mode', async () => {
+  it('should set nonInteractive to true when -p flag is used', async () => {
     process.stdin.isTTY = true;
-    process.argv = ['node', 'script.js', 'echo hello']; // Positional query makes it one-shot
+    process.argv = ['node', 'script.js', '-p', 'echo hello'];
     const argv = await parseArguments(createTestMergedSettings());
     const config = await loadCliConfig(
       createTestMergedSettings(),

packages/cli/src/config/config.ts

@@ -53,6 +53,7 @@ import { RESUME_LATEST } from '../utils/sessionUtils.js';
 import { isWorkspaceTrusted } from './trustedFolders.js';
 import { createPolicyEngineConfig } from './policy.js';
 import { ExtensionManager } from './extension-manager.js';
+import { McpServerEnablementManager } from './mcp/mcpServerEnablement.js';
 import type { ExtensionEvents } from '@google/gemini-cli-core/src/utils/extensionLoader.js';
 import { requestConsentNonInteractive } from './extensions/consent.js';
 import { promptForSetting } from './extensions/extensionSettings.js';
@@ -83,19 +84,23 @@ export interface CliArgs {
   outputFormat: string | undefined;
   fakeResponses: string | undefined;
   recordResponses: string | undefined;
+  startupMessages?: string[];
+  rawOutput: boolean | undefined;
+  acceptRawOutputRisk: boolean | undefined;
+  isCommand: boolean | undefined;
 }
 
 export async function parseArguments(
   settings: MergedSettings,
 ): Promise<CliArgs> {
   const rawArgv = hideBin(process.argv);
+  const startupMessages: string[] = [];
   const yargsInstance = yargs(rawArgv)
     .locale('en')
     .scriptName('gemini')
     .usage(
-      'Usage: gemini [options] [command]\n\nGemini CLI - Launch an interactive CLI, use -p/--prompt for non-interactive mode',
+      'Usage: gemini [options] [command]\n\nGemini CLI - Defaults to interactive mode. Use -p/--prompt for non-interactive (headless) mode.',
     )
-
     .option('debug', {
       alias: 'd',
       type: 'boolean',
@@ -106,7 +111,7 @@ export async function parseArguments(
       yargsInstance
         .positional('query', {
           description:
-            'Positional prompt. Defaults to one-shot; use -i/--prompt-interactive for interactive.',
+            'Initial prompt. Runs in interactive mode by default; use -p/--prompt for non-interactive.',
         })
         .option('model', {
           alias: 'm',
@@ -118,7 +123,8 @@ export async function parseArguments(
           alias: 'p',
           type: 'string',
           nargs: 1,
-          description: 'Prompt. Appended to input on stdin (if any).',
+          description:
+            'Run in non-interactive (headless) mode with the given prompt. Appended to input on stdin (if any).',
         })
         .option('prompt-interactive', {
           alias: 'i',
@@ -248,6 +254,15 @@ 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
@@ -330,11 +345,12 @@ export async function parseArguments(
     ? queryArg.join(' ')
     : queryArg;
 
-  // Route positional args: explicit -i flag -> interactive; else -> one-shot (even for @commands)
+  // -p/--prompt forces non-interactive mode; positional args default to interactive in TTY
   if (q && !result['prompt']) {
-    const hasExplicitInteractive =
-      result['promptInteractive'] === '' || !!result['promptInteractive'];
-    if (hasExplicitInteractive) {
+    if (process.stdin.isTTY) {
+      startupMessages.push(
+        'Positional arguments now default to interactive mode. To run in non-interactive mode, use the --prompt (-p) flag.',
+      );
       result['promptInteractive'] = q;
     } else {
       result['prompt'] = q;
@@ -343,6 +359,7 @@ export async function parseArguments(
 
   // Keep CliArgs.query as a string for downstream typing
   (result as Record<string, unknown>)['query'] = q || undefined;
+  (result as Record<string, unknown>)['startupMessages'] = startupMessages;
 
   // The import format is now only controlled by settings.memoryImportFormat
   // We no longer accept it as a CLI argument
@@ -465,7 +482,9 @@ 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,
@@ -559,12 +578,12 @@ export async function loadCliConfig(
     throw err;
   }
 
-  // Interactive mode: explicit -i flag or (TTY + no args + no -p flag)
-  const hasQuery = !!argv.query;
+  // -p/--prompt forces non-interactive (headless) mode
+  // -i/--prompt-interactive forces interactive mode with an initial prompt
   const interactive =
     !!argv.promptInteractive ||
     !!argv.experimentalAcp ||
-    (process.stdin.isTTY && !hasQuery && !argv.prompt);
+    (process.stdin.isTTY && !argv.query && !argv.prompt && !argv.isCommand);
 
   const allowedTools = argv.allowedTools || settings.tools?.allowed || [];
   const allowedToolsSet = new Set(allowedTools);
@@ -652,6 +671,12 @@ export async function loadCliConfig(
   const extensionsEnabled = settings.admin?.extensions?.enabled ?? true;
   const adminSkillsEnabled = settings.admin?.skills?.enabled ?? true;
 
+  // Create MCP enablement manager and callbacks
+  const mcpEnablementManager = McpServerEnablementManager.getInstance();
+  const mcpEnablementCallbacks = mcpEnabled
+    ? mcpEnablementManager.getEnablementCallbacks()
+    : undefined;
+
   return new Config({
     sessionId,
     clientVersion: await getVersion(),
@@ -673,6 +698,7 @@ export async function loadCliConfig(
     toolCallCommand: settings.tools?.callCommand,
     mcpServerCommand: mcpEnabled ? settings.mcp?.serverCommand : undefined,
     mcpServers: mcpEnabled ? settings.mcpServers : {},
+    mcpEnablementCallbacks,
     mcpEnabled,
     extensionsEnabled,
     agents: settings.agents,
@@ -751,14 +777,13 @@ 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:

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');
           }
         }
       }

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;
 }
 
 /**
@@ -119,51 +122,54 @@ export const defaultKeyBindings: KeyBindingConfig = {
   // Cursor Movement
   [Command.HOME]: [
     { key: 'a', ctrl: true },
-    { key: 'home', ctrl: false, shift: false },
+    { key: 'home', shift: false, ctrl: false },
   ],
   [Command.END]: [
     { key: 'e', ctrl: true },
-    { key: 'end', ctrl: false, shift: false },
+    { 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_UP]: [{ key: 'up', ctrl: false, command: false }],
-  [Command.MOVE_DOWN]: [{ key: 'down', ctrl: false, command: 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 }],
@@ -180,10 +186,10 @@ export const defaultKeyBindings: KeyBindingConfig = {
   [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' }],
 
@@ -203,14 +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' }],
@@ -220,33 +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' }],
@@ -313,6 +319,7 @@ export const commandCategories: readonly CommandCategory[] = [
       Command.REVERSE_SEARCH,
       Command.SUBMIT_REVERSE_SEARCH,
       Command.ACCEPT_SUGGESTION_REVERSE_SEARCH,
+      Command.REWIND,
     ],
   },
   {
@@ -352,7 +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,
@@ -409,6 +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.',
@@ -437,7 +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/mcp/index.ts

@@ -0,0 +1,17 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+export {
+  McpServerEnablementManager,
+  canLoadServer,
+  normalizeServerId,
+  isInSettingsList,
+  type McpServerEnablementState,
+  type McpServerEnablementConfig,
+  type McpServerDisplayState,
+  type EnablementCallbacks,
+  type ServerLoadResult,
+} from './mcpServerEnablement.js';

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

@@ -0,0 +1,188 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import fs from 'node:fs/promises';
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+
+vi.mock('@google/gemini-cli-core', async (importOriginal) => {
+  const actual =
+    await importOriginal<typeof import('@google/gemini-cli-core')>();
+  return {
+    ...actual,
+    Storage: {
+      ...actual.Storage,
+      getGlobalGeminiDir: () => '/virtual-home/.gemini',
+    },
+  };
+});
+
+import {
+  McpServerEnablementManager,
+  canLoadServer,
+  normalizeServerId,
+  isInSettingsList,
+  type EnablementCallbacks,
+} from './mcpServerEnablement.js';
+
+let inMemoryFs: Record<string, string> = {};
+
+function createMockEnablement(
+  sessionDisabled: boolean,
+  fileEnabled: boolean,
+): EnablementCallbacks {
+  return {
+    isSessionDisabled: () => sessionDisabled,
+    isFileEnabled: () => Promise.resolve(fileEnabled),
+  };
+}
+
+function setupFsMocks(): void {
+  vi.spyOn(fs, 'readFile').mockImplementation(async (filePath) => {
+    const content = inMemoryFs[filePath.toString()];
+    if (content === undefined) {
+      const error = new Error(`ENOENT: ${filePath}`);
+      (error as NodeJS.ErrnoException).code = 'ENOENT';
+      throw error;
+    }
+    return content;
+  });
+  vi.spyOn(fs, 'writeFile').mockImplementation(async (filePath, data) => {
+    inMemoryFs[filePath.toString()] = data.toString();
+  });
+  vi.spyOn(fs, 'mkdir').mockImplementation(async () => undefined);
+}
+
+describe('McpServerEnablementManager', () => {
+  let manager: McpServerEnablementManager;
+
+  beforeEach(() => {
+    inMemoryFs = {};
+    setupFsMocks();
+    McpServerEnablementManager.resetInstance();
+    manager = McpServerEnablementManager.getInstance();
+  });
+
+  afterEach(() => {
+    vi.restoreAllMocks();
+    McpServerEnablementManager.resetInstance();
+  });
+
+  it('should enable/disable servers with persistence', async () => {
+    expect(await manager.isFileEnabled('server')).toBe(true);
+    await manager.disable('server');
+    expect(await manager.isFileEnabled('server')).toBe(false);
+    await manager.enable('server');
+    expect(await manager.isFileEnabled('server')).toBe(true);
+  });
+
+  it('should handle session disable separately', async () => {
+    manager.disableForSession('server');
+    expect(manager.isSessionDisabled('server')).toBe(true);
+    expect(await manager.isFileEnabled('server')).toBe(true);
+    expect(await manager.isEffectivelyEnabled('server')).toBe(false);
+    manager.clearSessionDisable('server');
+    expect(await manager.isEffectivelyEnabled('server')).toBe(true);
+  });
+
+  it('should be case-insensitive', async () => {
+    await manager.disable('PlayWright');
+    expect(await manager.isFileEnabled('playwright')).toBe(false);
+  });
+
+  it('should return correct display state', async () => {
+    await manager.disable('file-disabled');
+    manager.disableForSession('session-disabled');
+
+    expect(await manager.getDisplayState('enabled')).toEqual({
+      enabled: true,
+      isSessionDisabled: false,
+      isPersistentDisabled: false,
+    });
+    expect(
+      (await manager.getDisplayState('file-disabled')).isPersistentDisabled,
+    ).toBe(true);
+    expect(
+      (await manager.getDisplayState('session-disabled')).isSessionDisabled,
+    ).toBe(true);
+  });
+
+  it('should share session state across getInstance calls', () => {
+    const instance1 = McpServerEnablementManager.getInstance();
+    const instance2 = McpServerEnablementManager.getInstance();
+
+    instance1.disableForSession('test-server');
+
+    expect(instance2.isSessionDisabled('test-server')).toBe(true);
+    expect(instance1).toBe(instance2);
+  });
+});
+
+describe('canLoadServer', () => {
+  it('blocks when admin has disabled MCP', async () => {
+    const result = await canLoadServer('s', { adminMcpEnabled: false });
+    expect(result.blockType).toBe('admin');
+  });
+
+  it('blocks when server is not in allowlist', async () => {
+    const result = await canLoadServer('s', {
+      adminMcpEnabled: true,
+      allowedList: ['other'],
+    });
+    expect(result.blockType).toBe('allowlist');
+  });
+
+  it('blocks when server is in excludelist', async () => {
+    const result = await canLoadServer('s', {
+      adminMcpEnabled: true,
+      excludedList: ['s'],
+    });
+    expect(result.blockType).toBe('excludelist');
+  });
+
+  it('blocks when server is session-disabled', async () => {
+    const result = await canLoadServer('s', {
+      adminMcpEnabled: true,
+      enablement: createMockEnablement(true, true),
+    });
+    expect(result.blockType).toBe('session');
+  });
+
+  it('blocks when server is file-disabled', async () => {
+    const result = await canLoadServer('s', {
+      adminMcpEnabled: true,
+      enablement: createMockEnablement(false, false),
+    });
+    expect(result.blockType).toBe('enablement');
+  });
+
+  it('allows when admin MCP is enabled and no restrictions', async () => {
+    const result = await canLoadServer('s', { adminMcpEnabled: true });
+    expect(result.allowed).toBe(true);
+  });
+
+  it('allows when server passes all checks', async () => {
+    const result = await canLoadServer('s', {
+      adminMcpEnabled: true,
+      allowedList: ['s'],
+      enablement: createMockEnablement(false, true),
+    });
+    expect(result.allowed).toBe(true);
+  });
+});
+
+describe('helper functions', () => {
+  it('normalizeServerId lowercases and trims', () => {
+    expect(normalizeServerId('  PlayWright  ')).toBe('playwright');
+  });
+
+  it('isInSettingsList supports ext: backward compat', () => {
+    expect(isInSettingsList('playwright', ['playwright']).found).toBe(true);
+    expect(isInSettingsList('ext:github:mcp', ['mcp']).found).toBe(true);
+    expect(
+      isInSettingsList('ext:github:mcp', ['mcp']).deprecationWarning,
+    ).toBeTruthy();
+  });
+});

packages/cli/src/config/mcp/mcpServerEnablement.ts

@@ -0,0 +1,357 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import fs from 'node:fs/promises';
+import path from 'node:path';
+import { Storage, coreEvents } from '@google/gemini-cli-core';
+
+/**
+ * Stored in JSON file - represents persistent enablement state.
+ */
+export interface McpServerEnablementState {
+  enabled: boolean;
+}
+
+/**
+ * File config format - map of server ID to enablement state.
+ */
+export interface McpServerEnablementConfig {
+  [serverId: string]: McpServerEnablementState;
+}
+
+/**
+ * For UI display - combines file and session state.
+ */
+export interface McpServerDisplayState {
+  /** Effective state (considering session override) */
+  enabled: boolean;
+  /** True if disabled via --session flag */
+  isSessionDisabled: boolean;
+  /** True if disabled in file */
+  isPersistentDisabled: boolean;
+}
+
+/**
+ * Callback types for enablement checks (passed from CLI to core).
+ */
+export interface EnablementCallbacks {
+  isSessionDisabled: (serverId: string) => boolean;
+  isFileEnabled: (serverId: string) => Promise<boolean>;
+}
+
+/**
+ * Result of canLoadServer check.
+ */
+export interface ServerLoadResult {
+  allowed: boolean;
+  reason?: string;
+  blockType?: 'admin' | 'allowlist' | 'excludelist' | 'session' | 'enablement';
+}
+
+/**
+ * Normalize a server ID to canonical lowercase form.
+ */
+export function normalizeServerId(serverId: string): string {
+  return serverId.toLowerCase().trim();
+}
+
+/**
+ * Check if a server ID is in a settings list (with backward compatibility).
+ * Handles case-insensitive matching and plain name fallback for ext: servers.
+ */
+export function isInSettingsList(
+  serverId: string,
+  list: string[],
+): { found: boolean; deprecationWarning?: string } {
+  const normalizedId = normalizeServerId(serverId);
+  const normalizedList = list.map(normalizeServerId);
+
+  // Exact canonical match
+  if (normalizedList.includes(normalizedId)) {
+    return { found: true };
+  }
+
+  // Backward compat: for ext: servers, check if plain name matches
+  if (normalizedId.startsWith('ext:')) {
+    const plainName = normalizedId.split(':').pop();
+    if (plainName && normalizedList.includes(plainName)) {
+      return {
+        found: true,
+        deprecationWarning:
+          `Settings reference '${plainName}' matches extension server '${serverId}'. ` +
+          `Update your settings to use the full identifier '${serverId}' instead.`,
+      };
+    }
+  }
+
+  return { found: false };
+}
+
+/**
+ * Single source of truth for whether a server can be loaded.
+ * Used by: isAllowedMcpServer(), connectServer(), CLI handlers, slash handlers.
+ *
+ * Uses callbacks instead of direct enablementManager reference to keep
+ * packages/core independent of packages/cli.
+ */
+export async function canLoadServer(
+  serverId: string,
+  config: {
+    adminMcpEnabled: boolean;
+    allowedList?: string[];
+    excludedList?: string[];
+    enablement?: EnablementCallbacks;
+  },
+): Promise<ServerLoadResult> {
+  const normalizedId = normalizeServerId(serverId);
+
+  // 1. Admin kill switch
+  if (!config.adminMcpEnabled) {
+    return {
+      allowed: false,
+      reason:
+        'MCP servers are disabled by administrator. Check admin settings or contact your admin.',
+      blockType: 'admin',
+    };
+  }
+
+  // 2. Allowlist check
+  if (config.allowedList && config.allowedList.length > 0) {
+    const { found, deprecationWarning } = isInSettingsList(
+      normalizedId,
+      config.allowedList,
+    );
+    if (deprecationWarning) {
+      coreEvents.emitFeedback('warning', deprecationWarning);
+    }
+    if (!found) {
+      return {
+        allowed: false,
+        reason: `Server '${serverId}' is not in mcp.allowed list. Add it to settings.json mcp.allowed array to enable.`,
+        blockType: 'allowlist',
+      };
+    }
+  }
+
+  // 3. Excludelist check
+  if (config.excludedList) {
+    const { found, deprecationWarning } = isInSettingsList(
+      normalizedId,
+      config.excludedList,
+    );
+    if (deprecationWarning) {
+      coreEvents.emitFeedback('warning', deprecationWarning);
+    }
+    if (found) {
+      return {
+        allowed: false,
+        reason: `Server '${serverId}' is blocked by mcp.excluded. Remove it from settings.json mcp.excluded array to enable.`,
+        blockType: 'excludelist',
+      };
+    }
+  }
+
+  // 4. Session disable check (before file-based enablement)
+  if (config.enablement?.isSessionDisabled(normalizedId)) {
+    return {
+      allowed: false,
+      reason: `Server '${serverId}' is disabled for this session. Run 'gemini mcp enable ${serverId} --session' to clear.`,
+      blockType: 'session',
+    };
+  }
+
+  // 5. File-based enablement check
+  if (
+    config.enablement &&
+    !(await config.enablement.isFileEnabled(normalizedId))
+  ) {
+    return {
+      allowed: false,
+      reason: `Server '${serverId}' is disabled. Run 'gemini mcp enable ${serverId}' to enable.`,
+      blockType: 'enablement',
+    };
+  }
+
+  return { allowed: true };
+}
+
+const MCP_ENABLEMENT_FILENAME = 'mcp-server-enablement.json';
+
+/**
+ * McpServerEnablementManager
+ *
+ * Manages the enabled/disabled state of MCP servers.
+ * Uses a simplified format compared to ExtensionEnablementManager.
+ * Supports both persistent (file) and session-only (in-memory) states.
+ *
+ * NOTE: Use getInstance() to get the singleton instance. This ensures
+ * session state (sessionDisabled Set) is shared across all code paths.
+ */
+export class McpServerEnablementManager {
+  private static instance: McpServerEnablementManager | null = null;
+
+  private readonly configFilePath: string;
+  private readonly configDir: string;
+  private readonly sessionDisabled = new Set<string>();
+
+  /**
+   * Get the singleton instance.
+   */
+  static getInstance(): McpServerEnablementManager {
+    if (!McpServerEnablementManager.instance) {
+      McpServerEnablementManager.instance = new McpServerEnablementManager();
+    }
+    return McpServerEnablementManager.instance;
+  }
+
+  /**
+   * Reset the singleton instance (for testing only).
+   */
+  static resetInstance(): void {
+    McpServerEnablementManager.instance = null;
+  }
+
+  constructor() {
+    this.configDir = Storage.getGlobalGeminiDir();
+    this.configFilePath = path.join(this.configDir, MCP_ENABLEMENT_FILENAME);
+  }
+
+  /**
+   * Check if server is enabled in FILE (persistent config only).
+   * Does NOT include session state.
+   */
+  async isFileEnabled(serverName: string): Promise<boolean> {
+    const config = await this.readConfig();
+    const state = config[normalizeServerId(serverName)];
+    return state?.enabled ?? true;
+  }
+
+  /**
+   * Check if server is session-disabled.
+   */
+  isSessionDisabled(serverName: string): boolean {
+    return this.sessionDisabled.has(normalizeServerId(serverName));
+  }
+
+  /**
+   * Check effective enabled state (combines file + session).
+   * Convenience method; canLoadServer() uses separate callbacks for granular blockType.
+   */
+  async isEffectivelyEnabled(serverName: string): Promise<boolean> {
+    if (this.isSessionDisabled(serverName)) {
+      return false;
+    }
+    return this.isFileEnabled(serverName);
+  }
+
+  /**
+   * Enable a server persistently.
+   * Removes the server from config file (defaults to enabled).
+   */
+  async enable(serverName: string): Promise<void> {
+    const normalizedName = normalizeServerId(serverName);
+    const config = await this.readConfig();
+
+    if (normalizedName in config) {
+      delete config[normalizedName];
+      await this.writeConfig(config);
+    }
+  }
+
+  /**
+   * Disable a server persistently.
+   * Adds server to config file with enabled: false.
+   */
+  async disable(serverName: string): Promise<void> {
+    const config = await this.readConfig();
+    config[normalizeServerId(serverName)] = { enabled: false };
+    await this.writeConfig(config);
+  }
+
+  /**
+   * Disable a server for current session only (in-memory).
+   */
+  disableForSession(serverName: string): void {
+    this.sessionDisabled.add(normalizeServerId(serverName));
+  }
+
+  /**
+   * Clear session disable for a server.
+   */
+  clearSessionDisable(serverName: string): void {
+    this.sessionDisabled.delete(normalizeServerId(serverName));
+  }
+
+  /**
+   * Get display state for a specific server (for UI).
+   */
+  async getDisplayState(serverName: string): Promise<McpServerDisplayState> {
+    const isSessionDisabled = this.isSessionDisabled(serverName);
+    const isPersistentDisabled = !(await this.isFileEnabled(serverName));
+
+    return {
+      enabled: !isSessionDisabled && !isPersistentDisabled,
+      isSessionDisabled,
+      isPersistentDisabled,
+    };
+  }
+
+  /**
+   * Get all display states (for UI listing).
+   */
+  async getAllDisplayStates(
+    serverIds: string[],
+  ): Promise<Record<string, McpServerDisplayState>> {
+    const result: Record<string, McpServerDisplayState> = {};
+    for (const serverId of serverIds) {
+      result[normalizeServerId(serverId)] =
+        await this.getDisplayState(serverId);
+    }
+    return result;
+  }
+
+  /**
+   * Get enablement callbacks for passing to core.
+   */
+  getEnablementCallbacks(): EnablementCallbacks {
+    return {
+      isSessionDisabled: (id) => this.isSessionDisabled(id),
+      isFileEnabled: (id) => this.isFileEnabled(id),
+    };
+  }
+
+  /**
+   * Read config from file asynchronously.
+   */
+  private async readConfig(): Promise<McpServerEnablementConfig> {
+    try {
+      const content = await fs.readFile(this.configFilePath, 'utf-8');
+      return JSON.parse(content) as McpServerEnablementConfig;
+    } catch (error) {
+      if (
+        error instanceof Error &&
+        'code' in error &&
+        error.code === 'ENOENT'
+      ) {
+        return {};
+      }
+      coreEvents.emitFeedback(
+        'error',
+        'Failed to read MCP server enablement config.',
+        error,
+      );
+      return {};
+    }
+  }
+
+  /**
+   * Write config to file asynchronously.
+   */
+  private async writeConfig(config: McpServerEnablementConfig): Promise<void> {
+    await fs.mkdir(this.configDir, { recursive: true });
+    await fs.writeFile(this.configFilePath, JSON.stringify(config, null, 2));
+  }
+}

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

@@ -2012,6 +2012,56 @@ describe('Settings Loading and Merging', () => {
       // 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', () => {

packages/cli/src/config/settings.ts

@@ -804,6 +804,14 @@ export function migrateDeprecatedSettings(
         anyModified = true;
       }
     }
+
+    // Migrate experimental agent settings
+    anyModified ||= migrateExperimentalSettings(
+      settings,
+      loadedSettings,
+      scope,
+      removeDeprecated,
+    );
   };
 
   processScope(SettingScope.User);
@@ -852,3 +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(

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',

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/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();
@@ -1151,6 +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({
@@ -1169,12 +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'];
     }
   });
 
@@ -1219,6 +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(
@@ -1232,14 +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

@@ -324,6 +324,12 @@ export async function main() {
   const argv = await parseArguments(settings.merged);
   parseArgsHandle?.end();
 
+  if (argv.startupMessages) {
+    argv.startupMessages.forEach((msg) => {
+      coreEvents.emitFeedback('info', msg);
+    });
+  }
+
   // Check for invalid input combinations early to prevent crashes
   if (argv.promptInteractive && !process.stdin.isTTY) {
     writeToStderr(
@@ -374,12 +380,12 @@ export async function main() {
   // the sandbox because the sandbox will interfere with the Oauth2 web
   // redirect.
   let initialAuthFailed = false;
-  if (
-    settings.merged.security.auth.selectedType &&
-    !settings.merged.security.auth.useExternal
-  ) {
+  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,
         );
@@ -390,7 +396,7 @@ 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,
@@ -668,9 +674,8 @@ 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;
         }
       }
     }
@@ -732,6 +737,7 @@ 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/mockCommandContext.ts

@@ -61,6 +61,8 @@ export const createMockCommandContext = (
       loadHistory: vi.fn(),
       toggleCorgiMode: vi.fn(),
       toggleVimEnabled: vi.fn(),
+      openAgentConfigDialog: vi.fn(),
+      closeAgentConfigDialog: vi.fn(),
       extensionsUpdateState: new Map(),
       setExtensionsUpdateState: vi.fn(),
       // eslint-disable-next-line @typescript-eslint/no-explicit-any

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(),
@@ -188,6 +198,7 @@ export const renderWithProviders = (
     config = configProxy as unknown as Config,
     useAlternateBuffer = true,
     uiActions,
+    persistentState,
   }: {
     shellFocus?: boolean;
     settings?: LoadedSettings;
@@ -197,6 +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(
@@ -217,6 +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) {
@@ -239,6 +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}>
@@ -247,20 +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>` },
+            ],
           });
         }
       }
@@ -676,6 +708,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       openSettingsDialog,
       openSessionBrowser,
       openModelDialog,
+      openAgentConfigDialog,
       openPermissionsDialog,
       quit: (messages: HistoryItem[]) => {
         setQuittingMessages(messages);
@@ -689,6 +722,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       toggleDebugProfiler,
       dispatchExtensionStateUpdate,
       addConfirmUpdateExtensionRequest,
+      setText: (text: string) => buffer.setText(text),
     }),
     [
       setAuthState,
@@ -697,6 +731,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       openSettingsDialog,
       openSessionBrowser,
       openModelDialog,
+      openAgentConfigDialog,
       setQuittingMessages,
       setDebugMessage,
       setShowPrivacyNotice,
@@ -705,6 +740,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       openPermissionsDialog,
       addConfirmUpdateExtensionRequest,
       toggleDebugProfiler,
+      buffer,
     ],
   );
 
@@ -812,6 +848,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
     pendingHistoryItems: pendingGeminiHistoryItems,
     thought,
     cancelOngoingRequest,
+    pendingToolCalls,
     handleApprovalModeChange,
     activePtyId,
     loopDetectionConfirmationRequest,
@@ -843,18 +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,
@@ -1233,13 +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) => {
@@ -1369,7 +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,
@@ -1385,7 +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,
@@ -1469,6 +1508,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
     isThemeDialogOpen ||
     isSettingsDialogOpen ||
     isModelDialogOpen ||
+    isAgentConfigDialogOpen ||
     isPermissionsDialogOpen ||
     isAuthenticating ||
     isAuthDialogOpen ||
@@ -1486,6 +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(),
   );
@@ -1552,6 +1602,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
       isSettingsDialogOpen,
       isSessionBrowserOpen,
       isModelDialogOpen,
+      isAgentConfigDialogOpen,
+      selectedAgentName,
+      selectedAgentDisplayName,
+      selectedAgentDefinition,
       isPermissionsDialogOpen,
       permissionsDialogProps,
       slashCommands,
@@ -1590,7 +1644,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       activeHooks,
       messageQueue,
       queueErrorMessage,
-      showAutoAcceptIndicator,
+      showApprovalModeIndicator,
       currentModel,
       userTier,
       proQuotaRequest,
@@ -1644,6 +1698,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
       isSettingsDialogOpen,
       isSessionBrowserOpen,
       isModelDialogOpen,
+      isAgentConfigDialogOpen,
+      selectedAgentName,
+      selectedAgentDisplayName,
+      selectedAgentDefinition,
       isPermissionsDialogOpen,
       permissionsDialogProps,
       slashCommands,
@@ -1682,7 +1740,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       activeHooks,
       messageQueue,
       queueErrorMessage,
-      showAutoAcceptIndicator,
+      showApprovalModeIndicator,
       userTier,
       proQuotaRequest,
       validationRequest,
@@ -1743,6 +1801,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
       exitPrivacyNotice,
       closeSettingsDialog,
       closeModelDialog,
+      openAgentConfigDialog,
+      closeAgentConfigDialog,
       openPermissionsDialog,
       closePermissionsDialog,
       setShellModeActive,
@@ -1784,6 +1844,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
       exitPrivacyNotice,
       closeSettingsDialog,
       closeModelDialog,
+      openAgentConfigDialog,
+      closeAgentConfigDialog,
       openPermissionsDialog,
       closePermissionsDialog,
       setShellModeActive,
@@ -1832,9 +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

@@ -218,6 +218,21 @@ describe('agentsCommand', () => {
     });
   });
 
+  it('should show an error if config is not available for enable', async () => {
+    const contextWithoutConfig = createMockCommandContext({
+      services: { config: null },
+    });
+    const enableCommand = agentsCommand.subCommands?.find(
+      (cmd) => cmd.name === 'enable',
+    );
+    const result = await enableCommand!.action!(contextWithoutConfig, 'test');
+    expect(result).toEqual({
+      type: 'message',
+      messageType: 'error',
+      content: 'Config not loaded.',
+    });
+  });
+
   it('should disable an agent successfully', async () => {
     const reloadSpy = vi.fn().mockResolvedValue(undefined);
     mockConfig.getAgentRegistry = vi.fn().mockReturnValue({
@@ -308,4 +323,130 @@ describe('agentsCommand', () => {
       content: 'Usage: /agents disable <agent-name>',
     });
   });
+
+  it('should show an error if config is not available for disable', async () => {
+    const contextWithoutConfig = createMockCommandContext({
+      services: { config: null },
+    });
+    const disableCommand = agentsCommand.subCommands?.find(
+      (cmd) => cmd.name === 'disable',
+    );
+    const result = await disableCommand!.action!(contextWithoutConfig, 'test');
+    expect(result).toEqual({
+      type: 'message',
+      messageType: 'error',
+      content: 'Config not loaded.',
+    });
+  });
+
+  describe('config sub-command', () => {
+    it('should open agent config dialog for a valid agent', async () => {
+      const mockDefinition = {
+        name: 'test-agent',
+        displayName: 'Test Agent',
+        description: 'test desc',
+      };
+      mockConfig.getAgentRegistry = vi.fn().mockReturnValue({
+        getDiscoveredDefinition: vi.fn().mockReturnValue(mockDefinition),
+      });
+
+      const configCommand = agentsCommand.subCommands?.find(
+        (cmd) => cmd.name === 'config',
+      );
+      expect(configCommand).toBeDefined();
+
+      const result = await configCommand!.action!(mockContext, 'test-agent');
+
+      expect(mockContext.ui.openAgentConfigDialog).not.toHaveBeenCalled();
+      expect(result).toEqual({
+        type: 'message',
+        messageType: 'info',
+        content:
+          "Configuration for 'test-agent' will be available in the next update.",
+      });
+    });
+
+    it('should use name if displayName is missing', async () => {
+      const mockDefinition = {
+        name: 'test-agent',
+        description: 'test desc',
+      };
+      mockConfig.getAgentRegistry = vi.fn().mockReturnValue({
+        getDiscoveredDefinition: vi.fn().mockReturnValue(mockDefinition),
+      });
+
+      const configCommand = agentsCommand.subCommands?.find(
+        (cmd) => cmd.name === 'config',
+      );
+      const result = await configCommand!.action!(mockContext, 'test-agent');
+
+      expect(result).toEqual({
+        type: 'message',
+        messageType: 'info',
+        content:
+          "Configuration for 'test-agent' will be available in the next update.",
+      });
+    });
+
+    it('should show error if agent is not found', async () => {
+      mockConfig.getAgentRegistry = vi.fn().mockReturnValue({
+        getDiscoveredDefinition: vi.fn().mockReturnValue(undefined),
+      });
+
+      const configCommand = agentsCommand.subCommands?.find(
+        (cmd) => cmd.name === 'config',
+      );
+      const result = await configCommand!.action!(mockContext, 'non-existent');
+
+      expect(result).toEqual({
+        type: 'message',
+        messageType: 'error',
+        content: "Agent 'non-existent' not found.",
+      });
+    });
+
+    it('should show usage error if no agent name provided', async () => {
+      const configCommand = agentsCommand.subCommands?.find(
+        (cmd) => cmd.name === 'config',
+      );
+      const result = await configCommand!.action!(mockContext, '  ');
+
+      expect(result).toEqual({
+        type: 'message',
+        messageType: 'error',
+        content: 'Usage: /agents config <agent-name>',
+      });
+    });
+
+    it('should show an error if config is not available', async () => {
+      const contextWithoutConfig = createMockCommandContext({
+        services: { config: null },
+      });
+      const configCommand = agentsCommand.subCommands?.find(
+        (cmd) => cmd.name === 'config',
+      );
+      const result = await configCommand!.action!(contextWithoutConfig, 'test');
+      expect(result).toEqual({
+        type: 'message',
+        messageType: 'error',
+        content: 'Config not loaded.',
+      });
+    });
+
+    it('should provide completions for discovered agents', async () => {
+      mockConfig.getAgentRegistry = vi.fn().mockReturnValue({
+        getAllDiscoveredAgentNames: vi
+          .fn()
+          .mockReturnValue(['agent1', 'agent2', 'other']),
+      });
+
+      const configCommand = agentsCommand.subCommands?.find(
+        (cmd) => cmd.name === 'config',
+      );
+      expect(configCommand?.completion).toBeDefined();
+
+      const completions = await configCommand!.completion!(mockContext, 'age');
+      expect(completions).toEqual(['agent1', 'agent2']);
+    });
+  });
 });

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

@@ -62,7 +62,13 @@ async function enableAction(
   args: string,
 ): Promise<SlashCommandActionReturn | void> {
   const { config, settings } = context.services;
-  if (!config) return;
+  if (!config) {
+    return {
+      type: 'message',
+      messageType: 'error',
+      content: 'Config not loaded.',
+    };
+  }
 
   const agentName = args.trim();
   if (!agentName) {
@@ -132,7 +138,13 @@ async function disableAction(
   args: string,
 ): Promise<SlashCommandActionReturn | void> {
   const { config, settings } = context.services;
-  if (!config) return;
+  if (!config) {
+    return {
+      type: 'message',
+      messageType: 'error',
+      content: 'Config not loaded.',
+    };
+  }
 
   const agentName = args.trim();
   if (!agentName) {
@@ -200,6 +212,53 @@ async function disableAction(
   };
 }
 
+async function configAction(
+  context: CommandContext,
+  args: string,
+): Promise<SlashCommandActionReturn | void> {
+  const { config } = context.services;
+  if (!config) {
+    return {
+      type: 'message',
+      messageType: 'error',
+      content: 'Config not loaded.',
+    };
+  }
+
+  const agentName = args.trim();
+  if (!agentName) {
+    return {
+      type: 'message',
+      messageType: 'error',
+      content: 'Usage: /agents config <agent-name>',
+    };
+  }
+
+  const agentRegistry = config.getAgentRegistry();
+  if (!agentRegistry) {
+    return {
+      type: 'message',
+      messageType: 'error',
+      content: 'Agent registry not found.',
+    };
+  }
+
+  const definition = agentRegistry.getDiscoveredDefinition(agentName);
+  if (!definition) {
+    return {
+      type: 'message',
+      messageType: 'error',
+      content: `Agent '${agentName}' not found.`,
+    };
+  }
+
+  return {
+    type: 'message',
+    messageType: 'info',
+    content: `Configuration for '${agentName}' will be available in the next update.`,
+  };
+}
+
 function completeAgentsToEnable(context: CommandContext, partialArg: string) {
   const { config, settings } = context.services;
   if (!config) return [];
@@ -221,6 +280,15 @@ function completeAgentsToDisable(context: CommandContext, partialArg: string) {
   return allAgents.filter((name: string) => name.startsWith(partialArg));
 }
 
+function completeAllAgents(context: CommandContext, partialArg: string) {
+  const { config } = context.services;
+  if (!config) return [];
+
+  const agentRegistry = config.getAgentRegistry();
+  const allAgents = agentRegistry?.getAllDiscoveredAgentNames() ?? [];
+  return allAgents.filter((name: string) => name.startsWith(partialArg));
+}
+
 const enableCommand: SlashCommand = {
   name: 'enable',
   description: 'Enable a disabled agent',
@@ -239,6 +307,15 @@ const disableCommand: SlashCommand = {
   completion: completeAgentsToDisable,
 };
 
+const configCommand: SlashCommand = {
+  name: 'config',
+  description: 'Configure an agent',
+  kind: CommandKind.BUILT_IN,
+  autoExecute: false,
+  action: configAction,
+  completion: completeAllAgents,
+};
+
 const agentsRefreshCommand: SlashCommand = {
   name: 'refresh',
   description: 'Reload the agent registry',
@@ -278,6 +355,7 @@ export const agentsCommand: SlashCommand = {
     agentsRefreshCommand,
     enableCommand,
     disableCommand,
+    configCommand,
   ],
   action: async (context: CommandContext, args) =>
     // Default to list if no subcommand is provided

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/initCommand.test.ts

@@ -13,10 +13,14 @@ import type { CommandContext } from './types.js';
 import type { SubmitPromptActionReturn } from '@google/gemini-cli-core';
 
 // Mock the 'fs' module
-vi.mock('fs', () => ({
-  existsSync: vi.fn(),
-  writeFileSync: vi.fn(),
-}));
+vi.mock('fs', async (importOriginal) => {
+  const actual = await importOriginal<typeof import('node:fs')>();
+  return {
+    ...actual,
+    existsSync: vi.fn(),
+    writeFileSync: vi.fn(),
+  };
+});
 
 describe('initCommand', () => {
   let mockContext: CommandContext;

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

@@ -23,6 +23,12 @@ import {
 } from '@google/gemini-cli-core';
 import { appEvents, AppEvent } from '../../utils/events.js';
 import { MessageType, type HistoryItemMcpStatus } from '../types.js';
+import {
+  McpServerEnablementManager,
+  normalizeServerId,
+  canLoadServer,
+} from '../../config/mcp/mcpServerEnablement.js';
+import { loadSettings } from '../../config/settings.js';
 
 const authCommand: SlashCommand = {
   name: 'auth',
@@ -241,6 +247,14 @@ const listAction = async (
     }
   }
 
+  // Get enablement state for all servers
+  const enablementManager = McpServerEnablementManager.getInstance();
+  const enablementState: HistoryItemMcpStatus['enablementState'] = {};
+  for (const serverName of serverNames) {
+    enablementState[serverName] =
+      await enablementManager.getDisplayState(serverName);
+  }
+
   const mcpStatusItem: HistoryItemMcpStatus = {
     type: MessageType.MCP_STATUS,
     servers: mcpServers,
@@ -263,6 +277,7 @@ const listAction = async (
       description: resource.description,
     })),
     authStatus,
+    enablementState,
     blockedServers: blockedMcpServers,
     discoveryInProgress,
     connectingServers,
@@ -346,6 +361,156 @@ const refreshCommand: SlashCommand = {
   },
 };
 
+async function handleEnableDisable(
+  context: CommandContext,
+  args: string,
+  enable: boolean,
+): Promise<MessageActionReturn> {
+  const { config } = context.services;
+  if (!config) {
+    return {
+      type: 'message',
+      messageType: 'error',
+      content: 'Config not loaded.',
+    };
+  }
+
+  const parts = args.trim().split(/\s+/);
+  const isSession = parts.includes('--session');
+  const serverName = parts.filter((p) => p !== '--session')[0];
+  const action = enable ? 'enable' : 'disable';
+
+  if (!serverName) {
+    return {
+      type: 'message',
+      messageType: 'error',
+      content: `Server name required. Usage: /mcp ${action} <server-name> [--session]`,
+    };
+  }
+
+  const name = normalizeServerId(serverName);
+
+  // Validate server exists
+  const servers = config.getMcpClientManager()?.getMcpServers() || {};
+  const normalizedServerNames = Object.keys(servers).map(normalizeServerId);
+  if (!normalizedServerNames.includes(name)) {
+    return {
+      type: 'message',
+      messageType: 'error',
+      content: `Server '${serverName}' not found. Use /mcp list to see available servers.`,
+    };
+  }
+
+  // Check if server is from an extension
+  const serverKey = Object.keys(servers).find(
+    (key) => normalizeServerId(key) === name,
+  );
+  const server = serverKey ? servers[serverKey] : undefined;
+  if (server?.extension) {
+    return {
+      type: 'message',
+      messageType: 'error',
+      content: `Server '${serverName}' is provided by extension '${server.extension.name}'.\nUse '/extensions ${action} ${server.extension.name}' to manage this extension.`,
+    };
+  }
+
+  const manager = McpServerEnablementManager.getInstance();
+
+  if (enable) {
+    const settings = loadSettings();
+    const result = await canLoadServer(name, {
+      adminMcpEnabled: settings.merged.admin?.mcp?.enabled ?? true,
+      allowedList: settings.merged.mcp?.allowed,
+      excludedList: settings.merged.mcp?.excluded,
+    });
+    if (
+      !result.allowed &&
+      (result.blockType === 'allowlist' || result.blockType === 'excludelist')
+    ) {
+      return {
+        type: 'message',
+        messageType: 'error',
+        content: result.reason ?? 'Blocked by settings.',
+      };
+    }
+    if (isSession) {
+      manager.clearSessionDisable(name);
+    } else {
+      await manager.enable(name);
+    }
+    if (result.blockType === 'admin') {
+      context.ui.addItem(
+        {
+          type: 'warning',
+          text: 'MCP disabled by admin. Will load when enabled.',
+        },
+        Date.now(),
+      );
+    }
+  } else {
+    if (isSession) {
+      manager.disableForSession(name);
+    } else {
+      await manager.disable(name);
+    }
+  }
+
+  const msg = `MCP server '${name}' ${enable ? 'enabled' : 'disabled'}${isSession ? ' for this session' : ''}.`;
+
+  const mcpClientManager = config.getMcpClientManager();
+  if (mcpClientManager) {
+    context.ui.addItem(
+      { type: 'info', text: 'Restarting MCP servers...' },
+      Date.now(),
+    );
+    await mcpClientManager.restart();
+  }
+  if (config.getGeminiClient()?.isInitialized())
+    await config.getGeminiClient().setTools();
+  context.ui.reloadCommands();
+
+  return { type: 'message', messageType: 'info', content: msg };
+}
+
+async function getEnablementCompletion(
+  context: CommandContext,
+  partialArg: string,
+  showEnabled: boolean,
+): Promise<string[]> {
+  const { config } = context.services;
+  if (!config) return [];
+  const servers = Object.keys(
+    config.getMcpClientManager()?.getMcpServers() || {},
+  );
+  const manager = McpServerEnablementManager.getInstance();
+  const results: string[] = [];
+  for (const n of servers) {
+    const state = await manager.getDisplayState(n);
+    if (state.enabled === showEnabled && n.startsWith(partialArg)) {
+      results.push(n);
+    }
+  }
+  return results;
+}
+
+const enableCommand: SlashCommand = {
+  name: 'enable',
+  description: 'Enable a disabled MCP server',
+  kind: CommandKind.BUILT_IN,
+  autoExecute: true,
+  action: (ctx, args) => handleEnableDisable(ctx, args, true),
+  completion: (ctx, arg) => getEnablementCompletion(ctx, arg, false),
+};
+
+const disableCommand: SlashCommand = {
+  name: 'disable',
+  description: 'Disable an MCP server',
+  kind: CommandKind.BUILT_IN,
+  autoExecute: true,
+  action: (ctx, args) => handleEnableDisable(ctx, args, false),
+  completion: (ctx, arg) => getEnablementCompletion(ctx, arg, true),
+};
+
 export const mcpCommand: SlashCommand = {
   name: 'mcp',
   description: 'Manage configured Model Context Protocol (MCP) servers',
@@ -357,6 +522,8 @@ export const mcpCommand: SlashCommand = {
     schemaCommand,
     authCommand,
     refreshCommand,
+    enableCommand,
+    disableCommand,
   ],
   action: async (context: CommandContext) => listAction(context),
 };

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({

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

@@ -15,6 +15,7 @@ import type {
   GitService,
   Logger,
   CommandActionReturn,
+  AgentDefinition,
 } from '@google/gemini-cli-core';
 import type { LoadedSettings } from '../../config/settings.js';
 import type { UseHistoryManagerReturn } from '../hooks/useHistoryManager.js';
@@ -66,13 +67,19 @@ export interface CommandContext {
      * Loads a new set of history items, replacing the current history.
      *
      * @param history The array of history items to load.
+     * @param postLoadInput Optional text to set in the input buffer after loading history.
      */
-    loadHistory: UseHistoryManagerReturn['loadHistory'];
+    loadHistory: (history: HistoryItem[], postLoadInput?: string) => void;
     /** Toggles a special display mode. */
     toggleCorgiMode: () => void;
     toggleDebugProfiler: () => void;
     toggleVimEnabled: () => Promise<boolean>;
     reloadCommands: () => void;
+    openAgentConfigDialog: (
+      name: string,
+      displayName: string,
+      definition: AgentDefinition,
+    ) => void;
     extensionsUpdateState: Map<string, ExtensionUpdateStatus>;
     dispatchExtensionStateUpdate: (action: ExtensionUpdateAction) => void;
     addConfirmUpdateExtensionRequest: (value: ConfirmationRequest) => void;
@@ -110,6 +117,7 @@ export interface OpenDialogActionReturn {
     | 'settings'
     | 'sessionBrowser'
     | 'model'
+    | 'agentConfig'
     | 'permissions';
 }
 

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

@@ -4,12 +4,15 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-import { describe, it, expect, vi } from 'vitest';
+import {
+  renderWithProviders,
+  persistentStateMock,
+} from '../../test-utils/render.js';
+import { describe, it, expect, vi, beforeEach } from 'vitest';
 import { AlternateBufferQuittingDisplay } from './AlternateBufferQuittingDisplay.js';
 import { ToolCallStatus } from '../types.js';
 import type { HistoryItem, HistoryItemWithoutId } from '../types.js';
 import { Text } from 'ink';
-import { renderWithProviders } from '../../test-utils/render.js';
 import type { Config } from '@google/gemini-cli-core';
 
 vi.mock('../utils/terminalSetup.js', () => ({
@@ -88,6 +91,7 @@ const mockConfig = {
   getModel: () => 'gemini-pro',
   getTargetDir: () => '/tmp',
   getDebugMode: () => false,
+  getIdeMode: () => false,
   getGeminiMdFileCount: () => 0,
   getExperiments: () => ({
     flags: {},
@@ -97,6 +101,9 @@ const mockConfig = {
 } as unknown as Config;
 
 describe('AlternateBufferQuittingDisplay', () => {
+  beforeEach(() => {
+    vi.clearAllMocks();
+  });
   const baseUIState = {
     terminalWidth: 80,
     mainAreaWidth: 80,
@@ -111,6 +118,7 @@ describe('AlternateBufferQuittingDisplay', () => {
   };
 
   it('renders with active and pending tool messages', () => {
+    persistentStateMock.setData({ tipsShown: 0 });
     const { lastFrame } = renderWithProviders(
       <AlternateBufferQuittingDisplay />,
       {
@@ -126,6 +134,7 @@ describe('AlternateBufferQuittingDisplay', () => {
   });
 
   it('renders with empty history and no pending items', () => {
+    persistentStateMock.setData({ tipsShown: 0 });
     const { lastFrame } = renderWithProviders(
       <AlternateBufferQuittingDisplay />,
       {
@@ -141,6 +150,7 @@ describe('AlternateBufferQuittingDisplay', () => {
   });
 
   it('renders with history but no pending items', () => {
+    persistentStateMock.setData({ tipsShown: 0 });
     const { lastFrame } = renderWithProviders(
       <AlternateBufferQuittingDisplay />,
       {
@@ -156,6 +166,7 @@ describe('AlternateBufferQuittingDisplay', () => {
   });
 
   it('renders with pending items but no history', () => {
+    persistentStateMock.setData({ tipsShown: 0 });
     const { lastFrame } = renderWithProviders(
       <AlternateBufferQuittingDisplay />,
       {
@@ -171,6 +182,7 @@ describe('AlternateBufferQuittingDisplay', () => {
   });
 
   it('renders with user and gemini messages', () => {
+    persistentStateMock.setData({ tipsShown: 0 });
     const history: HistoryItem[] = [
       { id: 1, type: 'user', text: 'Hello Gemini' },
       { id: 2, type: 'gemini', text: 'Hello User!' },

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

@@ -4,31 +4,20 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-import { renderWithProviders } from '../../test-utils/render.js';
+import {
+  renderWithProviders,
+  persistentStateMock,
+} from '../../test-utils/render.js';
 import { AppHeader } from './AppHeader.js';
-import { describe, it, expect, vi, beforeEach } from 'vitest';
+import { describe, it, expect, vi } from 'vitest';
 import { makeFakeConfig } from '@google/gemini-cli-core';
 import crypto from 'node:crypto';
 
-const persistentStateMock = vi.hoisted(() => ({
-  get: vi.fn(),
-  set: vi.fn(),
-}));
-
-vi.mock('../../utils/persistentState.js', () => ({
-  persistentState: persistentStateMock,
-}));
-
 vi.mock('../utils/terminalSetup.js', () => ({
   getTerminalProgram: () => null,
 }));
 
 describe('<AppHeader />', () => {
-  beforeEach(() => {
-    vi.clearAllMocks();
-    persistentStateMock.get.mockReturnValue({});
-  });
-
   it('should render the banner with default text', () => {
     const mockConfig = makeFakeConfig();
     const uiState = {
@@ -42,7 +31,10 @@ describe('<AppHeader />', () => {
 
     const { lastFrame, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
-      { config: mockConfig, uiState },
+      {
+        config: mockConfig,
+        uiState,
+      },
     );
 
     expect(lastFrame()).toContain('This is the default banner');
@@ -63,7 +55,10 @@ describe('<AppHeader />', () => {
 
     const { lastFrame, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
-      { config: mockConfig, uiState },
+      {
+        config: mockConfig,
+        uiState,
+      },
     );
 
     expect(lastFrame()).toContain('There are capacity issues');
@@ -83,7 +78,10 @@ describe('<AppHeader />', () => {
 
     const { lastFrame, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
-      { config: mockConfig, uiState },
+      {
+        config: mockConfig,
+        uiState,
+      },
     );
 
     expect(lastFrame()).not.toContain('Banner');
@@ -104,7 +102,10 @@ describe('<AppHeader />', () => {
 
     const { lastFrame, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
-      { config: mockConfig, uiState },
+      {
+        config: mockConfig,
+        uiState,
+      },
     );
 
     expect(lastFrame()).toContain('This is the default banner');
@@ -124,7 +125,10 @@ describe('<AppHeader />', () => {
 
     const { lastFrame, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
-      { config: mockConfig, uiState },
+      {
+        config: mockConfig,
+        uiState,
+      },
     );
 
     expect(lastFrame()).not.toContain('This is the default banner');
@@ -133,7 +137,6 @@ describe('<AppHeader />', () => {
   });
 
   it('should not render the default banner if shown count is 5 or more', () => {
-    persistentStateMock.get.mockReturnValue(5);
     const mockConfig = makeFakeConfig();
     const uiState = {
       history: [],
@@ -143,9 +146,21 @@ describe('<AppHeader />', () => {
       },
     };
 
+    persistentStateMock.setData({
+      defaultBannerShownCount: {
+        [crypto
+          .createHash('sha256')
+          .update(uiState.bannerData.defaultText)
+          .digest('hex')]: 5,
+      },
+    });
+
     const { lastFrame, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
-      { config: mockConfig, uiState },
+      {
+        config: mockConfig,
+        uiState,
+      },
     );
 
     expect(lastFrame()).not.toContain('This is the default banner');
@@ -154,7 +169,6 @@ describe('<AppHeader />', () => {
   });
 
   it('should increment the version count when default banner is displayed', () => {
-    persistentStateMock.get.mockReturnValue({});
     const mockConfig = makeFakeConfig();
     const uiState = {
       history: [],
@@ -164,6 +178,10 @@ describe('<AppHeader />', () => {
       },
     };
 
+    // Set tipsShown to 10 or more to prevent Tips from incrementing its count
+    // and interfering with the expected persistentState.set call.
+    persistentStateMock.setData({ tipsShown: 10 });
+
     const { unmount } = renderWithProviders(<AppHeader version="1.0.0" />, {
       config: mockConfig,
       uiState,
@@ -194,10 +212,87 @@ describe('<AppHeader />', () => {
 
     const { lastFrame, unmount } = renderWithProviders(
       <AppHeader version="1.0.0" />,
-      { config: mockConfig, uiState },
+      {
+        config: mockConfig,
+        uiState,
+      },
     );
 
     expect(lastFrame()).not.toContain('First line\\nSecond line');
     unmount();
   });
+
+  it('should render Tips when tipsShown is less than 10', () => {
+    const mockConfig = makeFakeConfig();
+    const uiState = {
+      history: [],
+      bannerData: {
+        defaultText: 'First line\\nSecond line',
+        warningText: '',
+      },
+      bannerVisible: true,
+    };
+
+    persistentStateMock.setData({ tipsShown: 5 });
+
+    const { lastFrame, unmount } = renderWithProviders(
+      <AppHeader version="1.0.0" />,
+      {
+        config: mockConfig,
+        uiState,
+      },
+    );
+
+    expect(lastFrame()).toContain('Tips');
+    expect(persistentStateMock.set).toHaveBeenCalledWith('tipsShown', 6);
+    unmount();
+  });
+
+  it('should NOT render Tips when tipsShown is 10 or more', () => {
+    const mockConfig = makeFakeConfig();
+
+    persistentStateMock.setData({ tipsShown: 10 });
+
+    const { lastFrame, unmount } = renderWithProviders(
+      <AppHeader version="1.0.0" />,
+      {
+        config: mockConfig,
+      },
+    );
+
+    expect(lastFrame()).not.toContain('Tips');
+    unmount();
+  });
+
+  it('should show tips until they have been shown 10 times (persistence flow)', () => {
+    persistentStateMock.setData({ tipsShown: 9 });
+
+    const mockConfig = makeFakeConfig();
+    const uiState = {
+      history: [],
+      bannerData: {
+        defaultText: 'First line\\nSecond line',
+        warningText: '',
+      },
+      bannerVisible: true,
+    };
+
+    // First session
+    const session1 = renderWithProviders(<AppHeader version="1.0.0" />, {
+      config: mockConfig,
+      uiState,
+    });
+
+    expect(session1.lastFrame()).toContain('Tips');
+    expect(persistentStateMock.get('tipsShown')).toBe(10);
+    session1.unmount();
+
+    // Second session - state is persisted in the fake
+    const session2 = renderWithProviders(<AppHeader version="1.0.0" />, {
+      config: mockConfig,
+    });
+
+    expect(session2.lastFrame()).not.toContain('Tips');
+    session2.unmount();
+  });
 });

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

@@ -12,6 +12,7 @@ import { useConfig } from '../contexts/ConfigContext.js';
 import { useUIState } from '../contexts/UIStateContext.js';
 import { Banner } from './Banner.js';
 import { useBanner } from '../hooks/useBanner.js';
+import { useTips } from '../hooks/useTips.js';
 
 interface AppHeaderProps {
   version: string;
@@ -23,6 +24,7 @@ export const AppHeader = ({ version }: AppHeaderProps) => {
   const { nightly, mainAreaWidth, bannerData, bannerVisible } = useUIState();
 
   const { bannerText } = useBanner(bannerData, config);
+  const { showTips } = useTips();
 
   return (
     <Box flexDirection="column">
@@ -38,9 +40,8 @@ export const AppHeader = ({ version }: AppHeaderProps) => {
           )}
         </>
       )}
-      {!(settings.merged.ui.hideTips || config.getScreenReader()) && (
-        <Tips config={config} />
-      )}
+      {!(settings.merged.ui.hideTips || config.getScreenReader()) &&
+        showTips && <Tips config={config} />}
     </Box>
   );
 };

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

@@ -5,23 +5,32 @@
  */
 
 import { render } from '../../test-utils/render.js';
-import { AutoAcceptIndicator } from './AutoAcceptIndicator.js';
+import { ApprovalModeIndicator } from './ApprovalModeIndicator.js';
 import { describe, it, expect } from 'vitest';
 import { ApprovalMode } from '@google/gemini-cli-core';
 
-describe('AutoAcceptIndicator', () => {
+describe('ApprovalModeIndicator', () => {
   it('renders correctly for AUTO_EDIT mode', () => {
     const { lastFrame } = render(
-      <AutoAcceptIndicator approvalMode={ApprovalMode.AUTO_EDIT} />,
+      <ApprovalModeIndicator approvalMode={ApprovalMode.AUTO_EDIT} />,
     );
     const output = lastFrame();
     expect(output).toContain('accepting edits');
-    expect(output).toContain('(shift + tab to toggle)');
+    expect(output).toContain('(shift + tab to cycle)');
+  });
+
+  it('renders correctly for PLAN mode', () => {
+    const { lastFrame } = render(
+      <ApprovalModeIndicator approvalMode={ApprovalMode.PLAN} />,
+    );
+    const output = lastFrame();
+    expect(output).toContain('plan mode');
+    expect(output).toContain('(shift + tab to cycle)');
   });
 
   it('renders correctly for YOLO mode', () => {
     const { lastFrame } = render(
-      <AutoAcceptIndicator approvalMode={ApprovalMode.YOLO} />,
+      <ApprovalModeIndicator approvalMode={ApprovalMode.YOLO} />,
     );
     const output = lastFrame();
     expect(output).toContain('YOLO mode');
@@ -30,7 +39,7 @@ describe('AutoAcceptIndicator', () => {
 
   it('renders nothing for DEFAULT mode', () => {
     const { lastFrame } = render(
-      <AutoAcceptIndicator approvalMode={ApprovalMode.DEFAULT} />,
+      <ApprovalModeIndicator approvalMode={ApprovalMode.DEFAULT} />,
     );
     const output = lastFrame();
     expect(output).not.toContain('accepting edits');

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

@@ -9,11 +9,11 @@ import { Box, Text } from 'ink';
 import { theme } from '../semantic-colors.js';
 import { ApprovalMode } from '@google/gemini-cli-core';
 
-interface AutoAcceptIndicatorProps {
+interface ApprovalModeIndicatorProps {
   approvalMode: ApprovalMode;
 }
 
-export const AutoAcceptIndicator: React.FC<AutoAcceptIndicatorProps> = ({
+export const ApprovalModeIndicator: React.FC<ApprovalModeIndicatorProps> = ({
   approvalMode,
 }) => {
   let textColor = '';
@@ -24,7 +24,12 @@ export const AutoAcceptIndicator: React.FC<AutoAcceptIndicatorProps> = ({
     case ApprovalMode.AUTO_EDIT:
       textColor = theme.status.warning;
       textContent = 'accepting edits';
-      subText = ' (shift + tab to toggle)';
+      subText = ' (shift + tab to cycle)';
+      break;
+    case ApprovalMode.PLAN:
+      textColor = theme.status.success;
+      textContent = 'plan mode';
+      subText = ' (shift + tab to cycle)';
       break;
     case ApprovalMode.YOLO:
       textColor = theme.status.error;

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

@@ -41,8 +41,8 @@ vi.mock('./HookStatusDisplay.js', () => ({
   HookStatusDisplay: () => <Text>HookStatusDisplay</Text>,
 }));
 
-vi.mock('./AutoAcceptIndicator.js', () => ({
-  AutoAcceptIndicator: () => <Text>AutoAcceptIndicator</Text>,
+vi.mock('./ApprovalModeIndicator.js', () => ({
+  ApprovalModeIndicator: () => <Text>ApprovalModeIndicator</Text>,
 }));
 
 vi.mock('./ShellModeIndicator.js', () => ({
@@ -95,7 +95,7 @@ const createMockUIState = (overrides: Partial<UIState> = {}): UIState =>
   ({
     streamingState: null,
     contextFileNames: [],
-    showAutoAcceptIndicator: ApprovalMode.DEFAULT,
+    showApprovalModeIndicator: ApprovalMode.DEFAULT,
     messageQueue: [],
     showErrorDetails: false,
     constrainHeight: false,
@@ -419,15 +419,15 @@ describe('Composer', () => {
       expect(lastFrame()).not.toContain('InputPrompt');
     });
 
-    it('shows AutoAcceptIndicator when approval mode is not default and shell mode is inactive', () => {
+    it('shows ApprovalModeIndicator when approval mode is not default and shell mode is inactive', () => {
       const uiState = createMockUIState({
-        showAutoAcceptIndicator: ApprovalMode.YOLO,
+        showApprovalModeIndicator: ApprovalMode.YOLO,
         shellModeActive: false,
       });
 
       const { lastFrame } = renderComposer(uiState);
 
-      expect(lastFrame()).toContain('AutoAcceptIndicator');
+      expect(lastFrame()).toContain('ApprovalModeIndicator');
     });
 
     it('shows ShellModeIndicator when shell mode is active', () => {

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

@@ -8,7 +8,7 @@ import { useState } from 'react';
 import { Box, useIsScreenReaderEnabled } from 'ink';
 import { LoadingIndicator } from './LoadingIndicator.js';
 import { StatusDisplay } from './StatusDisplay.js';
-import { AutoAcceptIndicator } from './AutoAcceptIndicator.js';
+import { ApprovalModeIndicator } from './ApprovalModeIndicator.js';
 import { ShellModeIndicator } from './ShellModeIndicator.js';
 import { DetailedMessagesDisplay } from './DetailedMessagesDisplay.js';
 import { RawMarkdownIndicator } from './RawMarkdownIndicator.js';
@@ -42,7 +42,7 @@ export const Composer = () => {
   const [suggestionsVisible, setSuggestionsVisible] = useState(false);
 
   const isAlternateBuffer = useAlternateBuffer();
-  const { showAutoAcceptIndicator } = uiState;
+  const { showApprovalModeIndicator } = uiState;
   const suggestionsPosition = isAlternateBuffer ? 'above' : 'below';
   const hideContextSummary =
     suggestionsVisible && suggestionsPosition === 'above';
@@ -92,9 +92,9 @@ export const Composer = () => {
           <StatusDisplay hideContextSummary={hideContextSummary} />
         </Box>
         <Box paddingTop={isNarrow ? 1 : 0}>
-          {showAutoAcceptIndicator !== ApprovalMode.DEFAULT &&
+          {showApprovalModeIndicator !== ApprovalMode.DEFAULT &&
             !uiState.shellModeActive && (
-              <AutoAcceptIndicator approvalMode={showAutoAcceptIndicator} />
+              <ApprovalModeIndicator approvalMode={showApprovalModeIndicator} />
             )}
           {uiState.shellModeActive && <ShellModeIndicator />}
           {!uiState.renderMarkdown && <RawMarkdownIndicator />}
@@ -131,7 +131,7 @@ export const Composer = () => {
           commandContext={uiState.commandContext}
           shellModeActive={uiState.shellModeActive}
           setShellModeActive={uiActions.setShellModeActive}
-          approvalMode={showAutoAcceptIndicator}
+          approvalMode={showApprovalModeIndicator}
           onEscapePromptChange={uiActions.onEscapePromptChange}
           focus={true}
           vimHandleInput={uiActions.vimHandleInput}

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

@@ -96,7 +96,9 @@ describe('FolderTrustDialog', () => {
     );
 
     // Unmount immediately (before 250ms)
-    unmount();
+    act(() => {
+      unmount();
+    });
 
     await vi.advanceTimersByTimeAsync(250);
     expect(relaunchApp).not.toHaveBeenCalled();

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

@@ -203,6 +203,15 @@ describe('<Footer />', () => {
   });
 
   describe('footer configuration filtering (golden snapshots)', () => {
+    beforeEach(() => {
+      vi.stubEnv('SANDBOX', '');
+      vi.stubEnv('SEATBELT_PROFILE', '');
+    });
+
+    afterEach(() => {
+      vi.unstubAllEnvs();
+    });
+
     it('renders complete footer with all sections visible (baseline)', () => {
       const { lastFrame } = renderWithProviders(<Footer />, {
         width: 120,

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

@@ -9,6 +9,7 @@ import { Box, Text } from 'ink';
 import { theme } from '../semantic-colors.js';
 import { type SlashCommand, CommandKind } from '../commands/types.js';
 import { KEYBOARD_SHORTCUTS_URL } from '../constants.js';
+import { sanitizeForListDisplay } from '../utils/textUtils.js';
 
 interface Help {
   commands: readonly SlashCommand[];
@@ -77,7 +78,8 @@ export const Help: React.FC<Help> = ({ commands }) => (
             {command.kind === CommandKind.MCP_PROMPT && (
               <Text color={theme.text.secondary}> [MCP]</Text>
             )}
-            {command.description && ' - ' + command.description}
+            {command.description &&
+              ' - ' + sanitizeForListDisplay(command.description, 100)}
           </Text>
           {command.subCommands &&
             command.subCommands
@@ -88,7 +90,8 @@ export const Help: React.FC<Help> = ({ commands }) => (
                     {'   '}
                     {subCommand.name}
                   </Text>
-                  {subCommand.description && ' - ' + subCommand.description}
+                  {subCommand.description &&
+                    ' - ' + sanitizeForListDisplay(subCommand.description, 100)}
                 </Text>
               ))}
         </Box>

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

@@ -176,6 +176,7 @@ describe('InputPrompt', () => {
       visualToTransformedMap: [0],
       transformationsByLine: [],
       getOffset: vi.fn().mockReturnValue(0),
+      pastedContent: {},
     } as unknown as TextBuffer;
 
     mockShellHistory = {
@@ -248,6 +249,8 @@ describe('InputPrompt', () => {
       checking: false,
     });
 
+    vi.mocked(clipboardy.read).mockResolvedValue('');
+
     props = {
       buffer: mockBuffer,
       onSubmit: vi.fn(),
@@ -632,10 +635,9 @@ describe('InputPrompt', () => {
 
       await waitFor(() => {
         expect(clipboardy.read).toHaveBeenCalled();
-        expect(mockBuffer.replaceRangeByOffset).toHaveBeenCalledWith(
-          expect.any(Number),
-          expect.any(Number),
+        expect(mockBuffer.insert).toHaveBeenCalledWith(
           'pasted text',
+          expect.objectContaining({ paste: true }),
         );
       });
       unmount();
@@ -1272,6 +1274,21 @@ describe('InputPrompt', () => {
     unmount();
   });
 
+  it('should render correctly in plan mode', async () => {
+    props.approvalMode = ApprovalMode.PLAN;
+    const { stdout, unmount } = renderWithProviders(<InputPrompt {...props} />);
+
+    await waitFor(() => {
+      const frame = stdout.lastFrame();
+      // In plan mode it uses '>' but with success color.
+      // We check that it contains '>' and not '*' or '!'.
+      expect(frame).toContain('>');
+      expect(frame).not.toContain('*');
+      expect(frame).not.toContain('!');
+    });
+    unmount();
+  });
+
   it('should NOT clear the buffer on Ctrl+C if it is empty', async () => {
     props.buffer.text = '';
     const { stdin, unmount } = renderWithProviders(<InputPrompt {...props} />, {
@@ -1718,6 +1735,99 @@ describe('InputPrompt', () => {
     });
   });
 
+  describe('large paste placeholder', () => {
+    it('should handle large clipboard paste (lines > 5) by calling buffer.insert', async () => {
+      vi.mocked(clipboardUtils.clipboardHasImage).mockResolvedValue(false);
+      const largeText = '1\n2\n3\n4\n5\n6';
+      vi.mocked(clipboardy.read).mockResolvedValue(largeText);
+
+      const { stdin, unmount } = renderWithProviders(
+        <InputPrompt {...props} />,
+      );
+
+      await act(async () => {
+        stdin.write('\x16'); // Ctrl+V
+      });
+
+      await waitFor(() => {
+        expect(mockBuffer.insert).toHaveBeenCalledWith(
+          largeText,
+          expect.objectContaining({ paste: true }),
+        );
+      });
+
+      unmount();
+    });
+
+    it('should handle large clipboard paste (chars > 500) by calling buffer.insert', async () => {
+      vi.mocked(clipboardUtils.clipboardHasImage).mockResolvedValue(false);
+      const largeText = 'a'.repeat(501);
+      vi.mocked(clipboardy.read).mockResolvedValue(largeText);
+
+      const { stdin, unmount } = renderWithProviders(
+        <InputPrompt {...props} />,
+      );
+
+      await act(async () => {
+        stdin.write('\x16'); // Ctrl+V
+      });
+
+      await waitFor(() => {
+        expect(mockBuffer.insert).toHaveBeenCalledWith(
+          largeText,
+          expect.objectContaining({ paste: true }),
+        );
+      });
+
+      unmount();
+    });
+
+    it('should handle normal clipboard paste by calling buffer.insert', async () => {
+      vi.mocked(clipboardUtils.clipboardHasImage).mockResolvedValue(false);
+      const smallText = 'hello world';
+      vi.mocked(clipboardy.read).mockResolvedValue(smallText);
+
+      const { stdin, unmount } = renderWithProviders(
+        <InputPrompt {...props} />,
+      );
+
+      await act(async () => {
+        stdin.write('\x16'); // Ctrl+V
+      });
+
+      await waitFor(() => {
+        expect(mockBuffer.insert).toHaveBeenCalledWith(
+          smallText,
+          expect.objectContaining({ paste: true }),
+        );
+      });
+
+      unmount();
+    });
+
+    it('should replace placeholder with actual content on submit', async () => {
+      // Setup buffer to have the placeholder
+      const largeText = '1\n2\n3\n4\n5\n6';
+      const id = '[Pasted Text: 6 lines]';
+      mockBuffer.text = `Check this: ${id}`;
+      mockBuffer.pastedContent = { [id]: largeText };
+
+      const { stdin, unmount } = renderWithProviders(
+        <InputPrompt {...props} />,
+      );
+
+      await act(async () => {
+        stdin.write('\r'); // Enter
+      });
+
+      await waitFor(() => {
+        expect(props.onSubmit).toHaveBeenCalledWith(`Check this: ${largeText}`);
+      });
+
+      unmount();
+    });
+  });
+
   describe('paste auto-submission protection', () => {
     beforeEach(() => {
       vi.useFakeTimers();
@@ -1729,6 +1839,7 @@ describe('InputPrompt', () => {
 
     afterEach(() => {
       vi.useRealTimers();
+      vi.restoreAllMocks();
     });
 
     it('should prevent auto-submission immediately after an unsafe paste', async () => {
@@ -1911,7 +2022,9 @@ describe('InputPrompt', () => {
       await act(async () => {
         stdin.write('\x1B\x1B');
         vi.advanceTimersByTime(100);
+      });
 
+      await waitFor(() => {
         expect(props.onSubmit).toHaveBeenCalledWith('/rewind');
       });
       unmount();

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

@@ -12,7 +12,10 @@ import { SuggestionsDisplay, MAX_WIDTH } from './SuggestionsDisplay.js';
 import { theme } from '../semantic-colors.js';
 import { useInputHistory } from '../hooks/useInputHistory.js';
 import type { TextBuffer } from './shared/text-buffer.js';
-import { logicalPosToOffset } from './shared/text-buffer.js';
+import {
+  logicalPosToOffset,
+  PASTED_TEXT_PLACEHOLDER_REGEX,
+} from './shared/text-buffer.js';
 import { cpSlice, cpLen, toCodePoints } from '../utils/textUtils.js';
 import chalk from 'chalk';
 import stringWidth from 'string-width';
@@ -27,7 +30,7 @@ import { useKeypress } from '../hooks/useKeypress.js';
 import { keyMatchers, Command } from '../keyMatchers.js';
 import type { CommandContext, SlashCommand } from '../commands/types.js';
 import type { Config } from '@google/gemini-cli-core';
-import { ApprovalMode, debugLogger } from '@google/gemini-cli-core';
+import { ApprovalMode, coreEvents, debugLogger } from '@google/gemini-cli-core';
 import {
   parseInputForHighlighting,
   parseSegmentsFromTokens,
@@ -221,13 +224,22 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
 
   const handleSubmitAndClear = useCallback(
     (submittedValue: string) => {
+      let processedValue = submittedValue;
+      if (buffer.pastedContent) {
+        // Replace placeholders like [Pasted Text: 6 lines] with actual content
+        processedValue = processedValue.replace(
+          PASTED_TEXT_PLACEHOLDER_REGEX,
+          (match) => buffer.pastedContent[match] || match,
+        );
+      }
+
       if (shellModeActive) {
-        shellHistory.addCommandToHistory(submittedValue);
+        shellHistory.addCommandToHistory(processedValue);
       }
       // Clear the buffer *before* calling onSubmit to prevent potential re-submission
       // if onSubmit triggers a re-render while the buffer still holds the old value.
       buffer.setText('');
-      onSubmit(submittedValue);
+      onSubmit(processedValue);
       resetCompletionState();
       resetReverseSearchCompletionState();
     },
@@ -360,8 +372,7 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
         stdout.write('\x1b]52;c;?\x07');
       } else {
         const textToInsert = await clipboardy.read();
-        const offset = buffer.getOffset();
-        buffer.replaceRangeByOffset(offset, offset, textToInsert);
+        buffer.insert(textToInsert, { paste: true });
       }
     } catch (error) {
       debugLogger.error('Error handling paste:', error);
@@ -505,18 +516,20 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
           escapeTimerRef.current = setTimeout(() => {
             resetEscapeState();
           }, 500);
-        } else {
-          // Second ESC
-          resetEscapeState();
-          if (buffer.text.length > 0) {
-            buffer.setText('');
-            resetCompletionState();
-          } else {
-            if (history.length > 0) {
-              onSubmit('/rewind');
-            }
-          }
+          return;
         }
+
+        // Second ESC
+        resetEscapeState();
+        if (buffer.text.length > 0) {
+          buffer.setText('');
+          resetCompletionState();
+          return;
+        } else if (history.length > 0) {
+          onSubmit('/rewind');
+          return;
+        }
+        coreEvents.emitFeedback('info', 'Nothing to rewind to');
         return;
       }
 
@@ -851,8 +864,9 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
         completion.promptCompletion.text &&
         key.sequence &&
         key.sequence.length === 1 &&
+        !key.alt &&
         !key.ctrl &&
-        !key.meta
+        !key.cmd
       ) {
         completion.promptCompletion.clear();
         setExpandedSuggestionIndex(-1);
@@ -1029,6 +1043,8 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
     !shellModeActive && approvalMode === ApprovalMode.AUTO_EDIT;
   const showYoloStyling =
     !shellModeActive && approvalMode === ApprovalMode.YOLO;
+  const showPlanStyling =
+    !shellModeActive && approvalMode === ApprovalMode.PLAN;
 
   let statusColor: string | undefined;
   let statusText = '';
@@ -1038,6 +1054,9 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
   } else if (showYoloStyling) {
     statusColor = theme.status.error;
     statusText = 'YOLO mode';
+  } else if (showPlanStyling) {
+    statusColor = theme.status.success;
+    statusText = 'Plan mode';
   } else if (showAutoAcceptStyling) {
     statusColor = theme.status.warning;
     statusText = 'Accepting edits';
@@ -1190,7 +1209,9 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
                   }
 
                   const color =
-                    seg.type === 'command' || seg.type === 'file'
+                    seg.type === 'command' ||
+                    seg.type === 'file' ||
+                    seg.type === 'paste'
                       ? theme.text.accent
                       : theme.text.primary;
 

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

@@ -91,9 +91,10 @@ describe('MultiFolderTrustDialog', () => {
     await act(async () => {
       keypressCallback({
         name: 'escape',
-        ctrl: false,
-        meta: false,
         shift: false,
+        alt: false,
+        ctrl: false,
+        cmd: false,
         sequence: '',
         insertable: false,
       });

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

@@ -4,7 +4,7 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-import { render } from '../../test-utils/render.js';
+import { render, persistentStateMock } from '../../test-utils/render.js';
 import { Notifications } from './Notifications.js';
 import { describe, it, expect, vi, beforeEach } from 'vitest';
 import { useAppContext, type AppState } from '../contexts/AppContext.js';
@@ -30,6 +30,7 @@ vi.mock('node:fs/promises', async () => {
     access: vi.fn(),
     writeFile: vi.fn(),
     mkdir: vi.fn().mockResolvedValue(undefined),
+    unlink: vi.fn().mockResolvedValue(undefined),
   };
 });
 vi.mock('node:os', () => ({
@@ -68,10 +69,11 @@ describe('Notifications', () => {
   const mockUseUIState = vi.mocked(useUIState);
   const mockUseIsScreenReaderEnabled = vi.mocked(useIsScreenReaderEnabled);
   const mockFsAccess = vi.mocked(fs.access);
-  const mockFsWriteFile = vi.mocked(fs.writeFile);
+  const mockFsUnlink = vi.mocked(fs.unlink);
 
   beforeEach(() => {
     vi.clearAllMocks();
+    persistentStateMock.reset();
     mockUseAppContext.mockReturnValue({
       startupWarnings: [],
       version: '1.0.0',
@@ -134,51 +136,47 @@ describe('Notifications', () => {
     expect(lastFrame()).toMatchSnapshot();
   });
 
-  it('renders screen reader nudge when enabled and not seen', async () => {
+  it('renders screen reader nudge when enabled and not seen (no legacy file)', async () => {
     mockUseIsScreenReaderEnabled.mockReturnValue(true);
-
-    let rejectAccess: (err: Error) => void;
-    mockFsAccess.mockImplementation(
-      () =>
-        new Promise((_, reject) => {
-          rejectAccess = reject;
-        }),
-    );
+    persistentStateMock.setData({ hasSeenScreenReaderNudge: false });
+    mockFsAccess.mockRejectedValue(new Error('No legacy file'));
 
     const { lastFrame } = render(<Notifications />);
 
-    // Trigger rejection inside act
-    await act(async () => {
-      rejectAccess(new Error('File not found'));
-    });
-
-    // Wait for effect to propagate
-    await vi.waitFor(() => {
-      expect(mockFsWriteFile).toHaveBeenCalled();
-    });
+    expect(lastFrame()).toContain('screen reader-friendly view');
+    expect(persistentStateMock.set).toHaveBeenCalledWith(
+      'hasSeenScreenReaderNudge',
+      true,
+    );
 
     expect(lastFrame()).toMatchSnapshot();
   });
 
-  it('does not render screen reader nudge when already seen', async () => {
+  it('migrates legacy screen reader nudge file', async () => {
     mockUseIsScreenReaderEnabled.mockReturnValue(true);
+    persistentStateMock.setData({ hasSeenScreenReaderNudge: undefined });
+    mockFsAccess.mockResolvedValue(undefined);
 
-    let resolveAccess: (val: undefined) => void;
-    mockFsAccess.mockImplementation(
-      () =>
-        new Promise((resolve) => {
-          resolveAccess = resolve;
-        }),
-    );
+    render(<Notifications />);
+
+    await act(async () => {
+      await vi.waitFor(() => {
+        expect(persistentStateMock.set).toHaveBeenCalledWith(
+          'hasSeenScreenReaderNudge',
+          true,
+        );
+        expect(mockFsUnlink).toHaveBeenCalled();
+      });
+    });
+  });
+
+  it('does not render screen reader nudge when already seen in persistent state', async () => {
+    mockUseIsScreenReaderEnabled.mockReturnValue(true);
+    persistentStateMock.setData({ hasSeenScreenReaderNudge: true });
 
     const { lastFrame } = render(<Notifications />);
 
-    // Trigger resolution inside act
-    await act(async () => {
-      resolveAccess(undefined);
-    });
-
     expect(lastFrame()).toBe('');
-    expect(mockFsWriteFile).not.toHaveBeenCalled();
+    expect(persistentStateMock.set).not.toHaveBeenCalled();
   });
 });

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

@@ -11,13 +11,9 @@ import { useUIState } from '../contexts/UIStateContext.js';
 import { theme } from '../semantic-colors.js';
 import { StreamingState } from '../types.js';
 import { UpdateNotification } from './UpdateNotification.js';
+import { persistentState } from '../../utils/persistentState.js';
 
-import {
-  GEMINI_DIR,
-  Storage,
-  debugLogger,
-  homedir,
-} from '@google/gemini-cli-core';
+import { GEMINI_DIR, Storage, homedir } from '@google/gemini-cli-core';
 
 import * as fs from 'node:fs/promises';
 import path from 'node:path';
@@ -38,15 +34,20 @@ export const Notifications = () => {
   const showInitError =
     initError && streamingState !== StreamingState.Responding;
 
-  const [hasSeenScreenReaderNudge, setHasSeenScreenReaderNudge] = useState<
-    boolean | undefined
-  >(undefined);
+  const [hasSeenScreenReaderNudge, setHasSeenScreenReaderNudge] = useState(() =>
+    persistentState.get('hasSeenScreenReaderNudge'),
+  );
 
   useEffect(() => {
-    const checkScreenReader = async () => {
+    const checkLegacyScreenReaderNudge = async () => {
+      if (hasSeenScreenReaderNudge !== undefined) return;
+
       try {
         await fs.access(screenReaderNudgeFilePath);
+        persistentState.set('hasSeenScreenReaderNudge', true);
         setHasSeenScreenReaderNudge(true);
+        // Best effort cleanup of legacy file
+        await fs.unlink(screenReaderNudgeFilePath).catch(() => {});
       } catch {
         setHasSeenScreenReaderNudge(false);
       }
@@ -54,28 +55,17 @@ export const Notifications = () => {
 
     if (isScreenReaderEnabled) {
       // eslint-disable-next-line @typescript-eslint/no-floating-promises
-      checkScreenReader();
+      checkLegacyScreenReaderNudge();
     }
-  }, [isScreenReaderEnabled]);
+  }, [isScreenReaderEnabled, hasSeenScreenReaderNudge]);
 
   const showScreenReaderNudge =
     isScreenReaderEnabled && hasSeenScreenReaderNudge === false;
 
   useEffect(() => {
-    const writeScreenReaderNudgeFile = async () => {
-      if (showScreenReaderNudge) {
-        try {
-          await fs.mkdir(path.dirname(screenReaderNudgeFilePath), {
-            recursive: true,
-          });
-          await fs.writeFile(screenReaderNudgeFilePath, 'true');
-        } catch (error) {
-          debugLogger.error('Error storing screen reader nudge', error);
-        }
-      }
-    };
-    // eslint-disable-next-line @typescript-eslint/no-floating-promises
-    writeScreenReaderNudgeFile();
+    if (showScreenReaderNudge) {
+      persistentState.set('hasSeenScreenReaderNudge', true);
+    }
   }, [showScreenReaderNudge]);
 
   if (

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

@@ -239,6 +239,7 @@ describe('RewindViewer', () => {
 
       // Select
       act(() => {
+        stdin.write('\x1b[A'); // Move up from 'Stay at current position'
         stdin.write('\r');
       });
       expect(lastFrame()).toMatchSnapshot('confirmation-dialog');
@@ -252,17 +253,16 @@ describe('RewindViewer', () => {
     it.each([
       {
         description: 'removes reference markers',
-        prompt:
-          'some command @file\n--- Content from referenced files ---\nContent from file:\nblah blah\n--- End of content ---',
+        prompt: `some command @file\n--- Content from referenced files ---\nContent from file:\nblah blah\n--- End of content ---`,
       },
       {
         description: 'strips expanded MCP resource content',
         prompt:
           'read @server3:mcp://demo-resource hello\n' +
-          '--- Content from referenced files ---\n' +
+          `--- Content from referenced files ---\n` +
           '\nContent from @server3:mcp://demo-resource:\n' +
           'This is the content of the demo resource.\n' +
-          '--- End of content ---',
+          `--- End of content ---`,
       },
     ])('$description', async ({ prompt }) => {
       const conversation = createConversation([
@@ -281,6 +281,7 @@ describe('RewindViewer', () => {
 
       // Select
       act(() => {
+        stdin.write('\x1b[A'); // Move up from 'Stay at current position'
         stdin.write('\r'); // Select
       });
 

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

@@ -5,7 +5,7 @@
  */
 
 import type React from 'react';
-import { useMemo } from 'react';
+import { useMemo, useState } from 'react';
 import { Box, Text } from 'ink';
 import { useUIState } from '../contexts/UIStateContext.js';
 import {
@@ -19,8 +19,9 @@ import { useKeypress } from '../hooks/useKeypress.js';
 import { useRewind } from '../hooks/useRewind.js';
 import { RewindConfirmation, RewindOutcome } from './RewindConfirmation.js';
 import { stripReferenceContent } from '../utils/formatters.js';
-import { MaxSizedBox } from './shared/MaxSizedBox.js';
 import { keyMatchers, Command } from '../keyMatchers.js';
+import { CliSpinner } from './CliSpinner.js';
+import { ExpandableText } from './shared/ExpandableText.js';
 
 interface RewindViewerProps {
   conversation: ConversationRecord;
@@ -29,7 +30,7 @@ interface RewindViewerProps {
     messageId: string,
     newText: string,
     outcome: RewindOutcome,
-  ) => void;
+  ) => Promise<void>;
 }
 
 const MAX_LINES_PER_BOX = 2;
@@ -39,6 +40,7 @@ export const RewindViewer: React.FC<RewindViewerProps> = ({
   onExit,
   onRewind,
 }) => {
+  const [isRewinding, setIsRewinding] = useState(false);
   const { terminalWidth, terminalHeight } = useUIState();
   const {
     selectedMessageId,
@@ -48,28 +50,58 @@ export const RewindViewer: React.FC<RewindViewerProps> = ({
     clearSelection,
   } = useRewind(conversation);
 
+  const [highlightedMessageId, setHighlightedMessageId] = useState<
+    string | null
+  >(null);
+  const [expandedMessageId, setExpandedMessageId] = useState<string | null>(
+    null,
+  );
+
   const interactions = useMemo(
     () => conversation.messages.filter((msg) => msg.type === 'user'),
     [conversation.messages],
   );
 
-  const items = useMemo(
-    () =>
-      interactions
-        .map((msg, idx) => ({
-          key: `${msg.id || 'msg'}-${idx}`,
-          value: msg,
-          index: idx,
-        }))
-        .reverse(),
-    [interactions],
-  );
+  const items = useMemo(() => {
+    const interactionItems = interactions.map((msg, idx) => ({
+      key: `${msg.id || 'msg'}-${idx}`,
+      value: msg,
+      index: idx,
+    }));
+
+    // Add "Current Position" as the last item
+    return [
+      ...interactionItems,
+      {
+        key: 'current-position',
+        value: {
+          id: 'current-position',
+          type: 'user',
+          content: 'Stay at current position',
+          timestamp: new Date().toISOString(),
+        } as MessageRecord,
+        index: interactionItems.length,
+      },
+    ];
+  }, [interactions]);
 
   useKeypress(
     (key) => {
       if (!selectedMessageId) {
         if (keyMatchers[Command.ESCAPE](key)) {
           onExit();
+          return;
+        }
+        if (keyMatchers[Command.EXPAND_SUGGESTION](key)) {
+          if (
+            highlightedMessageId &&
+            highlightedMessageId !== 'current-position'
+          ) {
+            setExpandedMessageId(highlightedMessageId);
+          }
+        }
+        if (keyMatchers[Command.COLLAPSE_SUGGESTION](key)) {
+          setExpandedMessageId(null);
         }
       }
     },
@@ -89,6 +121,28 @@ export const RewindViewer: React.FC<RewindViewerProps> = ({
   const maxItemsToShow = Math.max(1, Math.floor(listHeight / 4));
 
   if (selectedMessageId) {
+    if (isRewinding) {
+      return (
+        <Box
+          borderStyle="round"
+          borderColor={theme.border.default}
+          padding={1}
+          width={terminalWidth}
+          flexDirection="row"
+        >
+          <Box>
+            <CliSpinner />
+          </Box>
+          <Text>Rewinding...</Text>
+        </Box>
+      );
+    }
+
+    if (selectedMessageId === 'current-position') {
+      onExit();
+      return null;
+    }
+
     const selectedMessage = interactions.find(
       (m) => m.id === selectedMessageId,
     );
@@ -97,7 +151,7 @@ export const RewindViewer: React.FC<RewindViewerProps> = ({
         stats={confirmationStats}
         terminalWidth={terminalWidth}
         timestamp={selectedMessage?.timestamp}
-        onConfirm={(outcome) => {
+        onConfirm={async (outcome) => {
           if (outcome === RewindOutcome.Cancel) {
             clearSelection();
           } else {
@@ -109,7 +163,8 @@ export const RewindViewer: React.FC<RewindViewerProps> = ({
                 ? partToString(userPrompt.content)
                 : '';
               const cleanedText = stripReferenceContent(originalUserText);
-              onRewind(selectedMessageId, cleanedText, outcome);
+              setIsRewinding(true);
+              await onRewind(selectedMessageId, cleanedText, outcome);
             }
           }
         }}
@@ -133,17 +188,48 @@ export const RewindViewer: React.FC<RewindViewerProps> = ({
       <Box flexDirection="column" flexGrow={1}>
         <BaseSelectionList
           items={items}
+          initialIndex={items.length - 1}
           isFocused={true}
           showNumbers={false}
+          wrapAround={false}
           onSelect={(item: MessageRecord) => {
             const userPrompt = item;
             if (userPrompt && userPrompt.id) {
-              selectMessage(userPrompt.id);
+              if (userPrompt.id === 'current-position') {
+                onExit();
+              } else {
+                selectMessage(userPrompt.id);
+              }
+            }
+          }}
+          onHighlight={(item: MessageRecord) => {
+            if (item.id) {
+              setHighlightedMessageId(item.id);
+              // Collapse when moving selection
+              setExpandedMessageId(null);
             }
           }}
           maxItemsToShow={maxItemsToShow}
           renderItem={(itemWrapper, { isSelected }) => {
             const userPrompt = itemWrapper.value;
+
+            if (userPrompt.id === 'current-position') {
+              return (
+                <Box flexDirection="column" marginBottom={1}>
+                  <Text
+                    color={
+                      isSelected ? theme.status.success : theme.text.primary
+                    }
+                  >
+                    {partToString(userPrompt.content)}
+                  </Text>
+                  <Text color={theme.text.secondary}>
+                    Cancel rewind and stay here
+                  </Text>
+                </Box>
+              );
+            }
+
             const stats = getStats(userPrompt);
             const firstFileName = stats?.details?.at(0)?.fileName;
             const originalUserText = userPrompt.content
@@ -154,25 +240,15 @@ export const RewindViewer: React.FC<RewindViewerProps> = ({
             return (
               <Box flexDirection="column" marginBottom={1}>
                 <Box>
-                  <MaxSizedBox
-                    maxWidth={terminalWidth - 4}
-                    maxHeight={isSelected ? undefined : MAX_LINES_PER_BOX + 1}
-                    overflowDirection="bottom"
-                  >
-                    {cleanedText.split('\n').map((line, i) => (
-                      <Box key={i}>
-                        <Text
-                          color={
-                            isSelected
-                              ? theme.status.success
-                              : theme.text.primary
-                          }
-                        >
-                          {line}
-                        </Text>
-                      </Box>
-                    ))}
-                  </MaxSizedBox>
+                  <ExpandableText
+                    label={cleanedText}
+                    isExpanded={expandedMessageId === userPrompt.id}
+                    textColor={
+                      isSelected ? theme.status.success : theme.text.primary
+                    }
+                    maxWidth={(terminalWidth - 4) * MAX_LINES_PER_BOX}
+                    maxLines={MAX_LINES_PER_BOX}
+                  />
                 </Box>
                 {stats ? (
                   <Box flexDirection="row">
@@ -203,7 +279,8 @@ export const RewindViewer: React.FC<RewindViewerProps> = ({
 
       <Box marginTop={1}>
         <Text color={theme.text.secondary}>
-          (Use Enter to select a message, Esc to close)
+          (Use Enter to select a message, Esc to close, Right/Left to
+          expand/collapse)
         </Text>
       </Box>
     </Box>

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

@@ -93,10 +93,10 @@ const createMockConfig = (overrides: Partial<Config> = {}): Config =>
 const triggerKey = (
   partialKey: Partial<{
     name: string;
-    ctrl: boolean;
-    meta: boolean;
     shift: boolean;
-    paste: boolean;
+    alt: boolean;
+    ctrl: boolean;
+    cmd: boolean;
     insertable: boolean;
     sequence: string;
   }>,
@@ -108,9 +108,10 @@ const triggerKey = (
 
   const key = {
     name: '',
-    ctrl: false,
-    meta: false,
     shift: false,
+    alt: false,
+    ctrl: false,
+    cmd: false,
     insertable: false,
     sequence: '',
     ...partialKey,
@@ -263,7 +264,13 @@ describe('SessionBrowser component', () => {
 
     // Type the query "query".
     for (const ch of ['q', 'u', 'e', 'r', 'y']) {
-      triggerKey({ sequence: ch, name: ch, ctrl: false, meta: false });
+      triggerKey({
+        sequence: ch,
+        name: ch,
+        alt: false,
+        ctrl: false,
+        cmd: false,
+      });
     }
 
     await waitFor(() => {

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

@@ -781,9 +781,10 @@ export const useSessionBrowserInput = (
           state.setScrollOffset(0);
         } else if (
           key.sequence &&
+          key.sequence.length === 1 &&
+          !key.alt &&
           !key.ctrl &&
-          !key.meta &&
-          key.sequence.length === 1
+          !key.cmd
         ) {
           state.setSearchQuery((prev) => prev + key.sequence);
           state.setActiveIndex(0);

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

@@ -381,7 +381,7 @@ describe('SettingsDialog', () => {
 
       await waitFor(() => {
         // Should wrap to last setting (without relying on exact bullet character)
-        expect(lastFrame()).toContain('Codebase Investigator Max Num Turns');
+        expect(lastFrame()).toContain('Hook Notifications');
       });
 
       unmount();
@@ -1213,9 +1213,7 @@ describe('SettingsDialog', () => {
       await waitFor(() => {
         expect(lastFrame()).toContain('vim');
         expect(lastFrame()).toContain('Vim Mode');
-        expect(lastFrame()).not.toContain(
-          'Codebase Investigator Max Num Turns',
-        );
+        expect(lastFrame()).not.toContain('Hook Notifications');
       });
 
       unmount();

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

@@ -951,12 +951,10 @@ export function SettingsDialog({
                   const afterCursor = cpSlice(editBuffer, editCursorPos + 1);
                   displayValue =
                     beforeCursor + chalk.inverse(atCursor) + afterCursor;
-                } else if (
-                  cursorVisible &&
-                  editCursorPos >= cpLen(editBuffer)
-                ) {
+                } else if (editCursorPos >= cpLen(editBuffer)) {
                   // Cursor is at the end - show inverted space
-                  displayValue = editBuffer + chalk.inverse(' ');
+                  displayValue =
+                    editBuffer + (cursorVisible ? chalk.inverse(' ') : ' ');
                 } else {
                   // Cursor not visible
                   displayValue = editBuffer;

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

@@ -53,7 +53,14 @@ describe('ShellInputPrompt', () => {
     const handler = mockUseKeypress.mock.calls[0][0];
 
     // Simulate keypress
-    handler({ name, sequence, ctrl: false, shift: false, meta: false });
+    handler({
+      name,
+      shift: false,
+      alt: false,
+      ctrl: false,
+      cmd: false,
+      sequence,
+    });
 
     expect(mockWriteToPty).toHaveBeenCalledWith(1, sequence);
   });
@@ -66,7 +73,7 @@ describe('ShellInputPrompt', () => {
 
     const handler = mockUseKeypress.mock.calls[0][0];
 
-    handler({ name: key, ctrl: true, shift: true, meta: false });
+    handler({ name: key, shift: true, alt: false, ctrl: true, cmd: false });
 
     expect(mockScrollPty).toHaveBeenCalledWith(1, direction);
   });
@@ -78,10 +85,11 @@ describe('ShellInputPrompt', () => {
 
     handler({
       name: 'a',
-      sequence: 'a',
-      ctrl: false,
       shift: false,
-      meta: false,
+      alt: false,
+      ctrl: false,
+      cmd: false,
+      sequence: 'a',
     });
 
     expect(mockWriteToPty).not.toHaveBeenCalled();
@@ -94,10 +102,11 @@ describe('ShellInputPrompt', () => {
 
     handler({
       name: 'a',
-      sequence: 'a',
-      ctrl: false,
       shift: false,
-      meta: false,
+      alt: false,
+      ctrl: false,
+      cmd: false,
+      sequence: 'a',
     });
 
     expect(mockWriteToPty).not.toHaveBeenCalled();