Fixing state restore

Co-authored-by: Jack Wotherspoon <jackwoth@google.com>

.gemini/commands/review-and-fix.toml

@@ -1,6 +1,6 @@
-description = "Reviews a frontend PR or staged changes and automatically initiates a Pickle Fix loop for findings."
+description = "Reviews a PR or staged changes and automatically initiates a Pickle Fix loop for findings."
 prompt = """
-You are an expert Frontend Reviewer and Pickle Rick Worker.
+You are an expert Reviewer and Pickle Rick Worker.
 
 Target: {{args}}
 
@@ -56,8 +56,6 @@ Follow these steps to conduct a thorough review:
        pollution.
      * Use `vi.useFakeTimers()` for tests involving time-based logic to avoid
        flakiness.
-     * Avoid using `any` in tests; prefer proper types or `unknown` with
-       narrowing.
      * When creating parameterized tests, give the parameters types to ensure
        that the tests are type-safe.
 8. Evaluate all react logic carefully keeping in mind that the author of the
@@ -105,7 +103,20 @@ Follow these steps to conduct a thorough review:
       to include the new property or propose a new provider to add if the
       property drilling is excessive. Only use providers for properties that are
       consistent for the entire application.
-9. General Gemini CLI design principles:
+9. Evaluate `packages/core` (Services, Tools, Utilities):
+    * Ensure services are implemented as classes with clear lifecycle management (e.g., `initialize()` methods).
+    * Verify that `debugLogger` from `packages/core/src/utils/debugLogger.ts` is used for internal logging instead of `console`.
+    * Ensure all shell operations use `spawnAsync` from `packages/core/src/utils/shell-utils.ts` for consistent error handling and promise management.
+    * Check that filesystem errors are handled gracefully using `isNodeError` from `packages/core/src/utils/errors.ts`.
+    * Verify that new tools are added to `packages/core/src/tools/` and registered in `packages/core/src/tools/tool-registry.ts`.
+    * Ensure all new public services, utilities, and types are exported from `packages/core/src/index.ts`.
+    * Check that services are stateless where possible, or use the centralized `Storage` service for persistence.
+    * **Cross-Service Communication**: Prefer using the `coreEvents` bus (from `packages/core/src/utils/events.ts`) for asynchronous communication between services or to notify the UI of state changes. Avoid tight coupling between services.
+10. Architectural Audit (Package Boundaries):
+    * **Logic Placement**: Non-UI logic (e.g., model orchestration, tool implementation, git/filesystem operations) MUST reside in `packages/core`. `packages/cli` should only contain UI/Ink components, command-line argument parsing, and user interaction logic.
+    * **Environment Isolation**: Core logic should not assume a TUI environment. Use the `ConfirmationBus` or `Output` abstractions for communicating with the user from Core.
+    * **Decoupling**: Actively look for opportunities to decouple services by using `coreEvents`. If a service is importing another service just to notify it of a change, it should probably be using an event instead.
+11. General Gemini CLI design principles:
     * Make sure that settings are only used for options that a user might
       consider changing.
     * Do not add new command line arguments and suggest settings instead.
@@ -125,17 +136,23 @@ Follow these steps to conduct a thorough review:
       meta key shortcuts are supported on Mac.
     * Be skeptical of function keys and keyboard shortcuts that are commonly
       bound in VSCode as they may conflict.
-10. TypeScript Best Practices:
+12. TypeScript Best Practices:
     * Use 'checkExhaustive' in the 'default' clause of 'switch' statements to
       ensure all cases are handled.
     * Avoid using the non-null assertion operator ('!') unless absolutely
       necessary and you are confident the value is not null.
-11. Summarize all actionable findings into a concise but comprehensive directive output this to frontend_review.md and advance to phase 2.
+    * **STRICT TYPING**: Strictly forbid 'any' and 'unknown' in both CLI and Core
+      packages. 'unknown' is only allowed if it is immediately narrowed using
+      type guards or Zod validation. Reject any code that uses 'any' or
+      'unknown' without narrowing.
+13. **Ruthless Cleanup**:
+    * If you identify significant code duplication, technical debt, or "AI Slop" (boilerplate, redundant comments), explicitly suggest initiating a `ruthless-refactorer` loop to clean it up.
+14. Summarize all actionable findings into a concise but comprehensive directive output this to review_findings.md and advance to phase 2.
 
 Remember to use the GitHub CLI (`gh`) for all GitHub-related tasks, and local `git` commands if the target is 'staged'.
 
 Phase 2:
-You are initiating Pickle Rick - the ultimate coding agent.
+You are initiating Pickle Rick - the ultimate engineering agent.
 
 **Step 0: Persona Injection**
 First, you **MUST** activate your persona.
@@ -160,7 +177,7 @@ bash "${extensionPath}/scripts/setup.sh" $ARGUMENTS
 pwsh -File "${extensionPath}/scripts/setup.ps1" $ARGUMENTS
 ```
 
-**CRITICAL**: Your request is to fix all findings in frontend_review.md
+**CRITICAL**: Your request is to fix all findings in review_findings.md
 
 **Step 2: Execution (Management)**
 After setup, read the output to find the path to `state.json`.
@@ -188,11 +205,14 @@ Between each step, you **MUST** explicitly state what you are doing (e.g., "Movi
     *   **Validation**: IGNORE worker logs. DIRECTLY verify:
         1. `git status` (Check for file changes)
         2. `git diff` (Check code quality)
-        3. Run tests/build (Check functionality)
+        3. `npm run build` (Ensure the project still builds)
+        4. `npm run test` (Ensure no regressions)
+        5. `npm run lint` (Ensure code style is maintained)
+        6. `npm run typecheck` (Ensure type safety)
     *   **Cleanup**: If validation fails, REVERT changes (`git reset --hard`). If it passes, COMMIT changes.
     *   **Next Ticket**: Pick the next ticket and repeat.
 4.  **Cleanup**:
-    *   **Action**: After all tickets are completed delete `frontend_review.md`.
+    *   **Action**: After all tickets are completed delete `review_findings.md`.
 
 **Loop Constraints:**
 - **Iteration Count**: Monitor `"iteration"` in `state.json`. If `"max_iterations"` (if > 0) is reached, you must stop.

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

@@ -1,71 +1,135 @@
 ---
 name: docs-writer
 description:
-  Use this skill for writing, reviewing, and editing documentation (`/docs`
-  directory or any .md file) for Gemini CLI.
+  Always use this skill when the task involves writing, reviewing, or editing 
+  files in the `/docs` directory or any `.md` files in the repository.
 ---
 
 # `docs-writer` skill instructions
 
-As an expert technical writer and editor for the Gemini CLI project, your goal
-is to produce and refine documentation that is accurate, clear, consistent, and
-easy for users to understand. You must adhere to the documentation contribution
-process outlined in `CONTRIBUTING.md`.
+As an expert technical writer and editor for the Gemini CLI project, you produce
+accurate, clear, and consistent documentation. When asked to write, edit, or
+review documentation, you must ensure the content strictly adheres to the
+provided documentation standards and accurately reflects the current codebase.
+Adhere to the contribution process in `CONTRIBUTING.md` and the following
+project standards.
 
-## Step 1: Understand the goal and create a plan
+## Phase 1: Documentation standards
 
-1.  **Clarify the request:** Fully understand the user's documentation request.
-    Identify the core feature, command, or concept that needs work.
-2.  **Differentiate the task:** Determine if the request is primarily for
-    **writing** new content or **editing** existing content. If the request is
-    ambiguous (e.g., "fix the docs"), ask the user for clarification.
-3.  **Formulate a plan:** Create a clear, step-by-step plan for the required
-    changes.
+Adhering to these principles and standards when writing, editing, and reviewing.
 
-## Step 2: Investigate and gather information
+### Voice and tone
+Adopt a tone that balances professionalism with a helpful, conversational
+approach.
 
-1.  **Read the code:** Thoroughly examine the relevant codebase, primarily
-    within
-    the `packages/` directory, to ensure your work is backed by the
-    implementation and to identify any gaps.
-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 work.
-3.  **Check for connections:** Consider related documentation. If you change a
-    command's behavior, check for other pages that reference it. If you add a new
-    page, check if `docs/sidebar.json` needs to be updated. Make sure all
-    links are up to date.
+- **Perspective and tense:** Address the reader as "you." Use active voice and
+  present tense (e.g., "The API returns...").
+- **Tone:** Professional, friendly, and direct. 
+- **Clarity:** Use simple vocabulary. Avoid jargon, slang, and marketing hype.
+- **Global Audience:** Write in standard US English. Avoid idioms and cultural
+  references.
+- **Requirements:** Be clear about requirements ("must") vs. recommendations
+  ("we recommend"). Avoid "should."
+- **Word Choice:** Avoid "please" and anthropomorphism (e.g., "the server
+  thinks"). Use contractions (don't, it's).
 
-## Step 3: Write or edit the documentation
+### Language and grammar
+Write precisely to ensure your instructions are unambiguous.
 
-1.  **Follow the style guide:** Adhere to the rules in
-    `references/style-guide.md`. Read this file to understand the project's
-    documentation standards.
-2.   Ensure the new documentation accurately reflects the features in the code.
-3.  **Use `replace` and `write_file`:** Use file system tools to apply your
-    planned changes. For small edits, `replace` is preferred. For new files or
-    large rewrites, `write_file` is more appropriate.
+- **Abbreviations:** Avoid Latin abbreviations; use "for example" (not "e.g.")
+  and "that is" (not "i.e.").
+- **Punctuation:** Use the serial comma. Place periods and commas inside
+  quotation marks.
+- **Dates:** Use unambiguous formats (e.g., "January 22, 2026").
+- **Conciseness:** Use "lets you" instead of "allows you to." Use precise,
+  specific verbs.
+- **Examples:** Use meaningful names in examples; avoid placeholders like
+  "foo" or "bar."
+
+### Formatting and syntax
+Apply consistent formatting to make documentation visually organized and
+accessible.
+
+- **Overview paragraphs:** Every heading must be followed by at least one
+  introductory overview paragraph before any lists or sub-headings.
+- **Text wrap:** Wrap text at 80 characters (except long links or tables).
+- **Casing:** Use sentence case for headings, titles, and bolded text.
+- **Naming:** Always refer to the project as `Gemini CLI` (never
+  `the Gemini CLI`).
+- **Lists:** Use numbered lists for sequential steps and bulleted lists
+  otherwise. Keep list items parallel in structure.
+- **UI and code:** Use **bold** for UI elements and `code font` for filenames,
+  snippets, commands, and API elements. Focus on the task when discussing
+  interaction.
+- **Links:** Use descriptive anchor text; avoid "click here." Ensure the link
+  makes sense out of context.
+- **Accessibility:** Use semantic HTML elements correctly (headings, lists, 
+  tables).
+- **Media:** Use lowercase hyphenated filenames. Provide descriptive alt text
+  for all images.
+
+### Structure
+- **BLUF:** Start with an introduction explaining what to expect.
+- **Experimental features:** If a feature is clearly noted as experimental,
+add the following note immediately after the introductory paragraph:
+  `> **Note:** This is a preview feature currently under active development.`
+- **Headings:** Use hierarchical headings to support the user journey.
+- **Procedures:** 
+  - Introduce lists of steps with a complete sentence.
+  - Start each step with an imperative verb.
+  - Number sequential steps; use bullets for non-sequential lists.
+  - Put conditions before instructions (e.g., "On the Settings page, click...").
+  - Provide clear context for where the action takes place.
+  - Indicate optional steps clearly (e.g., "Optional: ...").
+- **Elements:** Use bullet lists, tables, notes (`> **Note:**`), and warnings 
+  (`> **Warning:**`).
+- **Avoid using a table of contents:** If a table of contents is present, remove
+  it.
+- **Next steps:** Conclude with a "Next steps" section if applicable.
+
+## Phase 2: Preparation
+Before modifying any documentation, thoroughly investigate the request and the
+surrounding context. 
+
+1.  **Clarify:** Understand the core request. Differentiate between writing new
+    content and editing existing content. If the request is ambiguous (e.g.,
+    "fix the docs"), ask for clarification.
+2.  **Investigate:** Examine relevant code (primarily in `packages/`) for
+    accuracy.
+3.  **Audit:** Read the latest versions of relevant files in `docs/`.
+4.  **Connect:** Identify all referencing pages if changing behavior. Check if
+    `docs/sidebar.json` needs updates.
+5.  **Plan:** Create a step-by-step plan before making changes.
+
+## Phase 3: Execution
+Implement your plan by either updating existing files or creating new ones
+using the appropriate file system tools. Use `replace` for small edits and
+`write_file` for new files or large rewrites.
+
+### Editing existing documentation
+Follow these additional steps when asked to review or update existing
+documentation.
+
+- **Gaps:** Identify areas where the documentation is incomplete or no longer
+  reflects existing code.
+- **Structure:** Apply "Structure (New Docs)" rules (BLUF, headings, etc.) when 
+  adding new sections to existing pages.
+- **Tone:** Ensure the tone is active and engaging. Use "you" and contractions.
+- **Clarity:** Correct awkward wording, spelling, and grammar. Rephrase
+  sentences to make them easier for users to understand.
+- **Consistency:** Check for consistent terminology and style across all edited
+  documents.
 
 
+## Phase 4: Verification and finalization
+Perform a final quality check to ensure that all changes are correctly formatted
+and that all links are functional.
 
-### Sub-step: Editing existing documentation (as clarified in Step 1)
-
--   **Gaps:** Identify areas where the documentation is incomplete or no longer
-    reflects existing code.
--   **Tone:** Ensure the tone is active and engaging, not passive.
--   **Clarity:** Correct awkward wording, spelling, and grammar. Rephrase
-    sentences to make them easier for users to understand.
--   **Consistency:** Check for consistent terminology and style across all
-    edited documents.
-
-## Step 4: Verify and finalize
-
-1.  **Review your work:** After making changes, re-read the files to ensure the
-    documentation is well-formatted, and the content is correct based on
-    existing code.
-2.  **Link verification:** Verify the validity of all links in the new content.
-    Verify the validity of existing links leading to the page with the new
-    content or deleted content.
-2.  **Offer to run npm format:** Once all changes are complete, offer to run the
-    project's formatting script to ensure consistency by proposing the command:
-    `npm run format`
+1.  **Accuracy:** Ensure content accurately reflects the implementation and
+  technical behavior.
+2.  **Self-review:** Re-read changes for formatting, correctness, and flow.
+3.  **Link check:** Verify all new and existing links leading to or from modified
+    pages.
+4.  **Format:** Once all changes are complete, ask to execute `npm run format`
+    to ensure consistent formatting across the project. If the user confirms,
+    execute the command.

.gemini/skills/docs-writer/references/style-guide.md

@@ -1,96 +0,0 @@
-# Documentation style guide
-
-## I. Core principles
-
-1.  **Clarity:** Write for easy understanding. Prioritize clear, direct, and
-    simple language.
-2.  **Consistency:** Use consistent terminology, formatting, and style
-    throughout the documentation.
-3.  **Accuracy:** Ensure all information is technically correct and up-to-date.
-4.  **Accessibility:** Design documentation to be usable by everyone. Focus on
-    semantic structure, clear link text, and image alternatives.
-5.  **Global audience:** Write in standard US English. Avoid slang, idioms, and
-    cultural references.
-6.  **Prescriptive:** Guide the reader by recommending specific actions and
-    paths, especially for complex tasks.
-
-## II. Voice and tone
-
-- **Professional yet friendly:** Maintain a helpful, knowledgeable, and
-  conversational tone without being frivolous.
-- **Direct:** Get straight to the point. Keep paragraphs short and focused.
-- **Second person:** Address the reader as "you."
-- **Present tense:** Use the present tense to describe functionality (e.g., "The
-  API returns a JSON object.").
-- **Avoid:** Jargon, slang, marketing hype, and overly casual language.
-
-## III. Language and grammar
-
-- **Active voice:** Prefer active voice over passive voice.
-  - _Example:_ "The system sends a notification." (Not: "A notification is sent
-    by the system.")
-- **Contractions:** Use common contractions (e.g., "don't," "it's") to maintain
-  a natural tone.
-- **Simple vocabulary:** Use common words. Define technical terms when
-  necessary.
-- **Conciseness:** Keep sentences short and focused, but don't omit helpful
-  information.
-- **"Please":** Avoid using the word "please."
-
-## IV. Procedures and steps
-
-- Start each step with an imperative verb (e.g., "Connect to the database").
-- Number steps sequentially.
-- Introduce lists of steps with a complete sentence.
-- Put conditions before instructions, not after.
-- Provide clear context for where the action takes place (e.g., "In the
-  administration console...").
-- Indicate optional steps clearly (e.g., "Optional: ...").
-
-## V. Formatting and punctuation
-
-- **Text wrap:** Wrap all text at 80 characters, with exceptions for long links
-  or tables.
-- **Headings, titles, and bold text:** Use sentence case. Structure headings
-  hierarchically.
-- **Lists:** Use numbered lists for sequential steps and bulleted lists for all
-  other lists. Keep list items parallel in structure.
-- **Serial comma:** Use the serial comma (e.g., "one, two, and three").
-- **Punctuation:** Use standard American punctuation. Place periods inside
-  quotation marks.
-- **Dates:** Use unambiguous date formatting (e.g., "January 22, 2026").
-
-## VI. UI, code, and links
-
-- **UI elements:** Put UI elements in **bold**. Focus on the task when
-  discussing interaction.
-- **Code:** Use `code font` for filenames, code snippets, commands, and API
-  elements. Use code blocks for multi-line samples.
-- **Links:** Use descriptive link text that indicates what the link leads to.
-  Avoid "click here."
-
-## VII. Word choice and terminology
-
-- **Consistent naming:** Use product and feature names consistently. Always
-  refer to Gemini CLI as `Gemini CLI`, never `the Gemini CLI`.
-- **Specific verbs:** Use precise verbs.
-- **Avoid:**
-  - Latin abbreviations (e.g., use "for example" instead of "e.g.").
-  - Placeholder names like "foo" and "bar" in examples; use meaningful names
-    instead.
-  - Anthropomorphism (e.g., "The server thinks...").
-  - "Should": Be clear about requirements ("must") vs. recommendations ("we
-    recommend").
-
-## VIII. Files and media
-
-- **Filenames:** Use lowercase letters, separate words with hyphens (-), and use
-  standard ASCII characters.
-- **Images:** Provide descriptive alt text for all images. Provide
-  high-resolution or vector images when practical.
-
-## IX. Accessibility quick check
-
-- Provide descriptive alt text for images.
-- Ensure link text makes sense out of context.
-- Use semantic HTML elements correctly (headings, lists, tables).

.github/workflows/ci.yml

@@ -177,6 +177,19 @@ jobs:
       - name: 'Smoke test bundle'
         run: 'node ./bundle/gemini.js --version'
 
+      - name: 'Smoke test npx installation'
+        run: |
+          # 1. Package the project into a tarball
+          TARBALL=$(npm pack | tail -n 1)
+
+          # 2. Move to a fresh directory for isolation
+          mkdir -p ../smoke-test-dir
+          mv "$TARBALL" ../smoke-test-dir/
+          cd ../smoke-test-dir
+
+          # 3. Run npx from the tarball
+          npx "./$TARBALL" --version
+
       - name: 'Wait for file system sync'
         run: 'sleep 2'
 
@@ -252,6 +265,19 @@ jobs:
       - name: 'Smoke test bundle'
         run: 'node ./bundle/gemini.js --version'
 
+      - name: 'Smoke test npx installation'
+        run: |
+          # 1. Package the project into a tarball
+          TARBALL=$(npm pack | tail -n 1)
+
+          # 2. Move to a fresh directory for isolation
+          mkdir -p ../smoke-test-dir
+          mv "$TARBALL" ../smoke-test-dir/
+          cd ../smoke-test-dir
+
+          # 3. Run npx from the tarball
+          npx "./$TARBALL" --version
+
       - name: 'Wait for file system sync'
         run: 'sleep 2'
 
@@ -396,6 +422,21 @@ jobs:
         run: 'node ./bundle/gemini.js --version'
         shell: 'pwsh'
 
+      - name: 'Smoke test npx installation'
+        run: |
+          # 1. Package the project into a tarball
+          $PACK_OUTPUT = npm pack
+          $TARBALL = $PACK_OUTPUT[-1]
+
+          # 2. Move to a fresh directory for isolation
+          New-Item -ItemType Directory -Force -Path ../smoke-test-dir
+          Move-Item $TARBALL ../smoke-test-dir/
+          Set-Location ../smoke-test-dir
+
+          # 3. Run npx from the tarball
+          npx "./$TARBALL" --version
+        shell: 'pwsh'
+
   ci:
     name: 'CI'
     if: 'always()'

.github/workflows/gemini-scheduled-stale-pr-closer.yml

@@ -43,19 +43,23 @@ jobs:
 
             // 1. Fetch maintainers for verification
             let maintainerLogins = new Set();
+            let teamFetchSucceeded = false;
             try {
               const members = await github.paginate(github.rest.teams.listMembersInOrg, {
                 org: context.repo.owner,
                 team_slug: 'gemini-cli-maintainers'
               });
-              maintainerLogins = new Set(members.map(m => m.login));
+              maintainerLogins = new Set(members.map(m => m.login.toLowerCase()));
+              teamFetchSucceeded = true;
+              core.info(`Successfully fetched ${maintainerLogins.size} team members from gemini-cli-maintainers`);
             } catch (e) {
-              core.warning('Failed to fetch team members');
+              core.warning(`Failed to fetch team members from gemini-cli-maintainers: ${e.message}. Falling back to author_association only.`);
             }
 
             const isMaintainer = (login, assoc) => {
-              if (maintainerLogins.size > 0) return maintainerLogins.has(login);
-              return ['OWNER', 'MEMBER', 'COLLABORATOR'].includes(assoc);
+              const isTeamMember = maintainerLogins.has(login.toLowerCase());
+              const isRepoMaintainer = ['OWNER', 'MEMBER', 'COLLABORATOR'].includes(assoc);
+              return isTeamMember || isRepoMaintainer;
             };
 
             // 2. Determine which PRs to check
@@ -153,7 +157,17 @@ jobs:
                 const labels = pr.labels.map(l => l.name.toLowerCase());
                 if (labels.includes('help wanted') || labels.includes('🔒 maintainer only')) continue;
 
-                let lastActivity = new Date(0);
+                // Skip PRs that were created less than 30 days ago - they cannot be stale yet
+                const prCreatedAt = new Date(pr.created_at);
+                if (prCreatedAt > thirtyDaysAgo) {
+                  const daysOld = Math.floor((Date.now() - prCreatedAt.getTime()) / (1000 * 60 * 60 * 24));
+                  core.info(`PR #${pr.number} was created ${daysOld} days ago. Skipping staleness check.`);
+                  continue;
+                }
+
+                // Initialize lastActivity to PR creation date (not epoch) as a safety baseline.
+                // This ensures we never incorrectly mark a PR as stale due to failed activity lookups.
+                let lastActivity = new Date(pr.created_at);
                 try {
                   const reviews = await github.paginate(github.rest.pulls.listReviews, {
                     owner: context.repo.owner,
@@ -177,8 +191,12 @@ jobs:
                       if (d > lastActivity) lastActivity = d;
                     }
                   }
-                } catch (e) {}
+                } catch (e) {
+                  core.warning(`Failed to fetch reviews/comments for PR #${pr.number}: ${e.message}`);
+                }
 
+                // For maintainer PRs, the PR creation itself counts as maintainer activity.
+                // (Now redundant since we initialize to pr.created_at, but kept for clarity)
                 if (maintainerPr) {
                   const d = new Date(pr.created_at);
                   if (d > lastActivity) lastActivity = d;

CONTRIBUTING.md

@@ -45,7 +45,7 @@ The process for contributing code is as follows:
     `🔒Maintainers only`, this means it is reserved for project maintainers. We
     will not accept pull requests related to these issues. In the near future,
     we will explicitly mark issues looking for contributions using the
-    `help  wanted` label. If you believe an issue is a good candidate for
+    `help-wanted` label. If you believe an issue is a good candidate for
     community contribution, please leave a comment on the issue. A maintainer
     will review it and apply the `help-wanted` label if appropriate. Only
     maintainers should attempt to add the `help-wanted` label to an issue.

README.md

@@ -124,6 +124,8 @@ npm install -g @google/gemini-cli@nightly
 
 ### Advanced Capabilities
 
+- **Automated Iterative Loops**: Use [Ralph Wiggum mode](./docs/ralph-wiggum.md)
+  to repeatedly execute prompts until a goal is met (e.g., fixing tests).
 - Ground your queries with built-in
   [Google Search](https://ai.google.dev/gemini-api/docs/grounding) for real-time
   information
@@ -256,6 +258,33 @@ use `--output-format stream-json` to get newline-delimited JSON events:
 gemini -p "Run tests and deploy" --output-format stream-json
 ```
 
+### Ralph Wiggum Mode (Iterative Automation)
+
+Ralph Wiggum mode is an advanced automation feature that allows Gemini CLI to
+repeatedly execute a prompt in a loop until a specific goal is achieved. This is
+ideal for tasks like fixing failing tests or complex refactoring.
+
+To use Ralph Wiggum mode, provide a prompt and a **completion promise** (a
+string to look for in the output). The CLI will:
+
+1.  Enter **YOLO mode** to auto-approve all tool calls.
+2.  Run the prompt and check the response for your completion string.
+3.  If not found, it repeats the process up to a specified **max iterations**.
+4.  **Persistent Context**: It uses a **memory file** (`memories.md` by default)
+    to pass notes between iterations. **Note:** Use a unique `--memory-file` for
+    different tasks in the same directory to ensure context isolation.
+
+```bash
+gemini -p "Fix the failing tests in this repo" \
+  --ralph-wiggum \
+  --completion-promise "ALL TESTS PASSED" \
+  --max-iterations 5 \
+  --memory-file "task-fix-tests.md"
+```
+
+At the end of the run, a summary table displays the result of each iteration and
+extracted test statistics.
+
 ### Quick Examples
 
 #### Start a new project

docs/cli/cli-reference.md

@@ -35,6 +35,9 @@ and parameters.
 | `--model`                        | `-m`  | string  | `auto`    | Model to use. See [Model Selection](#model-selection) for available values.                                |
 | `--prompt`                       | `-p`  | string  | -         | Prompt text. Appended to stdin input if provided. **Deprecated:** Use positional arguments instead.        |
 | `--prompt-interactive`           | `-i`  | string  | -         | Execute prompt and continue in interactive mode                                                            |
+| `--ralph-wiggum`                 | -     | boolean | `false`   | Enable Ralph Wiggum iterative loop mode                                                                    |
+| `--completion-promise`           | -     | string  | -         | String to look for to signal completion in Ralph Wiggum mode                                               |
+| `--max-iterations`               | -     | number  | `10`      | Maximum loop iterations for Ralph Wiggum mode                                                              |
 | `--sandbox`                      | `-s`  | boolean | `false`   | Run in a sandboxed environment for safer execution                                                         |
 | `--approval-mode`                | -     | string  | `default` | Approval mode for tool execution. Choices: `default`, `auto_edit`, `yolo`                                  |
 | `--yolo`                         | `-y`  | boolean | `false`   | **Deprecated.** Auto-approve all actions. Use `--approval-mode=yolo` instead.                              |
@@ -99,3 +102,18 @@ See [Extensions Documentation](../extensions/index.md) for more details.
 | `gemini mcp list`                                             | List all configured MCP servers | `gemini mcp list`                                                                                    |
 
 See [MCP Server Integration](../tools/mcp-server.md) for more details.
+
+## Skills management
+
+| Command                          | Description                           | Example                                           |
+| -------------------------------- | ------------------------------------- | ------------------------------------------------- |
+| `gemini skills list`             | List all discovered agent skills      | `gemini skills list`                              |
+| `gemini skills install <source>` | Install skill from Git, path, or file | `gemini skills install https://github.com/u/repo` |
+| `gemini skills link <path>`      | Link local agent skills via symlink   | `gemini skills link /path/to/my-skills`           |
+| `gemini skills uninstall <name>` | Uninstall an agent skill              | `gemini skills uninstall my-skill`                |
+| `gemini skills enable <name>`    | Enable an agent skill                 | `gemini skills enable my-skill`                   |
+| `gemini skills disable <name>`   | Disable an agent skill                | `gemini skills disable my-skill`                  |
+| `gemini skills enable --all`     | Enable all skills                     | `gemini skills enable --all`                      |
+| `gemini skills disable --all`    | Disable all skills                    | `gemini skills disable --all`                     |
+
+See [Agent Skills Documentation](./skills.md) for more details.

docs/cli/commands.md

@@ -10,6 +10,14 @@ Slash commands provide meta-level control over the CLI itself.
 
 ### Built-in Commands
 
+- **`/about`**
+  - **Description:** Show version info. Please share this information when
+    filing issues.
+
+- **`/auth`**
+  - **Description:** Open a dialog that lets you change the authentication
+    method.
+
 - **`/bug`**
   - **Description:** File an issue about Gemini CLI. By default, the issue is
     filed within the GitHub repository for Gemini CLI. The string you enter
@@ -22,10 +30,21 @@ Slash commands provide meta-level control over the CLI itself.
     conversation state interactively, or resuming a previous state from a later
     session.
   - **Sub-commands:**
-    - **`save`**
+    - **`delete <tag>`**
+      - **Description:** Deletes a saved conversation checkpoint.
+    - **`list`**
+      - **Description:** Lists available tags for chat state resumption.
+      - **Note:** This command only lists chats saved within the current
+        project. Because chat history is project-scoped, chats saved in other
+        project directories will not be displayed.
+    - **`resume <tag>`**
+      - **Description:** Resumes a conversation from a previous save.
+      - **Note:** You can only resume chats that were saved within the current
+        project. To resume a chat from a different project, you must run the
+        Gemini CLI from that project's directory.
+    - **`save <tag>`**
       - **Description:** Saves the current conversation history. You must add a
         `<tag>` for identifying the conversation state.
-      - **Usage:** `/chat save <tag>`
       - **Details on checkpoint location:** The default locations for saved chat
         checkpoints are:
         - Linux/macOS: `~/.gemini/tmp/<project_hash>/`
@@ -37,25 +56,11 @@ Slash commands provide meta-level control over the CLI itself.
           conversation states. For automatic checkpoints created before file
           modifications, see the
           [Checkpointing documentation](../cli/checkpointing.md).
-    - **`resume`**
-      - **Description:** Resumes a conversation from a previous save.
-      - **Usage:** `/chat resume <tag>`
-      - **Note:** You can only resume chats that were saved within the current
-        project. To resume a chat from a different project, you must run the
-        Gemini CLI from that project's directory.
-    - **`list`**
-      - **Description:** Lists available tags for chat state resumption.
-      - **Note:** This command only lists chats saved within the current
-        project. Because chat history is project-scoped, chats saved in other
-        project directories will not be displayed.
-    - **`delete`**
-      - **Description:** Deletes a saved conversation checkpoint.
-      - **Usage:** `/chat delete <tag>`
-    - **`share`**
+    - **`share [filename]`**
       - **Description** Writes the current conversation to a provided Markdown
-        or JSON file.
-      - **Usage** `/chat share file.md` or `/chat share file.json`. If no
-        filename is provided, then the CLI will generate one.
+        or JSON file. If no filename is provided, then the CLI will generate
+        one.
+      - **Usage** `/chat share file.md` or `/chat share file.json`.
 
 - **`/clear`**
   - **Description:** Clear the terminal screen, including the visible session
@@ -98,6 +103,9 @@ Slash commands provide meta-level control over the CLI itself.
         `--include-directories`.
       - **Usage:** `/directory show`
 
+- **`/docs`**
+  - **Description:** Open the Gemini CLI documentation in your browser.
+
 - **`/editor`**
   - **Description:** Open a dialog for selecting supported editors.
 
@@ -109,30 +117,65 @@ Slash commands provide meta-level control over the CLI itself.
   - **Description:** Display help information about Gemini CLI, including
     available commands and their usage.
 
+- **`/hooks`**
+  - **Description:** Manage hooks, which allow you to intercept and customize
+    Gemini CLI behavior at specific lifecycle events.
+  - **Sub-commands:**
+    - **`disable-all`**:
+      - **Description:** Disable all enabled hooks.
+    - **`disable <hook-name>`**:
+      - **Description:** Disable a hook by name.
+    - **`enable-all`**:
+      - **Description:** Enable all disabled hooks.
+    - **`enable <hook-name>`**:
+      - **Description:** Enable a hook by name.
+    - **`list`** (or `show`, `panel`):
+      - **Description:** Display all registered hooks with their status.
+
+- **`/ide`**
+  - **Description:** Manage IDE integration.
+  - **Sub-commands:**
+    - **`disable`**:
+      - **Description:** Disable IDE integration.
+    - **`enable`**:
+      - **Description:** Enable IDE integration.
+    - **`install`**:
+      - **Description:** Install required IDE companion.
+    - **`status`**:
+      - **Description:** Check status of IDE integration.
+
+- **`/init`**
+  - **Description:** To help users easily create a `GEMINI.md` file, this
+    command analyzes the current directory and generates a tailored context
+    file, making it simpler for them to provide project-specific instructions to
+    the Gemini agent.
+
+- **`/introspect`**
+  - **Description:** Provide debugging information about the current Gemini CLI
+    session, including the state of loaded sub-agents and active hooks. This
+    command is primarily for advanced users and developers.
+
 - **`/mcp`**
   - **Description:** Manage configured Model Context Protocol (MCP) servers.
   - **Sub-commands:**
-    - **`list`** or **`ls`**:
-      - **Description:** List configured MCP servers and tools. This is the
-        default action if no subcommand is specified.
-    - **`desc`**
-      - **Description:** List configured MCP servers and tools with
-        descriptions.
-    - **`schema`**:
-      - **Description:** List configured MCP servers and tools with descriptions
-        and schemas.
     - **`auth`**:
       - **Description:** Authenticate with an OAuth-enabled MCP server.
       - **Usage:** `/mcp auth <server-name>`
       - **Details:** If `<server-name>` is provided, it initiates the OAuth flow
         for that server. If no server name is provided, it lists all configured
         servers that support OAuth authentication.
+    - **`desc`**
+      - **Description:** List configured MCP servers and tools with
+        descriptions.
+    - **`list`** or **`ls`**:
+      - **Description:** List configured MCP servers and tools. This is the
+        default action if no subcommand is specified.
     - **`refresh`**:
       - **Description:** Restarts all MCP servers and re-discovers their
         available tools.
-
-- [**`/model`**](./model.md)
-  - **Description:** Opens a dialog to choose your Gemini model.
+    - **`schema`**:
+      - **Description:** List configured MCP servers and tools with descriptions
+        and schemas.
 
 - **`/memory`**
   - **Description:** Manage the AI's instructional context (hierarchical memory
@@ -141,23 +184,40 @@ Slash commands provide meta-level control over the CLI itself.
     - **`add`**:
       - **Description:** Adds the following text to the AI's memory. Usage:
         `/memory add <text to remember>`
-    - **`show`**:
-      - **Description:** Display the full, concatenated content of the current
-        hierarchical memory that has been loaded from all `GEMINI.md` files.
-        This lets you inspect the instructional context being provided to the
-        Gemini model.
+    - **`list`**:
+      - **Description:** Lists the paths of the GEMINI.md files in use for
+        hierarchical memory.
     - **`refresh`**:
       - **Description:** Reload the hierarchical instructional memory from all
         `GEMINI.md` files found in the configured locations (global,
         project/ancestors, and sub-directories). This command updates the model
         with the latest `GEMINI.md` content.
-    - **`list`**:
-      - **Description:** Lists the paths of the GEMINI.md files in use for
-        hierarchical memory.
+    - **`show`**:
+      - **Description:** Display the full, concatenated content of the current
+        hierarchical memory that has been loaded from all `GEMINI.md` files.
+        This lets you inspect the instructional context being provided to the
+        Gemini model.
     - **Note:** For more details on how `GEMINI.md` files contribute to
       hierarchical memory, see the
       [CLI Configuration documentation](../get-started/configuration.md).
 
+- [**`/model`**](./model.md)
+  - **Description:** Opens a dialog to choose your Gemini model.
+
+- **`/policies`**
+  - **Description:** Manage policies.
+  - **Sub-commands:**
+    - **`list`**:
+      - **Description:** List all active policies grouped by mode.
+
+- **`/privacy`**
+  - **Description:** Display the Privacy Notice and allow users to select
+    whether they consent to the collection of their data for service improvement
+    purposes.
+
+- **`/quit`** (or **`/exit`**)
+  - **Description:** Exit Gemini CLI.
+
 - **`/restore`**
   - **Description:** Restores the project files to the state they were in just
     before a tool was executed. This is particularly useful for undoing file
@@ -168,18 +228,24 @@ 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:** Navigates backward through the conversation history,
+    allowing you to review past interactions and potentially revert to a
+    previous state. This feature helps in managing complex or branched
+    conversations.
+
 - **`/resume`**
   - **Description:** Browse and resume previous conversation sessions. Opens an
     interactive session browser where you can search, filter, and select from
     automatically saved conversations.
   - **Features:**
-    - **Session Browser:** Interactive interface showing all saved sessions with
-      timestamps, message counts, and first user message for context
-    - **Search:** Use `/` to search through conversation content across all
-      sessions
-    - **Sorting:** Sort sessions by date or message count
     - **Management:** Delete unwanted sessions directly from the browser
     - **Resume:** Select any session to resume and continue the conversation
+    - **Search:** Use `/` to search through conversation content across all
+      sessions
+    - **Session Browser:** Interactive interface showing all saved sessions with
+      timestamps, message counts, and first user message for context
+    - **Sorting:** Sort sessions by date or message count
   - **Note:** All conversations are automatically saved as you chat - no manual
     saving required. See [Session Management](../cli/session-management.md) for
     complete details.
@@ -198,19 +264,26 @@ Slash commands provide meta-level control over the CLI itself.
     modify them as desired. Changes to some settings are applied immediately,
     while others require a restart.
 
+- **`/shells`** (or **`/bashes`**)
+  - **Description:** Toggle the background shells view. This allows you to view
+    and manage long-running processes that you've sent to the background.
+- **`/setup-github`**
+  - **Description:** Set up GitHub Actions to triage issues and review PRs with
+    Gemini.
+
 - [**`/skills`**](./skills.md)
   - **Description:** Manage Agent Skills, which provide on-demand expertise and
     specialized workflows.
   - **Sub-commands:**
+    - **`disable <name>`**:
+      - **Description:** Disable a specific skill by name.
+      - **Usage:** `/skills disable <name>`
+    - **`enable <name>`**:
+      - **Description:** Enable a specific skill by name.
+      - **Usage:** `/skills enable <name>`
     - **`list`**:
       - **Description:** List all discovered skills and their current status
         (enabled/disabled).
-    - **`enable`**:
-      - **Description:** Enable a specific skill by name.
-      - **Usage:** `/skills enable <name>`
-    - **`disable`**:
-      - **Description:** Disable a specific skill by name.
-      - **Usage:** `/skills disable <name>`
     - **`reload`**:
       - **Description:** Refresh the list of discovered skills from all tiers
         (workspace, user, and extensions).
@@ -222,18 +295,14 @@ Slash commands provide meta-level control over the CLI itself.
     cached tokens are being used, which occurs with API key authentication but
     not with OAuth authentication at this time.
 
+- **`/terminal-setup`**
+  - **Description:** Configure terminal keybindings for multiline input (VS
+    Code, Cursor, Windsurf).
+
 - [**`/theme`**](./themes.md)
   - **Description:** Open a dialog that lets you change the visual theme of
     Gemini CLI.
 
-- **`/auth`**
-  - **Description:** Open a dialog that lets you change the authentication
-    method.
-
-- **`/about`**
-  - **Description:** Show version info. Please share this information when
-    filing issues.
-
 - [**`/tools`**](../tools/index.md)
   - **Description:** Display a list of tools that are currently available within
     Gemini CLI.
@@ -245,37 +314,23 @@ Slash commands provide meta-level control over the CLI itself.
     - **`nodesc`** or **`nodescriptions`**:
       - **Description:** Hide tool descriptions, showing only the tool names.
 
-- **`/privacy`**
-  - **Description:** Display the Privacy Notice and allow users to select
-    whether they consent to the collection of their data for service improvement
-    purposes.
-
-- **`/quit`** (or **`/exit`**)
-  - **Description:** Exit Gemini CLI.
-
 - **`/vim`**
   - **Description:** Toggle vim mode on or off. When vim mode is enabled, the
     input area supports vim-style navigation and editing commands in both NORMAL
     and INSERT modes.
   - **Features:**
+    - **Count support:** Prefix commands with numbers (e.g., `3h`, `5w`, `10G`)
+    - **Editing commands:** Delete with `x`, change with `c`, insert with `i`,
+      `a`, `o`, `O`; complex operations like `dd`, `cc`, `dw`, `cw`
+    - **INSERT mode:** Standard text input with escape to return to NORMAL mode
     - **NORMAL mode:** Navigate with `h`, `j`, `k`, `l`; jump by words with `w`,
       `b`, `e`; go to line start/end with `0`, `$`, `^`; go to specific lines
       with `G` (or `gg` for first line)
-    - **INSERT mode:** Standard text input with escape to return to NORMAL mode
-    - **Editing commands:** Delete with `x`, change with `c`, insert with `i`,
-      `a`, `o`, `O`; complex operations like `dd`, `cc`, `dw`, `cw`
-    - **Count support:** Prefix commands with numbers (e.g., `3h`, `5w`, `10G`)
-    - **Repeat last command:** Use `.` to repeat the last editing operation
     - **Persistent setting:** Vim mode preference is saved to
       `~/.gemini/settings.json` and restored between sessions
-  - **Status indicator:** When enabled, shows `[NORMAL]` or `[INSERT]` in the
-    footer
-
-- **`/init`**
-  - **Description:** To help users easily create a `GEMINI.md` file, this
-    command analyzes the current directory and generates a tailored context
-    file, making it simpler for them to provide project-specific instructions to
-    the Gemini agent.
+    - **Repeat last command:** Use `.` to repeat the last editing operation
+    - **Status indicator:** When enabled, shows `[NORMAL]` or `[INSERT]` in the
+      footer
 
 ### Custom commands
 

docs/cli/creating-skills.md

@@ -0,0 +1,80 @@
+# Creating Agent Skills
+
+This guide provides an overview of how to create your own Agent Skills to extend
+the capabilities of Gemini CLI.
+
+## Getting started: The `skill-creator` skill
+
+The recommended way to create a new skill is to use the built-in `skill-creator`
+skill. To use it, ask Gemini CLI to create a new skill for you.
+
+**Example prompt:**
+
+> "create a new skill called 'code-reviewer'"
+
+Gemini CLI will then use the `skill-creator` to generate the skill:
+
+1.  Generate a new directory for your skill (e.g., `my-new-skill/`).
+2.  Create a `SKILL.md` file with the necessary YAML frontmatter (`name` and
+    `description`).
+3.  Create the standard resource directories: `scripts/`, `references/`, and
+    `assets/`.
+
+## Manual skill creation
+
+If you prefer to create skills manually:
+
+1.  **Create a directory** for your skill (e.g., `my-new-skill/`).
+2.  **Create a `SKILL.md` file** inside the new directory.
+
+To add additional resources that support the skill, refer to the skill
+structure.
+
+## Skill structure
+
+A skill is a directory containing a `SKILL.md` file at its root.
+
+### Folder structure
+
+While a `SKILL.md` file is the only required component, we recommend the
+following structure for organizing your skill's resources:
+
+```text
+my-skill/
+├── SKILL.md       (Required) Instructions and metadata
+├── scripts/       (Optional) Executable scripts
+├── references/    (Optional) Static documentation
+└── assets/        (Optional) Templates and other resources
+```
+
+### `SKILL.md` file
+
+The `SKILL.md` file is the core of your skill. This file uses YAML frontmatter
+for metadata and Markdown for instructions. For example:
+
+```markdown
+---
+name: code-reviewer
+description:
+  Use this skill to review code. It supports both local changes and remote Pull
+  Requests.
+---
+
+# Code Reviewer
+
+This skill guides the agent in conducting thorough code reviews.
+
+## Workflow
+
+### 1. Determine Review Target
+
+- **Remote PR**: If the user gives a PR number or URL, target that remote PR.
+- **Local Changes**: If changes are local... ...
+```
+
+- **`name`**: A unique identifier for the skill. This should match the directory
+  name.
+- **`description`**: A description of what the skill does and when Gemini should
+  use it.
+- **Body**: The Markdown body of the file contains the instructions that guide
+  the agent's behavior when the skill is active.

docs/cli/enterprise.md

@@ -203,6 +203,23 @@ with the actual Gemini CLI process, which inherits the environment variable.
 This makes it significantly more difficult for a user to bypass the enforced
 settings.
 
+## User isolation in shared environments
+
+In shared compute environments (like ML experiment runners or shared build
+servers), you can isolate Gemini CLI state by overriding the user's home
+directory.
+
+By default, Gemini CLI stores configuration and history in `~/.gemini`. You can
+use the `GEMINI_CLI_HOME` environment variable to point to a unique directory
+for a specific user or job. The CLI will create a `.gemini` folder inside the
+specified path.
+
+```bash
+# Isolate state for a specific job
+export GEMINI_CLI_HOME="/tmp/gemini-job-123"
+gemini
+```
+
 ## Restricting tool access
 
 You can significantly enhance security by controlling which tools the Gemini

docs/cli/keyboard-shortcuts.md

@@ -23,7 +23,7 @@ available combinations.
 | 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 left.  | `Left Arrow (no Shift, Alt, Ctrl, Cmd)`                      |
 | 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` |
@@ -106,6 +106,14 @@ available combinations.
 | 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 + O`<br />`Ctrl + S` |
+| Ctrl+B                                                                                                | `Ctrl + B`                 |
+| Ctrl+L                                                                                                | `Ctrl + L`                 |
+| Ctrl+K                                                                                                | `Ctrl + K`                 |
+| Enter                                                                                                 | `Enter`                    |
+| Esc                                                                                                   | `Esc`                      |
+| Shift+Tab                                                                                             | `Shift + Tab`              |
+| Tab                                                                                                   | `Tab (no Shift)`           |
+| Tab                                                                                                   | `Tab (no Shift)`           |
 | 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`                 |

docs/cli/settings.md

@@ -39,31 +39,33 @@ they appear in the UI.
 
 ### UI
 
-| UI Label                       | Setting                                 | Description                                                                                                                                                       | Default |
-| ------------------------------ | --------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
-| Hide Window Title              | `ui.hideWindowTitle`                    | Hide the window title bar                                                                                                                                         | `false` |
-| Show Thoughts in Title         | `ui.showStatusInTitle`                  | Show Gemini CLI model thoughts in the terminal window title during the working phase                                                                              | `false` |
-| Dynamic Window Title           | `ui.dynamicWindowTitle`                 | Update the terminal window title with current status icons (Ready: ◇, Action Required: ✋, Working: ✦)                                                            | `true`  |
-| Show Home Directory Warning    | `ui.showHomeDirectoryWarning`           | Show a warning when running Gemini CLI in the home directory.                                                                                                     | `true`  |
-| Hide Tips                      | `ui.hideTips`                           | Hide helpful tips in the UI                                                                                                                                       | `false` |
-| Hide Banner                    | `ui.hideBanner`                         | Hide the application banner                                                                                                                                       | `false` |
-| Hide Context Summary           | `ui.hideContextSummary`                 | Hide the context summary (GEMINI.md, MCP servers) above the input.                                                                                                | `false` |
-| Hide CWD                       | `ui.footer.hideCWD`                     | Hide the current working directory path in the footer.                                                                                                            | `false` |
-| Hide Sandbox Status            | `ui.footer.hideSandboxStatus`           | Hide the sandbox status indicator in the footer.                                                                                                                  | `false` |
-| Hide Model Info                | `ui.footer.hideModelInfo`               | Hide the model name and context usage in the footer.                                                                                                              | `false` |
-| Hide Context Window Percentage | `ui.footer.hideContextPercentage`       | Hides the context window remaining percentage.                                                                                                                    | `true`  |
-| Hide Footer                    | `ui.hideFooter`                         | Hide the footer from the UI                                                                                                                                       | `false` |
-| Show Memory Usage              | `ui.showMemoryUsage`                    | Display memory usage information in the UI                                                                                                                        | `false` |
-| Show Line Numbers              | `ui.showLineNumbers`                    | Show line numbers in the chat.                                                                                                                                    | `true`  |
-| Show Citations                 | `ui.showCitations`                      | Show citations for generated text in the chat.                                                                                                                    | `false` |
-| Show Model Info In Chat        | `ui.showModelInfoInChat`                | Show the model name in the chat for each model turn.                                                                                                              | `false` |
-| Show User Identity             | `ui.showUserIdentity`                   | Show the logged-in user's identity (e.g. email) in the UI.                                                                                                        | `true`  |
-| Use Alternate Screen Buffer    | `ui.useAlternateBuffer`                 | Use an alternate screen buffer for the UI, preserving shell history.                                                                                              | `false` |
-| Use Background Color           | `ui.useBackgroundColor`                 | Whether to use background colors in the UI.                                                                                                                       | `true`  |
-| Incremental Rendering          | `ui.incrementalRendering`               | Enable incremental rendering for the UI. This option will reduce flickering but may cause rendering artifacts. Only supported when useAlternateBuffer is enabled. | `true`  |
-| Show Spinner                   | `ui.showSpinner`                        | Show the spinner during operations.                                                                                                                               | `true`  |
-| Enable Loading Phrases         | `ui.accessibility.enableLoadingPhrases` | Enable loading phrases during operations.                                                                                                                         | `true`  |
-| Screen Reader Mode             | `ui.accessibility.screenReader`         | Render output in plain-text to be more screen reader accessible                                                                                                   | `false` |
+| UI Label                             | Setting                                 | Description                                                                                                                                                       | Default |
+| ------------------------------------ | --------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
+| Auto Theme Switching                 | `ui.autoThemeSwitching`                 | Automatically switch between default light and dark themes based on terminal background color.                                                                    | `true`  |
+| Terminal Background Polling Interval | `ui.terminalBackgroundPollingInterval`  | Interval in seconds to poll the terminal background color.                                                                                                        | `60`    |
+| Hide Window Title                    | `ui.hideWindowTitle`                    | Hide the window title bar                                                                                                                                         | `false` |
+| Show Thoughts in Title               | `ui.showStatusInTitle`                  | Show Gemini CLI model thoughts in the terminal window title during the working phase                                                                              | `false` |
+| Dynamic Window Title                 | `ui.dynamicWindowTitle`                 | Update the terminal window title with current status icons (Ready: ◇, Action Required: ✋, Working: ✦)                                                            | `true`  |
+| Show Home Directory Warning          | `ui.showHomeDirectoryWarning`           | Show a warning when running Gemini CLI in the home directory.                                                                                                     | `true`  |
+| Hide Tips                            | `ui.hideTips`                           | Hide helpful tips in the UI                                                                                                                                       | `false` |
+| Hide Banner                          | `ui.hideBanner`                         | Hide the application banner                                                                                                                                       | `false` |
+| Hide Context Summary                 | `ui.hideContextSummary`                 | Hide the context summary (GEMINI.md, MCP servers) above the input.                                                                                                | `false` |
+| Hide CWD                             | `ui.footer.hideCWD`                     | Hide the current working directory path in the footer.                                                                                                            | `false` |
+| Hide Sandbox Status                  | `ui.footer.hideSandboxStatus`           | Hide the sandbox status indicator in the footer.                                                                                                                  | `false` |
+| Hide Model Info                      | `ui.footer.hideModelInfo`               | Hide the model name and context usage in the footer.                                                                                                              | `false` |
+| Hide Context Window Percentage       | `ui.footer.hideContextPercentage`       | Hides the context window remaining percentage.                                                                                                                    | `true`  |
+| Hide Footer                          | `ui.hideFooter`                         | Hide the footer from the UI                                                                                                                                       | `false` |
+| Show Memory Usage                    | `ui.showMemoryUsage`                    | Display memory usage information in the UI                                                                                                                        | `false` |
+| Show Line Numbers                    | `ui.showLineNumbers`                    | Show line numbers in the chat.                                                                                                                                    | `true`  |
+| Show Citations                       | `ui.showCitations`                      | Show citations for generated text in the chat.                                                                                                                    | `false` |
+| Show Model Info In Chat              | `ui.showModelInfoInChat`                | Show the model name in the chat for each model turn.                                                                                                              | `false` |
+| Show User Identity                   | `ui.showUserIdentity`                   | Show the logged-in user's identity (e.g. email) in the UI.                                                                                                        | `true`  |
+| Use Alternate Screen Buffer          | `ui.useAlternateBuffer`                 | Use an alternate screen buffer for the UI, preserving shell history.                                                                                              | `false` |
+| Use Background Color                 | `ui.useBackgroundColor`                 | Whether to use background colors in the UI.                                                                                                                       | `true`  |
+| Incremental Rendering                | `ui.incrementalRendering`               | Enable incremental rendering for the UI. This option will reduce flickering but may cause rendering artifacts. Only supported when useAlternateBuffer is enabled. | `true`  |
+| Show Spinner                         | `ui.showSpinner`                        | Show the spinner during operations.                                                                                                                               | `true`  |
+| Enable Loading Phrases               | `ui.accessibility.enableLoadingPhrases` | Enable loading phrases during operations.                                                                                                                         | `true`  |
+| Screen Reader Mode                   | `ui.accessibility.screenReader`         | Render output in plain-text to be more screen reader accessible                                                                                                   | `false` |
 
 ### IDE
 
@@ -77,6 +79,7 @@ they appear in the UI.
 | ----------------------- | ---------------------------- | -------------------------------------------------------------------------------------- | ------- |
 | Max Session Turns       | `model.maxSessionTurns`      | Maximum number of user/model/tool turns to keep in a session. -1 means unlimited.      | `-1`    |
 | Compression Threshold   | `model.compressionThreshold` | The fraction of context usage at which to trigger context compression (e.g. 0.2, 0.3). | `0.5`   |
+| Disable Loop Detection  | `model.disableLoopDetection` | Disable automatic detection and prevention of infinite loops.                          | `false` |
 | Skip Next Speaker Check | `model.skipNextSpeakerCheck` | Skip the next speaker check.                                                           | `true`  |
 
 ### Context
@@ -97,7 +100,6 @@ they appear in the UI.
 | -------------------------------- | ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------- |
 | Enable Interactive Shell         | `tools.shell.enableInteractiveShell` | Use node-pty for an interactive shell experience. Fallback to child_process still applies.                                                                                     | `true`      |
 | Show Color                       | `tools.shell.showColor`              | Show color in shell output.                                                                                                                                                    | `false`     |
-| Auto Accept                      | `tools.autoAccept`                   | Automatically accept and execute tool calls that are considered safe (e.g., read-only operations).                                                                             | `false`     |
 | Approval Mode                    | `tools.approvalMode`                 | The default approval mode for tool execution. 'default' prompts for approval, 'auto_edit' auto-approves edit tools, and 'plan' is read-only mode. 'yolo' is not supported yet. | `"default"` |
 | Use Ripgrep                      | `tools.useRipgrep`                   | Use ripgrep for file content search instead of the fallback implementation. Provides faster search performance.                                                                | `true`      |
 | Enable Tool Output Truncation    | `tools.enableToolOutputTruncation`   | Enable truncation of large tool outputs.                                                                                                                                       | `true`      |
@@ -107,13 +109,14 @@ they appear in the UI.
 
 ### Security
 
-| UI Label                              | Setting                                         | Description                                                                     | Default |
-| ------------------------------------- | ----------------------------------------------- | ------------------------------------------------------------------------------- | ------- |
-| Disable YOLO Mode                     | `security.disableYoloMode`                      | Disable YOLO mode, even if enabled by a flag.                                   | `false` |
-| Allow Permanent Tool Approval         | `security.enablePermanentToolApproval`          | Enable the "Allow for all future sessions" option in tool confirmation dialogs. | `false` |
-| Blocks extensions from Git            | `security.blockGitExtensions`                   | Blocks installing and loading extensions from Git.                              | `false` |
-| Folder Trust                          | `security.folderTrust.enabled`                  | Setting to track whether Folder trust is enabled.                               | `false` |
-| Enable Environment Variable Redaction | `security.environmentVariableRedaction.enabled` | Enable redaction of environment variables that may contain secrets.             | `false` |
+| UI Label                              | Setting                                         | Description                                                                                                                                                             | Default |
+| ------------------------------------- | ----------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
+| Disable YOLO Mode                     | `security.disableYoloMode`                      | Disable YOLO mode, even if enabled by a flag.                                                                                                                           | `false` |
+| Allow Permanent Tool Approval         | `security.enablePermanentToolApproval`          | Enable the "Allow for all future sessions" option in tool confirmation dialogs.                                                                                         | `false` |
+| Blocks extensions from Git            | `security.blockGitExtensions`                   | Blocks installing and loading extensions from Git.                                                                                                                      | `false` |
+| Extension Source Regex Allowlist      | `security.allowedExtensions`                    | List of Regex patterns for allowed extensions. If nonempty, only extensions that match the patterns in this list are allowed. Overrides the blockGitExtensions setting. | `[]`    |
+| Folder Trust                          | `security.folderTrust.enabled`                  | Setting to track whether Folder trust is enabled.                                                                                                                       | `true`  |
+| Enable Environment Variable Redaction | `security.environmentVariableRedaction.enabled` | Enable redaction of environment variables that may contain secrets.                                                                                                     | `false` |
 
 ### Experimental
 

docs/cli/skills.md

@@ -52,6 +52,7 @@ locations override lower ones: **Workspace > User > Extension**.
 Use the `/skills` slash command to view and manage available expertise:
 
 - `/skills list` (default): Shows all discovered skills and their status.
+- `/skills link <path>`: Links agent skills from a local directory via symlink.
 - `/skills disable <name>`: Prevents a specific skill from being used.
 - `/skills enable <name>`: Re-enables a disabled skill.
 - `/skills reload`: Refreshes the list of discovered skills from all tiers.
@@ -67,6 +68,13 @@ The `gemini skills` command provides management utilities:
 # List all discovered skills
 gemini skills list
 
+# Link agent skills from a local directory via symlink
+# Discovers skills (SKILL.md or */SKILL.md) and creates symlinks in ~/.gemini/skills (user)
+gemini skills link /path/to/my-skills-repo
+
+# Link to the workspace scope (.gemini/skills)
+gemini skills link /path/to/my-skills-repo --scope workspace
+
 # Install a skill from a Git repository, local directory, or zipped skill file (.skill)
 # Uses the user scope by default (~/.gemini/skills)
 gemini skills install https://github.com/user/repo.git
@@ -89,85 +97,7 @@ gemini skills enable my-expertise
 gemini skills disable my-expertise --scope workspace
 ```
 
-## Creating a Skill
-
-A skill is a directory containing a `SKILL.md` file at its root. This file
-serves as the entry point for your skill and uses YAML frontmatter for metadata
-and Markdown for instructions.
-
-### Folder Structure
-
-Skills are self-contained directories. At a minimum, a skill requires a
-`SKILL.md` file, but can include other resources:
-
-```text
-my-skill/
-├── SKILL.md       (Required) Instructions and metadata
-├── scripts/       (Optional) Executable scripts/tools
-├── references/    (Optional) Static documentation and examples
-└── assets/        (Optional) Templates and binary resources
-```
-
-### Basic Structure (SKILL.md)
-
-```markdown
----
-name: <unique-name>
-description: <what the skill does and when Gemini should use it>
----
-
-<your instructions for how the agent should behave / use the skill>
-```
-
-- **`name`**: A unique identifier (lowercase, alphanumeric, and dashes).
-- **`description`**: The most critical field. Gemini uses this to decide when
-  the skill is relevant. Be specific about the expertise provided.
-- **Body**: Everything below the second `---` is injected as expert procedural
-  guidance for the model.
-
-### Example: Team Code Reviewer
-
-Create `~/.gemini/skills/code-reviewer/SKILL.md`:
-
-```markdown
----
-name: code-reviewer
-description:
-  Expertise in reviewing code for style, security, and performance. Use when the
-  user asks for "feedback," a "review," or to "check" their changes.
----
-
-# Code Reviewer
-
-You are an expert code reviewer. When reviewing code, follow this workflow:
-
-1.  **Analyze**: Review the staged changes or specific files provided. Ensure
-    that the changes are scoped properly and represent minimal changes required
-    to address the issue.
-2.  **Style**: Ensure code follows the workspace's conventions and idiomatic
-    patterns as described in the `GEMINI.md` file.
-3.  **Security**: Flag any potential security vulnerabilities.
-4.  **Tests**: Verify that new logic has corresponding test coverage and that
-    the test coverage adequately validates the changes.
-
-Provide your feedback as a concise bulleted list of "Strengths" and
-"Opportunities."
-```
-
-### Resource Conventions
-
-While you can structure your skill directory however you like, the Agent Skills
-standard encourages these conventions:
-
-- **`scripts/`**: Executable scripts (bash, python, node) the agent can run.
-- **`references/`**: Static documentation, schemas, or example data for the
-  agent to consult.
-- **`assets/`**: Code templates, boilerplate, or binary resources.
-
-When a skill is activated, Gemini CLI provides the model with a tree view of the
-entire skill directory, allowing it to discover and utilize these assets.
-
-## How it Works (Security & Privacy)
+## How it Works
 
 1.  **Discovery**: At the start of a session, Gemini CLI scans the discovery
     tiers and injects the name and description of all enabled skills into the
@@ -183,3 +113,15 @@ entire skill directory, allowing it to discover and utilize these assets.
       it permission to read any bundled assets.
 5.  **Execution**: The model proceeds with the specialized expertise active. It
     is instructed to prioritize the skill's procedural guidance within reason.
+
+### Skill activation
+
+Once a skill is activated (typically by Gemini identifying a task that matches
+the skill's description and your approval), its specialized instructions and
+resources are loaded into the agent's context. A skill remains active and its
+guidance is prioritized for the duration of the session.
+
+## Creating your own skills
+
+To create your own skills, see the [Create Agent Skills](./creating-skills.md)
+guide.

docs/core/subagents.md

@@ -24,30 +24,29 @@ the main agent's context or toolset.
 
 ## What are sub-agents?
 
-Think of sub-agents as "specialists" that the main Gemini agent can hire for a
-specific job.
+Sub-agents are "specialists" that the main Gemini agent can hire for a specific
+job.
 
 - **Focused context:** Each sub-agent has its own system prompt and persona.
 - **Specialized tools:** Sub-agents can have a restricted or specialized set of
   tools.
 - **Independent context window:** Interactions with a sub-agent happen in a
-  separate context loop. The main agent only sees the final result, saving
-  tokens in your main conversation history.
+  separate context loop, which saves tokens in your main conversation history.
 
-Sub-agents are exposed to the main agent as a tool of the same name which
-delegates to the sub-agent, when called. Once the sub-agent completes its task
-(or fails), it reports back to the main agent with its findings (usually as a
-text summary or structured report returned by the tool).
+Sub-agents are exposed to the main agent as a tool of the same name. When the
+main agent calls the tool, it delegates the task to the sub-agent. Once the
+sub-agent completes its task, it reports back to the main agent with its
+findings.
 
 ## Built-in sub-agents
 
-Gemini CLI comes with powerful built-in sub-agents.
+Gemini CLI comes with the following built-in sub-agents:
 
 ### Codebase Investigator
 
 - **Name:** `codebase_investigator`
-- **Purpose:** Deep analysis of the codebase, reverse engineering, and
-  understanding complex dependencies.
+- **Purpose:** Analyze the codebase, reverse engineer, and understand complex
+  dependencies.
 - **When to use:** "How does the authentication system work?", "Map out the
   dependencies of the `AgentRegistry` class."
 - **Configuration:** Enabled by default. You can configure it in
@@ -67,20 +66,25 @@ Gemini CLI comes with powerful built-in sub-agents.
 ### CLI Help Agent
 
 - **Name:** `cli_help`
-- **Purpose:** Expert knowledge about Gemini CLI itself, its commands,
+- **Purpose:** Get expert knowledge about Gemini CLI itself, its commands,
   configuration, and documentation.
 - **When to use:** "How do I configure a proxy?", "What does the `/rewind`
   command do?"
 - **Configuration:** Enabled by default.
 
+### Generalist Agent
+
+- **Name:** `generalist_agent`
+- **Purpose:** Route tasks to the appropriate specialized sub-agent.
+- **When to use:** Implicitly used by the main agent for routing. Not directly
+  invoked by the user.
+- **Configuration:** Enabled by default. No specific configuration options.
+
 ## Creating custom sub-agents
 
 You can create your own sub-agents to automate specific workflows or enforce
-specific personas.
-
-### Prerequisites
-
-To use custom sub-agents, you must enable them in your `settings.json`:
+specific personas. To use custom sub-agents, you must enable them in your
+`settings.json`:
 
 ```json
 {
@@ -112,7 +116,7 @@ description: Specialized in finding security vulnerabilities in code.
 kind: local
 tools:
   - read_file
-  - search_file_content
+  - grep_search
 model: gemini-2.5-pro
 temperature: 0.2
 max_turns: 10
@@ -123,10 +127,10 @@ vulnerabilities.
 
 Focus on:
 
-1. SQL Injection
-2. XSS (Cross-Site Scripting)
-3. Hardcoded credentials
-4. Unsafe file operations
+1.  SQL Injection
+2.  XSS (Cross-Site Scripting)
+3.  Hardcoded credentials
+4.  Unsafe file operations
 
 When you find a vulnerability, explain it clearly and suggest a fix. Do not fix
 it yourself; just report it.
@@ -142,22 +146,21 @@ it yourself; just report it.
 | `tools`        | array  | No       | List of tool names this agent can use. If omitted, it may have access to a default set.                                    |
 | `model`        | string | No       | Specific model to use (e.g., `gemini-2.5-pro`). Defaults to `inherit` (uses the main session model).                       |
 | `temperature`  | number | No       | Model temperature (0.0 - 2.0).                                                                                             |
-| `max_turns`    | number | No       | Maximum number of conversation turns allowed for this agent before it must return.                                         |
-| `timeout_mins` | number | No       | Maximum execution time in minutes.                                                                                         |
+| `max_turns`    | number | No       | Maximum number of conversation turns allowed for this agent before it must return. Defaults to `15`.                       |
+| `timeout_mins` | number | No       | Maximum execution time in minutes. Defaults to `5`.                                                                        |
 
 ### Optimizing your sub-agent
 
-The main agent system prompt contains language that encourages use of an expert
-sub-agent when one is available for the task at hand. It decides whether an
-agent is a relevant expert based on the agent's description. You can improve the
-reliability with which an agent is used by updating the description to more
-clearly indicate:
+The main agent's system prompt encourages it to use an expert sub-agent when one
+is available. It decides whether an agent is a relevant expert based on the
+agent's description. You can improve the reliability with which an agent is used
+by updating the description to more clearly indicate:
 
 - Its area of expertise.
 - When it should be used.
 - Some example scenarios.
 
-For example: the following sub-agent description should be called fairly
+For example, the following sub-agent description should be called fairly
 consistently for Git operations.
 
 > Git expert agent which should be used for all local and remote git operations.
@@ -173,7 +176,7 @@ that your sub-agent was called with a specific prompt and the given description.
 
 ## Remote subagents (Agent2Agent) (experimental)
 
-Gemini CLI can also delegate tasks to remote subagents using the Agent-to-Agent
+Gemini CLI can also delegate tasks to remote sub-agents using the Agent-to-Agent
 (A2A) protocol.
 
 > **Note: Remote subagents are currently an experimental feature.**

docs/get-started/configuration-v1.md

@@ -215,14 +215,6 @@ a few things you can try in order of recommendation:
     MCP servers of their own. This should not be used as an airtight security
     mechanism.
 
-- **`autoAccept`** (boolean):
-  - **Description:** Controls whether the CLI automatically accepts and executes
-    tool calls that are considered safe (e.g., read-only operations) without
-    explicit user confirmation. If set to `true`, the CLI will bypass the
-    confirmation prompt for tools deemed safe.
-  - **Default:** `false`
-  - **Example:** `"autoAccept": true`
-
 - **`theme`** (string):
   - **Description:** Sets the visual [theme](../cli/themes.md) for Gemini CLI.
   - **Default:** `"Default"`

docs/get-started/configuration.md

@@ -170,6 +170,15 @@ their corresponding top-level category object in your `settings.json` file.
     available options.
   - **Default:** `undefined`
 
+- **`ui.autoThemeSwitching`** (boolean):
+  - **Description:** Automatically switch between default light and dark themes
+    based on terminal background color.
+  - **Default:** `true`
+
+- **`ui.terminalBackgroundPollingInterval`** (number):
+  - **Description:** Interval in seconds to poll the terminal background color.
+  - **Default:** `60`
+
 - **`ui.customThemes`** (object):
   - **Description:** Custom theme definitions.
   - **Default:** `{}`
@@ -326,6 +335,12 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `0.5`
   - **Requires restart:** Yes
 
+- **`model.disableLoopDetection`** (boolean):
+  - **Description:** Disable automatic detection and prevention of infinite
+    loops.
+  - **Default:** `false`
+  - **Requires restart:** Yes
+
 - **`model.skipNextSpeakerCheck`** (boolean):
   - **Description:** Skip the next speaker check.
   - **Default:** `true`
@@ -661,11 +676,6 @@ their corresponding top-level category object in your `settings.json` file.
     performance.
   - **Default:** `true`
 
-- **`tools.autoAccept`** (boolean):
-  - **Description:** Automatically accept and execute tool calls that are
-    considered safe (e.g., read-only operations).
-  - **Default:** `false`
-
 - **`tools.approvalMode`** (enum):
   - **Description:** The default approval mode for tool execution. 'default'
     prompts for approval, 'auto_edit' auto-approves edit tools, and 'plan' is
@@ -733,12 +743,6 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `true`
   - **Requires restart:** Yes
 
-- **`tools.enableHooks`** (boolean):
-  - **Description:** Enables the hooks system experiment. When disabled, the
-    hooks system is completely deactivated regardless of other settings.
-  - **Default:** `true`
-  - **Requires restart:** Yes
-
 #### `mcp`
 
 - **`mcp.serverCommand`** (string):
@@ -779,9 +783,16 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `false`
   - **Requires restart:** Yes
 
+- **`security.allowedExtensions`** (array):
+  - **Description:** List of Regex patterns for allowed extensions. If nonempty,
+    only extensions that match the patterns in this list are allowed. Overrides
+    the blockGitExtensions setting.
+  - **Default:** `[]`
+  - **Requires restart:** Yes
+
 - **`security.folderTrust.enabled`** (boolean):
   - **Description:** Setting to track whether Folder trust is enabled.
-  - **Default:** `false`
+  - **Default:** `true`
   - **Requires restart:** Yes
 
 - **`security.environmentVariableRedaction.allowed`** (array):
@@ -1165,6 +1176,13 @@ the `advanced.excludedEnvVars` setting in your `settings.json` file.
   - Specifies the default Gemini model to use.
   - Overrides the hardcoded default
   - Example: `export GEMINI_MODEL="gemini-3-flash-preview"`
+- **`GEMINI_CLI_HOME`**:
+  - Specifies the root directory for Gemini CLI's user-level configuration and
+    storage.
+  - By default, this is the user's system home directory. The CLI will create a
+    `.gemini` folder inside this directory.
+  - Useful for shared compute environments or keeping CLI state isolated.
+  - Example: `export GEMINI_CLI_HOME="/path/to/user/config"`
 - **`GOOGLE_API_KEY`**:
   - Your Google Cloud API key.
   - Required for using Vertex AI in express mode.
@@ -1185,6 +1203,10 @@ the `advanced.excludedEnvVars` setting in your `settings.json` file.
   - **Description:** The path to your Google Application Credentials JSON file.
   - **Example:**
     `export GOOGLE_APPLICATION_CREDENTIALS="/path/to/your/credentials.json"`
+- **`GOOGLE_GENAI_API_VERSION`**:
+  - Specifies the API version to use for Gemini API requests.
+  - When set, overrides the default API version used by the SDK.
+  - Example: `export GOOGLE_GENAI_API_VERSION="v1"`
 - **`OTLP_GOOGLE_CLOUD_PROJECT`**:
   - Your Google Cloud Project ID for Telemetry in Google Cloud
   - Example: `export OTLP_GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"`.

docs/hooks/reference.md

@@ -167,8 +167,8 @@ case is response validation and automatic retries.
   - `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.
-  - `clearContext`: If `true`, clears conversation history (LLM memory) while
-    preserving UI display.
+  - `hookSpecificOutput.clearContext`: If `true`, clears conversation history
+    (LLM memory) while preserving UI display.
 - **Exit Code 2 (Retry)**: Rejects the response and triggers an automatic retry
   turn using `stderr` as the feedback prompt.
 

docs/index.md

@@ -1,149 +1,123 @@
-# Welcome to Gemini CLI documentation
+# Gemini CLI documentation
 
-This documentation provides a comprehensive guide to installing, using, and
-developing Gemini CLI, a tool that lets you interact with Gemini models through
-a command-line interface.
+Gemini CLI is an open-source AI agent that brings the power of Gemini directly
+into your terminal. It is designed to be a terminal-first, extensible, and
+powerful tool for developers, engineers, SREs, and beyond.
 
-## Gemini CLI overview
+Gemini CLI integrates with your local environment. It can read and edit files,
+execute shell commands, and search the web, all while maintaining your project
+context.
 
-Gemini CLI brings the capabilities of Gemini models to your terminal in an
-interactive Read-Eval-Print Loop (REPL) environment. Gemini CLI consists of a
-client-side application (`packages/cli`) that communicates with a local server
-(`packages/core`), which in turn manages requests to the Gemini API and its AI
-models. Gemini CLI also contains a variety of tools for tasks such as performing
-file system operations, running shells, and web fetching, which are managed by
-`packages/core`.
+## Get started
 
-## Navigating the documentation
+Begin your journey with Gemini CLI by setting up your environment and learning
+the basics.
 
-This documentation is organized into the following sections:
+- **[Quickstart](./get-started/index.md):** A streamlined guide to get you
+  chatting in minutes.
+- **[Installation](./get-started/installation.md):** Instructions for macOS,
+  Linux, and Windows.
+- **[Authentication](./get-started/authentication.md):** Set up access using
+  Google OAuth, API keys, or Vertex AI.
+- **[Examples](./get-started/examples.md):** View common usage scenarios to
+  inspire your own workflows.
 
-### Overview
+## Use Gemini CLI
 
-- **[Architecture overview](./architecture.md):** Understand the high-level
-  design of Gemini CLI, including its components and how they interact.
-- **[Contribution guide](../CONTRIBUTING.md):** Information for contributors and
-  developers, including setup, building, testing, and coding conventions.
+Master the core capabilities that let Gemini CLI interact with your system
+safely and effectively.
 
-### Get started
-
-- **[Gemini CLI quickstart](./get-started/index.md):** Let's get started with
-  Gemini CLI.
-- **[Gemini 3 Pro on Gemini CLI](./get-started/gemini-3.md):** Learn how to
-  enable and use Gemini 3.
-- **[Authentication](./get-started/authentication.md):** Authenticate to Gemini
-  CLI.
-- **[Configuration](./get-started/configuration.md):** Learn how to configure
-  the CLI.
-- **[Installation](./get-started/installation.md):** Install and run Gemini CLI.
-- **[Examples](./get-started/examples.md):** Example usage of Gemini CLI.
-
-### CLI
-
-- **[Introduction: Gemini CLI](./cli/index.md):** Overview of the command-line
+- **[Using the CLI](./cli/index.md):** Learn the basics of the command-line
   interface.
-- **[Commands](./cli/commands.md):** Description of available CLI commands.
-- **[Checkpointing](./cli/checkpointing.md):** Documentation for the
-  checkpointing feature.
-- **[Custom commands](./cli/custom-commands.md):** Create your own commands and
-  shortcuts for frequently used prompts.
-- **[Enterprise](./cli/enterprise.md):** Gemini CLI for enterprise.
-- **[Headless mode](./cli/headless.md):** Use Gemini CLI programmatically for
-  scripting and automation.
-- **[Keyboard shortcuts](./cli/keyboard-shortcuts.md):** A reference for all
-  keyboard shortcuts to improve your workflow.
-- **[Model selection](./cli/model.md):** Select the model used to process your
-  commands with `/model`.
-- **[Sandbox](./cli/sandbox.md):** Isolate tool execution in a secure,
-  containerized environment.
-- **[Agent Skills](./cli/skills.md):** Extend the CLI with specialized expertise
-  and procedural workflows.
-- **[Settings](./cli/settings.md):** Configure various aspects of the CLI's
-  behavior and appearance with `/settings`.
-- **[Telemetry](./cli/telemetry.md):** Overview of telemetry in the CLI.
-- **[Themes](./cli/themes.md):** Themes for Gemini CLI.
-- **[Token caching](./cli/token-caching.md):** Token caching and optimization.
-- **[Trusted Folders](./cli/trusted-folders.md):** An overview of the Trusted
-  Folders security feature.
-- **[Tutorials](./cli/tutorials.md):** Tutorials for Gemini CLI.
-- **[Uninstall](./cli/uninstall.md):** Methods for uninstalling the Gemini CLI.
+- **[File management](./tools/file-system.md):** Grant the model the ability to
+  read code and apply changes directly to your files.
+- **[Shell commands](./tools/shell.md):** Allow the model to run builds, tests,
+  and git commands.
+- **[Memory management](./tools/memory.md):** Teach Gemini CLI facts about your
+  project and preferences that persist across sessions.
+- **[Project context](./cli/gemini-md.md):** Use `GEMINI.md` files to provide
+  persistent context for your projects.
+- **[Web search and fetch](./tools/web-search.md):** Enable the model to fetch
+  real-time information from the internet.
+- **[Session management](./cli/session-management.md):** Save, resume, and
+  organize your chat sessions.
 
-### Core
+## Configuration
 
-- **[Introduction: Gemini CLI core](./core/index.md):** Information about Gemini
-  CLI core.
-- **[Memport](./core/memport.md):** Using the Memory Import Processor.
-- **[Tools API](./core/tools-api.md):** Information on how the core manages and
-  exposes tools.
-- **[System Prompt Override](./cli/system-prompt.md):** Replace built-in system
-  instructions using `GEMINI_SYSTEM_MD`.
+Customize Gemini CLI to match your workflow and preferences.
 
-- **[Policy Engine](./core/policy-engine.md):** Use the Policy Engine for
-  fine-grained control over tool execution.
+- **[Settings](./cli/settings.md):** Control response creativity, output
+  verbosity, and more.
+- **[Model selection](./cli/model.md):** Choose the best Gemini model for your
+  specific task.
+- **[Ignore files](./cli/gemini-ignore.md):** Use `.geminiignore` to keep
+  sensitive files out of the model's context.
+- **[Trusted folders](./cli/trusted-folders.md):** Define security boundaries
+  for file access and execution.
+- **[Token caching](./cli/token-caching.md):** Optimize performance and cost by
+  caching context.
+- **[Themes](./cli/themes.md):** Personalize the visual appearance of the CLI.
 
-### Tools
+## Advanced features
 
-- **[Introduction: Gemini CLI tools](./tools/index.md):** Information about
-  Gemini CLI's tools.
-- **[File system tools](./tools/file-system.md):** Documentation for the
-  `read_file` and `write_file` tools.
-- **[Shell tool](./tools/shell.md):** Documentation for the `run_shell_command`
-  tool.
-- **[Web fetch tool](./tools/web-fetch.md):** Documentation for the `web_fetch`
-  tool.
-- **[Web search tool](./tools/web-search.md):** Documentation for the
-  `google_web_search` tool.
-- **[Memory tool](./tools/memory.md):** Documentation for the `save_memory`
-  tool.
-- **[Todo tool](./tools/todos.md):** Documentation for the `write_todos` tool.
-- **[MCP servers](./tools/mcp-server.md):** Using MCP servers with Gemini CLI.
+Explore powerful features for complex workflows and enterprise environments.
 
-### Extensions
+- **[Headless mode](./cli/headless.md):** Run Gemini CLI in scripts or CI/CD
+  pipelines for automated reasoning.
+- **[Sandboxing](./cli/sandbox.md):** Execute untrusted code or tools in a
+  secure, isolated container.
+- **[Checkpointing](./cli/checkpointing.md):** Save and restore workspace state
+  to recover from experimental changes.
+- **[Custom commands](./cli/custom-commands.md):** Create shortcuts for
+  frequently used prompts.
+- **[System prompt override](./cli/system-prompt.md):** Customize the core
+  instructions given to the model.
+- **[Telemetry](./cli/telemetry.md):** Understand how usage data is collected
+  and managed.
+- **[Enterprise](./cli/enterprise.md):** Manage configurations and policies for
+  large teams.
 
-- **[Introduction: Extensions](./extensions/index.md):** How to extend the CLI
-  with new functionality.
+## Extensions
+
+Extend Gemini CLI's capabilities with new tools and behaviors using extensions.
+
+- **[Introduction](./extensions/index.md):** Learn about the extension system
+  and how to manage extensions.
 - **[Writing extensions](./extensions/writing-extensions.md):** Learn how to
-  build your own extension.
-- **[Extension releasing](./extensions/releasing.md):** How to release Gemini
-  CLI extensions.
+  create your first extension.
+- **[Extensions reference](./extensions/reference.md):** Deeply understand the
+  extension format, commands, and configuration.
+- **[Best practices](./extensions/best-practices.md):** Learn strategies for
+  building great extensions.
+- **[Extensions releasing](./extensions/releasing.md):** Learn how to share your
+  extensions with the world.
 
-### Hooks
+## Ecosystem and extensibility
 
-- **[Hooks](./hooks/index.md):** Intercept and customize Gemini CLI behavior at
-  key lifecycle points.
-- **[Writing Hooks](./hooks/writing-hooks.md):** Learn how to create your first
-  hook with a comprehensive example.
-- **[Best Practices](./hooks/best-practices.md):** Security, performance, and
-  debugging guidelines for hooks.
+Connect Gemini CLI to external services and other development tools.
 
-### IDE integration
+- **[MCP servers](./tools/mcp-server.md):** Connect to external services using
+  the Model Context Protocol.
+- **[IDE integration](./ide-integration/index.md):** Use Gemini CLI alongside VS
+  Code.
+- **[Hooks](./hooks/index.md):** (Preview) Write scripts that run on specific
+  CLI events.
+- **[Agent skills](./cli/skills.md):** (Preview) Add specialized expertise and
+  workflows.
+- **[Sub-agents](./core/subagents.md):** (Preview) Delegate tasks to specialized
+  agents.
 
-- **[Introduction to IDE integration](./ide-integration/index.md):** Connect the
-  CLI to your editor.
-- **[IDE companion extension spec](./ide-integration/ide-companion-spec.md):**
-  Spec for building IDE companion extensions.
+## Development and reference
 
-### Development
+Deep dive into the architecture and contribute to the project.
 
-- **[NPM](./npm.md):** Details on how the project's packages are structured.
-- **[Releases](./releases.md):** Information on the project's releases and
-  deployment cadence.
-- **[Changelog](./changelogs/index.md):** Highlights and notable changes to
+- **[Architecture](./architecture.md):** Understand the technical design of
   Gemini CLI.
-- **[Integration tests](./integration-tests.md):** Information about the
-  integration testing framework used in this project.
-- **[Issue and PR automation](./issue-and-pr-automation.md):** A detailed
-  overview of the automated processes we use to manage and triage issues and
-  pull requests.
-
-### Support
-
-- **[FAQ](./faq.md):** Frequently asked questions.
-- **[Troubleshooting guide](./troubleshooting.md):** Find solutions to common
-  problems.
-- **[Quota and pricing](./quota-and-pricing.md):** Learn about the free tier and
-  paid options.
-- **[Terms of service and privacy notice](./tos-privacy.md):** Information on
-  the terms of service and privacy notices applicable to your use of Gemini CLI.
-
-We hope this documentation helps you make the most of Gemini CLI!
+- **[Command reference](./cli/commands.md):** A complete list of available
+  commands.
+- **[Local development](./local-development.md):** Set up your environment to
+  contribute to Gemini CLI.
+- **[Contributing](../CONTRIBUTING.md):** Learn how to submit pull requests and
+  report issues.
+- **[FAQ](./faq.md):** Answers to common questions.
+- **[Troubleshooting](./troubleshooting.md):** Solutions for common issues.

docs/ralph-wiggum.md

@@ -0,0 +1,141 @@
+# Ralph Wiggum mode
+
+Ralph Wiggum mode is an iterative automation technique that lets Gemini CLI
+repeatedly execute a prompt until a specific goal is met. This mode is designed
+for tasks that benefit from persistent refinement, such as fixing failing tests
+or performing complex refactoring.
+
+> **Note:** This is a preview feature currently under active development.
+
+## Overview
+
+Inspired by the "Ralph Wiggum" technique, this mode treats failures as data and
+uses a feedback loop to reach a successful state. When you enable Ralph Wiggum
+mode, Gemini CLI enters YOLO (auto-approval) mode and continues to process the
+provided prompt until it detects your specified completion string in the model's
+output or reaches the maximum number of iterations.
+
+## Usage
+
+To use Ralph Wiggum mode, you must provide a prompt using the `-p` or `--prompt`
+flag. You then configure the loop behavior using the following flags:
+
+| Flag                   | Description                                                |
+| :--------------------- | :--------------------------------------------------------- |
+| `--ralph-wiggum`       | Enables the Ralph Wiggum iterative loop mode.              |
+| `--completion-promise` | The string to look for in the output to signal completion. |
+| `--max-iterations`     | The maximum number of times to run the loop (default: 10). |
+| `--memory-file`        | Task-specific memory file (default: `memories.md`).        |
+
+### Example
+
+The following command attempts to fix tests by running the loop up to 5 times
+until the string "TESTS PASSED" appears in the output, using a specific memory
+file for this task:
+
+```bash
+gemini -p "Fix the tests in packages/core" \
+  --ralph-wiggum \
+  --completion-promise "TESTS PASSED" \
+  --max-iterations 5 \
+  --memory-file "fix-core-tests.md"
+```
+
+## How it works
+
+When you run Gemini CLI with the `--ralph-wiggum` flag, the following process
+occurs:
+
+1.  **Enforces YOLO mode:** The tool automatically sets the approval mode to
+    `yolo`. This ensures that tool calls (like writing files or running shell
+    commands) are approved automatically to allow the automation to proceed
+    without human intervention.
+2.  **Iterative execution:** The CLI executes the provided prompt in a loop.
+3.  **Completion check:** After each iteration, the CLI scans the full text of
+    the assistant's response for the string provided in `--completion-promise`.
+4.  **Loop termination:**
+    - If the completion string is found, the loop exits successfully.
+    - If the completion string is not found, the CLI starts a new iteration
+      using the same initial prompt.
+    - If the number of iterations reaches the `--max-iterations` limit, the loop
+      stops.
+
+## Persistent context (Memories)
+
+To help the agent learn from previous attempts, Ralph Wiggum mode uses a
+`memories.md` file in your current working directory.
+
+- **Automatic creation:** If the file doesn't exist, the CLI creates it with a
+  default header.
+- **Context injection:** At the start of each iteration, the content of
+  `memories.md` is read and prepended to your prompt.
+- **Usage:** You (or the agent, via tool use) can write notes, error logs, or
+  successful patterns into this file. This allows the agent to "remember" what
+  failed in iteration 1 and avoid repeating the same mistake in iteration 2.
+
+## Summary statistics
+
+At the end of the execution, Ralph Wiggum mode provides a summary table in the
+terminal. This table details the performance of each iteration, including:
+
+- **Iteration number:** The sequence of the run.
+- **Status:** Whether the iteration met the completion promise ("Success") or
+  failed to do so ("Failed").
+- **Tests Passed/Failed:** If the output contains recognizable test runner
+  patterns (such as those from Vitest, Jest, or Mocha), the CLI extracts and
+  displays the number of passing and failing tests.
+
+### Example summary table
+
+```text
+--- Ralph Wiggum Mode Summary ---
+| Iteration | Status  | Tests Passed | Tests Failed |
+|-----------|---------|--------------|--------------|
+| 1         | Failed  | 2            | 10           |
+| 2         | Failed  | 8            | 4            |
+| 3         | Success | 12           | 0            |
+---------------------------------
+```
+
+## Best practices
+
+To get the most out of Ralph Wiggum mode, we recommend the following:
+
+- **Clear completion criteria:** Ensure your prompt instructs the model to emit
+  a specific, unique string (like "ALL TESTS PASSED") only when the task is
+  truly complete.
+- **Incremental goals:** Use prompts that encourage the model to make small,
+  verifiable changes in each iteration.
+- **Safety nets:** Always set a reasonable `--max-iterations` limit to prevent
+  unintended long-running processes.
+
+## Development and rebuilding
+
+If you're modifying Ralph Wiggum mode or enabling it in a development
+environment, you must recompile the TypeScript source code.
+
+### Full rebuild
+
+To build all packages in the monorepo, run the following command from the root
+directory:
+
+```bash
+npm run build
+```
+
+### Fast CLI rebuild
+
+If you've already performed a full build and are only making changes to the CLI
+package, you can run a targeted build:
+
+```bash
+npm run build -w @google/gemini-cli
+```
+
+### Running in development
+
+After rebuilding, test your changes using the `npm run start` script:
+
+```bash
+npm run start -- -p "Your task" --ralph-wiggum --completion-promise "SUCCESS"
+```

docs/sidebar.json

@@ -45,6 +45,7 @@
       { "label": "Custom commands", "slug": "docs/cli/custom-commands" },
       { "label": "Enterprise features", "slug": "docs/cli/enterprise" },
       { "label": "Headless mode & scripting", "slug": "docs/cli/headless" },
+      { "label": "Ralph Wiggum mode", "slug": "docs/ralph-wiggum" },
       { "label": "Sandboxing", "slug": "docs/cli/sandbox" },
       { "label": "System prompt override", "slug": "docs/cli/system-prompt" },
       { "label": "Telemetry", "slug": "docs/cli/telemetry" }
@@ -79,6 +80,10 @@
     "label": "Ecosystem and extensibility",
     "items": [
       { "label": "Agent skills", "slug": "docs/cli/skills" },
+      {
+        "label": "Creating Agent skills",
+        "slug": "docs/cli/creating-skills"
+      },
       {
         "label": "Sub-agents (experimental)",
         "slug": "docs/core/subagents"

docs/tools/file-system.md

@@ -117,14 +117,13 @@ directories) will be created.
   `Found 5 file(s) matching "*.ts" within src, sorted by modification time (newest first):\nsrc/file1.ts\nsrc/subdir/file2.ts...`
 - **Confirmation:** No.
 
-## 5. `search_file_content` (SearchText)
+## 5. `grep_search` (SearchText)
 
-`search_file_content` searches for a regular expression pattern within the
-content of files in a specified directory. Can filter files by a glob pattern.
-Returns the lines containing matches, along with their file paths and line
-numbers.
+`grep_search` searches for a regular expression pattern within the content of
+files in a specified directory. Can filter files by a glob pattern. Returns the
+lines containing matches, along with their file paths and line numbers.
 
-- **Tool name:** `search_file_content`
+- **Tool name:** `grep_search`
 - **Display name:** SearchText
 - **File:** `grep.ts`
 - **Parameters:**

evals/automated-tool-use.eval.ts

@@ -0,0 +1,170 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, expect } from 'vitest';
+import { evalTest } from './test-helper.js';
+
+describe('Automated tool use', () => {
+  /**
+   * Tests that the agent always utilizes --fix when calling eslint.
+   * We provide a 'lint' script in the package.json, which helps elicit
+   * a repro by guiding the agent into using the existing deficient script.
+   */
+  evalTest('USUALLY_PASSES', {
+    name: 'should use automated tools (eslint --fix) to fix code style issues',
+    files: {
+      'package.json': JSON.stringify(
+        {
+          name: 'typescript-project',
+          version: '1.0.0',
+          type: 'module',
+          scripts: {
+            lint: 'eslint .',
+          },
+          devDependencies: {
+            eslint: '^9.0.0',
+            globals: '^15.0.0',
+            typescript: '^5.0.0',
+            'typescript-eslint': '^8.0.0',
+            '@eslint/js': '^9.0.0',
+          },
+        },
+        null,
+        2,
+      ),
+      'eslint.config.js': `
+        import globals from "globals";
+        import pluginJs from "@eslint/js";
+        import tseslint from "typescript-eslint";
+
+        export default [
+          {
+            files: ["**/*.{js,mjs,cjs,ts}"], 
+            languageOptions: { 
+                globals: globals.node 
+            }
+          },
+          pluginJs.configs.recommended,
+          ...tseslint.configs.recommended,
+          {
+            rules: {
+                "prefer-const": "error",
+                "@typescript-eslint/no-unused-vars": "off"
+            }
+          }
+        ];
+      `,
+      'src/app.ts': `
+        export function main() {
+            let count = 10;
+            console.log(count);
+        }
+      `,
+    },
+    prompt:
+      'Fix the linter errors in this project. Make sure to avoid interactive commands.',
+    assert: async (rig) => {
+      // Check if run_shell_command was used with --fix
+      const toolCalls = rig.readToolLogs();
+      const shellCommands = toolCalls.filter(
+        (call) => call.toolRequest.name === 'run_shell_command',
+      );
+
+      const hasFixCommand = shellCommands.some((call) => {
+        let args = call.toolRequest.args;
+        if (typeof args === 'string') {
+          try {
+            args = JSON.parse(args);
+          } catch (e) {
+            return false;
+          }
+        }
+        const cmd = (args as any)['command'];
+        return (
+          cmd &&
+          (cmd.includes('eslint') || cmd.includes('npm run lint')) &&
+          cmd.includes('--fix')
+        );
+      });
+
+      expect(
+        hasFixCommand,
+        'Expected agent to use eslint --fix via run_shell_command',
+      ).toBe(true);
+    },
+  });
+
+  /**
+   * Tests that the agent uses prettier --write to fix formatting issues in files
+   * instead of trying to edit the files itself.
+   */
+  evalTest('USUALLY_PASSES', {
+    name: 'should use automated tools (prettier --write) to fix formatting issues',
+    files: {
+      'package.json': JSON.stringify(
+        {
+          name: 'typescript-project',
+          version: '1.0.0',
+          type: 'module',
+          scripts: {},
+          devDependencies: {
+            prettier: '^3.0.0',
+            typescript: '^5.0.0',
+          },
+        },
+        null,
+        2,
+      ),
+      '.prettierrc': JSON.stringify(
+        {
+          semi: true,
+          singleQuote: true,
+        },
+        null,
+        2,
+      ),
+      'src/app.ts': `
+export function main() {
+    const data={   name:'test',
+      val:123
+    }
+console.log(data)
+}
+`,
+    },
+    prompt:
+      'Fix the formatting errors in this project. Make sure to avoid interactive commands.',
+    assert: async (rig) => {
+      // Check if run_shell_command was used with --write
+      const toolCalls = rig.readToolLogs();
+      const shellCommands = toolCalls.filter(
+        (call) => call.toolRequest.name === 'run_shell_command',
+      );
+
+      const hasFixCommand = shellCommands.some((call) => {
+        let args = call.toolRequest.args;
+        if (typeof args === 'string') {
+          try {
+            args = JSON.parse(args);
+          } catch (e) {
+            return false;
+          }
+        }
+        const cmd = (args as any)['command'];
+        return (
+          cmd &&
+          cmd.includes('prettier') &&
+          (cmd.includes('--write') || cmd.includes('-w'))
+        );
+      });
+
+      expect(
+        hasFixCommand,
+        'Expected agent to use prettier --write via run_shell_command',
+      ).toBe(true);
+    },
+  });
+});

evals/interactive-hang.eval.ts

@@ -0,0 +1,47 @@
+import { describe, expect } from 'vitest';
+import { evalTest } from './test-helper.js';
+
+describe('interactive_commands', () => {
+  /**
+   * Validates that the agent does not use interactive commands unprompted.
+   * Interactive commands block the progress of the agent, requiring user
+   * intervention.
+   */
+  evalTest('USUALLY_PASSES', {
+    name: 'should not use interactive commands',
+    prompt: 'Execute tests.',
+    files: {
+      'package.json': JSON.stringify(
+        {
+          name: 'example',
+          type: 'module',
+          devDependencies: {
+            vitest: 'latest',
+          },
+        },
+        null,
+        2,
+      ),
+      'example.test.js': `
+        import { test, expect } from 'vitest';
+        test('it works', () => {
+          expect(1 + 1).toBe(2);
+        });
+      `,
+    },
+    assert: async (rig, result) => {
+      const logs = rig.readToolLogs();
+      const vitestCall = logs.find(
+        (l) =>
+          l.toolRequest.name === 'run_shell_command' &&
+          l.toolRequest.args.toLowerCase().includes('vitest'),
+      );
+
+      expect(vitestCall, 'Agent should have called vitest').toBeDefined();
+      expect(
+        vitestCall?.toolRequest.args,
+        'Agent should have passed run arg',
+      ).toMatch(/\b(run|--run)\b/);
+    },
+  });
+});

evals/test-helper.ts

@@ -7,9 +7,13 @@
 import { it } from 'vitest';
 import fs from 'node:fs';
 import path from 'node:path';
+import crypto from 'node:crypto';
 import { execSync } from 'node:child_process';
 import { TestRig } from '@google/gemini-cli-test-utils';
-import { createUnauthorizedToolError } from '@google/gemini-cli-core';
+import {
+  createUnauthorizedToolError,
+  parseAgentMarkdown,
+} from '@google/gemini-cli-core';
 
 export * from '@google/gemini-cli-test-utils';
 
@@ -41,11 +45,64 @@ export function evalTest(policy: EvalPolicy, evalCase: EvalCase) {
     try {
       rig.setup(evalCase.name, evalCase.params);
 
+      // Symlink node modules to reduce the amount of time needed to
+      // bootstrap test projects.
+      const rootNodeModules = path.join(process.cwd(), 'node_modules');
+      const testNodeModules = path.join(rig.testDir || '', 'node_modules');
+      if (fs.existsSync(rootNodeModules)) {
+        fs.symlinkSync(rootNodeModules, testNodeModules, 'dir');
+      }
+
       if (evalCase.files) {
+        const acknowledgedAgents: Record<string, Record<string, string>> = {};
+        const projectRoot = fs.realpathSync(rig.testDir!);
+
         for (const [filePath, content] of Object.entries(evalCase.files)) {
           const fullPath = path.join(rig.testDir!, filePath);
           fs.mkdirSync(path.dirname(fullPath), { recursive: true });
           fs.writeFileSync(fullPath, content);
+
+          // If it's an agent file, calculate hash for acknowledgement
+          if (
+            filePath.startsWith('.gemini/agents/') &&
+            filePath.endsWith('.md')
+          ) {
+            const hash = crypto
+              .createHash('sha256')
+              .update(content)
+              .digest('hex');
+
+            try {
+              const agentDefs = await parseAgentMarkdown(fullPath, content);
+              if (agentDefs.length > 0) {
+                const agentName = agentDefs[0].name;
+                if (!acknowledgedAgents[projectRoot]) {
+                  acknowledgedAgents[projectRoot] = {};
+                }
+                acknowledgedAgents[projectRoot][agentName] = hash;
+              }
+            } catch (error) {
+              console.warn(
+                `Failed to parse agent for test acknowledgement: ${filePath}`,
+                error,
+              );
+            }
+          }
+        }
+
+        // Write acknowledged_agents.json to the home directory
+        if (Object.keys(acknowledgedAgents).length > 0) {
+          const ackPath = path.join(
+            rig.homeDir!,
+            '.gemini',
+            'acknowledgments',
+            'agents.json',
+          );
+          fs.mkdirSync(path.dirname(ackPath), { recursive: true });
+          fs.writeFileSync(
+            ackPath,
+            JSON.stringify(acknowledgedAgents, null, 2),
+          );
         }
 
         const execOptions = { cwd: rig.testDir!, stdio: 'inherit' as const };
@@ -66,6 +123,7 @@ export function evalTest(policy: EvalPolicy, evalCase: EvalCase) {
       const result = await rig.run({
         args: evalCase.prompt,
         approvalMode: evalCase.approvalMode ?? 'yolo',
+        timeout: evalCase.timeout,
         env: {
           GEMINI_CLI_ACTIVITY_LOG_FILE: activityLogFile,
         },
@@ -88,6 +146,11 @@ export function evalTest(policy: EvalPolicy, evalCase: EvalCase) {
         });
       }
 
+      if (rig._lastRunStderr) {
+        const stderrFile = path.join(logDir, `${sanitizedName}.stderr.log`);
+        await fs.promises.writeFile(stderrFile, rig._lastRunStderr);
+      }
+
       await fs.promises.writeFile(
         logFile,
         JSON.stringify(rig.readToolLogs(), null, 2),
@@ -114,6 +177,7 @@ export interface EvalCase {
   name: string;
   params?: Record<string, any>;
   prompt: string;
+  timeout?: number;
   files?: Record<string, string>;
   approvalMode?: 'default' | 'auto_edit' | 'yolo' | 'plan';
   assert: (rig: TestRig, result: string) => Promise<void>;

integration-tests/acp-env-auth.test.ts

@@ -0,0 +1,163 @@
+/**
+ * @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 { spawn, ChildProcess } from 'node:child_process';
+import { join, resolve } from 'node:path';
+import { writeFileSync, mkdirSync } from 'node:fs';
+import { Writable, Readable } from 'node:stream';
+import { env } from 'node:process';
+import * as acp from '@agentclientprotocol/sdk';
+
+const sandboxEnv = env['GEMINI_SANDBOX'];
+const itMaybe = sandboxEnv && sandboxEnv !== 'false' ? it.skip : it;
+
+class MockClient implements acp.Client {
+  updates: acp.SessionNotification[] = [];
+  sessionUpdate = async (params: acp.SessionNotification) => {
+    this.updates.push(params);
+  };
+  requestPermission = async (): Promise<acp.RequestPermissionResponse> => {
+    throw new Error('unexpected');
+  };
+}
+
+describe('ACP Environment and Auth', () => {
+  let rig: TestRig;
+  let child: ChildProcess | undefined;
+
+  beforeEach(() => {
+    rig = new TestRig();
+  });
+
+  afterEach(async () => {
+    child?.kill();
+    child = undefined;
+    await rig.cleanup();
+  });
+
+  itMaybe(
+    'should load .env from project directory and use the provided API key',
+    async () => {
+      rig.setup('acp-env-loading');
+
+      // Create a project directory with a .env file containing a recognizable invalid key
+      const projectDir = resolve(join(rig.testDir!, 'project'));
+      mkdirSync(projectDir, { recursive: true });
+      writeFileSync(
+        join(projectDir, '.env'),
+        'GEMINI_API_KEY=test-key-from-env\n',
+      );
+
+      const bundlePath = join(import.meta.dirname, '..', 'bundle/gemini.js');
+
+      child = spawn('node', [bundlePath, '--experimental-acp'], {
+        cwd: rig.homeDir!,
+        stdio: ['pipe', 'pipe', 'inherit'],
+        env: {
+          ...process.env,
+          GEMINI_CLI_HOME: rig.homeDir!,
+          GEMINI_API_KEY: undefined,
+          VERBOSE: 'true',
+        },
+      });
+
+      const input = Writable.toWeb(child.stdin!);
+      const output = Readable.toWeb(
+        child.stdout!,
+      ) as ReadableStream<Uint8Array>;
+      const testClient = new MockClient();
+      const stream = acp.ndJsonStream(input, output);
+      const connection = new acp.ClientSideConnection(() => testClient, stream);
+
+      await connection.initialize({
+        protocolVersion: acp.PROTOCOL_VERSION,
+        clientCapabilities: {
+          fs: { readTextFile: false, writeTextFile: false },
+        },
+      });
+
+      // 1. newSession should succeed because it finds the key in .env
+      const { sessionId } = await connection.newSession({
+        cwd: projectDir,
+        mcpServers: [],
+      });
+
+      expect(sessionId).toBeDefined();
+
+      // 2. prompt should fail because the key is invalid,
+      // but the error should come from the API, not the internal auth check.
+      await expect(
+        connection.prompt({
+          sessionId,
+          prompt: [{ type: 'text', text: 'hello' }],
+        }),
+      ).rejects.toSatisfy((error: unknown) => {
+        const acpError = error as acp.RequestError;
+        const errorData = acpError.data as
+          | { error?: { message?: string } }
+          | undefined;
+        const message = String(errorData?.error?.message || acpError.message);
+        // It should NOT be our internal "Authentication required" message
+        expect(message).not.toContain('Authentication required');
+        // It SHOULD be an API error mentioning the invalid key
+        expect(message).toContain('API key not valid');
+        return true;
+      });
+
+      child.stdin!.end();
+    },
+  );
+
+  itMaybe(
+    'should fail with authRequired when no API key is found',
+    async () => {
+      rig.setup('acp-auth-failure');
+
+      const bundlePath = join(import.meta.dirname, '..', 'bundle/gemini.js');
+
+      child = spawn('node', [bundlePath, '--experimental-acp'], {
+        cwd: rig.homeDir!,
+        stdio: ['pipe', 'pipe', 'inherit'],
+        env: {
+          ...process.env,
+          GEMINI_CLI_HOME: rig.homeDir!,
+          GEMINI_API_KEY: undefined,
+          VERBOSE: 'true',
+        },
+      });
+
+      const input = Writable.toWeb(child.stdin!);
+      const output = Readable.toWeb(
+        child.stdout!,
+      ) as ReadableStream<Uint8Array>;
+      const testClient = new MockClient();
+      const stream = acp.ndJsonStream(input, output);
+      const connection = new acp.ClientSideConnection(() => testClient, stream);
+
+      await connection.initialize({
+        protocolVersion: acp.PROTOCOL_VERSION,
+        clientCapabilities: {
+          fs: { readTextFile: false, writeTextFile: false },
+        },
+      });
+
+      await expect(
+        connection.newSession({
+          cwd: resolve(rig.testDir!),
+          mcpServers: [],
+        }),
+      ).rejects.toMatchObject({
+        message: expect.stringContaining(
+          'Gemini API key is missing or not configured.',
+        ),
+      });
+
+      child.stdin!.end();
+    },
+  );
+});

integration-tests/globalSetup.ts

@@ -13,6 +13,7 @@ import { mkdir, readdir, rm } from 'node:fs/promises';
 import { join, dirname } from 'node:path';
 import { fileURLToPath } from 'node:url';
 import { canUseRipgrep } from '../packages/core/src/tools/ripGrep.js';
+import { disableMouseTracking } from '@google/gemini-cli-core';
 
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const rootDir = join(__dirname, '..');
@@ -74,9 +75,7 @@ export async function setup() {
 export async function teardown() {
   // Disable mouse tracking
   if (process.stdout.isTTY) {
-    process.stdout.write(
-      '\x1b[?1000l\x1b[?1003l\x1b[?1015l\x1b[?1006l\x1b[?1002l',
-    );
+    disableMouseTracking();
   }
 
   // Cleanup the test run directory unless KEEP_OUTPUT is set

integration-tests/ripgrep-real.test.ts

@@ -28,6 +28,10 @@ class MockConfig {
     return true;
   }
 
+  getFileFilteringRespectGitIgnore() {
+    return true;
+  }
+
   getFileFilteringRespectGeminiIgnore() {
     return true;
   }

integration-tests/run_shell_command.test.ts

@@ -564,11 +564,17 @@ describe('run_shell_command', () => {
 
   it('rejects invalid shell expressions', async () => {
     await rig.setup('rejects invalid shell expressions', {
-      settings: { tools: { core: ['run_shell_command'] } },
+      settings: {
+        tools: {
+          core: ['run_shell_command'],
+          allowed: ['run_shell_command(echo)'], // Specifically allow echo
+        },
+      },
     });
     const invalidCommand = getInvalidCommand();
     const result = await rig.run({
       args: `I am testing the error handling of the run_shell_command tool. Please attempt to run the following command, which I know has invalid syntax: \`${invalidCommand}\`. If the command fails as expected, please return the word FAIL, otherwise return the word SUCCESS.`,
+      approvalMode: 'default', // Use default mode so safety fallback triggers confirmation
     });
     expect(result).toContain('FAIL');
 

package-lock.json

@@ -1,22 +1,19 @@
 {
   "name": "@google/gemini-cli",
-  "version": "0.28.0-nightly.20260128.adc8e11bb",
+  "version": "0.29.0-nightly.20260203.71f46f116",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@google/gemini-cli",
-      "version": "0.28.0-nightly.20260128.adc8e11bb",
-      "hasInstallScript": true,
+      "version": "0.29.0-nightly.20260203.71f46f116",
       "workspaces": [
         "packages/*"
       ],
       "dependencies": {
         "ink": "npm:@jrichman/ink@6.4.8",
         "latest-version": "^9.0.0",
-        "punycode": "^2.3.1",
-        "simple-git": "^3.28.0",
-        "whatwg-url": "^5.0.0"
+        "simple-git": "^3.28.0"
       },
       "bin": {
         "gemini": "bundle/gemini.js"
@@ -56,7 +53,6 @@
         "mock-fs": "^5.5.0",
         "msw": "^2.10.4",
         "npm-run-all": "^4.1.5",
-        "patch-package": "^8.0.1",
         "prettier": "^3.5.3",
         "react-devtools-core": "^6.1.2",
         "semver": "^7.7.2",
@@ -5373,13 +5369,6 @@
       "integrity": "sha512-5xXB7kdQlFBP82ViMJTwwEc3gKCLGKR/eoxQm4zge7GPBl86tCdI0IdPJjoKd8mUSFXz5V7i/25sfsEkP4j46g==",
       "license": "MIT"
     },
-    "node_modules/@yarnpkg/lockfile": {
-      "version": "1.1.0",
-      "resolved": "https://registry.npmjs.org/@yarnpkg/lockfile/-/lockfile-1.1.0.tgz",
-      "integrity": "sha512-GpSwvyXOcOOlV70vbnzjj4fW5xW/FdUF6nQEt1ENy7m4ZCczi1+/buVUPAqmGfqznsORNFzUMjctTIp8a9tuCQ==",
-      "dev": true,
-      "license": "BSD-2-Clause"
-    },
     "node_modules/abort-controller": {
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/abort-controller/-/abort-controller-3.0.0.tgz",
@@ -6655,22 +6644,6 @@
         "node": ">=18"
       }
     },
-    "node_modules/ci-info": {
-      "version": "3.9.0",
-      "resolved": "https://registry.npmjs.org/ci-info/-/ci-info-3.9.0.tgz",
-      "integrity": "sha512-NIxF55hv4nSqQswkAeiOi1r83xy8JldOFDTWiug55KBu9Jnblncd2U6ViHmYgHf01TPZS77NJBhBMKdWj9HQMQ==",
-      "dev": true,
-      "funding": [
-        {
-          "type": "github",
-          "url": "https://github.com/sponsors/sibiraj-s"
-        }
-      ],
-      "license": "MIT",
-      "engines": {
-        "node": ">=8"
-      }
-    },
     "node_modules/cjs-module-lexer": {
       "version": "1.4.3",
       "resolved": "https://registry.npmjs.org/cjs-module-lexer/-/cjs-module-lexer-1.4.3.tgz",
@@ -9325,16 +9298,6 @@
         "url": "https://github.com/sponsors/sindresorhus"
       }
     },
-    "node_modules/find-yarn-workspace-root": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/find-yarn-workspace-root/-/find-yarn-workspace-root-2.0.0.tgz",
-      "integrity": "sha512-1IMnbjt4KzsQfnhnzNd8wUEgXZ44IzZaZmnLYx7D5FZlaHt2gW20Cri8Q+E/t5tIj4+epTBub+2Zxu/vNILzqQ==",
-      "dev": true,
-      "license": "Apache-2.0",
-      "dependencies": {
-        "micromatch": "^4.0.2"
-      }
-    },
     "node_modules/findup-sync": {
       "version": "5.0.0",
       "resolved": "https://registry.npmjs.org/findup-sync/-/findup-sync-5.0.0.tgz",
@@ -11560,26 +11523,6 @@
       "integrity": "sha512-fQhoXdcvc3V28x7C7BMs4P5+kNlgUURe2jmUT1T//oBRMDrqy1QPelJimwZGo7Hg9VPV3EQV5Bnq4hbFy2vetA==",
       "license": "BSD-2-Clause"
     },
-    "node_modules/json-stable-stringify": {
-      "version": "1.3.0",
-      "resolved": "https://registry.npmjs.org/json-stable-stringify/-/json-stable-stringify-1.3.0.tgz",
-      "integrity": "sha512-qtYiSSFlwot9XHtF9bD9c7rwKjr+RecWT//ZnPvSmEjpV5mmPOCN4j8UjY5hbjNkOwZ/jQv3J6R1/pL7RwgMsg==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "call-bind": "^1.0.8",
-        "call-bound": "^1.0.4",
-        "isarray": "^2.0.5",
-        "jsonify": "^0.0.1",
-        "object-keys": "^1.1.1"
-      },
-      "engines": {
-        "node": ">= 0.4"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/ljharb"
-      }
-    },
     "node_modules/json-stable-stringify-without-jsonify": {
       "version": "1.0.1",
       "resolved": "https://registry.npmjs.org/json-stable-stringify-without-jsonify/-/json-stable-stringify-without-jsonify-1.0.1.tgz",
@@ -11628,16 +11571,6 @@
         "node": ">= 10.0.0"
       }
     },
-    "node_modules/jsonify": {
-      "version": "0.0.1",
-      "resolved": "https://registry.npmjs.org/jsonify/-/jsonify-0.0.1.tgz",
-      "integrity": "sha512-2/Ki0GcmuqSrgFyelQq9M05y7PS0mEwuIzrf3f1fPqkVDVRvZrPZtVSMHxdgo8Aq0sxAOb/cr2aqqA3LeWHVPg==",
-      "dev": true,
-      "license": "Public Domain",
-      "funding": {
-        "url": "https://github.com/sponsors/ljharb"
-      }
-    },
     "node_modules/jsonwebtoken": {
       "version": "9.0.2",
       "resolved": "https://registry.npmjs.org/jsonwebtoken/-/jsonwebtoken-9.0.2.tgz",
@@ -11742,16 +11675,6 @@
         "json-buffer": "3.0.1"
       }
     },
-    "node_modules/klaw-sync": {
-      "version": "6.0.0",
-      "resolved": "https://registry.npmjs.org/klaw-sync/-/klaw-sync-6.0.0.tgz",
-      "integrity": "sha512-nIeuVSzdCCs6TDPTqI8w1Yre34sSq7AkZ4B3sfOBbI2CgVSB4Du4aLQijFU2+lhAFCwt9+42Hel6lQNIv6AntQ==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "graceful-fs": "^4.1.11"
-      }
-    },
     "node_modules/kleur": {
       "version": "3.0.3",
       "resolved": "https://registry.npmjs.org/kleur/-/kleur-3.0.3.tgz",
@@ -12861,6 +12784,28 @@
         }
       }
     },
+    "node_modules/node-fetch/node_modules/tr46": {
+      "version": "0.0.3",
+      "resolved": "https://registry.npmjs.org/tr46/-/tr46-0.0.3.tgz",
+      "integrity": "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw==",
+      "license": "MIT"
+    },
+    "node_modules/node-fetch/node_modules/webidl-conversions": {
+      "version": "3.0.1",
+      "resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-3.0.1.tgz",
+      "integrity": "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ==",
+      "license": "BSD-2-Clause"
+    },
+    "node_modules/node-fetch/node_modules/whatwg-url": {
+      "version": "5.0.0",
+      "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-5.0.0.tgz",
+      "integrity": "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw==",
+      "license": "MIT",
+      "dependencies": {
+        "tr46": "~0.0.3",
+        "webidl-conversions": "^3.0.0"
+      }
+    },
     "node_modules/node-gyp-build": {
       "version": "4.8.4",
       "resolved": "https://registry.npmjs.org/node-gyp-build/-/node-gyp-build-4.8.4.tgz",
@@ -13754,117 +13699,6 @@
         "node": "^12.20.0 || ^14.13.1 || >=16.0.0"
       }
     },
-    "node_modules/patch-package": {
-      "version": "8.0.1",
-      "resolved": "https://registry.npmjs.org/patch-package/-/patch-package-8.0.1.tgz",
-      "integrity": "sha512-VsKRIA8f5uqHQ7NGhwIna6Bx6D9s/1iXlA1hthBVBEbkq+t4kXD0HHt+rJhf/Z+Ci0F/HCB2hvn0qLdLG+Qxlw==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "@yarnpkg/lockfile": "^1.1.0",
-        "chalk": "^4.1.2",
-        "ci-info": "^3.7.0",
-        "cross-spawn": "^7.0.3",
-        "find-yarn-workspace-root": "^2.0.0",
-        "fs-extra": "^10.0.0",
-        "json-stable-stringify": "^1.0.2",
-        "klaw-sync": "^6.0.0",
-        "minimist": "^1.2.6",
-        "open": "^7.4.2",
-        "semver": "^7.5.3",
-        "slash": "^2.0.0",
-        "tmp": "^0.2.4",
-        "yaml": "^2.2.2"
-      },
-      "bin": {
-        "patch-package": "index.js"
-      },
-      "engines": {
-        "node": ">=14",
-        "npm": ">5"
-      }
-    },
-    "node_modules/patch-package/node_modules/fs-extra": {
-      "version": "10.1.0",
-      "resolved": "https://registry.npmjs.org/fs-extra/-/fs-extra-10.1.0.tgz",
-      "integrity": "sha512-oRXApq54ETRj4eMiFzGnHWGy+zo5raudjuxN0b8H7s/RU2oW0Wvsx9O0ACRN/kRq9E8Vu/ReskGB5o3ji+FzHQ==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "graceful-fs": "^4.2.0",
-        "jsonfile": "^6.0.1",
-        "universalify": "^2.0.0"
-      },
-      "engines": {
-        "node": ">=12"
-      }
-    },
-    "node_modules/patch-package/node_modules/is-docker": {
-      "version": "2.2.1",
-      "resolved": "https://registry.npmjs.org/is-docker/-/is-docker-2.2.1.tgz",
-      "integrity": "sha512-F+i2BKsFrH66iaUFc0woD8sLy8getkwTwtOBjvs56Cx4CgJDeKQeqfz8wAYiSb8JOprWhHH5p77PbmYCvvUuXQ==",
-      "dev": true,
-      "license": "MIT",
-      "bin": {
-        "is-docker": "cli.js"
-      },
-      "engines": {
-        "node": ">=8"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/sindresorhus"
-      }
-    },
-    "node_modules/patch-package/node_modules/is-wsl": {
-      "version": "2.2.0",
-      "resolved": "https://registry.npmjs.org/is-wsl/-/is-wsl-2.2.0.tgz",
-      "integrity": "sha512-fKzAra0rGJUUBwGBgNkHZuToZcn+TtXHpeCgmkMJMMYx1sQDYaCSyjJBSCa2nH1DGm7s3n1oBnohoVTBaN7Lww==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "is-docker": "^2.0.0"
-      },
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/patch-package/node_modules/open": {
-      "version": "7.4.2",
-      "resolved": "https://registry.npmjs.org/open/-/open-7.4.2.tgz",
-      "integrity": "sha512-MVHddDVweXZF3awtlAS+6pgKLlm/JgxZ90+/NBurBoQctVOOB/zDdVjcyPzQ+0laDGbsWgrRkflI65sQeOgT9Q==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "is-docker": "^2.0.0",
-        "is-wsl": "^2.1.1"
-      },
-      "engines": {
-        "node": ">=8"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/sindresorhus"
-      }
-    },
-    "node_modules/patch-package/node_modules/slash": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/slash/-/slash-2.0.0.tgz",
-      "integrity": "sha512-ZYKh3Wh2z1PpEXWr0MpSBZ0V6mZHAQfYevttO11c51CaWjGTaadiKZ+wVt1PbMlDV5qhMFslpZCemhwOK7C89A==",
-      "dev": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">=6"
-      }
-    },
-    "node_modules/patch-package/node_modules/universalify": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/universalify/-/universalify-2.0.1.tgz",
-      "integrity": "sha512-gptHNQghINnc/vTGIk0SOFGFNXw7JVrlRUtConJRlvaw6DuX0wO5Jeko9sWrMBhh+PsYAZ7oXAiOnf/UKogyiw==",
-      "dev": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">= 10.0.0"
-      }
-    },
     "node_modules/path-browserify": {
       "version": "1.0.1",
       "resolved": "https://registry.npmjs.org/path-browserify/-/path-browserify-1.0.1.tgz",
@@ -14311,6 +14145,7 @@
       "version": "2.3.1",
       "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.3.1.tgz",
       "integrity": "sha512-vYt7UD1U9Wg6138shLtLOvdAu+8DsC/ilFtEVHcH+wydcSpNE20AfSOduf6MkRFahL5FY7X1oU7nKVZFtfq8Fg==",
+      "devOptional": true,
       "license": "MIT",
       "engines": {
         "node": ">=6"
@@ -16801,12 +16636,6 @@
         "node": ">=0.6"
       }
     },
-    "node_modules/tr46": {
-      "version": "0.0.3",
-      "resolved": "https://registry.npmjs.org/tr46/-/tr46-0.0.3.tgz",
-      "integrity": "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw==",
-      "license": "MIT"
-    },
     "node_modules/tree-dump": {
       "version": "1.0.3",
       "resolved": "https://registry.npmjs.org/tree-dump/-/tree-dump-1.0.3.tgz",
@@ -17574,12 +17403,6 @@
         }
       }
     },
-    "node_modules/webidl-conversions": {
-      "version": "3.0.1",
-      "resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-3.0.1.tgz",
-      "integrity": "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ==",
-      "license": "BSD-2-Clause"
-    },
     "node_modules/whatwg-encoding": {
       "version": "3.1.1",
       "resolved": "https://registry.npmjs.org/whatwg-encoding/-/whatwg-encoding-3.1.1.tgz",
@@ -17603,16 +17426,6 @@
         "node": ">=18"
       }
     },
-    "node_modules/whatwg-url": {
-      "version": "5.0.0",
-      "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-5.0.0.tgz",
-      "integrity": "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw==",
-      "license": "MIT",
-      "dependencies": {
-        "tr46": "~0.0.3",
-        "webidl-conversions": "^3.0.0"
-      }
-    },
     "node_modules/which": {
       "version": "2.0.2",
       "resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz",
@@ -18208,7 +18021,7 @@
     },
     "packages/a2a-server": {
       "name": "@google/gemini-cli-a2a-server",
-      "version": "0.28.0-nightly.20260128.adc8e11bb",
+      "version": "0.29.0-nightly.20260203.71f46f116",
       "dependencies": {
         "@a2a-js/sdk": "^0.3.8",
         "@google-cloud/storage": "^7.16.0",
@@ -18264,7 +18077,7 @@
     },
     "packages/cli": {
       "name": "@google/gemini-cli",
-      "version": "0.28.0-nightly.20260128.adc8e11bb",
+      "version": "0.29.0-nightly.20260203.71f46f116",
       "license": "Apache-2.0",
       "dependencies": {
         "@agentclientprotocol/sdk": "^0.12.0",
@@ -18351,7 +18164,7 @@
     },
     "packages/core": {
       "name": "@google/gemini-cli-core",
-      "version": "0.28.0-nightly.20260128.adc8e11bb",
+      "version": "0.29.0-nightly.20260203.71f46f116",
       "license": "Apache-2.0",
       "dependencies": {
         "@a2a-js/sdk": "^0.3.8",
@@ -18510,7 +18323,7 @@
     },
     "packages/test-utils": {
       "name": "@google/gemini-cli-test-utils",
-      "version": "0.28.0-nightly.20260128.adc8e11bb",
+      "version": "0.29.0-nightly.20260203.71f46f116",
       "license": "Apache-2.0",
       "dependencies": {
         "@google/gemini-cli-core": "file:../core",
@@ -18527,7 +18340,7 @@
     },
     "packages/vscode-ide-companion": {
       "name": "gemini-cli-vscode-ide-companion",
-      "version": "0.28.0-nightly.20260128.adc8e11bb",
+      "version": "0.29.0-nightly.20260203.71f46f116",
       "license": "LICENSE",
       "dependencies": {
         "@modelcontextprotocol/sdk": "^1.23.0",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@google/gemini-cli",
-  "version": "0.28.0-nightly.20260128.adc8e11bb",
+  "version": "0.29.0-nightly.20260203.71f46f116",
   "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:0.28.0-nightly.20260128.adc8e11bb"
+    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.29.0-nightly.20260203.71f46f116"
   },
   "scripts": {
     "start": "cross-env NODE_ENV=development node scripts/start.js",
@@ -61,8 +61,7 @@
     "telemetry": "node scripts/telemetry.js",
     "check:lockfile": "node scripts/check-lockfile.js",
     "clean": "node scripts/clean.js",
-    "pre-commit": "node scripts/pre-commit.js",
-    "postinstall": "patch-package"
+    "pre-commit": "node scripts/pre-commit.js"
   },
   "overrides": {
     "ink": "npm:@jrichman/ink@6.4.8",
@@ -114,7 +113,6 @@
     "mock-fs": "^5.5.0",
     "msw": "^2.10.4",
     "npm-run-all": "^4.1.5",
-    "patch-package": "^8.0.1",
     "prettier": "^3.5.3",
     "react-devtools-core": "^6.1.2",
     "semver": "^7.7.2",
@@ -128,9 +126,7 @@
   "dependencies": {
     "ink": "npm:@jrichman/ink@6.4.8",
     "latest-version": "^9.0.0",
-    "punycode": "^2.3.1",
-    "simple-git": "^3.28.0",
-    "whatwg-url": "^5.0.0"
+    "simple-git": "^3.28.0"
   },
   "optionalDependencies": {
     "@lydell/node-pty": "1.1.0",

packages/a2a-server/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@google/gemini-cli-a2a-server",
-  "version": "0.28.0-nightly.20260128.adc8e11bb",
+  "version": "0.29.0-nightly.20260203.71f46f116",
   "description": "Gemini CLI A2A Server",
   "repository": {
     "type": "git",

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

@@ -11,6 +11,11 @@ import type { Settings } from './settings.js';
 import {
   type ExtensionLoader,
   FileDiscoveryService,
+  getCodeAssistServer,
+  Config,
+  ExperimentFlags,
+  fetchAdminControlsOnce,
+  type FetchAdminControlsResponse,
 } from '@google/gemini-cli-core';
 
 // Mock dependencies
@@ -19,11 +24,23 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
     await importOriginal<typeof import('@google/gemini-cli-core')>();
   return {
     ...actual,
-    Config: vi.fn().mockImplementation((params) => ({
-      initialize: vi.fn(),
-      refreshAuth: vi.fn(),
-      ...params, // Expose params for assertion
-    })),
+    Config: vi.fn().mockImplementation((params) => {
+      const mockConfig = {
+        ...params,
+        initialize: vi.fn(),
+        refreshAuth: vi.fn(),
+        getExperiments: vi.fn().mockReturnValue({
+          flags: {
+            [actual.ExperimentFlags.ENABLE_ADMIN_CONTROLS]: {
+              boolValue: false,
+            },
+          },
+        }),
+        getRemoteAdminSettings: vi.fn(),
+        setRemoteAdminSettings: vi.fn(),
+      };
+      return mockConfig;
+    }),
     loadServerHierarchicalMemory: vi
       .fn()
       .mockResolvedValue({ memoryContent: '', fileCount: 0, filePaths: [] }),
@@ -31,6 +48,11 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
       flush: vi.fn(),
     },
     FileDiscoveryService: vi.fn(),
+    getCodeAssistServer: vi.fn(),
+    fetchAdminControlsOnce: vi.fn(),
+    coreEvents: {
+      emitAdminSettingsChanged: vi.fn(),
+    },
   };
 });
 
@@ -56,6 +78,121 @@ describe('loadConfig', () => {
     delete process.env['GEMINI_API_KEY'];
   });
 
+  describe('admin settings overrides', () => {
+    it('should not fetch admin controls if experiment is disabled', async () => {
+      await loadConfig(mockSettings, mockExtensionLoader, taskId);
+      expect(fetchAdminControlsOnce).not.toHaveBeenCalled();
+    });
+
+    describe('when admin controls experiment is enabled', () => {
+      beforeEach(() => {
+        // We need to cast to any here to modify the mock implementation
+        // eslint-disable-next-line @typescript-eslint/no-explicit-any
+        (Config as any).mockImplementation((params: unknown) => {
+          const mockConfig = {
+            ...(params as object),
+            initialize: vi.fn(),
+            refreshAuth: vi.fn(),
+            getExperiments: vi.fn().mockReturnValue({
+              flags: {
+                [ExperimentFlags.ENABLE_ADMIN_CONTROLS]: {
+                  boolValue: true,
+                },
+              },
+            }),
+            getRemoteAdminSettings: vi.fn().mockReturnValue({}),
+            setRemoteAdminSettings: vi.fn(),
+          };
+          return mockConfig;
+        });
+      });
+
+      it('should fetch admin controls and apply them', async () => {
+        const mockAdminSettings: FetchAdminControlsResponse = {
+          mcpSetting: {
+            mcpEnabled: false,
+          },
+          cliFeatureSetting: {
+            extensionsSetting: {
+              extensionsEnabled: false,
+            },
+          },
+          strictModeDisabled: false,
+        };
+        vi.mocked(fetchAdminControlsOnce).mockResolvedValue(mockAdminSettings);
+
+        await loadConfig(mockSettings, mockExtensionLoader, taskId);
+
+        expect(Config).toHaveBeenLastCalledWith(
+          expect.objectContaining({
+            disableYoloMode: !mockAdminSettings.strictModeDisabled,
+            mcpEnabled: mockAdminSettings.mcpSetting?.mcpEnabled,
+            extensionsEnabled:
+              mockAdminSettings.cliFeatureSetting?.extensionsSetting
+                ?.extensionsEnabled,
+          }),
+        );
+      });
+
+      it('should treat unset admin settings as false when admin settings are passed', async () => {
+        const mockAdminSettings: FetchAdminControlsResponse = {
+          mcpSetting: {
+            mcpEnabled: true,
+          },
+        };
+        vi.mocked(fetchAdminControlsOnce).mockResolvedValue(mockAdminSettings);
+
+        await loadConfig(mockSettings, mockExtensionLoader, taskId);
+
+        expect(Config).toHaveBeenLastCalledWith(
+          expect.objectContaining({
+            disableYoloMode: !false,
+            mcpEnabled: mockAdminSettings.mcpSetting?.mcpEnabled,
+            extensionsEnabled: undefined,
+          }),
+        );
+      });
+
+      it('should not pass default unset admin settings when no admin settings are present', async () => {
+        const mockAdminSettings: FetchAdminControlsResponse = {};
+        vi.mocked(fetchAdminControlsOnce).mockResolvedValue(mockAdminSettings);
+
+        await loadConfig(mockSettings, mockExtensionLoader, taskId);
+
+        expect(Config).toHaveBeenLastCalledWith(expect.objectContaining({}));
+      });
+
+      it('should fetch admin controls using the code assist server when available', async () => {
+        const mockAdminSettings: FetchAdminControlsResponse = {
+          mcpSetting: {
+            mcpEnabled: true,
+          },
+          strictModeDisabled: true,
+        };
+        const mockCodeAssistServer = { projectId: 'test-project' };
+        vi.mocked(getCodeAssistServer).mockReturnValue(
+          // eslint-disable-next-line @typescript-eslint/no-explicit-any
+          mockCodeAssistServer as any,
+        );
+        vi.mocked(fetchAdminControlsOnce).mockResolvedValue(mockAdminSettings);
+
+        await loadConfig(mockSettings, mockExtensionLoader, taskId);
+
+        expect(fetchAdminControlsOnce).toHaveBeenCalledWith(
+          mockCodeAssistServer,
+          true,
+        );
+        expect(Config).toHaveBeenLastCalledWith(
+          expect.objectContaining({
+            disableYoloMode: !mockAdminSettings.strictModeDisabled,
+            mcpEnabled: mockAdminSettings.mcpSetting?.mcpEnabled,
+            extensionsEnabled: undefined,
+          }),
+        );
+      });
+    });
+  });
+
   it('should set customIgnoreFilePaths when CUSTOM_IGNORE_FILE_PATHS env var is present', async () => {
     const testPath = '/tmp/ignore';
     process.env['CUSTOM_IGNORE_FILE_PATHS'] = testPath;

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

@@ -24,6 +24,9 @@ import {
   PREVIEW_GEMINI_MODEL,
   homedir,
   GitService,
+  fetchAdminControlsOnce,
+  getCodeAssistServer,
+  ExperimentFlags,
 } from '@google/gemini-cli-core';
 
 import { logger } from '../utils/logger.js';
@@ -124,37 +127,50 @@ export async function loadConfig(
   configParams.userMemory = memoryContent;
   configParams.geminiMdFileCount = fileCount;
   configParams.geminiMdFilePaths = filePaths;
-  const config = new Config({
+
+  // Set an initial config to use to get a code assist server.
+  // This is needed to fetch admin controls.
+  const initialConfig = new Config({
     ...configParams,
   });
+
+  const codeAssistServer = getCodeAssistServer(initialConfig);
+
+  const adminControlsEnabled =
+    initialConfig.getExperiments()?.flags[ExperimentFlags.ENABLE_ADMIN_CONTROLS]
+      ?.boolValue ?? false;
+
+  // Initialize final config parameters to the previous parameters.
+  // If no admin controls are needed, these will be used as-is for the final
+  // config.
+  const finalConfigParams = { ...configParams };
+  if (adminControlsEnabled) {
+    const adminSettings = await fetchAdminControlsOnce(
+      codeAssistServer,
+      adminControlsEnabled,
+    );
+
+    // Admin settings are able to be undefined if unset, but if any are present,
+    // we should initialize them all.
+    // If any are present, undefined settings should be treated as if they were
+    // set to false.
+    // If NONE are present, disregard admin settings entirely, and pass the
+    // final config as is.
+    if (Object.keys(adminSettings).length !== 0) {
+      finalConfigParams.disableYoloMode = !adminSettings.strictModeDisabled;
+      finalConfigParams.mcpEnabled = adminSettings.mcpSetting?.mcpEnabled;
+      finalConfigParams.extensionsEnabled =
+        adminSettings.cliFeatureSetting?.extensionsSetting?.extensionsEnabled;
+    }
+  }
+
+  const config = new Config(finalConfigParams);
+
   // Needed to initialize ToolRegistry, and git checkpointing if enabled
   await config.initialize();
   startupProfiler.flush(config);
 
-  if (process.env['USE_CCPA']) {
-    logger.info('[Config] Using CCPA Auth:');
-    try {
-      if (adcFilePath) {
-        path.resolve(adcFilePath);
-      }
-    } catch (e) {
-      logger.error(
-        `[Config] USE_CCPA env var is true but unable to resolve GOOGLE_APPLICATION_CREDENTIALS file path ${adcFilePath}. Error ${e}`,
-      );
-    }
-    await config.refreshAuth(AuthType.LOGIN_WITH_GOOGLE);
-    logger.info(
-      `[Config] GOOGLE_CLOUD_PROJECT: ${process.env['GOOGLE_CLOUD_PROJECT']}`,
-    );
-  } else if (process.env['GEMINI_API_KEY']) {
-    logger.info('[Config] Using Gemini API Key');
-    await config.refreshAuth(AuthType.USE_GEMINI);
-  } else {
-    const errorMessage =
-      '[Config] Unable to set GeneratorConfig. Please provide a GEMINI_API_KEY or set USE_CCPA.';
-    logger.error(errorMessage);
-    throw new Error(errorMessage);
-  }
+  await refreshAuthentication(config, adcFilePath, 'Config');
 
   return config;
 }
@@ -222,3 +238,33 @@ function findEnvFile(startDir: string): string | null {
     currentDir = parentDir;
   }
 }
+
+async function refreshAuthentication(
+  config: Config,
+  adcFilePath: string | undefined,
+  logPrefix: string,
+): Promise<void> {
+  if (process.env['USE_CCPA']) {
+    logger.info(`[${logPrefix}] Using CCPA Auth:`);
+    try {
+      if (adcFilePath) {
+        path.resolve(adcFilePath);
+      }
+    } catch (e) {
+      logger.error(
+        `[${logPrefix}] USE_CCPA env var is true but unable to resolve GOOGLE_APPLICATION_CREDENTIALS file path ${adcFilePath}. Error ${e}`,
+      );
+    }
+    await config.refreshAuth(AuthType.LOGIN_WITH_GOOGLE);
+    logger.info(
+      `[${logPrefix}] GOOGLE_CLOUD_PROJECT: ${process.env['GOOGLE_CLOUD_PROJECT']}`,
+    );
+  } else if (process.env['GEMINI_API_KEY']) {
+    logger.info(`[${logPrefix}] Using Gemini API Key`);
+    await config.refreshAuth(AuthType.USE_GEMINI);
+  } else {
+    const errorMessage = `[${logPrefix}] Unable to set GeneratorConfig. Please provide a GEMINI_API_KEY or set USE_CCPA.`;
+    logger.error(errorMessage);
+    throw new Error(errorMessage);
+  }
+}

packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@google/gemini-cli",
-  "version": "0.28.0-nightly.20260128.adc8e11bb",
+  "version": "0.29.0-nightly.20260203.71f46f116",
   "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:0.28.0-nightly.20260128.adc8e11bb"
+    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.29.0-nightly.20260203.71f46f116"
   },
   "dependencies": {
     "@agentclientprotocol/sdk": "^0.12.0",

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

@@ -8,7 +8,10 @@ import { ExtensionManager } from '../../config/extension-manager.js';
 import { promptForSetting } from '../../config/extensions/extensionSettings.js';
 import { loadSettings } from '../../config/settings.js';
 import { requestConsentNonInteractive } from '../../config/extensions/consent.js';
-import { debugLogger } from '@google/gemini-cli-core';
+import {
+  debugLogger,
+  type ResolvedExtensionSetting,
+} from '@google/gemini-cli-core';
 
 export async function getExtensionManager() {
   const workspaceDir = process.cwd();
@@ -35,3 +38,15 @@ export async function getExtensionAndManager(name: string) {
 
   return { extension, extensionManager };
 }
+
+export function getFormattedSettingValue(
+  setting: ResolvedExtensionSetting,
+): string {
+  if (!setting.value) {
+    return '[not set]';
+  }
+  if (setting.sensitive) {
+    return '***';
+  }
+  return setting.value;
+}

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

@@ -21,6 +21,17 @@ import * as path from 'node:path';
 import * as os from 'node:os';
 import { GEMINI_DIR, debugLogger } from '@google/gemini-cli-core';
 
+vi.mock('fs', async (importOriginal) => {
+  const actualFs = await importOriginal<typeof fs>();
+  return {
+    ...actualFs,
+    existsSync: vi.fn(actualFs.existsSync),
+    readFileSync: vi.fn(actualFs.readFileSync),
+    writeFileSync: vi.fn(actualFs.writeFileSync),
+    mkdirSync: vi.fn(actualFs.mkdirSync),
+  };
+});
+
 vi.mock('fs/promises', () => ({
   readFile: vi.fn(),
   writeFile: vi.fn(),
@@ -30,6 +41,14 @@ vi.mock('../utils.js', () => ({
   exitCli: vi.fn(),
 }));
 
+vi.mock('../../config/trustedFolders.js', () => ({
+  isWorkspaceTrusted: vi.fn(() => ({
+    isTrusted: true,
+    source: undefined,
+  })),
+  isFolderTrustEnabled: vi.fn(() => false),
+}));
+
 describe('mcp remove command', () => {
   describe('unit tests with mocks', () => {
     let parser: Argv;

packages/cli/src/commands/skills.tsx

@@ -9,6 +9,7 @@ import { listCommand } from './skills/list.js';
 import { enableCommand } from './skills/enable.js';
 import { disableCommand } from './skills/disable.js';
 import { installCommand } from './skills/install.js';
+import { linkCommand } from './skills/link.js';
 import { uninstallCommand } from './skills/uninstall.js';
 import { initializeOutputListenersAndFlush } from '../gemini.js';
 import { defer } from '../deferred.js';
@@ -27,6 +28,7 @@ export const skillsCommand: CommandModule = {
       .command(defer(enableCommand, 'skills'))
       .command(defer(disableCommand, 'skills'))
       .command(defer(installCommand, 'skills'))
+      .command(defer(linkCommand, 'skills'))
       .command(defer(uninstallCommand, 'skills'))
       .demandCommand(1, 'You need at least one command before continuing.')
       .version(false),

packages/cli/src/commands/skills/link.test.ts

@@ -0,0 +1,69 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, vi, beforeEach } from 'vitest';
+import { handleLink, linkCommand } from './link.js';
+
+const mockLinkSkill = vi.hoisted(() => vi.fn());
+const mockRequestConsentNonInteractive = vi.hoisted(() => vi.fn());
+const mockSkillsConsentString = vi.hoisted(() => vi.fn());
+
+vi.mock('../../utils/skillUtils.js', () => ({
+  linkSkill: mockLinkSkill,
+}));
+
+vi.mock('@google/gemini-cli-core', () => ({
+  debugLogger: { log: vi.fn(), error: vi.fn() },
+}));
+
+vi.mock('../../config/extensions/consent.js', () => ({
+  requestConsentNonInteractive: mockRequestConsentNonInteractive,
+  skillsConsentString: mockSkillsConsentString,
+}));
+
+import { debugLogger } from '@google/gemini-cli-core';
+
+describe('skills link command', () => {
+  beforeEach(() => {
+    vi.clearAllMocks();
+    vi.spyOn(process, 'exit').mockImplementation(() => undefined as never);
+  });
+
+  describe('linkCommand', () => {
+    it('should have correct command and describe', () => {
+      expect(linkCommand.command).toBe('link <path>');
+      expect(linkCommand.describe).toContain('Links an agent skill');
+    });
+  });
+
+  it('should call linkSkill with correct arguments', async () => {
+    const sourcePath = '/source/path';
+    mockLinkSkill.mockResolvedValue([
+      { name: 'test-skill', location: '/dest/path' },
+    ]);
+
+    await handleLink({ path: sourcePath, scope: 'user' });
+
+    expect(mockLinkSkill).toHaveBeenCalledWith(
+      sourcePath,
+      'user',
+      expect.any(Function),
+      expect.any(Function),
+    );
+    expect(debugLogger.log).toHaveBeenCalledWith(
+      expect.stringContaining('Successfully linked skills'),
+    );
+  });
+
+  it('should handle linkSkill failure', async () => {
+    mockLinkSkill.mockRejectedValue(new Error('Link failed'));
+
+    await handleLink({ path: '/some/path' });
+
+    expect(debugLogger.error).toHaveBeenCalledWith('Link failed');
+    expect(process.exit).toHaveBeenCalledWith(1);
+  });
+});

packages/cli/src/commands/skills/link.ts

@@ -0,0 +1,93 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import type { CommandModule } from 'yargs';
+import { debugLogger } from '@google/gemini-cli-core';
+import chalk from 'chalk';
+
+import { getErrorMessage } from '../../utils/errors.js';
+import { exitCli } from '../utils.js';
+import {
+  requestConsentNonInteractive,
+  skillsConsentString,
+} from '../../config/extensions/consent.js';
+import { linkSkill } from '../../utils/skillUtils.js';
+
+interface LinkArgs {
+  path: string;
+  scope?: 'user' | 'workspace';
+  consent?: boolean;
+}
+
+export async function handleLink(args: LinkArgs) {
+  try {
+    const { scope = 'user', consent } = args;
+
+    await linkSkill(
+      args.path,
+      scope,
+      (msg) => debugLogger.log(msg),
+      async (skills, targetDir) => {
+        const consentString = await skillsConsentString(
+          skills,
+          args.path,
+          targetDir,
+          true,
+        );
+        if (consent) {
+          debugLogger.log('You have consented to the following:');
+          debugLogger.log(consentString);
+          return true;
+        }
+        return requestConsentNonInteractive(consentString);
+      },
+    );
+
+    debugLogger.log(chalk.green('\nSuccessfully linked skills.'));
+  } catch (error) {
+    debugLogger.error(getErrorMessage(error));
+    await exitCli(1);
+  }
+}
+
+export const linkCommand: CommandModule = {
+  command: 'link <path>',
+  describe:
+    'Links an agent skill from a local path. Updates to the source will be reflected immediately.',
+  builder: (yargs) =>
+    yargs
+      .positional('path', {
+        describe: 'The local path of the skill to link.',
+        type: 'string',
+        demandOption: true,
+      })
+      .option('scope', {
+        describe:
+          'The scope to link the skill into. Defaults to "user" (global).',
+        choices: ['user', 'workspace'],
+        default: 'user',
+      })
+      .option('consent', {
+        describe:
+          'Acknowledge the security risks of linking a skill and skip the confirmation prompt.',
+        type: 'boolean',
+        default: false,
+      })
+      .check((argv) => {
+        if (!argv.path) {
+          throw new Error('The path argument must be provided.');
+        }
+        return true;
+      }),
+  handler: async (argv) => {
+    await handleLink({
+      path: argv['path'] as string,
+      scope: argv['scope'] as 'user' | 'workspace',
+      consent: argv['consent'] as boolean | undefined,
+    });
+    await exitCli();
+  },
+};

packages/cli/src/config/auth.ts

@@ -8,7 +8,7 @@ import { AuthType } from '@google/gemini-cli-core';
 import { loadEnvironment, loadSettings } from './settings.js';
 
 export function validateAuthMethod(authMethod: string): string | null {
-  loadEnvironment(loadSettings().merged);
+  loadEnvironment(loadSettings().merged, process.cwd());
   if (
     authMethod === AuthType.LOGIN_WITH_GOOGLE ||
     authMethod === AuthType.COMPUTE_ADC

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

@@ -14,6 +14,7 @@ import {
   WRITE_FILE_TOOL_NAME,
   EDIT_TOOL_NAME,
   WEB_FETCH_TOOL_NAME,
+  ASK_USER_TOOL_NAME,
   type ExtensionLoader,
   debugLogger,
   ApprovalMode,
@@ -596,9 +597,9 @@ describe('parseArguments', () => {
 
   it('should set isCommand to true for hooks command', async () => {
     process.argv = ['node', 'script.js', 'hooks', 'migrate'];
-    // Hooks command enabled via tools settings
+    // Hooks command enabled via hooksConfig settings
     const settings = createTestMergedSettings({
-      tools: { enableHooks: true },
+      hooksConfig: { enabled: true },
     });
     const argv = await parseArguments(settings);
     expect(argv.isCommand).toBe(true);
@@ -1014,7 +1015,9 @@ describe('mergeExcludeTools', () => {
     process.argv = ['node', 'script.js', '-p', 'test'];
     const argv = await parseArguments(createTestMergedSettings());
     const config = await loadCliConfig(settings, 'test-session', argv);
-    expect(config.getExcludeTools()).toEqual(defaultExcludes);
+    expect(config.getExcludeTools()).toEqual(
+      new Set([...defaultExcludes, ASK_USER_TOOL_NAME]),
+    );
   });
 
   it('should handle settings with excludeTools but no extensions', async () => {
@@ -1098,6 +1101,7 @@ describe('Approval mode tool exclusion logic', () => {
     expect(excludedTools).toContain(SHELL_TOOL_NAME);
     expect(excludedTools).toContain(EDIT_TOOL_NAME);
     expect(excludedTools).toContain(WRITE_FILE_TOOL_NAME);
+    expect(excludedTools).toContain(ASK_USER_TOOL_NAME);
   });
 
   it('should exclude all interactive tools in non-interactive mode with explicit default approval mode', async () => {
@@ -1118,6 +1122,7 @@ describe('Approval mode tool exclusion logic', () => {
     expect(excludedTools).toContain(SHELL_TOOL_NAME);
     expect(excludedTools).toContain(EDIT_TOOL_NAME);
     expect(excludedTools).toContain(WRITE_FILE_TOOL_NAME);
+    expect(excludedTools).toContain(ASK_USER_TOOL_NAME);
   });
 
   it('should exclude only shell tools in non-interactive mode with auto_edit approval mode', async () => {
@@ -1138,9 +1143,10 @@ describe('Approval mode tool exclusion logic', () => {
     expect(excludedTools).toContain(SHELL_TOOL_NAME);
     expect(excludedTools).not.toContain(EDIT_TOOL_NAME);
     expect(excludedTools).not.toContain(WRITE_FILE_TOOL_NAME);
+    expect(excludedTools).toContain(ASK_USER_TOOL_NAME);
   });
 
-  it('should exclude no interactive tools in non-interactive mode with yolo approval mode', async () => {
+  it('should exclude only ask_user in non-interactive mode with yolo approval mode', async () => {
     process.argv = [
       'node',
       'script.js',
@@ -1158,6 +1164,7 @@ describe('Approval mode tool exclusion logic', () => {
     expect(excludedTools).not.toContain(SHELL_TOOL_NAME);
     expect(excludedTools).not.toContain(EDIT_TOOL_NAME);
     expect(excludedTools).not.toContain(WRITE_FILE_TOOL_NAME);
+    expect(excludedTools).toContain(ASK_USER_TOOL_NAME);
   });
 
   it('should exclude all interactive tools in non-interactive mode with plan approval mode', async () => {
@@ -1182,9 +1189,10 @@ describe('Approval mode tool exclusion logic', () => {
     expect(excludedTools).toContain(SHELL_TOOL_NAME);
     expect(excludedTools).toContain(EDIT_TOOL_NAME);
     expect(excludedTools).toContain(WRITE_FILE_TOOL_NAME);
+    expect(excludedTools).toContain(ASK_USER_TOOL_NAME);
   });
 
-  it('should exclude no interactive tools in non-interactive mode with legacy yolo flag', async () => {
+  it('should exclude only ask_user in non-interactive mode with legacy yolo flag', async () => {
     process.argv = ['node', 'script.js', '--yolo', '-p', 'test'];
     const argv = await parseArguments(createTestMergedSettings());
     const settings = createTestMergedSettings();
@@ -1195,6 +1203,7 @@ describe('Approval mode tool exclusion logic', () => {
     expect(excludedTools).not.toContain(SHELL_TOOL_NAME);
     expect(excludedTools).not.toContain(EDIT_TOOL_NAME);
     expect(excludedTools).not.toContain(WRITE_FILE_TOOL_NAME);
+    expect(excludedTools).toContain(ASK_USER_TOOL_NAME);
   });
 
   it('should not exclude interactive tools in interactive mode regardless of approval mode', async () => {
@@ -1219,6 +1228,7 @@ describe('Approval mode tool exclusion logic', () => {
       expect(excludedTools).not.toContain(SHELL_TOOL_NAME);
       expect(excludedTools).not.toContain(EDIT_TOOL_NAME);
       expect(excludedTools).not.toContain(WRITE_FILE_TOOL_NAME);
+      expect(excludedTools).not.toContain(ASK_USER_TOOL_NAME);
     }
   });
 
@@ -1255,7 +1265,7 @@ describe('Approval mode tool exclusion logic', () => {
     });
 
     await expect(loadCliConfig(settings, 'test-session', argv)).rejects.toThrow(
-      'Cannot start in YOLO mode since it is disabled by your admin',
+      'YOLO mode is disabled by your administrator. To enable it, please request an update to the settings at: https://goo.gle/manage-gemini-cli',
     );
   });
 
@@ -1556,12 +1566,12 @@ describe('loadCliConfig folderTrust', () => {
     expect(config.getFolderTrust()).toBe(true);
   });
 
-  it('should be false by default', async () => {
+  it('should be true by default', async () => {
     process.argv = ['node', 'script.js'];
     const argv = await parseArguments(createTestMergedSettings());
     const settings = createTestMergedSettings();
     const config = await loadCliConfig(settings, 'test-session', argv);
-    expect(config.getFolderTrust()).toBe(false);
+    expect(config.getFolderTrust()).toBe(true);
   });
 });
 
@@ -1777,6 +1787,7 @@ describe('loadCliConfig tool exclusions', () => {
     expect(config.getExcludeTools()).not.toContain('run_shell_command');
     expect(config.getExcludeTools()).not.toContain('replace');
     expect(config.getExcludeTools()).not.toContain('write_file');
+    expect(config.getExcludeTools()).not.toContain('ask_user');
   });
 
   it('should not exclude interactive tools in interactive mode with YOLO', async () => {
@@ -1791,6 +1802,7 @@ describe('loadCliConfig tool exclusions', () => {
     expect(config.getExcludeTools()).not.toContain('run_shell_command');
     expect(config.getExcludeTools()).not.toContain('replace');
     expect(config.getExcludeTools()).not.toContain('write_file');
+    expect(config.getExcludeTools()).not.toContain('ask_user');
   });
 
   it('should exclude interactive tools in non-interactive mode without YOLO', async () => {
@@ -1805,9 +1817,10 @@ describe('loadCliConfig tool exclusions', () => {
     expect(config.getExcludeTools()).toContain('run_shell_command');
     expect(config.getExcludeTools()).toContain('replace');
     expect(config.getExcludeTools()).toContain('write_file');
+    expect(config.getExcludeTools()).toContain('ask_user');
   });
 
-  it('should not exclude interactive tools in non-interactive mode with YOLO', async () => {
+  it('should exclude only ask_user in non-interactive mode with YOLO', async () => {
     process.stdin.isTTY = false;
     process.argv = ['node', 'script.js', '-p', 'test', '--yolo'];
     const argv = await parseArguments(createTestMergedSettings());
@@ -1819,6 +1832,7 @@ describe('loadCliConfig tool exclusions', () => {
     expect(config.getExcludeTools()).not.toContain('run_shell_command');
     expect(config.getExcludeTools()).not.toContain('replace');
     expect(config.getExcludeTools()).not.toContain('write_file');
+    expect(config.getExcludeTools()).toContain('ask_user');
   });
 
   it('should not exclude shell tool in non-interactive mode when --allowed-tools="ShellTool" is set', async () => {
@@ -2928,7 +2942,7 @@ describe('loadCliConfig disableYoloMode', () => {
       security: { disableYoloMode: true },
     });
     await expect(loadCliConfig(settings, 'test-session', argv)).rejects.toThrow(
-      'Cannot start in YOLO mode since it is disabled by your admin',
+      'YOLO mode is disabled by your administrator. To enable it, please request an update to the settings at: https://goo.gle/manage-gemini-cli',
     );
   });
 });
@@ -2960,7 +2974,7 @@ describe('loadCliConfig secureModeEnabled', () => {
     });
 
     await expect(loadCliConfig(settings, 'test-session', argv)).rejects.toThrow(
-      'Cannot start in YOLO mode since it is disabled by your admin',
+      'YOLO mode is disabled by your administrator. To enable it, please request an update to the settings at: https://goo.gle/manage-gemini-cli',
     );
   });
 
@@ -2974,7 +2988,7 @@ describe('loadCliConfig secureModeEnabled', () => {
     });
 
     await expect(loadCliConfig(settings, 'test-session', argv)).rejects.toThrow(
-      'Cannot start in YOLO mode since it is disabled by your admin',
+      'YOLO mode is disabled by your administrator. To enable it, please request an update to the settings at: https://goo.gle/manage-gemini-cli',
     );
   });
 

packages/cli/src/config/config.ts

@@ -31,6 +31,7 @@ import {
   debugLogger,
   loadServerHierarchicalMemory,
   WEB_FETCH_TOOL_NAME,
+  ASK_USER_TOOL_NAME,
   getVersion,
   PREVIEW_GEMINI_MODEL_AUTO,
   type HookDefinition,
@@ -38,6 +39,7 @@ import {
   type OutputFormat,
   coreEvents,
   GEMINI_MODEL_ALIAS_AUTO,
+  getAdminErrorMessage,
 } from '@google/gemini-cli-core';
 import {
   type Settings,
@@ -68,6 +70,11 @@ export interface CliArgs {
   prompt: string | undefined;
   promptInteractive: string | undefined;
 
+  ralphWiggum: boolean | undefined;
+  completionPromise: string | undefined;
+  maxIterations: number | undefined;
+  memoryFile: string | undefined;
+
   yolo: boolean | undefined;
   approvalMode: string | undefined;
   allowedMcpServerNames: string[] | undefined;
@@ -139,6 +146,31 @@ export async function parseArguments(
           description: 'Run in sandbox?',
         })
 
+        .option('ralph-wiggum', {
+          alias: 'ralphWiggum',
+          type: 'boolean',
+          description:
+            'Enable Ralph Wiggum mode (iterative loop with YOLO mode).',
+        })
+        .option('completion-promise', {
+          alias: 'completionPromise',
+          type: 'string',
+          description:
+            'The string to look for in the output to signal completion in Ralph Wiggum mode.',
+        })
+        .option('max-iterations', {
+          alias: 'maxIterations',
+          type: 'number',
+          description: 'Maximum number of iterations for Ralph Wiggum mode.',
+        })
+        .option('memory-file', {
+          alias: 'memoryFile',
+          type: 'string',
+          description:
+            'Task-specific memory file for Ralph Wiggum mode (defaults to memories.md).',
+          default: 'memories.md',
+        })
+
         .option('yolo', {
           alias: 'y',
           type: 'boolean',
@@ -308,7 +340,7 @@ export async function parseArguments(
     yargsInstance.command(skillsCommand);
   }
   // Register hooks command if hooks are enabled
-  if (settings.tools?.enableHooks) {
+  if (settings.hooksConfig.enabled) {
     yargsInstance.command(hooksCommand);
   }
 
@@ -432,7 +464,7 @@ export async function loadCliConfig(
   const ideMode = settings.ide?.enabled ?? false;
 
   const folderTrust = settings.security?.folderTrust?.enabled ?? false;
-  const trustedFolder = isWorkspaceTrusted(settings)?.isTrusted ?? false;
+  const trustedFolder = isWorkspaceTrusted(settings, cwd)?.isTrusted ?? false;
 
   // Set the context filename in the server's memoryTool module BEFORE loading memory
   // TODO(b/343434939): This is a bit of a hack. The contextFileName should ideally be passed
@@ -550,7 +582,7 @@ export async function loadCliConfig(
         );
       }
       throw new FatalConfigError(
-        'Cannot start in YOLO mode since it is disabled by your admin',
+        getAdminErrorMessage('YOLO mode', undefined /* config */),
       );
     }
   } else if (approvalMode === ApprovalMode.YOLO) {
@@ -595,6 +627,10 @@ export async function loadCliConfig(
   // In non-interactive mode, exclude tools that require a prompt.
   const extraExcludes: string[] = [];
   if (!interactive) {
+    // ask_user requires user interaction and must be excluded in all
+    // non-interactive modes, regardless of the approval mode.
+    extraExcludes.push(ASK_USER_TOOL_NAME);
+
     const defaultExcludes = [
       SHELL_TOOL_NAME,
       EDIT_TOOL_NAME,
@@ -761,6 +797,7 @@ export async function loadCliConfig(
     noBrowser: !!process.env['NO_BROWSER'],
     summarizeToolOutput: settings.model?.summarizeToolOutput,
     ideMode,
+    disableLoopDetection: settings.model?.disableLoopDetection,
     compressionThreshold: settings.model?.compressionThreshold,
     folderTrust,
     interactive,
@@ -790,10 +827,8 @@ export async function loadCliConfig(
     acceptRawOutputRisk: argv.acceptRawOutputRisk,
     modelConfigServiceConfig: settings.modelConfigs,
     // TODO: loading of hooks based on workspace trust
-    enableHooks:
-      (settings.tools?.enableHooks ?? true) &&
-      (settings.hooksConfig?.enabled ?? true),
-    enableHooksUI: settings.tools?.enableHooks ?? true,
+    enableHooks: settings.hooksConfig.enabled,
+    enableHooksUI: settings.hooksConfig.enabled,
     hooks: settings.hooks || {},
     disabledHooks: settings.hooksConfig?.disabled || [],
     projectHooks: projectHooks || {},

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

@@ -227,7 +227,6 @@ System using model: \${MODEL_NAME}
       settings: createTestMergedSettings({
         telemetry: { enabled: false },
         experimental: { extensionConfig: true },
-        tools: { enableHooks: true },
         hooksConfig: { enabled: true },
       }),
       requestConsent: vi.fn().mockResolvedValue(true),

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

@@ -108,6 +108,7 @@ describe('ExtensionManager Settings Scope', () => {
       settings: createTestMergedSettings({
         telemetry: { enabled: false },
         experimental: { extensionConfig: true },
+        security: { folderTrust: { enabled: false } },
       }),
     });
 
@@ -146,6 +147,7 @@ describe('ExtensionManager Settings Scope', () => {
       settings: createTestMergedSettings({
         telemetry: { enabled: false },
         experimental: { extensionConfig: true },
+        security: { folderTrust: { enabled: false } },
       }),
     });
 
@@ -182,6 +184,7 @@ describe('ExtensionManager Settings Scope', () => {
       settings: createTestMergedSettings({
         telemetry: { enabled: false },
         experimental: { extensionConfig: true },
+        security: { folderTrust: { enabled: false } },
       }),
     });
 
@@ -195,7 +198,7 @@ describe('ExtensionManager Settings Scope', () => {
       (s) => s.envVar === 'TEST_SETTING',
     );
     expect(setting).toBeDefined();
-    expect(setting?.value).toBe('[not set]');
+    expect(setting?.value).toBeUndefined();
     expect(setting?.scope).toBeUndefined();
 
     // Verify output string does not contain scope

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

@@ -51,7 +51,6 @@ describe('ExtensionManager theme loading', () => {
         experimental: { extensionConfig: true },
         security: { blockGitExtensions: false },
         admin: { extensions: { enabled: true }, mcp: { enabled: true } },
-        tools: { enableHooks: true },
       }),
       requestConsent: async () => true,
       requestSetting: async () => '',
@@ -134,6 +133,7 @@ describe('ExtensionManager theme loading', () => {
       }),
       isTrustedFolder: () => true,
       getImportFormat: () => 'tree',
+      reloadSkills: vi.fn(),
     } as unknown as Config;
 
     await extensionManager.start(mockConfig);
@@ -209,6 +209,7 @@ describe('ExtensionManager theme loading', () => {
       getAgentRegistry: () => ({
         reload: vi.fn().mockResolvedValue(undefined),
       }),
+      reloadSkills: vi.fn(),
     } as unknown as Config;
 
     await extensionManager.start(mockConfig);

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

@@ -70,6 +70,7 @@ import {
 } from './extensions/extensionSettings.js';
 import type { EventEmitter } from 'node:stream';
 import { themeManager } from '../ui/themes/theme-manager.js';
+import { getFormattedSettingValue } from '../commands/extensions/utils.js';
 
 interface ExtensionManagerParams {
   enabledExtensionOverrides?: string[];
@@ -144,6 +145,26 @@ export class ExtensionManager extends ExtensionLoader {
     previousExtensionConfig?: ExtensionConfig,
   ): Promise<GeminiCLIExtension> {
     if (
+      this.settings.security?.allowedExtensions &&
+      this.settings.security?.allowedExtensions.length > 0
+    ) {
+      const extensionAllowed = this.settings.security?.allowedExtensions.some(
+        (pattern) => {
+          try {
+            return new RegExp(pattern).test(installMetadata.source);
+          } catch (e) {
+            throw new Error(
+              `Invalid regex pattern in allowedExtensions setting: "${pattern}. Error: ${getErrorMessage(e)}`,
+            );
+          }
+        },
+      );
+      if (!extensionAllowed) {
+        throw new Error(
+          `Installing extension from source "${installMetadata.source}" is not allowed by the "allowedExtensions" security setting.`,
+        );
+      }
+    } else if (
       (installMetadata.type === 'git' ||
         installMetadata.type === 'github-release') &&
       this.settings.security.blockGitExtensions
@@ -152,6 +173,7 @@ export class ExtensionManager extends ExtensionLoader {
         'Installing extensions from remote sources is disallowed by your current settings.',
       );
     }
+
     const isUpdate = !!previousExtensionConfig;
     let newExtensionConfig: ExtensionConfig | null = null;
     let localSourcePath: string | undefined;
@@ -522,10 +544,39 @@ Would you like to attempt to install via "git clone" instead?`,
     const installMetadata = loadInstallMetadata(extensionDir);
     let effectiveExtensionPath = extensionDir;
     if (
+      this.settings.security?.allowedExtensions &&
+      this.settings.security?.allowedExtensions.length > 0
+    ) {
+      if (!installMetadata?.source) {
+        throw new Error(
+          `Failed to load extension ${extensionDir}. The ${INSTALL_METADATA_FILENAME} file is missing or misconfigured.`,
+        );
+      }
+      const extensionAllowed = this.settings.security?.allowedExtensions.some(
+        (pattern) => {
+          try {
+            return new RegExp(pattern).test(installMetadata?.source);
+          } catch (e) {
+            throw new Error(
+              `Invalid regex pattern in allowedExtensions setting: "${pattern}. Error: ${getErrorMessage(e)}`,
+            );
+          }
+        },
+      );
+      if (!extensionAllowed) {
+        debugLogger.warn(
+          `Failed to load extension ${extensionDir}. This extension is not allowed by the "allowedExtensions" security setting.`,
+        );
+        return null;
+      }
+    } else if (
       (installMetadata?.type === 'git' ||
         installMetadata?.type === 'github-release') &&
       this.settings.security.blockGitExtensions
     ) {
+      debugLogger.warn(
+        `Failed to load extension ${extensionDir}. Extensions from remote sources is disallowed by your current settings.`,
+      );
       return null;
     }
 
@@ -598,12 +649,7 @@ Would you like to attempt to install via "git clone" instead?`,
           resolvedSettings.push({
             name: setting.name,
             envVar: setting.envVar,
-            value:
-              value === undefined
-                ? '[not set]'
-                : setting.sensitive
-                  ? '***'
-                  : value,
+            value,
             sensitive: setting.sensitive ?? false,
             scope,
             source,
@@ -639,10 +685,7 @@ Would you like to attempt to install via "git clone" instead?`,
       };
 
       let hooks: { [K in HookEventName]?: HookDefinition[] } | undefined;
-      if (
-        this.settings.tools.enableHooks &&
-        this.settings.hooksConfig.enabled
-      ) {
+      if (this.settings.hooksConfig.enabled) {
         hooks = await this.loadExtensionHooks(
           effectiveExtensionPath,
           hydrationContext,
@@ -894,7 +937,7 @@ Would you like to attempt to install via "git clone" instead?`,
           }
           scope += ')';
         }
-        output += `\n  ${setting.name}: ${setting.value} ${scope}`;
+        output += `\n  ${setting.name}: ${getFormattedSettingValue(setting)} ${scope}`;
       });
     }
     return output;

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

@@ -622,6 +622,7 @@ describe('extension tests', () => {
     });
 
     it('should not load github extensions if blockGitExtensions is set', async () => {
+      const consoleSpy = vi.spyOn(console, 'warn').mockImplementation(() => {});
       createExtension({
         extensionsDir: userExtensionsDir,
         name: 'my-ext',
@@ -645,6 +646,73 @@ describe('extension tests', () => {
       const extension = extensions.find((e) => e.name === 'my-ext');
 
       expect(extension).toBeUndefined();
+      expect(consoleSpy).toHaveBeenCalledWith(
+        expect.stringContaining(
+          'Extensions from remote sources is disallowed by your current settings.',
+        ),
+      );
+      consoleSpy.mockRestore();
+    });
+
+    it('should load allowed extensions if the allowlist is set.', async () => {
+      createExtension({
+        extensionsDir: userExtensionsDir,
+        name: 'my-ext',
+        version: '1.0.0',
+        installMetadata: {
+          type: 'git',
+          source: 'http://allowed.com/foo/bar',
+        },
+      });
+      const extensionAllowlistSetting = createTestMergedSettings({
+        security: {
+          allowedExtensions: ['\\b(https?:\\/\\/)?(www\\.)?allowed\\.com\\S*'],
+        },
+      });
+      extensionManager = new ExtensionManager({
+        workspaceDir: tempWorkspaceDir,
+        requestConsent: mockRequestConsent,
+        requestSetting: mockPromptForSettings,
+        settings: extensionAllowlistSetting,
+      });
+      const extensions = await extensionManager.loadExtensions();
+
+      expect(extensions).toHaveLength(1);
+      expect(extensions[0].name).toBe('my-ext');
+    });
+
+    it('should not load disallowed extensions if the allowlist is set.', async () => {
+      const consoleSpy = vi.spyOn(console, 'warn').mockImplementation(() => {});
+      createExtension({
+        extensionsDir: userExtensionsDir,
+        name: 'my-ext',
+        version: '1.0.0',
+        installMetadata: {
+          type: 'git',
+          source: 'http://notallowed.com/foo/bar',
+        },
+      });
+      const extensionAllowlistSetting = createTestMergedSettings({
+        security: {
+          allowedExtensions: ['\\b(https?:\\/\\/)?(www\\.)?allowed\\.com\\S*'],
+        },
+      });
+      extensionManager = new ExtensionManager({
+        workspaceDir: tempWorkspaceDir,
+        requestConsent: mockRequestConsent,
+        requestSetting: mockPromptForSettings,
+        settings: extensionAllowlistSetting,
+      });
+      const extensions = await extensionManager.loadExtensions();
+      const extension = extensions.find((e) => e.name === 'my-ext');
+
+      expect(extension).toBeUndefined();
+      expect(consoleSpy).toHaveBeenCalledWith(
+        expect.stringContaining(
+          'This extension is not allowed by the "allowedExtensions" security setting',
+        ),
+      );
+      consoleSpy.mockRestore();
     });
 
     it('should not load any extensions if admin.extensions.enabled is false', async () => {
@@ -1116,6 +1184,30 @@ describe('extension tests', () => {
       );
     });
 
+    it('should not install a disallowed extension if the allowlist is set', async () => {
+      const gitUrl = 'https://somehost.com/somerepo.git';
+      const allowedExtensionsSetting = createTestMergedSettings({
+        security: {
+          allowedExtensions: ['\\b(https?:\\/\\/)?(www\\.)?allowed\\.com\\S*'],
+        },
+      });
+      extensionManager = new ExtensionManager({
+        workspaceDir: tempWorkspaceDir,
+        requestConsent: mockRequestConsent,
+        requestSetting: mockPromptForSettings,
+        settings: allowedExtensionsSetting,
+      });
+      await extensionManager.loadExtensions();
+      await expect(
+        extensionManager.installOrUpdateExtension({
+          source: gitUrl,
+          type: 'git',
+        }),
+      ).rejects.toThrow(
+        `Installing extension from source "${gitUrl}" is not allowed by the "allowedExtensions" security setting.`,
+      );
+    });
+
     it('should prompt for trust if workspace is not trusted', async () => {
       vi.mocked(isWorkspaceTrusted).mockReturnValue({
         isTrusted: false,

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

@@ -28,14 +28,19 @@ export async function skillsConsentString(
   skills: SkillDefinition[],
   source: string,
   targetDir?: string,
+  isLink = false,
 ): Promise<string> {
+  const action = isLink ? 'Linking' : 'Installing';
   const output: string[] = [];
-  output.push(`Installing agent skill(s) from "${source}".`);
-  output.push('\nThe following agent skill(s) will be installed:\n');
+  output.push(`${action} agent skill(s) from "${source}".`);
+  output.push(
+    `\nThe following agent skill(s) will be ${action.toLowerCase()}:\n`,
+  );
   output.push(...(await renderSkillsList(skills)));
 
   if (targetDir) {
-    output.push(`Install Destination: ${targetDir}`);
+    const destLabel = isLink ? 'Link' : 'Install';
+    output.push(`${destLabel} Destination: ${targetDir}`);
   }
   output.push('\n' + SKILLS_WARNING_MESSAGE);
 

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

@@ -786,6 +786,23 @@ describe('extensionSettings', () => {
       expect(await userKeychain.getSecret('VAR2')).toBeNull();
     });
 
+    it('should delete a non-sensitive setting if the new value is empty', async () => {
+      mockRequestSetting.mockResolvedValue('');
+
+      await updateSetting(
+        config,
+        '12345',
+        'VAR1',
+        mockRequestSetting,
+        ExtensionSettingScope.USER,
+        tempWorkspaceDir,
+      );
+
+      const expectedEnvPath = path.join(extensionDir, '.env');
+      const actualContent = await fsPromises.readFile(expectedEnvPath, 'utf-8');
+      expect(actualContent).not.toContain('VAR1=');
+    });
+
     it('should not throw if deleting a non-existent sensitive setting with empty value', async () => {
       mockRequestSetting.mockResolvedValue('');
       // Ensure it doesn't exist first

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

@@ -251,7 +251,11 @@ export async function updateSetting(
   }
 
   const parsedEnv = dotenv.parse(envContent);
-  parsedEnv[settingToUpdate.envVar] = newValue;
+  if (!newValue) {
+    delete parsedEnv[settingToUpdate.envVar];
+  } else {
+    parsedEnv[settingToUpdate.envVar] = newValue;
+  }
 
   // We only want to write back the variables that are not sensitive.
   const nonSensitiveSettings: Record<string, string> = {};

packages/cli/src/config/keyBindings.ts

@@ -72,6 +72,15 @@ export enum Command {
   OPEN_EXTERNAL_EDITOR = 'input.openExternalEditor',
   PASTE_CLIPBOARD = 'input.paste',
 
+  BACKGROUND_SHELL_ESCAPE = 'backgroundShellEscape',
+  BACKGROUND_SHELL_SELECT = 'backgroundShellSelect',
+  TOGGLE_BACKGROUND_SHELL = 'toggleBackgroundShell',
+  TOGGLE_BACKGROUND_SHELL_LIST = 'toggleBackgroundShellList',
+  KILL_BACKGROUND_SHELL = 'backgroundShell.kill',
+  UNFOCUS_BACKGROUND_SHELL = 'backgroundShell.unfocus',
+  UNFOCUS_BACKGROUND_SHELL_LIST = 'backgroundShell.listUnfocus',
+  SHOW_BACKGROUND_SHELL_UNFOCUS_WARNING = 'backgroundShell.unfocusWarning',
+
   // App Controls
   SHOW_ERROR_DETAILS = 'app.showErrorDetails',
   SHOW_FULL_TODOS = 'app.showFullTodos',
@@ -139,7 +148,6 @@ export const defaultKeyBindings: KeyBindingConfig = {
   ],
   [Command.MOVE_LEFT]: [
     { key: 'left', shift: false, alt: false, ctrl: false, cmd: false },
-    { key: 'b', ctrl: true },
   ],
   [Command.MOVE_RIGHT]: [
     { key: 'right', shift: false, alt: false, ctrl: false, cmd: false },
@@ -265,6 +273,16 @@ export const defaultKeyBindings: KeyBindingConfig = {
   [Command.TOGGLE_COPY_MODE]: [{ key: 's', ctrl: true }],
   [Command.TOGGLE_YOLO]: [{ key: 'y', ctrl: true }],
   [Command.CYCLE_APPROVAL_MODE]: [{ key: 'tab', shift: true }],
+  [Command.TOGGLE_BACKGROUND_SHELL]: [{ key: 'b', ctrl: true }],
+  [Command.TOGGLE_BACKGROUND_SHELL_LIST]: [{ key: 'l', ctrl: true }],
+  [Command.KILL_BACKGROUND_SHELL]: [{ key: 'k', ctrl: true }],
+  [Command.UNFOCUS_BACKGROUND_SHELL]: [{ key: 'tab', shift: true }],
+  [Command.UNFOCUS_BACKGROUND_SHELL_LIST]: [{ key: 'tab', shift: false }],
+  [Command.SHOW_BACKGROUND_SHELL_UNFOCUS_WARNING]: [
+    { key: 'tab', shift: false },
+  ],
+  [Command.BACKGROUND_SHELL_SELECT]: [{ key: 'return' }],
+  [Command.BACKGROUND_SHELL_ESCAPE]: [{ key: 'escape' }],
   [Command.SHOW_MORE_LINES]: [
     { key: 'o', ctrl: true },
     { key: 's', ctrl: true },
@@ -379,6 +397,14 @@ export const commandCategories: readonly CommandCategory[] = [
       Command.TOGGLE_YOLO,
       Command.CYCLE_APPROVAL_MODE,
       Command.SHOW_MORE_LINES,
+      Command.TOGGLE_BACKGROUND_SHELL,
+      Command.TOGGLE_BACKGROUND_SHELL_LIST,
+      Command.KILL_BACKGROUND_SHELL,
+      Command.BACKGROUND_SHELL_SELECT,
+      Command.BACKGROUND_SHELL_ESCAPE,
+      Command.UNFOCUS_BACKGROUND_SHELL,
+      Command.UNFOCUS_BACKGROUND_SHELL_LIST,
+      Command.SHOW_BACKGROUND_SHELL_UNFOCUS_WARNING,
       Command.FOCUS_SHELL_INPUT,
       Command.UNFOCUS_SHELL_INPUT,
       Command.CLEAR_SCREEN,
@@ -470,6 +496,14 @@ export const commandDescriptions: Readonly<Record<Command, string>> = {
     '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.BACKGROUND_SHELL_SELECT]: 'Enter',
+  [Command.BACKGROUND_SHELL_ESCAPE]: 'Esc',
+  [Command.TOGGLE_BACKGROUND_SHELL]: 'Ctrl+B',
+  [Command.TOGGLE_BACKGROUND_SHELL_LIST]: 'Ctrl+L',
+  [Command.KILL_BACKGROUND_SHELL]: 'Ctrl+K',
+  [Command.UNFOCUS_BACKGROUND_SHELL]: 'Shift+Tab',
+  [Command.UNFOCUS_BACKGROUND_SHELL_LIST]: 'Tab',
+  [Command.SHOW_BACKGROUND_SHELL_UNFOCUS_WARNING]: 'Tab',
   [Command.FOCUS_SHELL_INPUT]: 'Focus the shell input from the gemini input.',
   [Command.UNFOCUS_SHELL_INPUT]: 'Focus the Gemini input from the shell input.',
   [Command.CLEAR_SCREEN]: 'Clear the terminal screen and redraw the UI.',

packages/cli/src/config/policy-engine.integration.test.ts

@@ -164,7 +164,6 @@ describe('Policy Engine Integration Tests', () => {
     it('should handle complex mixed configurations', async () => {
       const settings: Settings = {
         tools: {
-          autoAccept: true, // Allows read-only tools
           allowed: ['custom-tool', 'my-server__special-tool'],
           exclude: ['glob', 'dangerous-tool'],
         },
@@ -438,7 +437,6 @@ describe('Policy Engine Integration Tests', () => {
     it('should verify priority ordering works correctly in practice', async () => {
       const settings: Settings = {
         tools: {
-          autoAccept: true, // Priority 50
           allowed: ['specific-tool'], // Priority 100
           exclude: ['blocked-tool'], // Priority 200
         },
@@ -614,7 +612,6 @@ describe('Policy Engine Integration Tests', () => {
     it('should verify rules are created with correct priorities', async () => {
       const settings: Settings = {
         tools: {
-          autoAccept: true,
           allowed: ['tool1', 'tool2'],
           exclude: ['tool3'],
         },

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

@@ -124,7 +124,6 @@ describe('settings-validation', () => {
         },
         tools: {
           sandbox: 'inherit',
-          autoAccept: false,
         },
       };
 

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

@@ -29,10 +29,11 @@ vi.mock('./settings.js', async (importActual) => {
 });
 
 // Mock trustedFolders
+import * as trustedFolders from './trustedFolders.js';
 vi.mock('./trustedFolders.js', () => ({
-  isWorkspaceTrusted: vi
-    .fn()
-    .mockReturnValue({ isTrusted: true, source: 'file' }),
+  isWorkspaceTrusted: vi.fn(),
+  isFolderTrustEnabled: vi.fn(),
+  loadTrustedFolders: vi.fn(),
 }));
 
 vi.mock('./settingsSchema.js', async (importOriginal) => {
@@ -66,13 +67,14 @@ import {
   getSystemSettingsPath,
   getSystemDefaultsPath,
   type Settings,
-  saveSettings,
   type SettingsFile,
+  saveSettings,
   getDefaultsFromSchema,
   loadEnvironment,
   migrateDeprecatedSettings,
   SettingScope,
   LoadedSettings,
+  sanitizeEnvVar,
 } from './settings.js';
 import { FatalConfigError, GEMINI_DIR } from '@google/gemini-cli-core';
 import { updateSettingsFilePreservingFormat } from '../utils/commentJson.js';
@@ -81,6 +83,7 @@ import {
   MergeStrategy,
   type SettingsSchema,
 } from './settingsSchema.js';
+import { createMockSettings } from '../test-utils/settings.js';
 
 const MOCK_WORKSPACE_DIR = '/mock/workspace';
 // Use the (mocked) GEMINI_DIR for consistency
@@ -104,7 +107,7 @@ vi.mock('fs', async (importOriginal) => {
     readFileSync: vi.fn(),
     writeFileSync: vi.fn(),
     mkdirSync: vi.fn(),
-    realpathSync: (p: string) => p,
+    realpathSync: vi.fn((p: string) => p),
   };
 });
 
@@ -118,9 +121,11 @@ const mockCoreEvents = vi.hoisted(() => ({
 vi.mock('@google/gemini-cli-core', async (importOriginal) => {
   const actual =
     await importOriginal<typeof import('@google/gemini-cli-core')>();
+  const os = await import('node:os');
   return {
     ...actual,
     coreEvents: mockCoreEvents,
+    homedir: vi.fn(() => os.homedir()),
   };
 });
 
@@ -151,7 +156,7 @@ describe('Settings Loading and Merging', () => {
     (mockFsExistsSync as Mock).mockReturnValue(false);
     (fs.readFileSync as Mock).mockReturnValue('{}'); // Return valid empty JSON
     (mockFsMkdirSync as Mock).mockImplementation(() => undefined);
-    vi.mocked(isWorkspaceTrusted).mockReturnValue({
+    vi.spyOn(trustedFolders, 'isWorkspaceTrusted').mockReturnValue({
       isTrusted: true,
       source: 'file',
     });
@@ -1459,6 +1464,44 @@ describe('Settings Loading and Merging', () => {
         });
       });
     });
+
+    it('should correctly skip workspace-level loading if workspaceDir is a symlink to home', () => {
+      const mockHomeDir = '/mock/home/user';
+      const mockSymlinkDir = '/mock/symlink/to/home';
+      const mockWorkspaceSettingsPath = path.join(
+        mockSymlinkDir,
+        GEMINI_DIR,
+        'settings.json',
+      );
+
+      vi.mocked(osActual.homedir).mockReturnValue(mockHomeDir);
+      vi.mocked(fs.realpathSync).mockImplementation((p: fs.PathLike) => {
+        const pStr = p.toString();
+        const resolved = path.resolve(pStr);
+        if (
+          resolved === path.resolve(mockSymlinkDir) ||
+          resolved === path.resolve(mockHomeDir)
+        ) {
+          return mockHomeDir;
+        }
+        return pStr;
+      });
+
+      (mockFsExistsSync as Mock).mockImplementation(
+        (p: string) =>
+          // Only return true for workspace settings path to see if it gets loaded
+          p === mockWorkspaceSettingsPath,
+      );
+
+      const settings = loadSettings(mockSymlinkDir);
+
+      // Verify that even though the file exists, it was NOT loaded because realpath matched home
+      expect(fs.readFileSync).not.toHaveBeenCalledWith(
+        mockWorkspaceSettingsPath,
+        'utf-8',
+      );
+      expect(settings.workspace.settings).toEqual({});
+    });
   });
 
   describe('excludedProjectEnvVars integration', () => {
@@ -1635,7 +1678,7 @@ describe('Settings Loading and Merging', () => {
     });
 
     it('should NOT merge workspace settings when workspace is not trusted', () => {
-      vi.mocked(isWorkspaceTrusted).mockReturnValue({
+      vi.spyOn(trustedFolders, 'isWorkspaceTrusted').mockReturnValue({
         isTrusted: false,
         source: 'file',
       });
@@ -1666,23 +1709,61 @@ describe('Settings Loading and Merging', () => {
       expect(settings.merged.context?.fileName).toBe('USER.md'); // User setting
       expect(settings.merged.ui?.theme).toBe('dark'); // User setting
     });
+
+    it('should NOT merge workspace settings when workspace trust is undefined', () => {
+      vi.spyOn(trustedFolders, 'isWorkspaceTrusted').mockReturnValue({
+        isTrusted: undefined,
+        source: undefined,
+      });
+      (mockFsExistsSync as Mock).mockReturnValue(true);
+      const userSettingsContent = {
+        ui: { theme: 'dark' },
+        tools: { sandbox: false },
+        context: { fileName: 'USER.md' },
+      };
+      const workspaceSettingsContent = {
+        tools: { sandbox: true },
+        context: { fileName: 'WORKSPACE.md' },
+      };
+
+      (fs.readFileSync as Mock).mockImplementation(
+        (p: fs.PathOrFileDescriptor) => {
+          if (p === USER_SETTINGS_PATH)
+            return JSON.stringify(userSettingsContent);
+          if (p === MOCK_WORKSPACE_SETTINGS_PATH)
+            return JSON.stringify(workspaceSettingsContent);
+          return '{}';
+        },
+      );
+
+      const settings = loadSettings(MOCK_WORKSPACE_DIR);
+
+      expect(settings.merged.tools?.sandbox).toBe(false); // User setting
+      expect(settings.merged.context?.fileName).toBe('USER.md'); // User setting
+    });
   });
 
   describe('loadEnvironment', () => {
     function setup({
       isFolderTrustEnabled = true,
-      isWorkspaceTrustedValue = true,
+      isWorkspaceTrustedValue = true as boolean | undefined,
     }) {
+      delete process.env['GEMINI_API_KEY']; // reset
       delete process.env['TESTTEST']; // reset
-      const geminiEnvPath = path.resolve(path.join(GEMINI_DIR, '.env'));
+      const geminiEnvPath = path.resolve(
+        path.join(MOCK_WORKSPACE_DIR, GEMINI_DIR, '.env'),
+      );
 
-      vi.mocked(isWorkspaceTrusted).mockReturnValue({
+      vi.spyOn(trustedFolders, 'isWorkspaceTrusted').mockReturnValue({
         isTrusted: isWorkspaceTrustedValue,
         source: 'file',
       });
-      (mockFsExistsSync as Mock).mockImplementation((p: fs.PathLike) =>
-        [USER_SETTINGS_PATH, geminiEnvPath].includes(p.toString()),
-      );
+      (mockFsExistsSync as Mock).mockImplementation((p: fs.PathLike) => {
+        const normalizedP = path.resolve(p.toString());
+        return [path.resolve(USER_SETTINGS_PATH), geminiEnvPath].includes(
+          normalizedP,
+        );
+      });
       const userSettingsContent: Settings = {
         ui: {
           theme: 'dark',
@@ -1698,9 +1779,11 @@ describe('Settings Loading and Merging', () => {
       };
       (fs.readFileSync as Mock).mockImplementation(
         (p: fs.PathOrFileDescriptor) => {
-          if (p === USER_SETTINGS_PATH)
+          const normalizedP = path.resolve(p.toString());
+          if (normalizedP === path.resolve(USER_SETTINGS_PATH))
             return JSON.stringify(userSettingsContent);
-          if (p === geminiEnvPath) return 'TESTTEST=1234';
+          if (normalizedP === geminiEnvPath)
+            return 'TESTTEST=1234\nGEMINI_API_KEY=test-key';
           return '{}';
         },
       );
@@ -1708,17 +1791,68 @@ describe('Settings Loading and Merging', () => {
 
     it('sets environment variables from .env files', () => {
       setup({ isFolderTrustEnabled: false, isWorkspaceTrustedValue: true });
-      loadEnvironment(loadSettings(MOCK_WORKSPACE_DIR).merged);
+      const settings = {
+        security: { folderTrust: { enabled: false } },
+      } as Settings;
+      loadEnvironment(settings, MOCK_WORKSPACE_DIR, isWorkspaceTrusted);
 
       expect(process.env['TESTTEST']).toEqual('1234');
+      expect(process.env['GEMINI_API_KEY']).toEqual('test-key');
     });
 
     it('does not load env files from untrusted spaces', () => {
       setup({ isFolderTrustEnabled: true, isWorkspaceTrustedValue: false });
-      loadEnvironment(loadSettings(MOCK_WORKSPACE_DIR).merged);
+      const settings = {
+        security: { folderTrust: { enabled: true } },
+      } as Settings;
+      loadEnvironment(settings, MOCK_WORKSPACE_DIR, isWorkspaceTrusted);
 
       expect(process.env['TESTTEST']).not.toEqual('1234');
     });
+
+    it('does not load env files when trust is undefined', () => {
+      delete process.env['TESTTEST'];
+      // isWorkspaceTrusted returns {isTrusted: undefined} for matched rules with no trust value, or no matching rules.
+      setup({ isFolderTrustEnabled: true, isWorkspaceTrustedValue: undefined });
+      const settings = {
+        security: { folderTrust: { enabled: true } },
+      } as Settings;
+
+      const mockTrustFn = vi.fn().mockReturnValue({ isTrusted: undefined });
+      loadEnvironment(settings, MOCK_WORKSPACE_DIR, mockTrustFn);
+
+      expect(process.env['TESTTEST']).not.toEqual('1234');
+      expect(process.env['GEMINI_API_KEY']).not.toEqual('test-key');
+    });
+
+    it('loads whitelisted env files from untrusted spaces if sandboxing is enabled', () => {
+      setup({ isFolderTrustEnabled: true, isWorkspaceTrustedValue: false });
+      const settings = loadSettings(MOCK_WORKSPACE_DIR);
+      settings.merged.tools.sandbox = true;
+      loadEnvironment(settings.merged, MOCK_WORKSPACE_DIR);
+
+      // GEMINI_API_KEY is in the whitelist, so it should be loaded.
+      expect(process.env['GEMINI_API_KEY']).toEqual('test-key');
+      // TESTTEST is NOT in the whitelist, so it should be blocked.
+      expect(process.env['TESTTEST']).not.toEqual('1234');
+    });
+
+    it('loads whitelisted env files from untrusted spaces if sandboxing is enabled via CLI flag', () => {
+      const originalArgv = [...process.argv];
+      process.argv.push('-s');
+      try {
+        setup({ isFolderTrustEnabled: true, isWorkspaceTrustedValue: false });
+        const settings = loadSettings(MOCK_WORKSPACE_DIR);
+        // Ensure sandbox is NOT in settings to test argv sniffing
+        settings.merged.tools.sandbox = undefined;
+        loadEnvironment(settings.merged, MOCK_WORKSPACE_DIR);
+
+        expect(process.env['GEMINI_API_KEY']).toEqual('test-key');
+        expect(process.env['TESTTEST']).not.toEqual('1234');
+      } finally {
+        process.argv = originalArgv;
+      }
+    });
   });
 
   describe('migrateDeprecatedSettings', () => {
@@ -1731,7 +1865,7 @@ describe('Settings Loading and Merging', () => {
       mockFsExistsSync.mockReturnValue(true);
       mockFsReadFileSync = vi.mocked(fs.readFileSync);
       mockFsReadFileSync.mockReturnValue('{}');
-      vi.mocked(isWorkspaceTrusted).mockReturnValue({
+      vi.spyOn(trustedFolders, 'isWorkspaceTrusted').mockReturnValue({
         isTrusted: true,
         source: undefined,
       });
@@ -1876,29 +2010,7 @@ describe('Settings Loading and Merging', () => {
         },
       };
 
-      const loadedSettings = new LoadedSettings(
-        {
-          path: getSystemSettingsPath(),
-          settings: {},
-          originalSettings: {},
-        },
-        {
-          path: getSystemDefaultsPath(),
-          settings: {},
-          originalSettings: {},
-        },
-        {
-          path: USER_SETTINGS_PATH,
-          settings: userSettingsContent as unknown as Settings,
-          originalSettings: userSettingsContent as unknown as Settings,
-        },
-        {
-          path: MOCK_WORKSPACE_SETTINGS_PATH,
-          settings: {},
-          originalSettings: {},
-        },
-        true,
-      );
+      const loadedSettings = createMockSettings(userSettingsContent);
 
       const setValueSpy = vi.spyOn(loadedSettings, 'setValue');
 
@@ -2067,11 +2179,8 @@ describe('Settings Loading and Merging', () => {
   describe('saveSettings', () => {
     it('should save settings using updateSettingsFilePreservingFormat', () => {
       const mockUpdateSettings = vi.mocked(updateSettingsFilePreservingFormat);
-      const settingsFile = {
-        path: '/mock/settings.json',
-        settings: { ui: { theme: 'dark' } },
-        originalSettings: { ui: { theme: 'dark' } },
-      } as unknown as SettingsFile;
+      const settingsFile = createMockSettings({ ui: { theme: 'dark' } }).user;
+      settingsFile.path = '/mock/settings.json';
 
       saveSettings(settingsFile);
 
@@ -2085,11 +2194,8 @@ describe('Settings Loading and Merging', () => {
       const mockFsMkdirSync = vi.mocked(fs.mkdirSync);
       mockFsExistsSync.mockReturnValue(false);
 
-      const settingsFile = {
-        path: '/mock/new/dir/settings.json',
-        settings: {},
-        originalSettings: {},
-      } as unknown as SettingsFile;
+      const settingsFile = createMockSettings({}).user;
+      settingsFile.path = '/mock/new/dir/settings.json';
 
       saveSettings(settingsFile);
 
@@ -2106,11 +2212,8 @@ describe('Settings Loading and Merging', () => {
         throw error;
       });
 
-      const settingsFile = {
-        path: '/mock/settings.json',
-        settings: {},
-        originalSettings: {},
-      } as unknown as SettingsFile;
+      const settingsFile = createMockSettings({}).user;
+      settingsFile.path = '/mock/settings.json';
 
       saveSettings(settingsFile);
 
@@ -2157,8 +2260,11 @@ describe('Settings Loading and Merging', () => {
       // 2. Now, set remote admin settings.
       loadedSettings.setRemoteAdminSettings({
         strictModeDisabled: false,
-        mcpSetting: { mcpEnabled: false },
-        cliFeatureSetting: { extensionsSetting: { extensionsEnabled: false } },
+        mcpSetting: { mcpEnabled: false, mcpConfig: {} },
+        cliFeatureSetting: {
+          extensionsSetting: { extensionsEnabled: false },
+          unmanagedCapabilitiesEnabled: false,
+        },
       });
 
       // 3. Verify that remote admin settings take precedence.
@@ -2198,8 +2304,11 @@ describe('Settings Loading and Merging', () => {
 
       const newRemoteSettings = {
         strictModeDisabled: false,
-        mcpSetting: { mcpEnabled: false },
-        cliFeatureSetting: { extensionsSetting: { extensionsEnabled: false } },
+        mcpSetting: { mcpEnabled: false, mcpConfig: {} },
+        cliFeatureSetting: {
+          extensionsSetting: { extensionsEnabled: false },
+          unmanagedCapabilitiesEnabled: false,
+        },
       };
 
       loadedSettings.setRemoteAdminSettings(newRemoteSettings);
@@ -2210,13 +2319,6 @@ describe('Settings Loading and Merging', () => {
       expect(loadedSettings.merged.admin?.extensions?.enabled).toBe(false);
       // Non-admin settings should remain untouched
       expect(loadedSettings.merged.ui?.theme).toBe('initial-theme');
-
-      // Verify that calling setRemoteAdminSettings with partial data overwrites previous remote settings
-      // and missing properties revert to schema defaults.
-      loadedSettings.setRemoteAdminSettings({ strictModeDisabled: true });
-      expect(loadedSettings.merged.admin?.secureModeEnabled).toBe(false);
-      expect(loadedSettings.merged.admin?.mcp?.enabled).toBe(false); // Defaulting to false if missing
-      expect(loadedSettings.merged.admin?.extensions?.enabled).toBe(false); // Defaulting to false if missing
     });
 
     it('should correctly handle undefined remote admin settings', () => {
@@ -2248,84 +2350,6 @@ describe('Settings Loading and Merging', () => {
       expect(loadedSettings.merged.admin?.extensions?.enabled).toBe(true);
     });
 
-    it('should correctly handle missing properties in remote admin settings', () => {
-      (mockFsExistsSync as Mock).mockReturnValue(true);
-      const systemSettingsContent = {
-        admin: {
-          secureModeEnabled: true,
-        },
-      };
-
-      (fs.readFileSync as Mock).mockImplementation(
-        (p: fs.PathOrFileDescriptor) => {
-          if (p === getSystemSettingsPath()) {
-            return JSON.stringify(systemSettingsContent);
-          }
-          return '{}';
-        },
-      );
-
-      const loadedSettings = loadSettings(MOCK_WORKSPACE_DIR);
-      // Ensure initial state from defaults (as file-based admin settings are ignored)
-      expect(loadedSettings.merged.admin?.secureModeEnabled).toBe(false);
-      expect(loadedSettings.merged.admin?.mcp?.enabled).toBe(true);
-      expect(loadedSettings.merged.admin?.extensions?.enabled).toBe(true);
-
-      // Set remote settings with only strictModeDisabled (false -> secureModeEnabled: true)
-      loadedSettings.setRemoteAdminSettings({
-        strictModeDisabled: false,
-      });
-
-      // Verify secureModeEnabled is updated, others default to false
-      expect(loadedSettings.merged.admin?.secureModeEnabled).toBe(true);
-      expect(loadedSettings.merged.admin?.mcp?.enabled).toBe(false);
-      expect(loadedSettings.merged.admin?.extensions?.enabled).toBe(false);
-
-      // Set remote settings with only mcpSetting.mcpEnabled
-      loadedSettings.setRemoteAdminSettings({
-        mcpSetting: { mcpEnabled: false },
-      });
-
-      // Verify mcpEnabled is updated, others remain defaults (secureModeEnabled defaults to true if strictModeDisabled is missing)
-      expect(loadedSettings.merged.admin?.secureModeEnabled).toBe(true);
-      expect(loadedSettings.merged.admin?.mcp?.enabled).toBe(false);
-      expect(loadedSettings.merged.admin?.extensions?.enabled).toBe(false);
-
-      // Set remote settings with only cliFeatureSetting.extensionsSetting.extensionsEnabled
-      loadedSettings.setRemoteAdminSettings({
-        cliFeatureSetting: { extensionsSetting: { extensionsEnabled: false } },
-      });
-
-      // Verify extensionsEnabled is updated, others remain defaults
-      expect(loadedSettings.merged.admin?.secureModeEnabled).toBe(true);
-      expect(loadedSettings.merged.admin?.mcp?.enabled).toBe(false);
-      expect(loadedSettings.merged.admin?.extensions?.enabled).toBe(false);
-
-      // Verify that missing strictModeDisabled falls back to secureModeEnabled
-      loadedSettings.setRemoteAdminSettings({
-        secureModeEnabled: false,
-      });
-      expect(loadedSettings.merged.admin?.secureModeEnabled).toBe(false);
-
-      loadedSettings.setRemoteAdminSettings({
-        secureModeEnabled: true,
-      });
-      expect(loadedSettings.merged.admin?.secureModeEnabled).toBe(true);
-
-      // Verify strictModeDisabled takes precedence over secureModeEnabled
-      loadedSettings.setRemoteAdminSettings({
-        strictModeDisabled: false,
-        secureModeEnabled: false,
-      });
-      expect(loadedSettings.merged.admin?.secureModeEnabled).toBe(true);
-
-      loadedSettings.setRemoteAdminSettings({
-        strictModeDisabled: true,
-        secureModeEnabled: true,
-      });
-      expect(loadedSettings.merged.admin?.secureModeEnabled).toBe(false);
-    });
-
     it('should set skills based on unmanagedCapabilitiesEnabled', () => {
       const loadedSettings = loadSettings();
       loadedSettings.setRemoteAdminSettings({
@@ -2343,51 +2367,6 @@ describe('Settings Loading and Merging', () => {
       expect(loadedSettings.merged.admin.skills?.enabled).toBe(false);
     });
 
-    it('should default mcp.enabled to false if mcpSetting is present but mcpEnabled is undefined', () => {
-      const loadedSettings = loadSettings(MOCK_WORKSPACE_DIR);
-      loadedSettings.setRemoteAdminSettings({
-        mcpSetting: {},
-      });
-      expect(loadedSettings.merged.admin?.mcp?.enabled).toBe(false);
-    });
-
-    it('should default extensions.enabled to false if extensionsSetting is present but extensionsEnabled is undefined', () => {
-      const loadedSettings = loadSettings(MOCK_WORKSPACE_DIR);
-      loadedSettings.setRemoteAdminSettings({
-        cliFeatureSetting: {
-          extensionsSetting: {},
-        },
-      });
-      expect(loadedSettings.merged.admin?.extensions?.enabled).toBe(false);
-    });
-
-    it('should force secureModeEnabled to true if undefined, overriding schema defaults', () => {
-      // Mock schema to have secureModeEnabled default to false to verify the override
-      const originalSchema = getSettingsSchema();
-      const modifiedSchema = JSON.parse(JSON.stringify(originalSchema));
-      if (modifiedSchema.admin?.properties?.secureModeEnabled) {
-        modifiedSchema.admin.properties.secureModeEnabled.default = false;
-      }
-      vi.mocked(getSettingsSchema).mockReturnValue(modifiedSchema);
-
-      try {
-        (mockFsExistsSync as Mock).mockReturnValue(true);
-        (fs.readFileSync as Mock).mockImplementation(() => '{}');
-
-        const loadedSettings = loadSettings(MOCK_WORKSPACE_DIR);
-
-        // Pass a non-empty object that doesn't have strictModeDisabled
-        loadedSettings.setRemoteAdminSettings({
-          mcpSetting: {},
-        });
-
-        // It should be forced to true by the logic (default secure), overriding the mock default of false
-        expect(loadedSettings.merged.admin?.secureModeEnabled).toBe(true);
-      } finally {
-        vi.mocked(getSettingsSchema).mockReturnValue(originalSchema);
-      }
-    });
-
     it('should handle completely empty remote admin settings response', () => {
       const loadedSettings = loadSettings(MOCK_WORKSPACE_DIR);
 
@@ -2437,4 +2416,391 @@ describe('Settings Loading and Merging', () => {
       });
     });
   });
+
+  describe('Security and Sandbox', () => {
+    let originalArgv: string[];
+    let originalEnv: NodeJS.ProcessEnv;
+
+    beforeEach(() => {
+      originalArgv = [...process.argv];
+      originalEnv = { ...process.env };
+      // Clear relevant env vars
+      delete process.env['GEMINI_API_KEY'];
+      delete process.env['GOOGLE_API_KEY'];
+      delete process.env['GOOGLE_CLOUD_PROJECT'];
+      delete process.env['GOOGLE_CLOUD_LOCATION'];
+      delete process.env['CLOUD_SHELL'];
+      delete process.env['MALICIOUS_VAR'];
+      delete process.env['FOO'];
+      vi.resetAllMocks();
+      vi.mocked(fs.existsSync).mockReturnValue(false);
+    });
+
+    afterEach(() => {
+      process.argv = originalArgv;
+      process.env = originalEnv;
+    });
+
+    describe('sandbox detection', () => {
+      it('should detect sandbox when -s is a real flag', () => {
+        process.argv = ['node', 'gemini', '-s', 'some prompt'];
+        vi.mocked(isWorkspaceTrusted).mockReturnValue({
+          isTrusted: false,
+          source: 'file',
+        });
+        vi.mocked(fs.existsSync).mockReturnValue(true);
+        vi.mocked(fs.readFileSync).mockReturnValue(
+          'FOO=bar\nGEMINI_API_KEY=secret',
+        );
+
+        loadEnvironment(
+          createMockSettings({ tools: { sandbox: false } }).merged,
+          MOCK_WORKSPACE_DIR,
+        );
+
+        // If sandboxed and untrusted, FOO should NOT be loaded, but GEMINI_API_KEY should be.
+        expect(process.env['FOO']).toBeUndefined();
+        expect(process.env['GEMINI_API_KEY']).toBe('secret');
+      });
+
+      it('should detect sandbox when --sandbox is a real flag', () => {
+        process.argv = ['node', 'gemini', '--sandbox', 'prompt'];
+        vi.mocked(isWorkspaceTrusted).mockReturnValue({
+          isTrusted: false,
+          source: 'file',
+        });
+        vi.mocked(fs.existsSync).mockReturnValue(true);
+        vi.mocked(fs.readFileSync).mockReturnValue('GEMINI_API_KEY=secret');
+
+        loadEnvironment(
+          createMockSettings({ tools: { sandbox: false } }).merged,
+          MOCK_WORKSPACE_DIR,
+        );
+
+        expect(process.env['GEMINI_API_KEY']).toBe('secret');
+      });
+
+      it('should ignore sandbox flags if they appear after --', () => {
+        process.argv = ['node', 'gemini', '--', '-s', 'some prompt'];
+        vi.mocked(isWorkspaceTrusted).mockReturnValue({
+          isTrusted: false,
+          source: 'file',
+        });
+        vi.mocked(fs.existsSync).mockImplementation((path) =>
+          path.toString().endsWith('.env'),
+        );
+        vi.mocked(fs.readFileSync).mockReturnValue('GEMINI_API_KEY=secret');
+
+        loadEnvironment(
+          createMockSettings({ tools: { sandbox: false } }).merged,
+          MOCK_WORKSPACE_DIR,
+        );
+
+        expect(process.env['GEMINI_API_KEY']).toBeUndefined();
+      });
+
+      it('should NOT be tricked by positional arguments that look like flags', () => {
+        process.argv = ['node', 'gemini', 'my -s prompt'];
+        vi.mocked(isWorkspaceTrusted).mockReturnValue({
+          isTrusted: false,
+          source: 'file',
+        });
+        vi.mocked(fs.existsSync).mockImplementation((path) =>
+          path.toString().endsWith('.env'),
+        );
+        vi.mocked(fs.readFileSync).mockReturnValue('GEMINI_API_KEY=secret');
+
+        loadEnvironment(
+          createMockSettings({ tools: { sandbox: false } }).merged,
+          MOCK_WORKSPACE_DIR,
+        );
+
+        expect(process.env['GEMINI_API_KEY']).toBeUndefined();
+      });
+    });
+
+    describe('env var sanitization', () => {
+      it('should strictly enforce whitelist in untrusted/sandboxed mode', () => {
+        process.argv = ['node', 'gemini', '-s', 'prompt'];
+        vi.mocked(isWorkspaceTrusted).mockReturnValue({
+          isTrusted: false,
+          source: 'file',
+        });
+        vi.mocked(fs.existsSync).mockImplementation((path) =>
+          path.toString().endsWith('.env'),
+        );
+        vi.mocked(fs.readFileSync).mockReturnValue(`
+GEMINI_API_KEY=secret-key
+MALICIOUS_VAR=should-be-ignored
+GOOGLE_API_KEY=another-secret
+    `);
+
+        loadEnvironment(
+          createMockSettings({ tools: { sandbox: false } }).merged,
+          MOCK_WORKSPACE_DIR,
+        );
+
+        expect(process.env['GEMINI_API_KEY']).toBe('secret-key');
+        expect(process.env['GOOGLE_API_KEY']).toBe('another-secret');
+        expect(process.env['MALICIOUS_VAR']).toBeUndefined();
+      });
+
+      it('should sanitize shell injection characters in whitelisted env vars in untrusted mode', () => {
+        process.argv = ['node', 'gemini', '--sandbox', 'prompt'];
+        vi.mocked(isWorkspaceTrusted).mockReturnValue({
+          isTrusted: false,
+          source: 'file',
+        });
+        vi.mocked(fs.existsSync).mockImplementation((path) =>
+          path.toString().endsWith('.env'),
+        );
+
+        const maliciousPayload = 'key-$(whoami)-`id`-&|;><*?[]{}';
+        vi.mocked(fs.readFileSync).mockReturnValue(
+          `GEMINI_API_KEY=${maliciousPayload}`,
+        );
+
+        loadEnvironment(
+          createMockSettings({ tools: { sandbox: false } }).merged,
+          MOCK_WORKSPACE_DIR,
+        );
+
+        // sanitizeEnvVar: value.replace(/[^a-zA-Z0-9\-_./]/g, '')
+        expect(process.env['GEMINI_API_KEY']).toBe('key-whoami-id-');
+      });
+
+      it('should allow . and / in whitelisted env vars but sanitize other characters in untrusted mode', () => {
+        process.argv = ['node', 'gemini', '--sandbox', 'prompt'];
+        vi.mocked(isWorkspaceTrusted).mockReturnValue({
+          isTrusted: false,
+          source: 'file',
+        });
+        vi.mocked(fs.existsSync).mockImplementation((path) =>
+          path.toString().endsWith('.env'),
+        );
+
+        const complexPayload = 'secret-123/path.to/somewhere;rm -rf /';
+        vi.mocked(fs.readFileSync).mockReturnValue(
+          `GEMINI_API_KEY=${complexPayload}`,
+        );
+
+        loadEnvironment(
+          createMockSettings({ tools: { sandbox: false } }).merged,
+          MOCK_WORKSPACE_DIR,
+        );
+
+        expect(process.env['GEMINI_API_KEY']).toBe(
+          'secret-123/path.to/somewhererm-rf/',
+        );
+      });
+
+      it('should NOT sanitize variables from trusted sources', () => {
+        process.argv = ['node', 'gemini', 'prompt'];
+        vi.mocked(isWorkspaceTrusted).mockReturnValue({
+          isTrusted: true,
+          source: 'file',
+        });
+        vi.mocked(fs.existsSync).mockReturnValue(true);
+
+        vi.mocked(fs.readFileSync).mockReturnValue('FOO=$(bar)');
+
+        loadEnvironment(
+          createMockSettings({ tools: { sandbox: false } }).merged,
+          MOCK_WORKSPACE_DIR,
+        );
+
+        // Trusted source, no sanitization
+        expect(process.env['FOO']).toBe('$(bar)');
+      });
+
+      it('should load environment variables normally when workspace is TRUSTED even if "sandboxed"', () => {
+        process.argv = ['node', 'gemini', '-s', 'prompt'];
+        vi.mocked(isWorkspaceTrusted).mockReturnValue({
+          isTrusted: true,
+          source: 'file',
+        });
+        vi.mocked(fs.existsSync).mockImplementation((path) =>
+          path.toString().endsWith('.env'),
+        );
+        vi.mocked(fs.readFileSync).mockReturnValue(`
+GEMINI_API_KEY=un-sanitized;key!
+MALICIOUS_VAR=allowed-because-trusted
+    `);
+
+        loadEnvironment(
+          createMockSettings({ tools: { sandbox: false } }).merged,
+          MOCK_WORKSPACE_DIR,
+        );
+
+        expect(process.env['GEMINI_API_KEY']).toBe('un-sanitized;key!');
+        expect(process.env['MALICIOUS_VAR']).toBe('allowed-because-trusted');
+      });
+
+      it('should sanitize value in sanitizeEnvVar helper', () => {
+        expect(sanitizeEnvVar('$(calc)')).toBe('calc');
+        expect(sanitizeEnvVar('`rm -rf /`')).toBe('rm-rf/');
+        expect(sanitizeEnvVar('normal-project-123')).toBe('normal-project-123');
+        expect(sanitizeEnvVar('us-central1')).toBe('us-central1');
+      });
+    });
+
+    describe('Cloud Shell security', () => {
+      it('should handle Cloud Shell special defaults securely when untrusted', () => {
+        process.env['CLOUD_SHELL'] = 'true';
+        process.argv = ['node', 'gemini', '-s', 'prompt'];
+        vi.mocked(isWorkspaceTrusted).mockReturnValue({
+          isTrusted: false,
+          source: 'file',
+        });
+
+        // No .env file
+        vi.mocked(fs.existsSync).mockReturnValue(false);
+
+        loadEnvironment(
+          createMockSettings({ tools: { sandbox: false } }).merged,
+          MOCK_WORKSPACE_DIR,
+        );
+
+        expect(process.env['GOOGLE_CLOUD_PROJECT']).toBe('cloudshell-gca');
+      });
+
+      it('should sanitize GOOGLE_CLOUD_PROJECT in Cloud Shell when loaded from .env in untrusted mode', () => {
+        process.env['CLOUD_SHELL'] = 'true';
+        process.argv = ['node', 'gemini', '-s', 'prompt'];
+        vi.mocked(isWorkspaceTrusted).mockReturnValue({
+          isTrusted: false,
+          source: 'file',
+        });
+        vi.mocked(fs.existsSync).mockReturnValue(true);
+        vi.mocked(fs.readFileSync).mockReturnValue(
+          'GOOGLE_CLOUD_PROJECT=attacker-project;inject',
+        );
+
+        loadEnvironment(
+          createMockSettings({ tools: { sandbox: false } }).merged,
+          MOCK_WORKSPACE_DIR,
+        );
+
+        expect(process.env['GOOGLE_CLOUD_PROJECT']).toBe(
+          'attacker-projectinject',
+        );
+      });
+    });
+  });
+});
+
+describe('LoadedSettings Isolation and Serializability', () => {
+  let loadedSettings: LoadedSettings;
+
+  interface TestData {
+    a: {
+      b: number;
+    };
+  }
+
+  beforeEach(() => {
+    vi.resetAllMocks();
+
+    // Create a minimal LoadedSettings instance
+    const emptyScope = {
+      path: '/mock/settings.json',
+      settings: {},
+      originalSettings: {},
+    } as unknown as SettingsFile;
+
+    loadedSettings = new LoadedSettings(
+      emptyScope, // system
+      emptyScope, // systemDefaults
+      { ...emptyScope }, // user
+      emptyScope, // workspace
+      true, // isTrusted
+    );
+  });
+
+  describe('setValue Isolation', () => {
+    it('should isolate state between settings and originalSettings', () => {
+      const complexValue: TestData = { a: { b: 1 } };
+      loadedSettings.setValue(SettingScope.User, 'test', complexValue);
+
+      const userSettings = loadedSettings.forScope(SettingScope.User);
+      const settingsValue = (userSettings.settings as Record<string, unknown>)[
+        'test'
+      ] as TestData;
+      const originalValue = (
+        userSettings.originalSettings as Record<string, unknown>
+      )['test'] as TestData;
+
+      // Verify they are equal but different references
+      expect(settingsValue).toEqual(complexValue);
+      expect(originalValue).toEqual(complexValue);
+      expect(settingsValue).not.toBe(complexValue);
+      expect(originalValue).not.toBe(complexValue);
+      expect(settingsValue).not.toBe(originalValue);
+
+      // Modify the in-memory setting object
+      settingsValue.a.b = 2;
+
+      // originalSettings should NOT be affected
+      expect(originalValue.a.b).toBe(1);
+    });
+
+    it('should not share references between settings and originalSettings (original servers test)', () => {
+      const mcpServers = {
+        'test-server': { command: 'echo' },
+      };
+
+      loadedSettings.setValue(SettingScope.User, 'mcpServers', mcpServers);
+
+      // Modify the original object
+      delete (mcpServers as Record<string, unknown>)['test-server'];
+
+      // The settings in LoadedSettings should still have the server
+      const userSettings = loadedSettings.forScope(SettingScope.User);
+      expect(
+        (userSettings.settings.mcpServers as Record<string, unknown>)[
+          'test-server'
+        ],
+      ).toBeDefined();
+      expect(
+        (userSettings.originalSettings.mcpServers as Record<string, unknown>)[
+          'test-server'
+        ],
+      ).toBeDefined();
+
+      // They should also be different objects from each other
+      expect(userSettings.settings.mcpServers).not.toBe(
+        userSettings.originalSettings.mcpServers,
+      );
+    });
+  });
+
+  describe('setValue Serializability', () => {
+    it('should preserve Map/Set types (via structuredClone)', () => {
+      const mapValue = { myMap: new Map([['key', 'value']]) };
+      loadedSettings.setValue(SettingScope.User, 'test', mapValue);
+
+      const userSettings = loadedSettings.forScope(SettingScope.User);
+      const settingsValue = (userSettings.settings as Record<string, unknown>)[
+        'test'
+      ] as { myMap: Map<string, string> };
+
+      // Map is preserved by structuredClone
+      expect(settingsValue.myMap).toBeInstanceOf(Map);
+      expect(settingsValue.myMap.get('key')).toBe('value');
+
+      // But it should be a different reference
+      expect(settingsValue.myMap).not.toBe(mapValue.myMap);
+    });
+
+    it('should handle circular references (structuredClone supports them, but deepMerge may not)', () => {
+      const circular: Record<string, unknown> = { a: 1 };
+      circular['self'] = circular;
+
+      // structuredClone(circular) works, but LoadedSettings.setValue calls
+      // computeMergedSettings() -> customDeepMerge() which blows up on circularity.
+      expect(() => {
+        loadedSettings.setValue(SettingScope.User, 'test', circular);
+      }).toThrow(/Maximum call stack size exceeded/);
+    });
+  });
 });

packages/cli/src/config/settings.ts

@@ -16,7 +16,7 @@ import {
   Storage,
   coreEvents,
   homedir,
-  type FetchAdminControlsResponse,
+  type AdminControlsSettings,
 } from '@google/gemini-cli-core';
 import stripJsonComments from 'strip-json-comments';
 import { DefaultLight } from '../ui/themes/default-light.js';
@@ -50,7 +50,9 @@ import {
   formatValidationError,
 } from './settings-validation.js';
 
-function getMergeStrategyForPath(path: string[]): MergeStrategy | undefined {
+export function getMergeStrategyForPath(
+  path: string[],
+): MergeStrategy | undefined {
   let current: SettingDefinition | undefined = undefined;
   let currentSchema: SettingsSchema | undefined = getSettingsSchema();
   let parent: SettingDefinition | undefined = undefined;
@@ -75,6 +77,21 @@ export const USER_SETTINGS_PATH = Storage.getGlobalSettingsPath();
 export const USER_SETTINGS_DIR = path.dirname(USER_SETTINGS_PATH);
 export const DEFAULT_EXCLUDED_ENV_VARS = ['DEBUG', 'DEBUG_MODE'];
 
+const AUTH_ENV_VAR_WHITELIST = [
+  'GEMINI_API_KEY',
+  'GOOGLE_API_KEY',
+  'GOOGLE_CLOUD_PROJECT',
+  'GOOGLE_CLOUD_LOCATION',
+];
+
+/**
+ * Sanitizes an environment variable value to prevent shell injection.
+ * Restricts values to a safe character set: alphanumeric, -, _, ., /
+ */
+export function sanitizeEnvVar(value: string): string {
+  return value.replace(/[^a-zA-Z0-9\-_./]/g, '');
+}
+
 export function getSystemSettingsPath(): string {
   if (process.env['GEMINI_CLI_SYSTEM_SETTINGS_PATH']) {
     return process.env['GEMINI_CLI_SYSTEM_SETTINGS_PATH'];
@@ -275,8 +292,11 @@ export class LoadedSettings {
     this.system = system;
     this.systemDefaults = systemDefaults;
     this.user = user;
-    this.workspace = workspace;
+    this._workspaceFile = workspace;
     this.isTrusted = isTrusted;
+    this.workspace = isTrusted
+      ? workspace
+      : this.createEmptyWorkspace(workspace);
     this.errors = errors;
     this._merged = this.computeMergedSettings();
   }
@@ -284,10 +304,11 @@ export class LoadedSettings {
   readonly system: SettingsFile;
   readonly systemDefaults: SettingsFile;
   readonly user: SettingsFile;
-  readonly workspace: SettingsFile;
-  readonly isTrusted: boolean;
+  workspace: SettingsFile;
+  isTrusted: boolean;
   readonly errors: SettingsError[];
 
+  private _workspaceFile: SettingsFile;
   private _merged: MergedSettings;
   private _remoteAdminSettings: Partial<Settings> | undefined;
 
@@ -295,6 +316,26 @@ export class LoadedSettings {
     return this._merged;
   }
 
+  setTrusted(isTrusted: boolean): void {
+    if (this.isTrusted === isTrusted) {
+      return;
+    }
+    this.isTrusted = isTrusted;
+    this.workspace = isTrusted
+      ? this._workspaceFile
+      : this.createEmptyWorkspace(this._workspaceFile);
+    this._merged = this.computeMergedSettings();
+    coreEvents.emitSettingsChanged();
+  }
+
+  private createEmptyWorkspace(workspace: SettingsFile): SettingsFile {
+    return {
+      ...workspace,
+      settings: {},
+      originalSettings: {},
+    };
+  }
+
   private computeMergedSettings(): MergedSettings {
     const merged = mergeSettings(
       this.system.settings,
@@ -339,21 +380,30 @@ export class LoadedSettings {
 
   setValue(scope: LoadableSettingScope, key: string, value: unknown): void {
     const settingsFile = this.forScope(scope);
-    setNestedProperty(settingsFile.settings, key, value);
-    setNestedProperty(settingsFile.originalSettings, key, value);
+
+    // Clone value to prevent reference sharing between settings and originalSettings
+    const valueToSet =
+      typeof value === 'object' && value !== null
+        ? structuredClone(value)
+        : value;
+
+    setNestedProperty(settingsFile.settings, key, valueToSet);
+    // Use a fresh clone for originalSettings to ensure total independence
+    setNestedProperty(
+      settingsFile.originalSettings,
+      key,
+      structuredClone(valueToSet),
+    );
+
     this._merged = this.computeMergedSettings();
     saveSettings(settingsFile);
     coreEvents.emitSettingsChanged();
   }
 
-  setRemoteAdminSettings(remoteSettings: FetchAdminControlsResponse): void {
+  setRemoteAdminSettings(remoteSettings: AdminControlsSettings): void {
     const admin: Settings['admin'] = {};
-    const {
-      secureModeEnabled,
-      strictModeDisabled,
-      mcpSetting,
-      cliFeatureSetting,
-    } = remoteSettings;
+    const { strictModeDisabled, mcpSetting, cliFeatureSetting } =
+      remoteSettings;
 
     if (Object.keys(remoteSettings).length === 0) {
       this._remoteAdminSettings = { admin };
@@ -361,19 +411,13 @@ export class LoadedSettings {
       return;
     }
 
-    if (strictModeDisabled !== undefined) {
-      admin.secureModeEnabled = !strictModeDisabled;
-    } else if (secureModeEnabled !== undefined) {
-      admin.secureModeEnabled = secureModeEnabled;
-    } else {
-      admin.secureModeEnabled = true;
-    }
-    admin.mcp = { enabled: mcpSetting?.mcpEnabled ?? false };
+    admin.secureModeEnabled = !strictModeDisabled;
+    admin.mcp = { enabled: mcpSetting?.mcpEnabled };
     admin.extensions = {
-      enabled: cliFeatureSetting?.extensionsSetting?.extensionsEnabled ?? false,
+      enabled: cliFeatureSetting?.extensionsSetting?.extensionsEnabled,
     };
     admin.skills = {
-      enabled: cliFeatureSetting?.unmanagedCapabilitiesEnabled ?? false,
+      enabled: cliFeatureSetting?.unmanagedCapabilitiesEnabled,
     };
 
     this._remoteAdminSettings = { admin };
@@ -410,38 +454,63 @@ function findEnvFile(startDir: string): string | null {
   }
 }
 
-export function setUpCloudShellEnvironment(envFilePath: string | null): void {
+export function setUpCloudShellEnvironment(
+  envFilePath: string | null,
+  isTrusted: boolean,
+  isSandboxed: boolean,
+): void {
   // Special handling for GOOGLE_CLOUD_PROJECT in Cloud Shell:
   // Because GOOGLE_CLOUD_PROJECT in Cloud Shell tracks the project
   // set by the user using "gcloud config set project" we do not want to
   // use its value. So, unless the user overrides GOOGLE_CLOUD_PROJECT in
   // one of the .env files, we set the Cloud Shell-specific default here.
+  let value = 'cloudshell-gca';
+
   if (envFilePath && fs.existsSync(envFilePath)) {
     const envFileContent = fs.readFileSync(envFilePath);
     const parsedEnv = dotenv.parse(envFileContent);
     if (parsedEnv['GOOGLE_CLOUD_PROJECT']) {
       // .env file takes precedence in Cloud Shell
-      process.env['GOOGLE_CLOUD_PROJECT'] = parsedEnv['GOOGLE_CLOUD_PROJECT'];
-    } else {
-      // If not in .env, set to default and override global
-      process.env['GOOGLE_CLOUD_PROJECT'] = 'cloudshell-gca';
+      value = parsedEnv['GOOGLE_CLOUD_PROJECT'];
+      if (!isTrusted && isSandboxed) {
+        value = sanitizeEnvVar(value);
+      }
     }
-  } else {
-    // If no .env file, set to default and override global
-    process.env['GOOGLE_CLOUD_PROJECT'] = 'cloudshell-gca';
   }
+  process.env['GOOGLE_CLOUD_PROJECT'] = value;
 }
 
-export function loadEnvironment(settings: Settings): void {
-  const envFilePath = findEnvFile(process.cwd());
+export function loadEnvironment(
+  settings: Settings,
+  workspaceDir: string,
+  isWorkspaceTrustedFn = isWorkspaceTrusted,
+): void {
+  const envFilePath = findEnvFile(workspaceDir);
+  const trustResult = isWorkspaceTrustedFn(settings, workspaceDir);
 
-  if (!isWorkspaceTrusted(settings).isTrusted) {
+  const isTrusted = trustResult.isTrusted ?? false;
+  // Check settings OR check process.argv directly since this might be called
+  // before arguments are fully parsed. This is a best-effort sniffing approach
+  // that happens early in the CLI lifecycle. It is designed to detect the
+  // sandbox flag before the full command-line parser is initialized to ensure
+  // security constraints are applied when loading environment variables.
+  const args = process.argv.slice(2);
+  const doubleDashIndex = args.indexOf('--');
+  const relevantArgs =
+    doubleDashIndex === -1 ? args : args.slice(0, doubleDashIndex);
+
+  const isSandboxed =
+    !!settings.tools?.sandbox ||
+    relevantArgs.includes('-s') ||
+    relevantArgs.includes('--sandbox');
+
+  if (trustResult.isTrusted !== true && !isSandboxed) {
     return;
   }
 
   // Cloud Shell environment variable handling
   if (process.env['CLOUD_SHELL'] === 'true') {
-    setUpCloudShellEnvironment(envFilePath);
+    setUpCloudShellEnvironment(envFilePath, isTrusted, isSandboxed);
   }
 
   if (envFilePath) {
@@ -457,6 +526,16 @@ export function loadEnvironment(settings: Settings): void {
 
       for (const key in parsedEnv) {
         if (Object.hasOwn(parsedEnv, key)) {
+          let value = parsedEnv[key];
+          // If the workspace is untrusted but we are sandboxed, only allow whitelisted variables.
+          if (!isTrusted && isSandboxed) {
+            if (!AUTH_ENV_VAR_WHITELIST.includes(key)) {
+              continue;
+            }
+            // Sanitize the value for untrusted sources
+            value = sanitizeEnvVar(value);
+          }
+
           // If it's a project .env file, skip loading excluded variables.
           if (isProjectEnvFile && excludedVars.includes(key)) {
             continue;
@@ -464,7 +543,7 @@ export function loadEnvironment(settings: Settings): void {
 
           // Load variable only if it's not already set in the environment.
           if (!Object.hasOwn(process.env, key)) {
-            process.env[key] = parsedEnv[key];
+            process.env[key] = value;
           }
         }
       }
@@ -595,12 +674,14 @@ export function loadSettings(
   // For the initial trust check, we can only use user and system settings.
   const initialTrustCheckSettings = customDeepMerge(
     getMergeStrategyForPath,
-    {},
-    systemSettings,
+    getDefaultsFromSchema(),
+    systemDefaultSettings,
     userSettings,
+    systemSettings,
   );
   const isTrusted =
-    isWorkspaceTrusted(initialTrustCheckSettings as Settings).isTrusted ?? true;
+    isWorkspaceTrusted(initialTrustCheckSettings as Settings, workspaceDir)
+      .isTrusted ?? false;
 
   // Create a temporary merged settings object to pass to loadEnvironment.
   const tempMergedSettings = mergeSettings(
@@ -613,7 +694,7 @@ export function loadSettings(
 
   // loadEnvironment depends on settings so we have to create a temp version of
   // the settings to avoid a cycle
-  loadEnvironment(tempMergedSettings);
+  loadEnvironment(tempMergedSettings, workspaceDir);
 
   // Check for any fatal errors before proceeding
   const fatalErrors = settingsErrors.filter((e) => e.severity === 'error');
@@ -674,57 +755,55 @@ export function migrateDeprecatedSettings(
   removeDeprecated = false,
 ): boolean {
   let anyModified = false;
+
+  const migrateBoolean = (
+    settings: Record<string, unknown>,
+    oldKey: string,
+    newKey: string,
+  ): boolean => {
+    let modified = false;
+    const oldValue = settings[oldKey];
+    const newValue = settings[newKey];
+
+    if (typeof oldValue === 'boolean') {
+      if (typeof newValue === 'boolean') {
+        // Both exist, trust the new one
+        if (removeDeprecated) {
+          delete settings[oldKey];
+          modified = true;
+        }
+      } else {
+        // Only old exists, migrate to new (inverted)
+        settings[newKey] = !oldValue;
+        if (removeDeprecated) {
+          delete settings[oldKey];
+        }
+        modified = true;
+      }
+    }
+    return modified;
+  };
+
   const processScope = (scope: LoadableSettingScope) => {
     const settings = loadedSettings.forScope(scope).settings;
 
-    // Migrate inverted boolean settings (disableX -> enableX)
-    // These settings were renamed and their boolean logic inverted
+    // Migrate general settings
     const generalSettings = settings.general as
       | Record<string, unknown>
       | undefined;
-    const uiSettings = settings.ui as Record<string, unknown> | undefined;
-    const contextSettings = settings.context as
-      | Record<string, unknown>
-      | undefined;
-
-    // Migrate general settings (disableAutoUpdate, disableUpdateNag)
     if (generalSettings) {
-      const newGeneral: Record<string, unknown> = { ...generalSettings };
+      const newGeneral = { ...generalSettings };
       let modified = false;
 
-      if (typeof newGeneral['disableAutoUpdate'] === 'boolean') {
-        if (typeof newGeneral['enableAutoUpdate'] === 'boolean') {
-          // Both exist, trust the new one
-          if (removeDeprecated) {
-            delete newGeneral['disableAutoUpdate'];
-            modified = true;
-          }
-        } else {
-          const oldValue = newGeneral['disableAutoUpdate'];
-          newGeneral['enableAutoUpdate'] = !oldValue;
-          if (removeDeprecated) {
-            delete newGeneral['disableAutoUpdate'];
-          }
-          modified = true;
-        }
-      }
-
-      if (typeof newGeneral['disableUpdateNag'] === 'boolean') {
-        if (typeof newGeneral['enableAutoUpdateNotification'] === 'boolean') {
-          // Both exist, trust the new one
-          if (removeDeprecated) {
-            delete newGeneral['disableUpdateNag'];
-            modified = true;
-          }
-        } else {
-          const oldValue = newGeneral['disableUpdateNag'];
-          newGeneral['enableAutoUpdateNotification'] = !oldValue;
-          if (removeDeprecated) {
-            delete newGeneral['disableUpdateNag'];
-          }
-          modified = true;
-        }
-      }
+      modified =
+        migrateBoolean(newGeneral, 'disableAutoUpdate', 'enableAutoUpdate') ||
+        modified;
+      modified =
+        migrateBoolean(
+          newGeneral,
+          'disableUpdateNag',
+          'enableAutoUpdateNotification',
+        ) || modified;
 
       if (modified) {
         loadedSettings.setValue(scope, 'general', newGeneral);
@@ -733,94 +812,63 @@ export function migrateDeprecatedSettings(
     }
 
     // Migrate ui settings
+    const uiSettings = settings.ui as Record<string, unknown> | undefined;
     if (uiSettings) {
-      const newUi: Record<string, unknown> = { ...uiSettings };
-      let modified = false;
-
-      // Migrate ui.accessibility.disableLoadingPhrases -> ui.accessibility.enableLoadingPhrases
+      const newUi = { ...uiSettings };
       const accessibilitySettings = newUi['accessibility'] as
         | Record<string, unknown>
         | undefined;
-      if (
-        accessibilitySettings &&
-        typeof accessibilitySettings['disableLoadingPhrases'] === 'boolean'
-      ) {
-        const newAccessibility: Record<string, unknown> = {
-          ...accessibilitySettings,
-        };
-        if (
-          typeof accessibilitySettings['enableLoadingPhrases'] === 'boolean'
-        ) {
-          // Both exist, trust the new one
-          if (removeDeprecated) {
-            delete newAccessibility['disableLoadingPhrases'];
-            newUi['accessibility'] = newAccessibility;
-            modified = true;
-          }
-        } else {
-          const oldValue = accessibilitySettings['disableLoadingPhrases'];
-          newAccessibility['enableLoadingPhrases'] = !oldValue;
-          if (removeDeprecated) {
-            delete newAccessibility['disableLoadingPhrases'];
-          }
-          newUi['accessibility'] = newAccessibility;
-          modified = true;
-        }
-      }
 
-      if (modified) {
-        loadedSettings.setValue(scope, 'ui', newUi);
-        anyModified = true;
+      if (accessibilitySettings) {
+        const newAccessibility = { ...accessibilitySettings };
+        if (
+          migrateBoolean(
+            newAccessibility,
+            'disableLoadingPhrases',
+            'enableLoadingPhrases',
+          )
+        ) {
+          newUi['accessibility'] = newAccessibility;
+          loadedSettings.setValue(scope, 'ui', newUi);
+          anyModified = true;
+        }
       }
     }
 
     // Migrate context settings
+    const contextSettings = settings.context as
+      | Record<string, unknown>
+      | undefined;
     if (contextSettings) {
-      const newContext: Record<string, unknown> = { ...contextSettings };
-      let modified = false;
-
-      // Migrate context.fileFiltering.disableFuzzySearch -> context.fileFiltering.enableFuzzySearch
+      const newContext = { ...contextSettings };
       const fileFilteringSettings = newContext['fileFiltering'] as
         | Record<string, unknown>
         | undefined;
-      if (
-        fileFilteringSettings &&
-        typeof fileFilteringSettings['disableFuzzySearch'] === 'boolean'
-      ) {
-        const newFileFiltering: Record<string, unknown> = {
-          ...fileFilteringSettings,
-        };
-        if (typeof fileFilteringSettings['enableFuzzySearch'] === 'boolean') {
-          // Both exist, trust the new one
-          if (removeDeprecated) {
-            delete newFileFiltering['disableFuzzySearch'];
-            newContext['fileFiltering'] = newFileFiltering;
-            modified = true;
-          }
-        } else {
-          const oldValue = fileFilteringSettings['disableFuzzySearch'];
-          newFileFiltering['enableFuzzySearch'] = !oldValue;
-          if (removeDeprecated) {
-            delete newFileFiltering['disableFuzzySearch'];
-          }
-          newContext['fileFiltering'] = newFileFiltering;
-          modified = true;
-        }
-      }
 
-      if (modified) {
-        loadedSettings.setValue(scope, 'context', newContext);
-        anyModified = true;
+      if (fileFilteringSettings) {
+        const newFileFiltering = { ...fileFilteringSettings };
+        if (
+          migrateBoolean(
+            newFileFiltering,
+            'disableFuzzySearch',
+            'enableFuzzySearch',
+          )
+        ) {
+          newContext['fileFiltering'] = newFileFiltering;
+          loadedSettings.setValue(scope, 'context', newContext);
+          anyModified = true;
+        }
       }
     }
 
     // Migrate experimental agent settings
-    anyModified ||= migrateExperimentalSettings(
-      settings,
-      loadedSettings,
-      scope,
-      removeDeprecated,
-    );
+    anyModified =
+      migrateExperimentalSettings(
+        settings,
+        loadedSettings,
+        scope,
+        removeDeprecated,
+      ) || anyModified;
   };
 
   processScope(SettingScope.User);

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

@@ -294,7 +294,7 @@ describe('SettingsSchema', () => {
       expect(
         getSettingsSchema().security.properties.folderTrust.properties.enabled
           .default,
-      ).toBe(false);
+      ).toBe(true);
       expect(
         getSettingsSchema().security.properties.folderTrust.properties.enabled
           .showInDialog,

packages/cli/src/config/settingsSchema.ts

@@ -351,6 +351,26 @@ const SETTINGS_SCHEMA = {
           'The color theme for the UI. See the CLI themes guide for available options.',
         showInDialog: false,
       },
+      autoThemeSwitching: {
+        type: 'boolean',
+        label: 'Auto Theme Switching',
+        category: 'UI',
+        requiresRestart: false,
+        default: true,
+        description:
+          'Automatically switch between default light and dark themes based on terminal background color.',
+        showInDialog: true,
+      },
+      terminalBackgroundPollingInterval: {
+        type: 'number',
+        label: 'Terminal Background Polling Interval',
+        category: 'UI',
+        requiresRestart: false,
+        default: 60,
+        description:
+          'Interval in seconds to poll the terminal background color.',
+        showInDialog: true,
+      },
       customThemes: {
         type: 'object',
         label: 'Custom Themes',
@@ -739,6 +759,16 @@ const SETTINGS_SCHEMA = {
           'The fraction of context usage at which to trigger context compression (e.g. 0.2, 0.3).',
         showInDialog: true,
       },
+      disableLoopDetection: {
+        type: 'boolean',
+        label: 'Disable Loop Detection',
+        category: 'Model',
+        requiresRestart: true,
+        default: false,
+        description:
+          'Disable automatic detection and prevention of infinite loops.',
+        showInDialog: true,
+      },
       skipNextSpeakerCheck: {
         type: 'boolean',
         label: 'Skip Next Speaker Check',
@@ -1041,17 +1071,6 @@ const SETTINGS_SCHEMA = {
           },
         },
       },
-      autoAccept: {
-        type: 'boolean',
-        label: 'Auto Accept',
-        category: 'Tools',
-        requiresRestart: false,
-        default: false,
-        description: oneLine`
-          Automatically accept and execute tool calls that are considered safe (e.g., read-only operations).
-        `,
-        showInDialog: true,
-      },
       approvalMode: {
         type: 'enum',
         label: 'Approval Mode',
@@ -1179,16 +1198,6 @@ const SETTINGS_SCHEMA = {
         `,
         showInDialog: true,
       },
-      enableHooks: {
-        type: 'boolean',
-        label: 'Enable Hooks System (Experimental)',
-        category: 'Advanced',
-        requiresRestart: true,
-        default: true,
-        description:
-          'Enables the hooks system experiment. When disabled, the hooks system is completely deactivated regardless of other settings.',
-        showInDialog: false,
-      },
     },
   },
 
@@ -1278,6 +1287,17 @@ const SETTINGS_SCHEMA = {
         description: 'Blocks installing and loading extensions from Git.',
         showInDialog: true,
       },
+      allowedExtensions: {
+        type: 'array',
+        label: 'Extension Source Regex Allowlist',
+        category: 'Security',
+        requiresRestart: true,
+        default: [] as string[],
+        description:
+          'List of Regex patterns for allowed extensions. If nonempty, only extensions that match the patterns in this list are allowed. Overrides the blockGitExtensions setting.',
+        showInDialog: true,
+        items: { type: 'string' },
+      },
       folderTrust: {
         type: 'object',
         label: 'Folder Trust',
@@ -1292,7 +1312,7 @@ const SETTINGS_SCHEMA = {
             label: 'Folder Trust',
             category: 'Security',
             requiresRestart: true,
-            default: false,
+            default: true,
             description: 'Setting to track whether Folder trust is enabled.',
             showInDialog: true,
           },

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

@@ -5,7 +5,11 @@
  */
 
 import * as osActual from 'node:os';
-import { FatalConfigError, ideContextStore } from '@google/gemini-cli-core';
+import {
+  FatalConfigError,
+  ideContextStore,
+  AuthType,
+} from '@google/gemini-cli-core';
 import {
   describe,
   it,
@@ -26,6 +30,9 @@ import {
   isWorkspaceTrusted,
   resetTrustedFoldersForTesting,
 } from './trustedFolders.js';
+import { loadEnvironment, getSettingsSchema } from './settings.js';
+import { createMockSettings } from '../test-utils/settings.js';
+import { validateAuthMethod } from './auth.js';
 import type { Settings } from './settings.js';
 
 vi.mock('os', async (importOriginal) => {
@@ -53,6 +60,7 @@ vi.mock('fs', async (importOriginal) => {
     readFileSync: vi.fn(),
     writeFileSync: vi.fn(),
     mkdirSync: vi.fn(),
+    realpathSync: vi.fn().mockImplementation((p) => p),
   };
 });
 vi.mock('strip-json-comments', () => ({
@@ -60,22 +68,23 @@ vi.mock('strip-json-comments', () => ({
 }));
 
 describe('Trusted Folders Loading', () => {
-  let mockFsExistsSync: Mocked<typeof fs.existsSync>;
   let mockStripJsonComments: Mocked<typeof stripJsonComments>;
   let mockFsWriteFileSync: Mocked<typeof fs.writeFileSync>;
 
   beforeEach(() => {
     resetTrustedFoldersForTesting();
     vi.resetAllMocks();
-    mockFsExistsSync = vi.mocked(fs.existsSync);
     mockStripJsonComments = vi.mocked(stripJsonComments);
     mockFsWriteFileSync = vi.mocked(fs.writeFileSync);
     vi.mocked(osActual.homedir).mockReturnValue('/mock/home/user');
     (mockStripJsonComments as unknown as Mock).mockImplementation(
       (jsonString: string) => jsonString,
     );
-    (mockFsExistsSync as Mock).mockReturnValue(false);
-    (fs.readFileSync as Mock).mockReturnValue('{}');
+    vi.mocked(fs.existsSync).mockReturnValue(false);
+    vi.mocked(fs.readFileSync).mockReturnValue('{}');
+    vi.mocked(fs.realpathSync).mockImplementation((p: fs.PathLike) =>
+      p.toString(),
+    );
   });
 
   afterEach(() => {
@@ -90,13 +99,16 @@ describe('Trusted Folders Loading', () => {
 
   describe('isPathTrusted', () => {
     function setup({ config = {} as Record<string, TrustLevel> } = {}) {
-      (mockFsExistsSync as Mock).mockImplementation(
-        (p) => p === getTrustedFoldersPath(),
+      vi.mocked(fs.existsSync).mockImplementation(
+        (p: fs.PathLike) => p.toString() === getTrustedFoldersPath(),
+      );
+      vi.mocked(fs.readFileSync).mockImplementation(
+        (p: fs.PathOrFileDescriptor) => {
+          if (p.toString() === getTrustedFoldersPath())
+            return JSON.stringify(config);
+          return '{}';
+        },
       );
-      (fs.readFileSync as Mock).mockImplementation((p) => {
-        if (p === getTrustedFoldersPath()) return JSON.stringify(config);
-        return '{}';
-      });
 
       const folders = loadTrustedFolders();
 
@@ -124,26 +136,62 @@ describe('Trusted Folders Loading', () => {
       expect(folders.isPathTrusted('/trustedparent/trustme')).toBe(true);
 
       // No explicit rule covers this file
-      expect(folders.isPathTrusted('/secret/bankaccounts.json')).toBe(
-        undefined,
-      );
-      expect(folders.isPathTrusted('/secret/mine/privatekey.pem')).toBe(
-        undefined,
-      );
+      expect(folders.isPathTrusted('/secret/bankaccounts.json')).toBe(false);
+      expect(folders.isPathTrusted('/secret/mine/privatekey.pem')).toBe(false);
       expect(folders.isPathTrusted('/user/someotherfolder')).toBe(undefined);
     });
+
+    it('prioritizes the longest matching path (precedence)', () => {
+      const { folders } = setup({
+        config: {
+          '/a': TrustLevel.TRUST_FOLDER,
+          '/a/b': TrustLevel.DO_NOT_TRUST,
+          '/a/b/c': TrustLevel.TRUST_FOLDER,
+          '/parent/trustme': TrustLevel.TRUST_PARENT, // effective path is /parent
+          '/parent/trustme/butnotthis': TrustLevel.DO_NOT_TRUST,
+        },
+      });
+
+      // /a/b/c/d matches /a (len 2), /a/b (len 4), /a/b/c (len 6).
+      // /a/b/c wins (TRUST_FOLDER).
+      expect(folders.isPathTrusted('/a/b/c/d')).toBe(true);
+
+      // /a/b/x matches /a (len 2), /a/b (len 4).
+      // /a/b wins (DO_NOT_TRUST).
+      expect(folders.isPathTrusted('/a/b/x')).toBe(false);
+
+      // /a/x matches /a (len 2).
+      // /a wins (TRUST_FOLDER).
+      expect(folders.isPathTrusted('/a/x')).toBe(true);
+
+      // Overlap with TRUST_PARENT
+      // /parent/trustme/butnotthis/file matches:
+      // - /parent/trustme (len 15, TRUST_PARENT -> effective /parent)
+      // - /parent/trustme/butnotthis (len 26, DO_NOT_TRUST)
+      // /parent/trustme/butnotthis wins.
+      expect(folders.isPathTrusted('/parent/trustme/butnotthis/file')).toBe(
+        false,
+      );
+
+      // /parent/other matches /parent/trustme (len 15, effective /parent)
+      expect(folders.isPathTrusted('/parent/other')).toBe(true);
+    });
   });
 
   it('should load user rules if only user file exists', () => {
     const userPath = getTrustedFoldersPath();
-    (mockFsExistsSync as Mock).mockImplementation((p) => p === userPath);
+    vi.mocked(fs.existsSync).mockImplementation(
+      (p: fs.PathLike) => p.toString() === userPath,
+    );
     const userContent = {
       '/user/folder': TrustLevel.TRUST_FOLDER,
     };
-    (fs.readFileSync as Mock).mockImplementation((p) => {
-      if (p === userPath) return JSON.stringify(userContent);
-      return '{}';
-    });
+    vi.mocked(fs.readFileSync).mockImplementation(
+      (p: fs.PathOrFileDescriptor) => {
+        if (p.toString() === userPath) return JSON.stringify(userContent);
+        return '{}';
+      },
+    );
 
     const { rules, errors } = loadTrustedFolders();
     expect(rules).toEqual([
@@ -154,11 +202,15 @@ describe('Trusted Folders Loading', () => {
 
   it('should handle JSON parsing errors gracefully', () => {
     const userPath = getTrustedFoldersPath();
-    (mockFsExistsSync as Mock).mockImplementation((p) => p === userPath);
-    (fs.readFileSync as Mock).mockImplementation((p) => {
-      if (p === userPath) return 'invalid json';
-      return '{}';
-    });
+    vi.mocked(fs.existsSync).mockImplementation(
+      (p: fs.PathLike) => p.toString() === userPath,
+    );
+    vi.mocked(fs.readFileSync).mockImplementation(
+      (p: fs.PathOrFileDescriptor) => {
+        if (p.toString() === userPath) return 'invalid json';
+        return '{}';
+      },
+    );
 
     const { rules, errors } = loadTrustedFolders();
     expect(rules).toEqual([]);
@@ -171,14 +223,18 @@ describe('Trusted Folders Loading', () => {
     const customPath = '/custom/path/to/trusted_folders.json';
     process.env['GEMINI_CLI_TRUSTED_FOLDERS_PATH'] = customPath;
 
-    (mockFsExistsSync as Mock).mockImplementation((p) => p === customPath);
+    vi.mocked(fs.existsSync).mockImplementation(
+      (p: fs.PathLike) => p.toString() === customPath,
+    );
     const userContent = {
       '/user/folder/from/env': TrustLevel.TRUST_FOLDER,
     };
-    (fs.readFileSync as Mock).mockImplementation((p) => {
-      if (p === customPath) return JSON.stringify(userContent);
-      return '{}';
-    });
+    vi.mocked(fs.readFileSync).mockImplementation(
+      (p: fs.PathOrFileDescriptor) => {
+        if (p.toString() === customPath) return JSON.stringify(userContent);
+        return '{}';
+      },
+    );
 
     const { rules, errors } = loadTrustedFolders();
     expect(rules).toEqual([
@@ -221,14 +277,16 @@ describe('isWorkspaceTrusted', () => {
   beforeEach(() => {
     resetTrustedFoldersForTesting();
     vi.spyOn(process, 'cwd').mockImplementation(() => mockCwd);
-    vi.spyOn(fs, 'readFileSync').mockImplementation((p) => {
-      if (p === getTrustedFoldersPath()) {
-        return JSON.stringify(mockRules);
-      }
-      return '{}';
-    });
+    vi.spyOn(fs, 'readFileSync').mockImplementation(
+      (p: fs.PathOrFileDescriptor) => {
+        if (p.toString() === getTrustedFoldersPath()) {
+          return JSON.stringify(mockRules);
+        }
+        return '{}';
+      },
+    );
     vi.spyOn(fs, 'existsSync').mockImplementation(
-      (p) => p === getTrustedFoldersPath(),
+      (p: fs.PathLike) => p.toString() === getTrustedFoldersPath(),
     );
   });
 
@@ -241,12 +299,14 @@ describe('isWorkspaceTrusted', () => {
   it('should throw a fatal error if the config is malformed', () => {
     mockCwd = '/home/user/projectA';
     // This mock needs to be specific to this test to override the one in beforeEach
-    vi.spyOn(fs, 'readFileSync').mockImplementation((p) => {
-      if (p === getTrustedFoldersPath()) {
-        return '{"foo": "bar",}'; // Malformed JSON with trailing comma
-      }
-      return '{}';
-    });
+    vi.spyOn(fs, 'readFileSync').mockImplementation(
+      (p: fs.PathOrFileDescriptor) => {
+        if (p.toString() === getTrustedFoldersPath()) {
+          return '{"foo": "bar",}'; // Malformed JSON with trailing comma
+        }
+        return '{}';
+      },
+    );
     expect(() => isWorkspaceTrusted(mockSettings)).toThrow(FatalConfigError);
     expect(() => isWorkspaceTrusted(mockSettings)).toThrow(
       /Please fix the configuration file/,
@@ -255,12 +315,14 @@ describe('isWorkspaceTrusted', () => {
 
   it('should throw a fatal error if the config is not a JSON object', () => {
     mockCwd = '/home/user/projectA';
-    vi.spyOn(fs, 'readFileSync').mockImplementation((p) => {
-      if (p === getTrustedFoldersPath()) {
-        return 'null';
-      }
-      return '{}';
-    });
+    vi.spyOn(fs, 'readFileSync').mockImplementation(
+      (p: fs.PathOrFileDescriptor) => {
+        if (p.toString() === getTrustedFoldersPath()) {
+          return 'null';
+        }
+        return '{}';
+      },
+    );
     expect(() => isWorkspaceTrusted(mockSettings)).toThrow(FatalConfigError);
     expect(() => isWorkspaceTrusted(mockSettings)).toThrow(
       /not a valid JSON object/,
@@ -303,10 +365,10 @@ describe('isWorkspaceTrusted', () => {
     });
   });
 
-  it('should return undefined for a child of an untrusted folder', () => {
+  it('should return false for a child of an untrusted folder', () => {
     mockCwd = '/home/user/untrusted/src';
     mockRules['/home/user/untrusted'] = TrustLevel.DO_NOT_TRUST;
-    expect(isWorkspaceTrusted(mockSettings).isTrusted).toBeUndefined();
+    expect(isWorkspaceTrusted(mockSettings).isTrusted).toBe(false);
   });
 
   it('should return undefined when no rules match', () => {
@@ -316,11 +378,24 @@ describe('isWorkspaceTrusted', () => {
     expect(isWorkspaceTrusted(mockSettings).isTrusted).toBeUndefined();
   });
 
-  it('should prioritize trust over distrust', () => {
+  it('should prioritize specific distrust over parent trust', () => {
     mockCwd = '/home/user/projectA/untrusted';
     mockRules['/home/user/projectA'] = TrustLevel.TRUST_FOLDER;
     mockRules['/home/user/projectA/untrusted'] = TrustLevel.DO_NOT_TRUST;
     expect(isWorkspaceTrusted(mockSettings)).toEqual({
+      isTrusted: false,
+      source: 'file',
+    });
+  });
+
+  it('should use workspaceDir instead of process.cwd() when provided', () => {
+    mockCwd = '/home/user/untrusted';
+    const workspaceDir = '/home/user/projectA';
+    mockRules['/home/user/projectA'] = TrustLevel.TRUST_FOLDER;
+    mockRules['/home/user/untrusted'] = TrustLevel.DO_NOT_TRUST;
+
+    // process.cwd() is untrusted, but workspaceDir is trusted
+    expect(isWorkspaceTrusted(mockSettings, workspaceDir)).toEqual({
       isTrusted: true,
       source: 'file',
     });
@@ -338,6 +413,19 @@ describe('isWorkspaceTrusted', () => {
 });
 
 describe('isWorkspaceTrusted with IDE override', () => {
+  const mockCwd = '/home/user/projectA';
+
+  beforeEach(() => {
+    resetTrustedFoldersForTesting();
+    vi.spyOn(process, 'cwd').mockImplementation(() => mockCwd);
+    vi.spyOn(fs, 'realpathSync').mockImplementation((p: fs.PathLike) =>
+      p.toString(),
+    );
+    vi.spyOn(fs, 'existsSync').mockImplementation((p: fs.PathLike) =>
+      p.toString().endsWith('trustedFolders.json') ? false : true,
+    );
+  });
+
   afterEach(() => {
     vi.clearAllMocks();
     ideContextStore.clear();
@@ -377,10 +465,15 @@ describe('isWorkspaceTrusted with IDE override', () => {
   });
 
   it('should fall back to config when ideTrust is undefined', () => {
-    vi.spyOn(fs, 'existsSync').mockReturnValue(true);
-    vi.spyOn(fs, 'readFileSync').mockReturnValue(
-      JSON.stringify({ [process.cwd()]: TrustLevel.TRUST_FOLDER }),
+    vi.spyOn(fs, 'existsSync').mockImplementation((p) =>
+      p === getTrustedFoldersPath() || p === mockCwd ? true : false,
     );
+    vi.spyOn(fs, 'readFileSync').mockImplementation((p) => {
+      if (p === getTrustedFoldersPath()) {
+        return JSON.stringify({ [mockCwd]: TrustLevel.TRUST_FOLDER });
+      }
+      return '{}';
+    });
     expect(isWorkspaceTrusted(mockSettings)).toEqual({
       isTrusted: true,
       source: 'file',
@@ -406,8 +499,11 @@ describe('isWorkspaceTrusted with IDE override', () => {
 describe('Trusted Folders Caching', () => {
   beforeEach(() => {
     resetTrustedFoldersForTesting();
-    vi.mocked(fs.existsSync).mockReturnValue(true);
-    vi.mocked(fs.readFileSync).mockReturnValue('{}');
+    vi.spyOn(fs, 'existsSync').mockReturnValue(true);
+    vi.spyOn(fs, 'readFileSync').mockReturnValue('{}');
+    vi.spyOn(fs, 'realpathSync').mockImplementation((p: fs.PathLike) =>
+      p.toString(),
+    );
   });
 
   afterEach(() => {
@@ -441,14 +537,20 @@ describe('invalid trust levels', () => {
   beforeEach(() => {
     resetTrustedFoldersForTesting();
     vi.spyOn(process, 'cwd').mockImplementation(() => mockCwd);
-    vi.spyOn(fs, 'readFileSync').mockImplementation((p) => {
-      if (p === getTrustedFoldersPath()) {
-        return JSON.stringify(mockRules);
-      }
-      return '{}';
-    });
+    vi.spyOn(fs, 'realpathSync').mockImplementation((p: fs.PathLike) =>
+      p.toString(),
+    );
+    vi.spyOn(fs, 'readFileSync').mockImplementation(
+      (p: fs.PathOrFileDescriptor) => {
+        if (p.toString() === getTrustedFoldersPath()) {
+          return JSON.stringify(mockRules);
+        }
+        return '{}';
+      },
+    );
     vi.spyOn(fs, 'existsSync').mockImplementation(
-      (p) => p === getTrustedFoldersPath(),
+      (p: fs.PathLike) =>
+        p.toString() === getTrustedFoldersPath() || p.toString() === mockCwd,
     );
   });
 
@@ -482,3 +584,235 @@ describe('invalid trust levels', () => {
     expect(() => isWorkspaceTrusted(mockSettings)).toThrow(FatalConfigError);
   });
 });
+
+describe('Verification: Auth and Trust Interaction', () => {
+  let mockCwd: string;
+  const mockRules: Record<string, TrustLevel> = {};
+
+  beforeEach(() => {
+    vi.stubEnv('GEMINI_API_KEY', '');
+    resetTrustedFoldersForTesting();
+    vi.spyOn(process, 'cwd').mockImplementation(() => mockCwd);
+    vi.spyOn(fs, 'readFileSync').mockImplementation((p) => {
+      if (p === getTrustedFoldersPath()) {
+        return JSON.stringify(mockRules);
+      }
+      if (p === path.resolve(mockCwd, '.env')) {
+        return 'GEMINI_API_KEY=shhh-secret';
+      }
+      return '{}';
+    });
+    vi.spyOn(fs, 'existsSync').mockImplementation(
+      (p) =>
+        p === getTrustedFoldersPath() || p === path.resolve(mockCwd, '.env'),
+    );
+  });
+
+  afterEach(() => {
+    vi.unstubAllEnvs();
+    Object.keys(mockRules).forEach((key) => delete mockRules[key]);
+  });
+
+  it('should verify loadEnvironment returns early and validateAuthMethod fails when untrusted', () => {
+    // 1. Mock untrusted workspace
+    mockCwd = '/home/user/untrusted';
+    mockRules[mockCwd] = TrustLevel.DO_NOT_TRUST;
+
+    // 2. Load environment (should return early)
+    const settings = createMockSettings({
+      security: { folderTrust: { enabled: true } },
+    });
+    loadEnvironment(settings.merged, mockCwd);
+
+    // 3. Verify env var NOT loaded
+    expect(process.env['GEMINI_API_KEY']).toBe('');
+
+    // 4. Verify validateAuthMethod fails
+    const result = validateAuthMethod(AuthType.USE_GEMINI);
+    expect(result).toContain(
+      'you must specify the GEMINI_API_KEY environment variable',
+    );
+  });
+
+  it('should identify if sandbox flag is available in Settings', () => {
+    const schema = getSettingsSchema();
+    expect(schema.tools.properties).toBeDefined();
+    expect('sandbox' in schema.tools.properties).toBe(true);
+  });
+});
+
+describe('Trusted Folders realpath caching', () => {
+  beforeEach(() => {
+    resetTrustedFoldersForTesting();
+    vi.resetAllMocks();
+    vi.spyOn(fs, 'realpathSync').mockImplementation((p: fs.PathLike) =>
+      p.toString(),
+    );
+  });
+
+  afterEach(() => {
+    vi.restoreAllMocks();
+  });
+
+  it('should only call fs.realpathSync once for the same path', () => {
+    const mockPath = '/some/path';
+    const mockRealPath = '/real/path';
+
+    vi.spyOn(fs, 'existsSync').mockReturnValue(true);
+    const realpathSpy = vi
+      .spyOn(fs, 'realpathSync')
+      .mockReturnValue(mockRealPath);
+    vi.spyOn(fs, 'readFileSync').mockReturnValue(
+      JSON.stringify({
+        [mockPath]: TrustLevel.TRUST_FOLDER,
+        '/another/path': TrustLevel.TRUST_FOLDER,
+      }),
+    );
+
+    const folders = loadTrustedFolders();
+
+    // Call isPathTrusted multiple times with the same path
+    folders.isPathTrusted(mockPath);
+    folders.isPathTrusted(mockPath);
+    folders.isPathTrusted(mockPath);
+
+    // fs.realpathSync should only be called once for mockPath (at the start of isPathTrusted)
+    // And once for each rule in the config (if they are different)
+
+    // Let's check calls for mockPath
+    const mockPathCalls = realpathSpy.mock.calls.filter(
+      (call) => call[0] === mockPath,
+    );
+
+    expect(mockPathCalls.length).toBe(1);
+  });
+
+  it('should cache results for rule paths in the loop', () => {
+    const rulePath = '/rule/path';
+    const locationPath = '/location/path';
+
+    vi.spyOn(fs, 'existsSync').mockReturnValue(true);
+    const realpathSpy = vi
+      .spyOn(fs, 'realpathSync')
+      .mockImplementation((p: fs.PathLike) => p.toString()); // identity for simplicity
+    vi.spyOn(fs, 'readFileSync').mockReturnValue(
+      JSON.stringify({
+        [rulePath]: TrustLevel.TRUST_FOLDER,
+      }),
+    );
+
+    const folders = loadTrustedFolders();
+
+    // First call
+    folders.isPathTrusted(locationPath);
+    const firstCallCount = realpathSpy.mock.calls.length;
+    expect(firstCallCount).toBe(2); // locationPath and rulePath
+
+    // Second call with same location and same config
+    folders.isPathTrusted(locationPath);
+    const secondCallCount = realpathSpy.mock.calls.length;
+
+    // Should still be 2 because both were cached
+    expect(secondCallCount).toBe(2);
+  });
+});
+
+describe('isWorkspaceTrusted with Symlinks', () => {
+  const mockSettings: Settings = {
+    security: {
+      folderTrust: {
+        enabled: true,
+      },
+    },
+  };
+
+  beforeEach(() => {
+    resetTrustedFoldersForTesting();
+    vi.resetAllMocks();
+    vi.spyOn(fs, 'realpathSync').mockImplementation((p: fs.PathLike) =>
+      p.toString(),
+    );
+  });
+
+  afterEach(() => {
+    vi.restoreAllMocks();
+  });
+
+  it('should trust a folder even if CWD is a symlink and rule is realpath', () => {
+    const symlinkPath = '/var/folders/project';
+    const realPath = '/private/var/folders/project';
+
+    vi.spyOn(process, 'cwd').mockReturnValue(symlinkPath);
+
+    // Mock fs.existsSync to return true for trust config and both paths
+    vi.spyOn(fs, 'existsSync').mockImplementation((p: fs.PathLike) => {
+      const pathStr = p.toString();
+      if (pathStr === getTrustedFoldersPath()) return true;
+      if (pathStr === symlinkPath) return true;
+      if (pathStr === realPath) return true;
+      return false;
+    });
+
+    // Mock realpathSync to resolve symlink to realpath
+    vi.spyOn(fs, 'realpathSync').mockImplementation((p: fs.PathLike) => {
+      const pathStr = p.toString();
+      if (pathStr === symlinkPath) return realPath;
+      if (pathStr === realPath) return realPath;
+      return pathStr;
+    });
+
+    // Rule is saved with realpath
+    const mockRules = {
+      [realPath]: TrustLevel.TRUST_FOLDER,
+    };
+    vi.spyOn(fs, 'readFileSync').mockImplementation(
+      (p: fs.PathOrFileDescriptor) => {
+        if (p.toString() === getTrustedFoldersPath())
+          return JSON.stringify(mockRules);
+        return '{}';
+      },
+    );
+
+    // Should be trusted because both resolve to the same realpath
+    expect(isWorkspaceTrusted(mockSettings).isTrusted).toBe(true);
+  });
+
+  it('should trust a folder even if CWD is realpath and rule is a symlink', () => {
+    const symlinkPath = '/var/folders/project';
+    const realPath = '/private/var/folders/project';
+
+    vi.spyOn(process, 'cwd').mockReturnValue(realPath);
+
+    // Mock fs.existsSync
+    vi.spyOn(fs, 'existsSync').mockImplementation((p: fs.PathLike) => {
+      const pathStr = p.toString();
+      if (pathStr === getTrustedFoldersPath()) return true;
+      if (pathStr === symlinkPath) return true;
+      if (pathStr === realPath) return true;
+      return false;
+    });
+
+    // Mock realpathSync
+    vi.spyOn(fs, 'realpathSync').mockImplementation((p: fs.PathLike) => {
+      const pathStr = p.toString();
+      if (pathStr === symlinkPath) return realPath;
+      if (pathStr === realPath) return realPath;
+      return pathStr;
+    });
+
+    // Rule is saved with symlink path
+    const mockRules = {
+      [symlinkPath]: TrustLevel.TRUST_FOLDER,
+    };
+    vi.spyOn(fs, 'readFileSync').mockImplementation(
+      (p: fs.PathOrFileDescriptor) => {
+        if (p.toString() === getTrustedFoldersPath())
+          return JSON.stringify(mockRules);
+        return '{}';
+      },
+    );
+
+    // Should be trusted because both resolve to the same realpath
+    expect(isWorkspaceTrusted(mockSettings).isTrusted).toBe(true);
+  });
+});

packages/cli/src/config/trustedFolders.ts

@@ -36,7 +36,9 @@ export enum TrustLevel {
   DO_NOT_TRUST = 'DO_NOT_TRUST',
 }
 
-export function isTrustLevel(value: unknown): value is TrustLevel {
+export function isTrustLevel(
+  value: string | number | boolean | object | null | undefined,
+): value is TrustLevel {
   return (
     typeof value === 'string' &&
     Object.values(TrustLevel).includes(value as TrustLevel)
@@ -63,6 +65,32 @@ export interface TrustResult {
   source: 'ide' | 'file' | undefined;
 }
 
+const realPathCache = new Map<string, string>();
+
+/**
+ * FOR TESTING PURPOSES ONLY.
+ * Clears the real path cache.
+ */
+export function clearRealPathCacheForTesting(): void {
+  realPathCache.clear();
+}
+
+function getRealPath(location: string): string {
+  let realPath = realPathCache.get(location);
+  if (realPath !== undefined) {
+    return realPath;
+  }
+
+  try {
+    realPath = fs.existsSync(location) ? fs.realpathSync(location) : location;
+  } catch {
+    realPath = location;
+  }
+
+  realPathCache.set(location, realPath);
+  return realPath;
+}
+
 export class LoadedTrustedFolders {
   constructor(
     readonly user: TrustedFoldersFile,
@@ -88,39 +116,36 @@ export class LoadedTrustedFolders {
     config?: Record<string, TrustLevel>,
   ): boolean | undefined {
     const configToUse = config ?? this.user.config;
-    const trustedPaths: string[] = [];
-    const untrustedPaths: string[] = [];
 
-    for (const rule of Object.entries(configToUse).map(
-      ([path, trustLevel]) => ({ path, trustLevel }),
-    )) {
-      switch (rule.trustLevel) {
-        case TrustLevel.TRUST_FOLDER:
-          trustedPaths.push(rule.path);
-          break;
-        case TrustLevel.TRUST_PARENT:
-          trustedPaths.push(path.dirname(rule.path));
-          break;
-        case TrustLevel.DO_NOT_TRUST:
-          untrustedPaths.push(rule.path);
-          break;
-        default:
-          // Do nothing for unknown trust levels.
-          break;
+    // Resolve location to its realpath for canonical comparison
+    const realLocation = getRealPath(location);
+
+    let longestMatchLen = -1;
+    let longestMatchTrust: TrustLevel | undefined = undefined;
+
+    for (const [rulePath, trustLevel] of Object.entries(configToUse)) {
+      const effectivePath =
+        trustLevel === TrustLevel.TRUST_PARENT
+          ? path.dirname(rulePath)
+          : rulePath;
+
+      // Resolve effectivePath to its realpath for canonical comparison
+      const realEffectivePath = getRealPath(effectivePath);
+
+      if (isWithinRoot(realLocation, realEffectivePath)) {
+        if (rulePath.length > longestMatchLen) {
+          longestMatchLen = rulePath.length;
+          longestMatchTrust = trustLevel;
+        }
       }
     }
 
-    for (const trustedPath of trustedPaths) {
-      if (isWithinRoot(location, trustedPath)) {
-        return true;
-      }
-    }
-
-    for (const untrustedPath of untrustedPaths) {
-      if (path.normalize(location) === path.normalize(untrustedPath)) {
-        return false;
-      }
-    }
+    if (longestMatchTrust === TrustLevel.DO_NOT_TRUST) return false;
+    if (
+      longestMatchTrust === TrustLevel.TRUST_FOLDER ||
+      longestMatchTrust === TrustLevel.TRUST_PARENT
+    )
+      return true;
 
     return undefined;
   }
@@ -150,6 +175,7 @@ let loadedTrustedFolders: LoadedTrustedFolders | undefined;
  */
 export function resetTrustedFoldersForTesting(): void {
   loadedTrustedFolders = undefined;
+  clearRealPathCacheForTesting();
 }
 
 export function loadTrustedFolders(): LoadedTrustedFolders {
@@ -161,11 +187,13 @@ export function loadTrustedFolders(): LoadedTrustedFolders {
   const userConfig: Record<string, TrustLevel> = {};
 
   const userPath = getTrustedFoldersPath();
-  // Load user trusted folders
   try {
     if (fs.existsSync(userPath)) {
       const content = fs.readFileSync(userPath, 'utf-8');
-      const parsed: unknown = JSON.parse(stripJsonComments(content));
+      const parsed = JSON.parse(stripJsonComments(content)) as Record<
+        string,
+        string
+      >;
 
       if (
         typeof parsed !== 'object' ||
@@ -190,7 +218,7 @@ export function loadTrustedFolders(): LoadedTrustedFolders {
         }
       }
     }
-  } catch (error: unknown) {
+  } catch (error) {
     errors.push({
       message: getErrorMessage(error),
       path: userPath,
@@ -222,11 +250,12 @@ export function saveTrustedFolders(
 
 /** Is folder trust feature enabled per the current applied settings */
 export function isFolderTrustEnabled(settings: Settings): boolean {
-  const folderTrustSetting = settings.security?.folderTrust?.enabled ?? false;
+  const folderTrustSetting = settings.security?.folderTrust?.enabled ?? true;
   return folderTrustSetting;
 }
 
 function getWorkspaceTrustFromLocalConfig(
+  workspaceDir: string,
   trustConfig?: Record<string, TrustLevel>,
 ): TrustResult {
   const folders = loadTrustedFolders();
@@ -241,7 +270,7 @@ function getWorkspaceTrustFromLocalConfig(
     );
   }
 
-  const isTrusted = folders.isPathTrusted(process.cwd(), configToUse);
+  const isTrusted = folders.isPathTrusted(workspaceDir, configToUse);
   return {
     isTrusted,
     source: isTrusted !== undefined ? 'file' : undefined,
@@ -250,6 +279,7 @@ function getWorkspaceTrustFromLocalConfig(
 
 export function isWorkspaceTrusted(
   settings: Settings,
+  workspaceDir: string = process.cwd(),
   trustConfig?: Record<string, TrustLevel>,
 ): TrustResult {
   if (!isFolderTrustEnabled(settings)) {
@@ -262,5 +292,5 @@ export function isWorkspaceTrusted(
   }
 
   // Fall back to the local user configuration
-  return getWorkspaceTrustFromLocalConfig(trustConfig);
+  return getWorkspaceTrustFromLocalConfig(workspaceDir, trustConfig);
 }

packages/cli/src/deferred.test.ts

@@ -13,14 +13,13 @@ import {
 } from './deferred.js';
 import { ExitCodes } from '@google/gemini-cli-core';
 import type { ArgumentsCamelCase, CommandModule } from 'yargs';
-import type { MergedSettings } from './config/settings.js';
+import { createMockSettings } from './test-utils/settings.js';
 import type { MockInstance } from 'vitest';
 
-const { mockRunExitCleanup, mockDebugLogger } = vi.hoisted(() => ({
+const { mockRunExitCleanup, mockCoreEvents } = vi.hoisted(() => ({
   mockRunExitCleanup: vi.fn(),
-  mockDebugLogger: {
-    log: vi.fn(),
-    error: vi.fn(),
+  mockCoreEvents: {
+    emitFeedback: vi.fn(),
   },
 }));
 
@@ -28,7 +27,7 @@ vi.mock('@google/gemini-cli-core', async () => {
   const actual = await vi.importActual('@google/gemini-cli-core');
   return {
     ...actual,
-    debugLogger: mockDebugLogger,
+    coreEvents: mockCoreEvents,
   };
 });
 
@@ -47,16 +46,10 @@ describe('deferred', () => {
     setDeferredCommand(undefined as unknown as DeferredCommand); // Reset deferred command
   });
 
-  const createMockSettings = (adminSettings: unknown = {}): MergedSettings =>
-    ({
-      admin: adminSettings,
-    }) as unknown as MergedSettings;
-
   describe('runDeferredCommand', () => {
     it('should do nothing if no deferred command is set', async () => {
-      await runDeferredCommand(createMockSettings());
-      expect(mockDebugLogger.log).not.toHaveBeenCalled();
-      expect(mockDebugLogger.error).not.toHaveBeenCalled();
+      await runDeferredCommand(createMockSettings().merged);
+      expect(mockCoreEvents.emitFeedback).not.toHaveBeenCalled();
       expect(mockExit).not.toHaveBeenCalled();
     });
 
@@ -68,7 +61,9 @@ describe('deferred', () => {
         commandName: 'mcp',
       });
 
-      const settings = createMockSettings({ mcp: { enabled: true } });
+      const settings = createMockSettings({
+        merged: { admin: { mcp: { enabled: true } } },
+      }).merged;
       await runDeferredCommand(settings);
       expect(mockHandler).toHaveBeenCalled();
       expect(mockRunExitCleanup).toHaveBeenCalled();
@@ -82,11 +77,14 @@ describe('deferred', () => {
         commandName: 'mcp',
       });
 
-      const settings = createMockSettings({ mcp: { enabled: false } });
+      const settings = createMockSettings({
+        merged: { admin: { mcp: { enabled: false } } },
+      }).merged;
       await runDeferredCommand(settings);
 
-      expect(mockDebugLogger.error).toHaveBeenCalledWith(
-        'Error: MCP is disabled by your admin.',
+      expect(mockCoreEvents.emitFeedback).toHaveBeenCalledWith(
+        'error',
+        'MCP is disabled by your administrator. To enable it, please request an update to the settings at: https://goo.gle/manage-gemini-cli',
       );
       expect(mockRunExitCleanup).toHaveBeenCalled();
       expect(mockExit).toHaveBeenCalledWith(ExitCodes.FATAL_CONFIG_ERROR);
@@ -99,11 +97,14 @@ describe('deferred', () => {
         commandName: 'extensions',
       });
 
-      const settings = createMockSettings({ extensions: { enabled: false } });
+      const settings = createMockSettings({
+        merged: { admin: { extensions: { enabled: false } } },
+      }).merged;
       await runDeferredCommand(settings);
 
-      expect(mockDebugLogger.error).toHaveBeenCalledWith(
-        'Error: Extensions are disabled by your admin.',
+      expect(mockCoreEvents.emitFeedback).toHaveBeenCalledWith(
+        'error',
+        'Extensions is disabled by your administrator. To enable it, please request an update to the settings at: https://goo.gle/manage-gemini-cli',
       );
       expect(mockRunExitCleanup).toHaveBeenCalled();
       expect(mockExit).toHaveBeenCalledWith(ExitCodes.FATAL_CONFIG_ERROR);
@@ -116,11 +117,14 @@ describe('deferred', () => {
         commandName: 'skills',
       });
 
-      const settings = createMockSettings({ skills: { enabled: false } });
+      const settings = createMockSettings({
+        merged: { admin: { skills: { enabled: false } } },
+      }).merged;
       await runDeferredCommand(settings);
 
-      expect(mockDebugLogger.error).toHaveBeenCalledWith(
-        'Error: Agent skills are disabled by your admin.',
+      expect(mockCoreEvents.emitFeedback).toHaveBeenCalledWith(
+        'error',
+        'Agent skills is disabled by your administrator. To enable it, please request an update to the settings at: https://goo.gle/manage-gemini-cli',
       );
       expect(mockRunExitCleanup).toHaveBeenCalled();
       expect(mockExit).toHaveBeenCalledWith(ExitCodes.FATAL_CONFIG_ERROR);
@@ -134,7 +138,7 @@ describe('deferred', () => {
         commandName: 'mcp',
       });
 
-      const settings = createMockSettings({}); // No admin settings
+      const settings = createMockSettings({}).merged; // No admin settings
       await runDeferredCommand(settings);
 
       expect(mockHandler).toHaveBeenCalled();
@@ -162,7 +166,7 @@ describe('deferred', () => {
       expect(originalHandler).not.toHaveBeenCalled();
 
       // Now manually run it to verify it captured correctly
-      await runDeferredCommand(createMockSettings());
+      await runDeferredCommand(createMockSettings().merged);
       expect(originalHandler).toHaveBeenCalledWith(argv);
       expect(mockExit).toHaveBeenCalledWith(ExitCodes.SUCCESS);
     });
@@ -180,11 +184,14 @@ describe('deferred', () => {
       const deferredMcp = defer(commandModule, 'mcp');
       await deferredMcp.handler({} as ArgumentsCamelCase);
 
-      const mcpSettings = createMockSettings({ mcp: { enabled: false } });
+      const mcpSettings = createMockSettings({
+        merged: { admin: { mcp: { enabled: false } } },
+      }).merged;
       await runDeferredCommand(mcpSettings);
 
-      expect(mockDebugLogger.error).toHaveBeenCalledWith(
-        'Error: MCP is disabled by your admin.',
+      expect(mockCoreEvents.emitFeedback).toHaveBeenCalledWith(
+        'error',
+        'MCP is disabled by your administrator. To enable it, please request an update to the settings at: https://goo.gle/manage-gemini-cli',
       );
     });
 
@@ -203,10 +210,14 @@ describe('deferred', () => {
       // confirming it didn't capture 'mcp', 'extensions', or 'skills'
       // and defaulted to 'unknown' (or something else safe).
       const settings = createMockSettings({
-        mcp: { enabled: false },
-        extensions: { enabled: false },
-        skills: { enabled: false },
-      });
+        merged: {
+          admin: {
+            mcp: { enabled: false },
+            extensions: { enabled: false },
+            skills: { enabled: false },
+          },
+        },
+      }).merged;
 
       await runDeferredCommand(settings);
 

packages/cli/src/deferred.ts

@@ -4,7 +4,11 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 import type { ArgumentsCamelCase, CommandModule } from 'yargs';
-import { debugLogger, ExitCodes } from '@google/gemini-cli-core';
+import {
+  coreEvents,
+  ExitCodes,
+  getAdminErrorMessage,
+} from '@google/gemini-cli-core';
 import { runExitCleanup } from './utils/cleanup.js';
 import type { MergedSettings } from './config/settings.js';
 import process from 'node:process';
@@ -30,7 +34,10 @@ export async function runDeferredCommand(settings: MergedSettings) {
   const commandName = deferredCommand.commandName;
 
   if (commandName === 'mcp' && adminSettings?.mcp?.enabled === false) {
-    debugLogger.error('Error: MCP is disabled by your admin.');
+    coreEvents.emitFeedback(
+      'error',
+      getAdminErrorMessage('MCP', undefined /* config */),
+    );
     await runExitCleanup();
     process.exit(ExitCodes.FATAL_CONFIG_ERROR);
   }
@@ -39,13 +46,19 @@ export async function runDeferredCommand(settings: MergedSettings) {
     commandName === 'extensions' &&
     adminSettings?.extensions?.enabled === false
   ) {
-    debugLogger.error('Error: Extensions are disabled by your admin.');
+    coreEvents.emitFeedback(
+      'error',
+      getAdminErrorMessage('Extensions', undefined /* config */),
+    );
     await runExitCleanup();
     process.exit(ExitCodes.FATAL_CONFIG_ERROR);
   }
 
   if (commandName === 'skills' && adminSettings?.skills?.enabled === false) {
-    debugLogger.error('Error: Agent skills are disabled by your admin.');
+    coreEvents.emitFeedback(
+      'error',
+      getAdminErrorMessage('Agent skills', undefined /* config */),
+    );
     await runExitCleanup();
     process.exit(ExitCodes.FATAL_CONFIG_ERROR);
   }

packages/cli/src/gemini.tsx

@@ -25,6 +25,7 @@ import { getStartupWarnings } from './utils/startupWarnings.js';
 import { getUserStartupWarnings } from './utils/userStartupWarnings.js';
 import { ConsolePatcher } from './ui/utils/ConsolePatcher.js';
 import { runNonInteractive } from './nonInteractiveCli.js';
+import { runRalphWiggum } from './ralphWiggum.js';
 import {
   cleanupCheckpoints,
   registerCleanup,
@@ -32,6 +33,10 @@ import {
   runExitCleanup,
   registerTelemetryConfig,
 } from './utils/cleanup.js';
+import {
+  cleanupToolOutputFiles,
+  cleanupExpiredSessions,
+} from './utils/sessionCleanup.js';
 import {
   type Config,
   type ResumedSessionData,
@@ -63,7 +68,7 @@ import {
   getVersion,
   ValidationCancelledError,
   ValidationRequiredError,
-  type FetchAdminControlsResponse,
+  type AdminControlsSettings,
 } from '@google/gemini-cli-core';
 import {
   initializeApp,
@@ -71,7 +76,6 @@ import {
 } from './core/initializer.js';
 import { validateAuthMethod } from './config/auth.js';
 import { runZedIntegration } from './zed-integration/zedIntegration.js';
-import { cleanupExpiredSessions } from './utils/sessionCleanup.js';
 import { validateNonInteractiveAuth } from './validateNonInterActiveAuth.js';
 import { checkForUpdates } from './ui/utils/updateCheck.js';
 import { handleAutoUpdate } from './utils/handleAutoUpdate.js';
@@ -95,6 +99,7 @@ import { deleteSession, listSessions } from './utils/sessions.js';
 import { createPolicyUpdater } from './config/policy.js';
 import { ScrollProvider } from './ui/contexts/ScrollProvider.js';
 import { isAlternateBufferEnabled } from './ui/hooks/useAlternateBuffer.js';
+import { TerminalProvider } from './ui/contexts/TerminalContext.js';
 
 import { setupTerminalAndTheme } from './utils/terminalTheme.js';
 import { profiler } from './ui/components/DebugProfiler.js';
@@ -225,19 +230,21 @@ export async function startInteractiveUI(
               settings.merged.general.debugKeystrokeLogging
             }
           >
-            <ScrollProvider>
-              <SessionStatsProvider>
-                <VimModeProvider settings={settings}>
-                  <AppContainer
-                    config={config}
-                    startupWarnings={startupWarnings}
-                    version={version}
-                    resumedSessionData={resumedSessionData}
-                    initializationResult={initializationResult}
-                  />
-                </VimModeProvider>
-              </SessionStatsProvider>
-            </ScrollProvider>
+            <TerminalProvider>
+              <ScrollProvider>
+                <SessionStatsProvider>
+                  <VimModeProvider settings={settings}>
+                    <AppContainer
+                      config={config}
+                      startupWarnings={startupWarnings}
+                      version={version}
+                      resumedSessionData={resumedSessionData}
+                      initializationResult={initializationResult}
+                    />
+                  </VimModeProvider>
+                </SessionStatsProvider>
+              </ScrollProvider>
+            </TerminalProvider>
           </MouseProvider>
         </KeypressProvider>
       </SettingsContext.Provider>
@@ -320,7 +327,10 @@ export async function main() {
     );
   });
 
-  await cleanupCheckpoints();
+  await Promise.all([
+    cleanupCheckpoints(),
+    cleanupToolOutputFiles(settings.merged),
+  ]);
 
   const parseArgsHandle = startupProfiler.start('parse_arguments');
   const argv = await parseArguments(settings.merged);
@@ -731,13 +741,25 @@ export async function main() {
 
     initializeOutputListenersAndFlush();
 
-    await runNonInteractive({
-      config,
-      settings,
-      input,
-      prompt_id,
-      resumedSessionData,
-    });
+    if (argv.ralphWiggum) {
+      await runRalphWiggum({
+        config,
+        settings,
+        input,
+        prompt_id,
+        resumedSessionData,
+        completionPromise: argv.completionPromise,
+        maxIterations: argv.maxIterations,
+      });
+    } else {
+      await runNonInteractive({
+        config,
+        settings,
+        input,
+        prompt_id,
+        resumedSessionData,
+      });
+    }
     // Call cleanup before process.exit, which causes cleanup to not run
     await runExitCleanup();
     process.exit(ExitCodes.SUCCESS);
@@ -800,13 +822,13 @@ export function initializeOutputListenersAndFlush() {
 }
 
 function setupAdminControlsListener() {
-  let pendingSettings: FetchAdminControlsResponse | undefined;
+  let pendingSettings: AdminControlsSettings | undefined;
   let config: Config | undefined;
 
   const messageHandler = (msg: unknown) => {
     const message = msg as {
       type?: string;
-      settings?: FetchAdminControlsResponse;
+      settings?: AdminControlsSettings;
     };
     if (message?.type === 'admin-settings' && message.settings) {
       if (config) {

packages/cli/src/nonInteractiveCli.test.ts

@@ -258,6 +258,9 @@ describe('runNonInteractive', () => {
       [{ text: 'Test input' }],
       expect.any(AbortSignal),
       'prompt-id-1',
+      undefined,
+      false,
+      'Test input',
     );
     expect(getWrittenOutput()).toBe('Hello World\n');
     // Note: Telemetry shutdown is now handled in runExitCleanup() in cleanup.ts
@@ -374,6 +377,9 @@ describe('runNonInteractive', () => {
       [{ text: 'Tool response' }],
       expect.any(AbortSignal),
       'prompt-id-2',
+      undefined,
+      false,
+      undefined,
     );
     expect(getWrittenOutput()).toBe('Final answer\n');
   });
@@ -531,6 +537,9 @@ describe('runNonInteractive', () => {
       ],
       expect.any(AbortSignal),
       'prompt-id-3',
+      undefined,
+      false,
+      undefined,
     );
     expect(getWrittenOutput()).toBe('Sorry, let me try again.\n');
   });
@@ -670,6 +679,9 @@ describe('runNonInteractive', () => {
       processedParts,
       expect.any(AbortSignal),
       'prompt-id-7',
+      undefined,
+      false,
+      rawInput,
     );
 
     // 6. Assert the final output is correct
@@ -703,6 +715,9 @@ describe('runNonInteractive', () => {
       [{ text: 'Test input' }],
       expect.any(AbortSignal),
       'prompt-id-1',
+      undefined,
+      false,
+      'Test input',
     );
     expect(processStdoutSpy).toHaveBeenCalledWith(
       JSON.stringify(
@@ -833,6 +848,9 @@ describe('runNonInteractive', () => {
       [{ text: 'Empty response test' }],
       expect.any(AbortSignal),
       'prompt-id-empty',
+      undefined,
+      false,
+      'Empty response test',
     );
 
     // This should output JSON with empty response but include stats
@@ -967,6 +985,9 @@ describe('runNonInteractive', () => {
       [{ text: 'Prompt from command' }],
       expect.any(AbortSignal),
       'prompt-id-slash',
+      undefined,
+      false,
+      '/testcommand',
     );
 
     expect(getWrittenOutput()).toBe('Response from command\n');
@@ -1010,6 +1031,9 @@ describe('runNonInteractive', () => {
       [{ text: 'Slash command output' }],
       expect.any(AbortSignal),
       'prompt-id-slash',
+      undefined,
+      false,
+      '/help',
     );
     expect(getWrittenOutput()).toBe('Response to slash command\n');
     handleSlashCommandSpy.mockRestore();
@@ -1184,6 +1208,9 @@ describe('runNonInteractive', () => {
       [{ text: '/unknowncommand' }],
       expect.any(AbortSignal),
       'prompt-id-unknown',
+      undefined,
+      false,
+      '/unknowncommand',
     );
 
     expect(getWrittenOutput()).toBe('Response to unknown\n');

packages/cli/src/nonInteractiveCli.ts

@@ -47,7 +47,7 @@ import {
 } from './utils/errors.js';
 import { TextOutput } from './ui/utils/textOutput.js';
 
-interface RunNonInteractiveParams {
+export interface RunNonInteractiveParams {
   config: Config;
   settings: LoadedSettings;
   input: string;
@@ -55,13 +55,15 @@ interface RunNonInteractiveParams {
   resumedSessionData?: ResumedSessionData;
 }
 
+// Moved to ralphWiggum.ts
+
 export async function runNonInteractive({
   config,
   settings,
   input,
   prompt_id,
   resumedSessionData,
-}: RunNonInteractiveParams): Promise<void> {
+}: RunNonInteractiveParams): Promise<string> {
   return promptIdContext.run(prompt_id, async () => {
     const consolePatcher = new ConsolePatcher({
       stderr: true,
@@ -181,6 +183,9 @@ export async function runNonInteractive({
       }
     };
 
+    // Store accumulated response text to return
+    let fullResponseText = '';
+
     let errorToHandle: unknown | undefined;
     try {
       consolePatcher.patch();
@@ -301,6 +306,9 @@ export async function runNonInteractive({
           currentMessages[0]?.parts || [],
           abortController.signal,
           prompt_id,
+          undefined,
+          false,
+          turnCount === 1 ? input : undefined,
         );
 
         let responseText = '';
@@ -313,6 +321,13 @@ export async function runNonInteractive({
             const isRaw =
               config.getRawOutput() || config.getAcceptRawOutputRisk();
             const output = isRaw ? event.value : stripAnsi(event.value);
+
+            // Accumulate full response
+            if (event.value) {
+              fullResponseText += event.value;
+              responseText += output;
+            }
+
             if (streamFormatter) {
               streamFormatter.emitEvent({
                 type: JsonStreamEventType.MESSAGE,
@@ -322,7 +337,7 @@ export async function runNonInteractive({
                 delta: true,
               });
             } else if (config.getOutputFormat() === OutputFormat.JSON) {
-              responseText += output;
+              // responseText is already updated
             } else {
               if (event.value) {
                 textOutput.write(output);
@@ -378,7 +393,7 @@ export async function runNonInteractive({
                 ),
               });
             }
-            return;
+            return fullResponseText;
           } else if (event.type === GeminiEventType.AgentExecutionBlocked) {
             const blockMessage = `Agent execution blocked: ${event.value.systemMessage?.trim() || event.value.reason}`;
             if (config.getOutputFormat() === OutputFormat.TEXT) {
@@ -485,7 +500,7 @@ export async function runNonInteractive({
             } else {
               textOutput.ensureTrailingNewline(); // Ensure a final newline
             }
-            return;
+            return fullResponseText;
           }
 
           currentMessages = [{ role: 'user', parts: toolResponseParts }];
@@ -509,7 +524,7 @@ export async function runNonInteractive({
           } else {
             textOutput.ensureTrailingNewline(); // Ensure a final newline
           }
-          return;
+          return fullResponseText;
         }
       }
     } catch (error) {
@@ -525,5 +540,6 @@ export async function runNonInteractive({
     if (errorToHandle) {
       handleError(errorToHandle, config);
     }
+    return fullResponseText;
   });
 }

packages/cli/src/ralphWiggum.test.ts

@@ -0,0 +1,67 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, vi, beforeEach } from 'vitest';
+import { runRalphWiggum } from './ralphWiggum.js';
+import * as nonInteractiveCli from './nonInteractiveCli.js';
+import fs from 'node:fs';
+import type { Config, ResumedSessionData } from '@google/gemini-cli-core';
+import type { LoadedSettings } from './config/settings.js';
+
+// Mock dependencies
+vi.mock('node:fs');
+vi.mock('./nonInteractiveCli.js');
+
+describe('runRalphWiggum', () => {
+  const mockConfig = {} as unknown as Config;
+  const mockSettings = {} as unknown as LoadedSettings;
+  const mockInput = 'Fix bugs';
+  const mockPromptId = 'prompt-123';
+  const mockResumedSessionData = {
+    conversation: { messages: [], sessionId: 'session-123' },
+    filePath: 'session.json',
+  } as unknown as ResumedSessionData;
+
+  beforeEach(() => {
+    vi.resetAllMocks();
+    // Default mock implementation for fs
+    vi.mocked(fs.existsSync).mockReturnValue(false);
+    vi.mocked(fs.writeFileSync).mockReturnValue(undefined);
+    vi.mocked(fs.readFileSync).mockReturnValue('');
+  });
+
+  it('should preserve resumedSessionData in second iteration', async () => {
+    // Setup runNonInteractive to return "Failed" first, then "Success"
+    const runNonInteractiveMock = vi.mocked(
+      nonInteractiveCli.runNonInteractive,
+    );
+    runNonInteractiveMock
+      .mockResolvedValueOnce('Test failed')
+      .mockResolvedValueOnce('Test Success');
+
+    await runRalphWiggum({
+      config: mockConfig,
+      settings: mockSettings,
+      input: mockInput,
+      prompt_id: mockPromptId,
+      resumedSessionData: mockResumedSessionData,
+      completionPromise: 'Success',
+      maxIterations: 2,
+    });
+
+    expect(runNonInteractiveMock).toHaveBeenCalledTimes(2);
+
+    // First call should have resumedSessionData
+    expect(runNonInteractiveMock.mock.calls[0][0].resumedSessionData).toBe(
+      mockResumedSessionData,
+    );
+
+    // Second call should have resumedSessionData (FIXED)
+    expect(runNonInteractiveMock.mock.calls[1][0].resumedSessionData).toBe(
+      mockResumedSessionData,
+    );
+  });
+});

packages/cli/src/ralphWiggum.ts

@@ -0,0 +1,180 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import fs from 'node:fs';
+import path from 'node:path';
+import {
+  runNonInteractive,
+  type RunNonInteractiveParams,
+} from './nonInteractiveCli.js';
+
+interface IterationResult {
+  iteration: number;
+  status: 'Success' | 'Failed';
+  testsPassed?: number;
+  testsFailed?: number;
+  testsTotal?: number;
+}
+
+function extractTestStats(output: string): {
+  passed?: number;
+  failed?: number;
+  total?: number;
+} {
+  // Common patterns for test runners (Vitest, Jest, Mocha, etc.)
+  const patterns = [
+    // Vitest/Jest: "Tests:       3 passed, 1 failed, 4 total"
+    /Tests:\s*(?:(\d+)\s+passed)?(?:,\s*)?(?:(\d+)\s+failed)?(?:,\s*)?(?:(\d+)\s+total)?/i,
+    // Mocha: "3 passing (10ms)"
+    /(\d+)\s+passing/i,
+    // Mocha: "1 failing"
+    /(\d+)\s+failing/i,
+    // Generic: "Passed: 3, Failed: 1"
+    /Passed:\s*(\d+)/i,
+    /Failed:\s*(\d+)/i,
+  ];
+
+  let passed: number | undefined;
+  let failed: number | undefined;
+  let total: number | undefined;
+
+  // Try Vitest/Jest pattern first as it is most comprehensive
+  const vitestMatch = output.match(patterns[0]);
+  if (vitestMatch && (vitestMatch[1] || vitestMatch[2] || vitestMatch[3])) {
+    passed = vitestMatch[1] ? parseInt(vitestMatch[1], 10) : 0;
+    failed = vitestMatch[2] ? parseInt(vitestMatch[2], 10) : 0;
+    total = vitestMatch[3] ? parseInt(vitestMatch[3], 10) : 0;
+    return { passed, failed, total };
+  }
+
+  // Fallback to individual patterns
+  const passingMatch = output.match(patterns[1]);
+  if (passingMatch) {
+    passed = parseInt(passingMatch[1], 10);
+  } else {
+    const passedMatch = output.match(patterns[3]);
+    if (passedMatch) passed = parseInt(passedMatch[1], 10);
+  }
+
+  const failingMatch = output.match(patterns[2]);
+  if (failingMatch) {
+    failed = parseInt(failingMatch[1], 10);
+  } else {
+    const failedMatch = output.match(patterns[4]);
+    if (failedMatch) failed = parseInt(failedMatch[1], 10);
+  }
+
+  return { passed, failed, total };
+}
+
+function printSummary(results: IterationResult[]) {
+  process.stderr.write('\n--- Ralph Wiggum Mode Summary ---\n');
+  process.stderr.write(
+    '| Iteration | Status  | Tests Passed | Tests Failed |\n',
+  );
+  process.stderr.write(
+    '|-----------|---------|--------------|--------------|\n',
+  );
+  for (const result of results) {
+    const passed = result.testsPassed !== undefined ? result.testsPassed : '-';
+    const failed = result.testsFailed !== undefined ? result.testsFailed : '-';
+    process.stderr.write(
+      `| ${result.iteration.toString().padEnd(9)} | ${result.status.padEnd(7)} | ${passed.toString().padEnd(12)} | ${failed.toString().padEnd(12)} |\n`,
+    );
+  }
+  process.stderr.write('---------------------------------\n\n');
+}
+
+export async function runRalphWiggum({
+  config,
+  settings,
+  input,
+  prompt_id,
+  resumedSessionData,
+  completionPromise,
+  maxIterations,
+  memoryFile,
+}: RunNonInteractiveParams & {
+  completionPromise?: string;
+  maxIterations?: number;
+  memoryFile?: string;
+}): Promise<void> {
+  const effectiveMaxIterations = maxIterations ?? 10;
+  let iterations = 0;
+  const currentResumedSessionData = resumedSessionData;
+  const results: IterationResult[] = [];
+  const effectiveMemoryFile = memoryFile || 'memories.md';
+  const memoriesPath = path.join(process.cwd(), effectiveMemoryFile);
+
+  if (!fs.existsSync(memoriesPath)) {
+    fs.writeFileSync(
+      memoriesPath,
+      `# Ralph Wiggum Memories\n\nTask: ${input}\n\nUse this file (${effectiveMemoryFile}) to store notes on what worked and what didn't work across iterations. The agent will read this at the start of each run.\n\n`,
+    );
+  }
+
+  process.stderr.write(
+    `[Ralph Wiggum] Starting loop. Max iterations: ${effectiveMaxIterations}\n`,
+  );
+
+  while (iterations < effectiveMaxIterations) {
+    iterations++;
+    process.stderr.write(
+      `[Ralph Wiggum] Iteration ${iterations}/${effectiveMaxIterations}\n`,
+    );
+
+    let currentInput = input;
+    try {
+      if (fs.existsSync(memoriesPath)) {
+        const memories = fs.readFileSync(memoriesPath, 'utf-8');
+        if (memories.trim()) {
+          currentInput = `Context from previous iterations (${effectiveMemoryFile}):\n${memories}\n\nTask:\n${input}`;
+          process.stderr.write(
+            `[Ralph Wiggum] Loaded context from ${effectiveMemoryFile}\n`,
+          );
+        }
+      }
+    } catch (error) {
+      process.stderr.write(
+        `[Ralph Wiggum] Failed to read ${effectiveMemoryFile}: ${error}\n`,
+      );
+    }
+
+    const output = await runNonInteractive({
+      config,
+      settings,
+      input: currentInput,
+      prompt_id,
+      resumedSessionData: currentResumedSessionData,
+    });
+
+    const stats = extractTestStats(output);
+    const success =
+      completionPromise && output.includes(completionPromise) ? true : false;
+
+    results.push({
+      iteration: iterations,
+      status: success ? 'Success' : 'Failed',
+      testsPassed: stats.passed,
+      testsFailed: stats.failed,
+      testsTotal: stats.total,
+    });
+
+    if (success) {
+      process.stderr.write(
+        `[Ralph Wiggum] Completion promise "${completionPromise}" met. Exiting.\n`,
+      );
+      printSummary(results);
+      return;
+    }
+
+    // currentResumedSessionData = undefined; // Fixed: Keep resumedSessionData for subsequent iterations
+  }
+  process.stderr.write(
+    `[Ralph Wiggum] Max iterations reached without meeting completion promise.\n`,
+  );
+  printSummary(results);
+}

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

@@ -98,6 +98,17 @@ vi.mock('../ui/commands/toolsCommand.js', () => ({ toolsCommand: {} }));
 vi.mock('../ui/commands/skillsCommand.js', () => ({
   skillsCommand: { name: 'skills' },
 }));
+vi.mock('../ui/commands/planCommand.js', async () => {
+  const { CommandKind } = await import('../ui/commands/types.js');
+  return {
+    planCommand: {
+      name: 'plan',
+      description: 'Plan command',
+      kind: CommandKind.BUILT_IN,
+    },
+  };
+});
+
 vi.mock('../ui/commands/mcpCommand.js', () => ({
   mcpCommand: {
     name: 'mcp',
@@ -115,6 +126,7 @@ describe('BuiltinCommandLoader', () => {
     vi.clearAllMocks();
     mockConfig = {
       getFolderTrust: vi.fn().mockReturnValue(true),
+      isPlanEnabled: vi.fn().mockReturnValue(false),
       getEnableExtensionReloading: () => false,
       getEnableHooks: () => false,
       getEnableHooksUI: () => false,
@@ -216,6 +228,22 @@ describe('BuiltinCommandLoader', () => {
     expect(agentsCmd).toBeDefined();
   });
 
+  it('should include plan command when plan mode is enabled', async () => {
+    (mockConfig.isPlanEnabled as Mock).mockReturnValue(true);
+    const loader = new BuiltinCommandLoader(mockConfig);
+    const commands = await loader.loadCommands(new AbortController().signal);
+    const planCmd = commands.find((c) => c.name === 'plan');
+    expect(planCmd).toBeDefined();
+  });
+
+  it('should exclude plan command when plan mode is disabled', async () => {
+    (mockConfig.isPlanEnabled as Mock).mockReturnValue(false);
+    const loader = new BuiltinCommandLoader(mockConfig);
+    const commands = await loader.loadCommands(new AbortController().signal);
+    const planCmd = commands.find((c) => c.name === 'plan');
+    expect(planCmd).toBeUndefined();
+  });
+
   it('should exclude agents command when agents are disabled', async () => {
     mockConfig.isAgentsEnabled = vi.fn().mockReturnValue(false);
     const loader = new BuiltinCommandLoader(mockConfig);
@@ -256,6 +284,7 @@ describe('BuiltinCommandLoader profile', () => {
     vi.resetModules();
     mockConfig = {
       getFolderTrust: vi.fn().mockReturnValue(false),
+      isPlanEnabled: vi.fn().mockReturnValue(false),
       getCheckpointingEnabled: () => false,
       getEnableExtensionReloading: () => false,
       getEnableHooks: () => false,

packages/cli/src/services/BuiltinCommandLoader.ts

@@ -12,7 +12,11 @@ import {
   type CommandContext,
 } from '../ui/commands/types.js';
 import type { MessageActionReturn, Config } from '@google/gemini-cli-core';
-import { isNightly, startupProfiler } from '@google/gemini-cli-core';
+import {
+  isNightly,
+  startupProfiler,
+  getAdminErrorMessage,
+} from '@google/gemini-cli-core';
 import { aboutCommand } from '../ui/commands/aboutCommand.js';
 import { agentsCommand } from '../ui/commands/agentsCommand.js';
 import { authCommand } from '../ui/commands/authCommand.js';
@@ -36,8 +40,9 @@ import { memoryCommand } from '../ui/commands/memoryCommand.js';
 import { modelCommand } from '../ui/commands/modelCommand.js';
 import { oncallCommand } from '../ui/commands/oncallCommand.js';
 import { permissionsCommand } from '../ui/commands/permissionsCommand.js';
-import { privacyCommand } from '../ui/commands/privacyCommand.js';
+import { planCommand } from '../ui/commands/planCommand.js';
 import { policiesCommand } from '../ui/commands/policiesCommand.js';
+import { privacyCommand } from '../ui/commands/privacyCommand.js';
 import { profileCommand } from '../ui/commands/profileCommand.js';
 import { quitCommand } from '../ui/commands/quitCommand.js';
 import { restoreCommand } from '../ui/commands/restoreCommand.js';
@@ -47,6 +52,7 @@ import { themeCommand } from '../ui/commands/themeCommand.js';
 import { toolsCommand } from '../ui/commands/toolsCommand.js';
 import { skillsCommand } from '../ui/commands/skillsCommand.js';
 import { settingsCommand } from '../ui/commands/settingsCommand.js';
+import { shellsCommand } from '../ui/commands/shellsCommand.js';
 import { vimCommand } from '../ui/commands/vimCommand.js';
 import { setupGithubCommand } from '../ui/commands/setupGithubCommand.js';
 import { terminalSetupCommand } from '../ui/commands/terminalSetupCommand.js';
@@ -101,7 +107,10 @@ export class BuiltinCommandLoader implements ICommandLoader {
               ): Promise<MessageActionReturn> => ({
                 type: 'message',
                 messageType: 'error',
-                content: 'Extensions are disabled by your admin.',
+                content: getAdminErrorMessage(
+                  'Extensions',
+                  this.config ?? undefined,
+                ),
               }),
             },
           ]
@@ -126,7 +135,7 @@ export class BuiltinCommandLoader implements ICommandLoader {
               ): Promise<MessageActionReturn> => ({
                 type: 'message',
                 messageType: 'error',
-                content: 'MCP is disabled by your admin.',
+                content: getAdminErrorMessage('MCP', this.config ?? undefined),
               }),
             },
           ]
@@ -134,8 +143,9 @@ export class BuiltinCommandLoader implements ICommandLoader {
       memoryCommand,
       modelCommand,
       ...(this.config?.getFolderTrust() ? [permissionsCommand] : []),
-      privacyCommand,
+      ...(this.config?.isPlanEnabled() ? [planCommand] : []),
       policiesCommand,
+      privacyCommand,
       ...(isDevelopment ? [profileCommand] : []),
       quitCommand,
       restoreCommand(this.config),
@@ -157,13 +167,17 @@ export class BuiltinCommandLoader implements ICommandLoader {
                 ): Promise<MessageActionReturn> => ({
                   type: 'message',
                   messageType: 'error',
-                  content: 'Agent skills are disabled by your admin.',
+                  content: getAdminErrorMessage(
+                    'Agent skills',
+                    this.config ?? undefined,
+                  ),
                 }),
               },
             ]
           : [skillsCommand]
         : []),
       settingsCommand,
+      shellsCommand,
       vimCommand,
       setupGithubCommand,
       terminalSetupCommand,

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

@@ -0,0 +1,178 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { vi } from 'vitest';
+import type { Config } from '@google/gemini-cli-core';
+import type { LoadedSettings, Settings } from '../config/settings.js';
+import { createTestMergedSettings } from '../config/settings.js';
+
+/**
+ * Creates a mocked Config object with default values and allows overrides.
+ */
+export const createMockConfig = (overrides: Partial<Config> = {}): Config =>
+  ({
+    getSandbox: vi.fn(() => undefined),
+    getQuestion: vi.fn(() => ''),
+    isInteractive: vi.fn(() => false),
+    setTerminalBackground: vi.fn(),
+    storage: {
+      getProjectTempDir: vi.fn().mockReturnValue('/tmp/gemini-test'),
+    },
+    getDebugMode: vi.fn(() => false),
+    getProjectRoot: vi.fn(() => '/'),
+    refreshAuth: vi.fn().mockResolvedValue(undefined),
+    getRemoteAdminSettings: vi.fn(() => undefined),
+    initialize: vi.fn().mockResolvedValue(undefined),
+    getPolicyEngine: vi.fn(() => ({})),
+    getMessageBus: vi.fn(() => ({ subscribe: vi.fn() })),
+    getHookSystem: vi.fn(() => ({
+      fireSessionEndEvent: vi.fn().mockResolvedValue(undefined),
+      fireSessionStartEvent: vi.fn().mockResolvedValue(undefined),
+    })),
+    getListExtensions: vi.fn(() => false),
+    getExtensions: vi.fn(() => []),
+    getListSessions: vi.fn(() => false),
+    getDeleteSession: vi.fn(() => undefined),
+    setSessionId: vi.fn(),
+    getSessionId: vi.fn().mockReturnValue('mock-session-id'),
+    getContentGeneratorConfig: vi.fn(() => ({ authType: 'google' })),
+    getExperimentalZedIntegration: vi.fn(() => false),
+    isBrowserLaunchSuppressed: vi.fn(() => false),
+    setRemoteAdminSettings: vi.fn(),
+    isYoloModeDisabled: vi.fn(() => false),
+    isPlanEnabled: vi.fn(() => false),
+    isEventDrivenSchedulerEnabled: vi.fn(() => false),
+    getCoreTools: vi.fn(() => []),
+    getAllowedTools: vi.fn(() => []),
+    getApprovalMode: vi.fn(() => 'default'),
+    getFileFilteringRespectGitIgnore: vi.fn(() => true),
+    getOutputFormat: vi.fn(() => 'text'),
+    getUsageStatisticsEnabled: vi.fn(() => true),
+    getScreenReader: vi.fn(() => false),
+    getGeminiMdFileCount: vi.fn(() => 0),
+    getDeferredCommand: vi.fn(() => undefined),
+    getFileSystemService: vi.fn(() => ({})),
+    clientVersion: '1.0.0',
+    getModel: vi.fn().mockReturnValue('gemini-pro'),
+    getWorkingDir: vi.fn().mockReturnValue('/mock/cwd'),
+    getToolRegistry: vi.fn().mockReturnValue({
+      getTools: vi.fn().mockReturnValue([]),
+      getAllTools: vi.fn().mockReturnValue([]),
+    }),
+    getAgentRegistry: vi.fn().mockReturnValue({}),
+    getPromptRegistry: vi.fn().mockReturnValue({}),
+    getResourceRegistry: vi.fn().mockReturnValue({}),
+    getSkillManager: vi.fn().mockReturnValue({
+      isAdminEnabled: vi.fn().mockReturnValue(false),
+    }),
+    getFileService: vi.fn().mockReturnValue({}),
+    getGitService: vi.fn().mockResolvedValue({}),
+    getUserMemory: vi.fn().mockReturnValue(''),
+    getGeminiMdFilePaths: vi.fn().mockReturnValue([]),
+    getShowMemoryUsage: vi.fn().mockReturnValue(false),
+    getAccessibility: vi.fn().mockReturnValue({}),
+    getTelemetryEnabled: vi.fn().mockReturnValue(false),
+    getTelemetryLogPromptsEnabled: vi.fn().mockReturnValue(false),
+    getTelemetryOtlpEndpoint: vi.fn().mockReturnValue(''),
+    getTelemetryOtlpProtocol: vi.fn().mockReturnValue('grpc'),
+    getTelemetryTarget: vi.fn().mockReturnValue(''),
+    getTelemetryOutfile: vi.fn().mockReturnValue(undefined),
+    getTelemetryUseCollector: vi.fn().mockReturnValue(false),
+    getTelemetryUseCliAuth: vi.fn().mockReturnValue(false),
+    getGeminiClient: vi.fn().mockReturnValue({
+      isInitialized: vi.fn().mockReturnValue(true),
+    }),
+    updateSystemInstructionIfInitialized: vi.fn().mockResolvedValue(undefined),
+    getModelRouterService: vi.fn().mockReturnValue({}),
+    getModelAvailabilityService: vi.fn().mockReturnValue({}),
+    getEnableRecursiveFileSearch: vi.fn().mockReturnValue(true),
+    getFileFilteringEnableFuzzySearch: vi.fn().mockReturnValue(true),
+    getFileFilteringRespectGeminiIgnore: vi.fn().mockReturnValue(true),
+    getFileFilteringOptions: vi.fn().mockReturnValue({}),
+    getCustomExcludes: vi.fn().mockReturnValue([]),
+    getCheckpointingEnabled: vi.fn().mockReturnValue(false),
+    getProxy: vi.fn().mockReturnValue(undefined),
+    getBugCommand: vi.fn().mockReturnValue(undefined),
+    getExtensionManagement: vi.fn().mockReturnValue(true),
+    getExtensionLoader: vi.fn().mockReturnValue({}),
+    getEnabledExtensions: vi.fn().mockReturnValue([]),
+    getEnableExtensionReloading: vi.fn().mockReturnValue(false),
+    getDisableLLMCorrection: vi.fn().mockReturnValue(false),
+    getNoBrowser: vi.fn().mockReturnValue(false),
+    getAgentsSettings: vi.fn().mockReturnValue({}),
+    getSummarizeToolOutputConfig: vi.fn().mockReturnValue(undefined),
+    getIdeMode: vi.fn().mockReturnValue(false),
+    getFolderTrust: vi.fn().mockReturnValue(true),
+    isTrustedFolder: vi.fn().mockReturnValue(true),
+    getCompressionThreshold: vi.fn().mockResolvedValue(undefined),
+    getUserCaching: vi.fn().mockResolvedValue(false),
+    getNumericalRoutingEnabled: vi.fn().mockResolvedValue(false),
+    getClassifierThreshold: vi.fn().mockResolvedValue(undefined),
+    getBannerTextNoCapacityIssues: vi.fn().mockResolvedValue(''),
+    getBannerTextCapacityIssues: vi.fn().mockResolvedValue(''),
+    isInteractiveShellEnabled: vi.fn().mockReturnValue(false),
+    isSkillsSupportEnabled: vi.fn().mockReturnValue(false),
+    reloadSkills: vi.fn().mockResolvedValue(undefined),
+    reloadAgents: vi.fn().mockResolvedValue(undefined),
+    getUseRipgrep: vi.fn().mockReturnValue(false),
+    getEnableInteractiveShell: vi.fn().mockReturnValue(false),
+    getSkipNextSpeakerCheck: vi.fn().mockReturnValue(false),
+    getContinueOnFailedApiCall: vi.fn().mockReturnValue(false),
+    getRetryFetchErrors: vi.fn().mockReturnValue(false),
+    getEnableShellOutputEfficiency: vi.fn().mockReturnValue(true),
+    getShellToolInactivityTimeout: vi.fn().mockReturnValue(300000),
+    getShellExecutionConfig: vi.fn().mockReturnValue({}),
+    setShellExecutionConfig: vi.fn(),
+    getEnablePromptCompletion: vi.fn().mockReturnValue(false),
+    getEnableToolOutputTruncation: vi.fn().mockReturnValue(true),
+    getTruncateToolOutputThreshold: vi.fn().mockReturnValue(1000),
+    getTruncateToolOutputLines: vi.fn().mockReturnValue(100),
+    getNextCompressionTruncationId: vi.fn().mockReturnValue(1),
+    getUseWriteTodos: vi.fn().mockReturnValue(false),
+    getFileExclusions: vi.fn().mockReturnValue({}),
+    getEnableHooks: vi.fn().mockReturnValue(true),
+    getEnableHooksUI: vi.fn().mockReturnValue(true),
+    getMcpClientManager: vi.fn().mockReturnValue({
+      getMcpInstructions: vi.fn().mockReturnValue(''),
+      getMcpServers: vi.fn().mockReturnValue({}),
+    }),
+    getEnableEventDrivenScheduler: vi.fn().mockReturnValue(false),
+    getAdminSkillsEnabled: vi.fn().mockReturnValue(false),
+    getDisabledSkills: vi.fn().mockReturnValue([]),
+    getExperimentalJitContext: vi.fn().mockReturnValue(false),
+    getTerminalBackground: vi.fn().mockReturnValue(undefined),
+    getEmbeddingModel: vi.fn().mockReturnValue('embedding-model'),
+    getQuotaErrorOccurred: vi.fn().mockReturnValue(false),
+    getMaxSessionTurns: vi.fn().mockReturnValue(100),
+    getExcludeTools: vi.fn().mockReturnValue(new Set()),
+    getAllowedMcpServers: vi.fn().mockReturnValue([]),
+    getBlockedMcpServers: vi.fn().mockReturnValue([]),
+    getExperiments: vi.fn().mockReturnValue(undefined),
+    getPreviewFeatures: vi.fn().mockReturnValue(false),
+    getHasAccessToPreviewModel: vi.fn().mockReturnValue(false),
+    ...overrides,
+  }) as unknown as Config;
+
+/**
+ * Creates a mocked LoadedSettings object for tests.
+ */
+export function createMockSettings(
+  overrides: Record<string, unknown> = {},
+): LoadedSettings {
+  const merged = createTestMergedSettings(
+    (overrides['merged'] as Partial<Settings>) || {},
+  );
+
+  return {
+    system: { settings: {} },
+    systemDefaults: { settings: {} },
+    user: { settings: {} },
+    workspace: { settings: {} },
+    errors: [],
+    ...overrides,
+    merged,
+  } as unknown as LoadedSettings;
+}

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

@@ -10,7 +10,7 @@ import type React from 'react';
 import { vi } from 'vitest';
 import { act, useState } from 'react';
 import os from 'node:os';
-import { LoadedSettings, type Settings } from '../config/settings.js';
+import { LoadedSettings } from '../config/settings.js';
 import { KeypressProvider } from '../ui/contexts/KeypressContext.js';
 import { SettingsContext } from '../ui/contexts/SettingsContext.js';
 import { ShellFocusContext } from '../ui/contexts/ShellFocusContext.js';
@@ -27,10 +27,12 @@ import {
 import { type HistoryItemToolGroup, StreamingState } from '../ui/types.js';
 import { ToolActionsProvider } from '../ui/contexts/ToolActionsContext.js';
 import { AskUserActionsProvider } from '../ui/contexts/AskUserActionsContext.js';
+import { TerminalProvider } from '../ui/contexts/TerminalContext.js';
 
 import { makeFakeConfig, type Config } from '@google/gemini-cli-core';
 import { FakePersistentState } from './persistentStateFake.js';
 import { AppContext, type AppState } from '../ui/contexts/AppContext.js';
+import { createMockSettings } from './settings.js';
 
 export const persistentStateMock = new FakePersistentState();
 
@@ -134,20 +136,6 @@ export const mockSettings = new LoadedSettings(
   [],
 );
 
-export const createMockSettings = (
-  overrides: Partial<Settings>,
-): LoadedSettings => {
-  const settings = overrides as Settings;
-  return new LoadedSettings(
-    { path: '', settings: {}, originalSettings: {} },
-    { path: '', settings: {}, originalSettings: {} },
-    { path: '', settings, originalSettings: settings },
-    { path: '', settings: {}, originalSettings: {} },
-    true,
-    [],
-  );
-};
-
 // A minimal mock UIState to satisfy the context provider.
 // Tests that need specific UIState values should provide their own.
 const baseMockUiState = {
@@ -157,6 +145,9 @@ const baseMockUiState = {
   terminalHeight: 40,
   currentModel: 'gemini-pro',
   terminalBackgroundColor: undefined,
+  activePtyId: undefined,
+  backgroundShells: new Map(),
+  backgroundShellHeight: 0,
 };
 
 export const mockAppState: AppState = {
@@ -201,7 +192,11 @@ const mockUIActions: UIActions = {
   handleApiKeyCancel: vi.fn(),
   setBannerVisible: vi.fn(),
   setEmbeddedShellFocused: vi.fn(),
+  dismissBackgroundShell: vi.fn(),
+  setActiveBackgroundShellPid: vi.fn(),
+  setIsBackgroundShellListOpen: vi.fn(),
   setAuthContext: vi.fn(),
+  handleWarning: vi.fn(),
   handleRestart: vi.fn(),
   handleNewAgentsSelect: vi.fn(),
 };
@@ -310,16 +305,18 @@ export const renderWithProviders = (
                           <MouseProvider
                             mouseEventsEnabled={mouseEventsEnabled}
                           >
-                            <ScrollProvider>
-                              <Box
-                                width={terminalWidth}
-                                flexShrink={0}
-                                flexGrow={0}
-                                flexDirection="column"
-                              >
-                                {component}
-                              </Box>
-                            </ScrollProvider>
+                            <TerminalProvider>
+                              <ScrollProvider>
+                                <Box
+                                  width={terminalWidth}
+                                  flexShrink={0}
+                                  flexGrow={0}
+                                  flexDirection="column"
+                                >
+                                  {component}
+                                </Box>
+                              </ScrollProvider>
+                            </TerminalProvider>
                           </MouseProvider>
                         </KeypressProvider>
                       </AskUserActionsProvider>

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

@@ -0,0 +1,79 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+/* eslint-disable @typescript-eslint/no-explicit-any */
+
+import {
+  LoadedSettings,
+  createTestMergedSettings,
+  type SettingsError,
+} from '../config/settings.js';
+
+export interface MockSettingsFile {
+  settings: any;
+  originalSettings: any;
+  path: string;
+}
+
+interface CreateMockSettingsOptions {
+  system?: MockSettingsFile;
+  systemDefaults?: MockSettingsFile;
+  user?: MockSettingsFile;
+  workspace?: MockSettingsFile;
+  isTrusted?: boolean;
+  errors?: SettingsError[];
+  merged?: any;
+  [key: string]: any;
+}
+
+/**
+ * Creates a mock LoadedSettings object for testing.
+ *
+ * @param overrides - Partial settings or LoadedSettings properties to override.
+ *                   If 'merged' is provided, it overrides the computed merged settings.
+ *                   Any functions in overrides are assigned directly to the LoadedSettings instance.
+ */
+export const createMockSettings = (
+  overrides: CreateMockSettingsOptions = {},
+): LoadedSettings => {
+  const {
+    system,
+    systemDefaults,
+    user,
+    workspace,
+    isTrusted,
+    errors,
+    merged: mergedOverride,
+    ...settingsOverrides
+  } = overrides;
+
+  const loaded = new LoadedSettings(
+    (system as any) || { path: '', settings: {}, originalSettings: {} },
+    (systemDefaults as any) || { path: '', settings: {}, originalSettings: {} },
+    (user as any) || {
+      path: '',
+      settings: settingsOverrides,
+      originalSettings: settingsOverrides,
+    },
+    (workspace as any) || { path: '', settings: {}, originalSettings: {} },
+    isTrusted ?? true,
+    errors || [],
+  );
+
+  if (mergedOverride) {
+    // @ts-expect-error - overriding private field for testing
+    loaded._merged = createTestMergedSettings(mergedOverride);
+  }
+
+  // Assign any function overrides (e.g., vi.fn() for methods)
+  for (const key in overrides) {
+    if (typeof overrides[key] === 'function') {
+      (loaded as any)[key] = overrides[key];
+    }
+  }
+
+  return loaded;
+};

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

@@ -88,6 +88,7 @@ describe('App', () => {
       defaultText: 'Mock Banner Text',
       warningText: '',
     },
+    backgroundShells: new Map(),
   };
 
   it('should render main content and composer when not quitting', () => {
@@ -234,7 +235,6 @@ describe('App', () => {
     expect(lastFrame()).toContain('Tips for getting started');
     expect(lastFrame()).toContain('Notifications');
     expect(lastFrame()).toContain('Action Required'); // From ToolConfirmationQueue
-    expect(lastFrame()).toContain('1 of 1');
     expect(lastFrame()).toContain('Composer');
     expect(lastFrame()).toMatchSnapshot();
   });

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

@@ -21,7 +21,6 @@ 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 { MessageType } from './types.js';
 import {
   type Config,
   makeFakeConfig,
@@ -29,16 +28,8 @@ import {
   type UserFeedbackPayload,
   type ResumedSessionData,
   AuthType,
-  UserAccountManager,
-  type ContentGeneratorConfig,
   type AgentDefinition,
-  MessageBusType,
-  QuestionType,
 } from '@google/gemini-cli-core';
-import {
-  AskUserActionsContext,
-  type AskUserState,
-} from './contexts/AskUserActionsContext.js';
 
 // Mock coreEvents
 const mockCoreEvents = vi.hoisted(() => ({
@@ -53,11 +44,6 @@ const mockIdeClient = vi.hoisted(() => ({
   getInstance: vi.fn().mockReturnValue(new Promise(() => {})),
 }));
 
-// Mock UserAccountManager
-const mockUserAccountManager = vi.hoisted(() => ({
-  getCachedGoogleAccount: vi.fn().mockReturnValue(null),
-}));
-
 // Mock stdout
 const mocks = vi.hoisted(() => ({
   mockStdout: { write: vi.fn() },
@@ -87,9 +73,6 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
     })),
     enableMouseEvents: vi.fn(),
     disableMouseEvents: vi.fn(),
-    UserAccountManager: vi
-      .fn()
-      .mockImplementation(() => mockUserAccountManager),
     FileDiscoveryService: vi.fn().mockImplementation(() => ({
       initialize: vi.fn(),
     })),
@@ -124,11 +107,9 @@ vi.mock('ink', async (importOriginal) => {
 // so we can assert against them in our tests.
 let capturedUIState: UIState;
 let capturedUIActions: UIActions;
-let capturedAskUserRequest: AskUserState | null;
 function TestContextConsumer() {
   capturedUIState = useContext(UIStateContext)!;
   capturedUIActions = useContext(UIActionsContext)!;
-  capturedAskUserRequest = useContext(AskUserActionsContext)?.request ?? null;
   return null;
 }
 
@@ -165,6 +146,12 @@ vi.mock('./components/shared/text-buffer.js');
 vi.mock('./hooks/useLogger.js');
 vi.mock('./hooks/useInputHistoryStore.js');
 vi.mock('./hooks/useHookDisplayState.js');
+vi.mock('./hooks/useTerminalTheme.js', () => ({
+  useTerminalTheme: vi.fn(),
+}));
+
+import { useHookDisplayState } from './hooks/useHookDisplayState.js';
+import { useTerminalTheme } from './hooks/useTerminalTheme.js';
 
 // Mock external utilities
 vi.mock('../utils/events.js');
@@ -193,7 +180,6 @@ import { useTextBuffer } from './components/shared/text-buffer.js';
 import { useLogger } from './hooks/useLogger.js';
 import { useLoadingIndicator } from './hooks/useLoadingIndicator.js';
 import { useInputHistoryStore } from './hooks/useInputHistoryStore.js';
-import { useHookDisplayState } from './hooks/useHookDisplayState.js';
 import { useKeypress, type Key } from './hooks/useKeypress.js';
 import { measureElement } from 'ink';
 import { useTerminalSize } from './hooks/useTerminalSize.js';
@@ -268,6 +254,26 @@ describe('AppContainer State Management', () => {
   const mockedUseKeypress = useKeypress as Mock;
   const mockedUseInputHistoryStore = useInputHistoryStore as Mock;
   const mockedUseHookDisplayState = useHookDisplayState as Mock;
+  const mockedUseTerminalTheme = useTerminalTheme as Mock;
+
+  const DEFAULT_GEMINI_STREAM_MOCK = {
+    streamingState: 'idle',
+    submitQuery: vi.fn(),
+    initError: null,
+    pendingHistoryItems: [],
+    thought: null,
+    cancelOngoingRequest: vi.fn(),
+    handleApprovalModeChange: vi.fn(),
+    activePtyId: null,
+    loopDetectionConfirmationRequest: null,
+    backgroundShellCount: 0,
+    isBackgroundShellVisible: false,
+    toggleBackgroundShell: vi.fn(),
+    backgroundCurrentShell: vi.fn(),
+    backgroundShells: new Map(),
+    registerBackgroundShell: vi.fn(),
+    dismissBackgroundShell: vi.fn(),
+  };
 
   beforeEach(() => {
     vi.clearAllMocks();
@@ -279,7 +285,6 @@ describe('AppContainer State Management', () => {
     mocks.mockStdout.write.mockClear();
 
     capturedUIState = null!;
-    capturedAskUserRequest = null;
 
     // **Provide a default return value for EVERY mocked hook.**
     mockedUseQuotaAndFallback.mockReturnValue({
@@ -334,14 +339,7 @@ describe('AppContainer State Management', () => {
       handleNewMessage: vi.fn(),
       clearConsoleMessages: vi.fn(),
     });
-    mockedUseGeminiStream.mockReturnValue({
-      streamingState: 'idle',
-      submitQuery: vi.fn(),
-      initError: null,
-      pendingHistoryItems: [],
-      thought: null,
-      cancelOngoingRequest: vi.fn(),
-    });
+    mockedUseGeminiStream.mockReturnValue(DEFAULT_GEMINI_STREAM_MOCK);
     mockedUseVim.mockReturnValue({ handleInput: vi.fn() });
     mockedUseFolderTrust.mockReturnValue({
       isFolderTrustDialogOpen: false,
@@ -368,7 +366,9 @@ describe('AppContainer State Management', () => {
     mockedUseTextBuffer.mockReturnValue({
       text: '',
       setText: vi.fn(),
-      // Add other properties if AppContainer uses them
+      lines: [''],
+      cursor: [0, 0],
+      handleInput: vi.fn().mockReturnValue(false),
     });
     mockedUseLogger.mockReturnValue({
       getPreviousUserMessages: vi.fn().mockResolvedValue([]),
@@ -383,6 +383,7 @@ describe('AppContainer State Management', () => {
       currentLoadingPhrase: '',
     });
     mockedUseHookDisplayState.mockReturnValue([]);
+    mockedUseTerminalTheme.mockReturnValue(undefined);
 
     // Mock Config
     mockConfig = makeFakeConfig();
@@ -416,7 +417,6 @@ describe('AppContainer State Management', () => {
           ...defaultMergedSettings.ui,
           showStatusInTitle: false,
           hideWindowTitle: false,
-          showUserIdentity: true,
         },
         useAlternateBuffer: false,
       },
@@ -488,162 +488,6 @@ describe('AppContainer State Management', () => {
     });
   });
 
-  describe('Authentication Check', () => {
-    it('displays correct message for LOGIN_WITH_GOOGLE auth type', async () => {
-      // Explicitly mock implementation to ensure we control the instance
-      (UserAccountManager as unknown as Mock).mockImplementation(
-        () => mockUserAccountManager,
-      );
-
-      mockUserAccountManager.getCachedGoogleAccount.mockReturnValue(
-        'test@example.com',
-      );
-      const mockAddItem = vi.fn();
-      mockedUseHistory.mockReturnValue({
-        history: [],
-        addItem: mockAddItem,
-        updateItem: vi.fn(),
-        clearItems: vi.fn(),
-        loadHistory: vi.fn(),
-      });
-
-      // Explicitly enable showUserIdentity
-      mockSettings.merged.ui = {
-        ...mockSettings.merged.ui,
-        showUserIdentity: true,
-      };
-
-      // Need to ensure config.getContentGeneratorConfig() returns appropriate authType
-      const authConfig = makeFakeConfig();
-      // Mock getTargetDir as well since makeFakeConfig might not set it up fully for the component
-      vi.spyOn(authConfig, 'getTargetDir').mockReturnValue('/test/workspace');
-      vi.spyOn(authConfig, 'initialize').mockResolvedValue(undefined);
-      vi.spyOn(authConfig, 'getExtensionLoader').mockReturnValue(
-        mockExtensionManager,
-      );
-
-      vi.spyOn(authConfig, 'getContentGeneratorConfig').mockReturnValue({
-        authType: AuthType.LOGIN_WITH_GOOGLE,
-      } as unknown as ContentGeneratorConfig);
-      vi.spyOn(authConfig, 'getUserTierName').mockReturnValue('Standard Tier');
-
-      let unmount: () => void;
-      await act(async () => {
-        const result = renderAppContainer({ config: authConfig });
-        unmount = result.unmount;
-      });
-
-      await waitFor(() => {
-        expect(UserAccountManager).toHaveBeenCalled();
-        expect(
-          mockUserAccountManager.getCachedGoogleAccount,
-        ).toHaveBeenCalled();
-        expect(mockAddItem).toHaveBeenCalledWith(
-          expect.objectContaining({
-            text: 'Logged in with Google: test@example.com (Plan: Standard Tier)',
-          }),
-        );
-      });
-      await act(async () => {
-        unmount!();
-      });
-    });
-    it('displays correct message for USE_GEMINI auth type', async () => {
-      // Explicitly mock implementation to ensure we control the instance
-      (UserAccountManager as unknown as Mock).mockImplementation(
-        () => mockUserAccountManager,
-      );
-
-      mockUserAccountManager.getCachedGoogleAccount.mockReturnValue(null);
-      const mockAddItem = vi.fn();
-      mockedUseHistory.mockReturnValue({
-        history: [],
-        addItem: mockAddItem,
-        updateItem: vi.fn(),
-        clearItems: vi.fn(),
-        loadHistory: vi.fn(),
-      });
-
-      const authConfig = makeFakeConfig();
-      vi.spyOn(authConfig, 'getTargetDir').mockReturnValue('/test/workspace');
-      vi.spyOn(authConfig, 'initialize').mockResolvedValue(undefined);
-      vi.spyOn(authConfig, 'getExtensionLoader').mockReturnValue(
-        mockExtensionManager,
-      );
-
-      vi.spyOn(authConfig, 'getContentGeneratorConfig').mockReturnValue({
-        authType: AuthType.USE_GEMINI,
-      } as unknown as ContentGeneratorConfig);
-      vi.spyOn(authConfig, 'getUserTierName').mockReturnValue('Standard Tier');
-
-      let unmount: () => void;
-      await act(async () => {
-        const result = renderAppContainer({ config: authConfig });
-        unmount = result.unmount;
-      });
-
-      await waitFor(() => {
-        expect(mockAddItem).toHaveBeenCalledWith(
-          expect.objectContaining({
-            text: expect.stringContaining('Authenticated with gemini-api-key'),
-          }),
-        );
-      });
-      await act(async () => {
-        unmount!();
-      });
-    });
-
-    it('does not display authentication message if showUserIdentity is false', async () => {
-      mockUserAccountManager.getCachedGoogleAccount.mockReturnValue(
-        'test@example.com',
-      );
-      const mockAddItem = vi.fn();
-      mockedUseHistory.mockReturnValue({
-        history: [],
-        addItem: mockAddItem,
-        updateItem: vi.fn(),
-        clearItems: vi.fn(),
-        loadHistory: vi.fn(),
-      });
-
-      mockSettings.merged.ui = {
-        ...mockSettings.merged.ui,
-        showUserIdentity: false,
-      };
-
-      const authConfig = makeFakeConfig();
-      vi.spyOn(authConfig, 'getTargetDir').mockReturnValue('/test/workspace');
-      vi.spyOn(authConfig, 'initialize').mockResolvedValue(undefined);
-      vi.spyOn(authConfig, 'getExtensionLoader').mockReturnValue(
-        mockExtensionManager,
-      );
-
-      vi.spyOn(authConfig, 'getContentGeneratorConfig').mockReturnValue({
-        authType: AuthType.LOGIN_WITH_GOOGLE,
-      } as unknown as ContentGeneratorConfig);
-
-      let unmount: () => void;
-      await act(async () => {
-        const result = renderAppContainer({ config: authConfig });
-        unmount = result.unmount;
-      });
-
-      // Give it some time to potentially call addItem
-      await new Promise((resolve) => setTimeout(resolve, 100));
-
-      expect(mockAddItem).not.toHaveBeenCalledWith(
-        expect.objectContaining({
-          type: MessageType.INFO,
-        }),
-      );
-
-      await act(async () => {
-        unmount!();
-      });
-    });
-  });
-
   describe('Context Providers', () => {
     it('provides AppContext with correct values', async () => {
       let unmount: () => void;
@@ -1193,12 +1037,9 @@ describe('AppContainer State Management', () => {
 
       // Mock the streaming state as Active
       mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
         streamingState: 'responding',
-        submitQuery: vi.fn(),
-        initError: null,
-        pendingHistoryItems: [],
         thought: { subject: 'Some thought' },
-        cancelOngoingRequest: vi.fn(),
       });
 
       // Act: Render the container
@@ -1234,12 +1075,9 @@ describe('AppContainer State Management', () => {
 
       // Mock the streaming state
       mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
         streamingState: 'responding',
-        submitQuery: vi.fn(),
-        initError: null,
-        pendingHistoryItems: [],
         thought: { subject: 'Some thought' },
-        cancelOngoingRequest: vi.fn(),
       });
 
       // Act: Render the container
@@ -1306,12 +1144,9 @@ describe('AppContainer State Management', () => {
       // Mock the streaming state and thought
       const thoughtSubject = 'Processing request';
       mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
         streamingState: 'responding',
-        submitQuery: vi.fn(),
-        initError: null,
-        pendingHistoryItems: [],
         thought: { subject: thoughtSubject },
-        cancelOngoingRequest: vi.fn(),
       });
 
       // Act: Render the container
@@ -1347,14 +1182,7 @@ describe('AppContainer State Management', () => {
       } as unknown as LoadedSettings;
 
       // Mock the streaming state as Idle with no thought
-      mockedUseGeminiStream.mockReturnValue({
-        streamingState: 'idle',
-        submitQuery: vi.fn(),
-        initError: null,
-        pendingHistoryItems: [],
-        thought: null,
-        cancelOngoingRequest: vi.fn(),
-      });
+      mockedUseGeminiStream.mockReturnValue(DEFAULT_GEMINI_STREAM_MOCK);
 
       // Act: Render the container
       const { unmount } = renderAppContainer({
@@ -1391,12 +1219,9 @@ describe('AppContainer State Management', () => {
       // Mock the streaming state and thought
       const thoughtSubject = 'Confirm tool execution';
       mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
         streamingState: 'waiting_for_confirmation',
-        submitQuery: vi.fn(),
-        initError: null,
-        pendingHistoryItems: [],
         thought: { subject: thoughtSubject },
-        cancelOngoingRequest: vi.fn(),
       });
 
       // Act: Render the container
@@ -1448,16 +1273,11 @@ describe('AppContainer State Management', () => {
 
         // Mock an active shell pty but not focused
         mockedUseGeminiStream.mockReturnValue({
+          ...DEFAULT_GEMINI_STREAM_MOCK,
           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 + 100, // Trigger aggressive delay
           retryStatus: null,
         });
@@ -1512,12 +1332,9 @@ describe('AppContainer State Management', () => {
 
         // Mock an active shell pty with redirection active
         mockedUseGeminiStream.mockReturnValue({
+          ...DEFAULT_GEMINI_STREAM_MOCK,
           streamingState: 'responding',
-          submitQuery: vi.fn(),
-          initError: null,
-          pendingHistoryItems: [],
           thought: { subject: 'Executing shell command' },
-          cancelOngoingRequest: vi.fn(),
           pendingToolCalls: [
             {
               request: {
@@ -1527,9 +1344,7 @@ describe('AppContainer State Management', () => {
               status: 'executing',
             } as unknown as TrackedToolCall,
           ],
-          handleApprovalModeChange: vi.fn(),
           activePtyId: 'pty-1',
-          loopDetectionConfirmationRequest: null,
           lastOutputTime: startTime,
           retryStatus: null,
         });
@@ -1587,16 +1402,11 @@ describe('AppContainer State Management', () => {
 
         // Mock an active shell pty with NO output since operation started (silent)
         mockedUseGeminiStream.mockReturnValue({
+          ...DEFAULT_GEMINI_STREAM_MOCK,
           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,
         });
@@ -1643,12 +1453,9 @@ describe('AppContainer State Management', () => {
         // Mock an active shell pty but not focused
         let lastOutputTime = startTime + 1000;
         mockedUseGeminiStream.mockImplementation(() => ({
+          ...DEFAULT_GEMINI_STREAM_MOCK,
           streamingState: 'responding',
-          submitQuery: vi.fn(),
-          initError: null,
-          pendingHistoryItems: [],
           thought: { subject: 'Executing shell command' },
-          cancelOngoingRequest: vi.fn(),
           activePtyId: 'pty-1',
           lastOutputTime,
         }));
@@ -1669,12 +1476,9 @@ describe('AppContainer State Management', () => {
         // Update lastOutputTime to simulate new output
         lastOutputTime = startTime + 21000;
         mockedUseGeminiStream.mockImplementation(() => ({
+          ...DEFAULT_GEMINI_STREAM_MOCK,
           streamingState: 'responding',
-          submitQuery: vi.fn(),
-          initError: null,
-          pendingHistoryItems: [],
           thought: { subject: 'Executing shell command' },
-          cancelOngoingRequest: vi.fn(),
           activePtyId: 'pty-1',
           lastOutputTime,
         }));
@@ -1734,12 +1538,9 @@ describe('AppContainer State Management', () => {
       // Mock the streaming state and thought with a short subject
       const shortTitle = 'Short';
       mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
         streamingState: 'responding',
-        submitQuery: vi.fn(),
-        initError: null,
-        pendingHistoryItems: [],
         thought: { subject: shortTitle },
-        cancelOngoingRequest: vi.fn(),
       });
 
       // Act: Render the container
@@ -1778,12 +1579,9 @@ describe('AppContainer State Management', () => {
       // Mock the streaming state and thought
       const title = 'Test Title';
       mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
         streamingState: 'responding',
-        submitQuery: vi.fn(),
-        initError: null,
-        pendingHistoryItems: [],
         thought: { subject: title },
-        cancelOngoingRequest: vi.fn(),
       });
 
       // Act: Render the container
@@ -1821,12 +1619,8 @@ describe('AppContainer State Management', () => {
 
       // Mock the streaming state
       mockedUseGeminiStream.mockReturnValue({
+        ...DEFAULT_GEMINI_STREAM_MOCK,
         streamingState: 'responding',
-        submitQuery: vi.fn(),
-        initError: null,
-        pendingHistoryItems: [],
-        thought: null,
-        cancelOngoingRequest: vi.fn(),
       });
 
       // Act: Render the container
@@ -1928,12 +1722,7 @@ describe('AppContainer State Management', () => {
       mockedMeasureElement.mockReturnValue({ width: 80, height: 10 }); // Footer is taller than the screen
 
       mockedUseGeminiStream.mockReturnValue({
-        streamingState: 'idle',
-        submitQuery: vi.fn(),
-        initError: null,
-        pendingHistoryItems: [],
-        thought: null,
-        cancelOngoingRequest: vi.fn(),
+        ...DEFAULT_GEMINI_STREAM_MOCK,
         activePtyId: 'some-id',
       });
 
@@ -1952,7 +1741,7 @@ describe('AppContainer State Management', () => {
   });
 
   describe('Keyboard Input Handling (CTRL+C / CTRL+D)', () => {
-    let handleGlobalKeypress: (key: Key) => void;
+    let handleGlobalKeypress: (key: Key) => boolean;
     let mockHandleSlashCommand: Mock;
     let mockCancelOngoingRequest: Mock;
     let rerender: () => void;
@@ -1987,9 +1776,11 @@ describe('AppContainer State Management', () => {
 
     beforeEach(() => {
       // Capture the keypress handler from the AppContainer
-      mockedUseKeypress.mockImplementation((callback: (key: Key) => void) => {
-        handleGlobalKeypress = callback;
-      });
+      mockedUseKeypress.mockImplementation(
+        (callback: (key: Key) => boolean) => {
+          handleGlobalKeypress = callback;
+        },
+      );
 
       // Mock slash command handler
       mockHandleSlashCommand = vi.fn();
@@ -2005,11 +1796,7 @@ describe('AppContainer State Management', () => {
       // Mock request cancellation
       mockCancelOngoingRequest = vi.fn();
       mockedUseGeminiStream.mockReturnValue({
-        streamingState: 'idle',
-        submitQuery: vi.fn(),
-        initError: null,
-        pendingHistoryItems: [],
-        thought: null,
+        ...DEFAULT_GEMINI_STREAM_MOCK,
         cancelOngoingRequest: mockCancelOngoingRequest,
       });
 
@@ -2017,6 +1804,9 @@ describe('AppContainer State Management', () => {
       mockedUseTextBuffer.mockReturnValue({
         text: '',
         setText: vi.fn(),
+        lines: [''],
+        cursor: [0, 0],
+        handleInput: vi.fn().mockReturnValue(false),
       });
 
       vi.useFakeTimers();
@@ -2030,11 +1820,8 @@ describe('AppContainer State Management', () => {
     describe('CTRL+C', () => {
       it('should cancel ongoing request on first press', async () => {
         mockedUseGeminiStream.mockReturnValue({
+          ...DEFAULT_GEMINI_STREAM_MOCK,
           streamingState: 'responding',
-          submitQuery: vi.fn(),
-          initError: null,
-          pendingHistoryItems: [],
-          thought: null,
           cancelOngoingRequest: mockCancelOngoingRequest,
         });
         await setupKeypressTest();
@@ -2079,19 +1866,6 @@ describe('AppContainer State Management', () => {
     });
 
     describe('CTRL+D', () => {
-      it('should do nothing if text buffer is not empty', async () => {
-        mockedUseTextBuffer.mockReturnValue({
-          text: 'some text',
-          setText: vi.fn(),
-        });
-        await setupKeypressTest();
-
-        pressKey({ name: 'd', ctrl: true }, 2);
-
-        expect(mockHandleSlashCommand).not.toHaveBeenCalled();
-        unmount();
-      });
-
       it('should quit on second press if buffer is empty', async () => {
         await setupKeypressTest();
 
@@ -2106,6 +1880,50 @@ describe('AppContainer State Management', () => {
         unmount();
       });
 
+      it('should NOT quit if buffer is not empty (bubbles from InputPrompt)', async () => {
+        mockedUseTextBuffer.mockReturnValue({
+          text: 'some text',
+          setText: vi.fn(),
+          lines: ['some text'],
+          cursor: [0, 9], // At the end
+          handleInput: vi.fn().mockReturnValue(false),
+        });
+        await setupKeypressTest();
+
+        // Capture return value
+        let result = true;
+        const originalPressKey = (key: Partial<Key>) => {
+          act(() => {
+            result = handleGlobalKeypress({
+              name: 'd',
+              shift: false,
+              alt: false,
+              ctrl: true,
+              cmd: false,
+              ...key,
+            } as Key);
+          });
+          rerender();
+        };
+
+        originalPressKey({ name: 'd', ctrl: true });
+
+        // AppContainer's handler should return true if it reaches it
+        expect(result).toBe(true);
+        // But it should only be called once, so count is 1, not quitting yet.
+        expect(mockHandleSlashCommand).not.toHaveBeenCalled();
+
+        originalPressKey({ name: 'd', ctrl: true });
+        // Now count is 2, it should quit.
+        expect(mockHandleSlashCommand).toHaveBeenCalledWith(
+          '/quit',
+          undefined,
+          undefined,
+          false,
+        );
+        unmount();
+      });
+
       it('should reset press count after a timeout', async () => {
         await setupKeypressTest();
 
@@ -2125,7 +1943,7 @@ describe('AppContainer State Management', () => {
   });
 
   describe('Copy Mode (CTRL+S)', () => {
-    let handleGlobalKeypress: (key: Key) => void;
+    let handleGlobalKeypress: (key: Key) => boolean;
     let rerender: () => void;
     let unmount: () => void;
 
@@ -2155,9 +1973,11 @@ describe('AppContainer State Management', () => {
 
     beforeEach(() => {
       mocks.mockStdout.write.mockClear();
-      mockedUseKeypress.mockImplementation((callback: (key: Key) => void) => {
-        handleGlobalKeypress = callback;
-      });
+      mockedUseKeypress.mockImplementation(
+        (callback: (key: Key) => boolean) => {
+          handleGlobalKeypress = callback;
+        },
+      );
       vi.useFakeTimers();
     });
 
@@ -2510,6 +2330,59 @@ describe('AppContainer State Management', () => {
       expect(capturedUIState.activeHooks).toEqual(mockHooks);
       unmount!();
     });
+
+    it('handles consent request events', async () => {
+      let unmount: () => void;
+      await act(async () => {
+        const result = renderAppContainer();
+        unmount = result.unmount;
+      });
+      await waitFor(() => expect(capturedUIState).toBeTruthy());
+
+      const handler = mockCoreEvents.on.mock.calls.find(
+        (call: unknown[]) => call[0] === CoreEvent.ConsentRequest,
+      )?.[1];
+      expect(handler).toBeDefined();
+
+      const onConfirm = vi.fn();
+      const payload = {
+        prompt: 'Do you consent?',
+        onConfirm,
+      };
+
+      act(() => {
+        handler(payload);
+      });
+
+      expect(capturedUIState.authConsentRequest).toBeDefined();
+      expect(capturedUIState.authConsentRequest?.prompt).toBe(
+        'Do you consent?',
+      );
+
+      act(() => {
+        capturedUIState.authConsentRequest?.onConfirm(true);
+      });
+
+      expect(onConfirm).toHaveBeenCalledWith(true);
+      expect(capturedUIState.authConsentRequest).toBeNull();
+      unmount!();
+    });
+
+    it('unsubscribes from ConsentRequest on unmount', async () => {
+      let unmount: () => void;
+      await act(async () => {
+        const result = renderAppContainer();
+        unmount = result.unmount;
+      });
+      await waitFor(() => expect(capturedUIState).toBeTruthy());
+
+      unmount!();
+
+      expect(mockCoreEvents.off).toHaveBeenCalledWith(
+        CoreEvent.ConsentRequest,
+        expect.any(Function),
+      );
+    });
   });
 
   describe('Shell Interaction', () => {
@@ -2521,12 +2394,7 @@ describe('AppContainer State Management', () => {
         });
 
       mockedUseGeminiStream.mockReturnValue({
-        streamingState: 'idle',
-        submitQuery: vi.fn(),
-        initError: null,
-        pendingHistoryItems: [],
-        thought: null,
-        cancelOngoingRequest: vi.fn(),
+        ...DEFAULT_GEMINI_STREAM_MOCK,
         activePtyId: 'some-pty-id', // Make sure activePtyId is set
       });
 
@@ -2676,41 +2544,6 @@ describe('AppContainer State Management', () => {
 
       unmount!();
     });
-
-    it('should show ask user dialog when request is received', async () => {
-      let unmount: () => void;
-      await act(async () => {
-        const result = renderAppContainer();
-        unmount = result.unmount;
-      });
-
-      const questions = [
-        {
-          question: 'What is your favorite color?',
-          header: 'Color Preference',
-          type: QuestionType.TEXT,
-        },
-      ];
-
-      await act(async () => {
-        await mockConfig.getMessageBus().publish({
-          type: MessageBusType.ASK_USER_REQUEST,
-          questions,
-          correlationId: 'test-id',
-        });
-      });
-
-      await waitFor(
-        () => {
-          expect(capturedAskUserRequest).not.toBeNull();
-          expect(capturedAskUserRequest?.questions).toEqual(questions);
-          expect(capturedAskUserRequest?.correlationId).toBe('test-id');
-        },
-        { timeout: 2000 },
-      );
-
-      unmount!();
-    });
   });
 
   describe('Regression Tests', () => {

packages/cli/src/ui/AppContainer.tsx

@@ -27,13 +27,10 @@ import {
   type HistoryItemWithoutId,
   type HistoryItemToolGroup,
   AuthState,
+  type ConfirmationRequest,
 } from './types.js';
 import { MessageType, StreamingState } from './types.js';
 import { ToolActionsProvider } from './contexts/ToolActionsContext.js';
-import {
-  AskUserActionsProvider,
-  type AskUserState,
-} from './contexts/AskUserActionsContext.js';
 import {
   type EditorType,
   type Config,
@@ -47,7 +44,6 @@ import {
   getErrorMessage,
   getAllGeminiMdFilenames,
   AuthType,
-  UserAccountManager,
   clearCachedCredentialFile,
   type ResumedSessionData,
   recordExitFail,
@@ -68,8 +64,7 @@ import {
   SessionStartSource,
   SessionEndReason,
   generateSummary,
-  MessageBusType,
-  type AskUserRequest,
+  type ConsentRequestPayload,
   type AgentsDiscoveredPayload,
   ChangeAuthRequestedError,
 } from '@google/gemini-cli-core';
@@ -97,6 +92,7 @@ import { computeTerminalTitle } from '../utils/windowTitle.js';
 import { useTextBuffer } from './components/shared/text-buffer.js';
 import { useLogger } from './hooks/useLogger.js';
 import { useGeminiStream } from './hooks/useGeminiStream.js';
+import { type BackgroundShell } from './hooks/shellCommandProcessor.js';
 import { useVim } from './hooks/vim.js';
 import { type LoadableSettingScope, SettingScope } from '../config/settings.js';
 import { type InitializationResult } from '../core/initializer.js';
@@ -136,6 +132,7 @@ import { terminalCapabilityManager } from './utils/terminalCapabilityManager.js'
 import { useInputHistoryStore } from './hooks/useInputHistoryStore.js';
 import { useBanner } from './hooks/useBanner.js';
 import { useHookDisplayState } from './hooks/useHookDisplayState.js';
+import { useBackgroundShellManager } from './hooks/useBackgroundShellManager.js';
 import {
   WARNING_PROMPT_DURATION_MS,
   QUEUE_ERROR_DISPLAY_DURATION_MS,
@@ -143,6 +140,7 @@ import {
 import { LoginWithGoogleRestartDialog } from './auth/LoginWithGoogleRestartDialog.js';
 import { NewAgentsChoice } from './components/NewAgentsNotification.js';
 import { isSlashCommand } from './utils/commandUtils.js';
+import { useTerminalTheme } from './hooks/useTerminalTheme.js';
 
 function isToolExecuting(pendingHistoryItems: HistoryItemWithoutId[]) {
   return pendingHistoryItems.some((item) => {
@@ -192,51 +190,6 @@ export const AppContainer = (props: AppContainerProps) => {
   const historyManager = useHistory({
     chatRecordingService: config.getGeminiClient()?.getChatRecordingService(),
   });
-  const { addItem } = historyManager;
-
-  const authCheckPerformed = useRef(false);
-  useEffect(() => {
-    if (authCheckPerformed.current) return;
-    authCheckPerformed.current = true;
-
-    if (resumedSessionData || settings.merged.ui.showUserIdentity === false) {
-      return;
-    }
-    const authType = config.getContentGeneratorConfig()?.authType;
-
-    // Run this asynchronously to avoid blocking the event loop.
-    // eslint-disable-next-line @typescript-eslint/no-floating-promises
-    (async () => {
-      try {
-        const userAccountManager = new UserAccountManager();
-        const email = userAccountManager.getCachedGoogleAccount();
-        const tierName = config.getUserTierName();
-
-        if (authType) {
-          let message =
-            authType === AuthType.LOGIN_WITH_GOOGLE
-              ? email
-                ? `Logged in with Google: ${email}`
-                : 'Logged in with Google'
-              : `Authenticated with ${authType}`;
-          if (tierName) {
-            message += ` (Plan: ${tierName})`;
-          }
-          addItem({
-            type: MessageType.INFO,
-            text: message,
-          });
-        }
-      } catch (_e) {
-        // Ignore errors during initial auth check
-      }
-    })();
-  }, [
-    config,
-    resumedSessionData,
-    settings.merged.ui.showUserIdentity,
-    addItem,
-  ]);
 
   useMemoryMonitor(historyManager);
   const isAlternateBuffer = useAlternateBuffer();
@@ -257,6 +210,10 @@ export const AppContainer = (props: AppContainerProps) => {
   );
   const [copyModeEnabled, setCopyModeEnabled] = useState(false);
   const [pendingRestorePrompt, setPendingRestorePrompt] = useState(false);
+  const toggleBackgroundShellRef = useRef<() => void>(() => {});
+  const isBackgroundShellVisibleRef = useRef<boolean>(false);
+  const backgroundShellsRef = useRef<Map<number, BackgroundShell>>(new Map());
+
   const [adminSettingsChanged, setAdminSettingsChanged] = useState(false);
 
   const [shellModeActive, setShellModeActive] = useState(false);
@@ -267,7 +224,7 @@ export const AppContainer = (props: AppContainerProps) => {
   const activeHooks = useHookDisplayState();
   const [updateInfo, setUpdateInfo] = useState<UpdateObject | null>(null);
   const [isTrustedFolder, setIsTrustedFolder] = useState<boolean | undefined>(
-    isWorkspaceTrusted(settings.merged).isTrusted,
+    () => isWorkspaceTrusted(settings.merged).isTrusted,
   );
 
   const [queueErrorMessage, setQueueErrorMessage] = useState<string | null>(
@@ -336,11 +293,6 @@ export const AppContainer = (props: AppContainerProps) => {
     AgentDefinition | undefined
   >();
 
-  // AskUser dialog state
-  const [askUserRequest, setAskUserRequest] = useState<AskUserState | null>(
-    null,
-  );
-
   const openAgentConfigDialog = useCallback(
     (name: string, displayName: string, definition: AgentDefinition) => {
       setSelectedAgentName(name);
@@ -358,56 +310,6 @@ export const AppContainer = (props: AppContainerProps) => {
     setSelectedAgentDefinition(undefined);
   }, []);
 
-  // Subscribe to ASK_USER_REQUEST messages from the message bus
-  useEffect(() => {
-    const messageBus = config.getMessageBus();
-
-    const handler = (msg: AskUserRequest) => {
-      setAskUserRequest({
-        questions: msg.questions,
-        correlationId: msg.correlationId,
-      });
-    };
-
-    messageBus.subscribe(MessageBusType.ASK_USER_REQUEST, handler);
-
-    return () => {
-      messageBus.unsubscribe(MessageBusType.ASK_USER_REQUEST, handler);
-    };
-  }, [config]);
-
-  // Handler to submit ask_user answers
-  const handleAskUserSubmit = useCallback(
-    async (answers: { [questionIndex: string]: string }) => {
-      if (!askUserRequest) return;
-
-      const messageBus = config.getMessageBus();
-      await messageBus.publish({
-        type: MessageBusType.ASK_USER_RESPONSE,
-        correlationId: askUserRequest.correlationId,
-        answers,
-      });
-
-      setAskUserRequest(null);
-    },
-    [config, askUserRequest],
-  );
-
-  // Handler to cancel ask_user dialog
-  const handleAskUserCancel = useCallback(async () => {
-    if (!askUserRequest) return;
-
-    const messageBus = config.getMessageBus();
-    await messageBus.publish({
-      type: MessageBusType.ASK_USER_RESPONSE,
-      correlationId: askUserRequest.correlationId,
-      answers: {},
-      cancelled: true,
-    });
-
-    setAskUserRequest(null);
-  }, [config, askUserRequest]);
-
   const toggleDebugProfiler = useCallback(
     () => setShowDebugProfiler((prev) => !prev),
     [],
@@ -487,6 +389,12 @@ export const AppContainer = (props: AppContainerProps) => {
     registerCleanup(async () => {
       // Turn off mouse scroll.
       disableMouseEvents();
+
+      // Kill all background shells
+      for (const pid of backgroundShellsRef.current.keys()) {
+        ShellExecutionService.kill(pid);
+      }
+
       const ideClient = await IdeClient.getInstance();
       await ideClient.disconnect();
 
@@ -579,6 +487,14 @@ export const AppContainer = (props: AppContainerProps) => {
     shellModeActive,
     getPreferredEditor,
   });
+  const bufferRef = useRef(buffer);
+  useEffect(() => {
+    bufferRef.current = buffer;
+  }, [buffer]);
+
+  const stableSetText = useCallback((text: string) => {
+    bufferRef.current.setText(text);
+  }, []);
 
   // Initialize input history from logger (past sessions)
   useEffect(() => {
@@ -640,6 +556,9 @@ export const AppContainer = (props: AppContainerProps) => {
     initializationResult.themeError,
   );
 
+  // Poll for terminal background color changes to auto-switch theme
+  useTerminalTheme(handleThemeSelect, config);
+
   const {
     authState,
     setAuthState,
@@ -835,6 +754,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
 
   const { toggleVimEnabled } = useVimMode();
 
+  const setIsBackgroundShellListOpenRef = useRef<(open: boolean) => void>(
+    () => {},
+  );
+
   const slashCommandActions = useMemo(
     () => ({
       openAuthDialog: () => setAuthState(AuthState.Updating),
@@ -858,7 +781,18 @@ Logging in with Google... Restarting Gemini CLI to continue.
       toggleDebugProfiler,
       dispatchExtensionStateUpdate,
       addConfirmUpdateExtensionRequest,
-      setText: (text: string) => buffer.setText(text),
+      toggleBackgroundShell: () => {
+        toggleBackgroundShellRef.current();
+        if (!isBackgroundShellVisibleRef.current) {
+          setEmbeddedShellFocused(true);
+          if (backgroundShellsRef.current.size > 1) {
+            setIsBackgroundShellListOpenRef.current(true);
+          } else {
+            setIsBackgroundShellListOpenRef.current(false);
+          }
+        }
+      },
+      setText: stableSetText,
     }),
     [
       setAuthState,
@@ -876,7 +810,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
       openPermissionsDialog,
       addConfirmUpdateExtensionRequest,
       toggleDebugProfiler,
-      buffer,
+      stableSetText,
     ],
   );
 
@@ -885,7 +819,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
     slashCommands,
     pendingHistoryItems: pendingSlashCommandHistoryItems,
     commandContext,
-    confirmationRequest,
+    confirmationRequest: commandConfirmationRequest,
   } = useSlashCommandProcessor(
     config,
     settings,
@@ -902,6 +836,26 @@ Logging in with Google... Restarting Gemini CLI to continue.
     setCustomDialog,
   );
 
+  const [authConsentRequest, setAuthConsentRequest] =
+    useState<ConfirmationRequest | null>(null);
+
+  useEffect(() => {
+    const handleConsentRequest = (payload: ConsentRequestPayload) => {
+      setAuthConsentRequest({
+        prompt: payload.prompt,
+        onConfirm: (confirmed: boolean) => {
+          setAuthConsentRequest(null);
+          payload.onConfirm(confirmed);
+        },
+      });
+    };
+
+    coreEvents.on(CoreEvent.ConsentRequest, handleConsentRequest);
+    return () => {
+      coreEvents.off(CoreEvent.ConsentRequest, handleConsentRequest);
+    };
+  }, []);
+
   const performMemoryRefresh = useCallback(async () => {
     historyManager.addItem(
       {
@@ -989,6 +943,12 @@ Logging in with Google... Restarting Gemini CLI to continue.
     activePtyId,
     loopDetectionConfirmationRequest,
     lastOutputTime,
+    backgroundShellCount,
+    isBackgroundShellVisible,
+    toggleBackgroundShell,
+    backgroundCurrentShell,
+    backgroundShells,
+    dismissBackgroundShell,
     retryStatus,
   } = useGeminiStream(
     config.getGeminiClient(),
@@ -1011,7 +971,30 @@ Logging in with Google... Restarting Gemini CLI to continue.
     embeddedShellFocused,
   );
 
+  toggleBackgroundShellRef.current = toggleBackgroundShell;
+  isBackgroundShellVisibleRef.current = isBackgroundShellVisible;
+  backgroundShellsRef.current = backgroundShells;
+
+  const {
+    activeBackgroundShellPid,
+    setIsBackgroundShellListOpen,
+    isBackgroundShellListOpen,
+    setActiveBackgroundShellPid,
+    backgroundShellHeight,
+  } = useBackgroundShellManager({
+    backgroundShells,
+    backgroundShellCount,
+    isBackgroundShellVisible,
+    activePtyId,
+    embeddedShellFocused,
+    setEmbeddedShellFocused,
+    terminalHeight,
+  });
+
+  setIsBackgroundShellListOpenRef.current = setIsBackgroundShellListOpen;
+
   const lastOutputTimeRef = useRef(0);
+
   useEffect(() => {
     lastOutputTimeRef.current = lastOutputTime;
   }, [lastOutputTime]);
@@ -1160,7 +1143,11 @@ Logging in with Google... Restarting Gemini CLI to continue.
   // Compute available terminal height based on controls measurement
   const availableTerminalHeight = Math.max(
     0,
-    terminalHeight - controlsHeight - staticExtraHeight - 2,
+    terminalHeight -
+      controlsHeight -
+      staticExtraHeight -
+      2 -
+      backgroundShellHeight,
   );
 
   config.setShellExecutionConfig({
@@ -1384,7 +1371,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
     if (ctrlCPressCount > 1) {
       // eslint-disable-next-line @typescript-eslint/no-floating-promises
       handleSlashCommand('/quit', undefined, undefined, false);
-    } else {
+    } else if (ctrlCPressCount > 0) {
       ctrlCTimerRef.current = setTimeout(() => {
         setCtrlCPressCount(0);
         ctrlCTimerRef.current = null;
@@ -1403,7 +1390,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
     if (ctrlDPressCount > 1) {
       // eslint-disable-next-line @typescript-eslint/no-floating-promises
       handleSlashCommand('/quit', undefined, undefined, false);
-    } else {
+    } else if (ctrlDPressCount > 0) {
       ctrlDTimerRef.current = setTimeout(() => {
         setCtrlDPressCount(0);
         ctrlDTimerRef.current = null;
@@ -1444,7 +1431,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
   });
 
   const handleGlobalKeypress = useCallback(
-    (key: Key) => {
+    (key: Key): boolean => {
       if (copyModeEnabled) {
         setCopyModeEnabled(false);
         enableMouseEvents();
@@ -1464,10 +1451,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
       }
 
       if (keyMatchers[Command.QUIT](key)) {
-        // Skip when ask_user dialog is open (use Esc to cancel instead)
-        if (askUserRequest) {
-          return;
-        }
         // If the user presses Ctrl+C, we want to cancel any ongoing requests.
         // This should happen regardless of the count.
         cancelOngoingRequest?.();
@@ -1475,9 +1458,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
         setCtrlCPressCount((prev) => prev + 1);
         return true;
       } else if (keyMatchers[Command.EXIT](key)) {
-        if (buffer.text.length > 0) {
-          return false;
-        }
         setCtrlDPressCount((prev) => prev + 1);
         return true;
       }
@@ -1520,9 +1500,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
         setConstrainHeight(false);
         return true;
       } else if (
-        keyMatchers[Command.UNFOCUS_SHELL_INPUT](key) &&
-        activePtyId &&
-        embeddedShellFocused
+        keyMatchers[Command.FOCUS_SHELL_INPUT](key) &&
+        (activePtyId || (isBackgroundShellVisible && backgroundShells.size > 0))
       ) {
         if (key.name === 'tab' && key.shift) {
           // Always change focus
@@ -1530,26 +1509,72 @@ Logging in with Google... Restarting Gemini CLI to continue.
           return true;
         }
 
+        if (embeddedShellFocused) {
+          handleWarning('Press Shift+Tab to focus out.');
+          return true;
+        }
+
         const now = Date.now();
         // If the shell hasn't produced output in the last 100ms, it's considered idle.
         const isIdle = now - lastOutputTimeRef.current >= 100;
-        if (isIdle) {
+        if (isIdle && !activePtyId) {
           if (tabFocusTimeoutRef.current) {
             clearTimeout(tabFocusTimeoutRef.current);
           }
-          tabFocusTimeoutRef.current = setTimeout(() => {
-            tabFocusTimeoutRef.current = null;
-            // If the shell produced output since the tab press, we assume it handled the tab
-            // (e.g. autocomplete) so we should not toggle focus.
-            if (lastOutputTimeRef.current > now) {
-              handleWarning('Press Shift+Tab to focus out.');
-              return;
+          toggleBackgroundShell();
+          if (!isBackgroundShellVisible) {
+            // We are about to show it, so focus it
+            setEmbeddedShellFocused(true);
+            if (backgroundShells.size > 1) {
+              setIsBackgroundShellListOpen(true);
             }
-            setEmbeddedShellFocused(false);
-          }, 100);
+          } else {
+            // We are about to hide it
+            tabFocusTimeoutRef.current = setTimeout(() => {
+              tabFocusTimeoutRef.current = null;
+              // If the shell produced output since the tab press, we assume it handled the tab
+              // (e.g. autocomplete) so we should not toggle focus.
+              if (lastOutputTimeRef.current > now) {
+                handleWarning('Press Shift+Tab to focus out.');
+                return;
+              }
+              setEmbeddedShellFocused(false);
+            }, 100);
+          }
           return true;
         }
-        handleWarning('Press Shift+Tab to focus out.');
+
+        // Not idle, just focus it
+        setEmbeddedShellFocused(true);
+        return true;
+      } else if (keyMatchers[Command.TOGGLE_BACKGROUND_SHELL](key)) {
+        if (activePtyId) {
+          backgroundCurrentShell();
+          // After backgrounding, we explicitly do NOT show or focus the background UI.
+        } else {
+          if (isBackgroundShellVisible && !embeddedShellFocused) {
+            setEmbeddedShellFocused(true);
+          } else {
+            toggleBackgroundShell();
+            // Toggle focus based on intent: if we were hiding, unfocus; if showing, focus.
+            if (!isBackgroundShellVisible && backgroundShells.size > 0) {
+              setEmbeddedShellFocused(true);
+              if (backgroundShells.size > 1) {
+                setIsBackgroundShellListOpen(true);
+              }
+            } else {
+              setEmbeddedShellFocused(false);
+            }
+          }
+        }
+        return true;
+      } else if (keyMatchers[Command.TOGGLE_BACKGROUND_SHELL_LIST](key)) {
+        if (backgroundShells.size > 0 && isBackgroundShellVisible) {
+          if (!embeddedShellFocused) {
+            setEmbeddedShellFocused(true);
+          }
+          setIsBackgroundShellListOpen(true);
+        }
         return true;
       }
       return false;
@@ -1561,11 +1586,9 @@ Logging in with Google... Restarting Gemini CLI to continue.
       config,
       ideContextState,
       setCtrlCPressCount,
-      buffer.text.length,
       setCtrlDPressCount,
       handleSlashCommand,
       cancelOngoingRequest,
-      askUserRequest,
       activePtyId,
       embeddedShellFocused,
       settings.merged.general.debugKeystrokeLogging,
@@ -1573,6 +1596,13 @@ Logging in with Google... Restarting Gemini CLI to continue.
       setCopyModeEnabled,
       copyModeEnabled,
       isAlternateBuffer,
+      backgroundCurrentShell,
+      toggleBackgroundShell,
+      backgroundShells,
+      isBackgroundShellVisible,
+      setIsBackgroundShellListOpen,
+      lastOutputTimeRef,
+      tabFocusTimeoutRef,
       handleWarning,
     ],
   );
@@ -1586,7 +1616,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
     const paddedTitle = computeTerminalTitle({
       streamingState,
       thoughtSubject: thought?.subject,
-      isConfirming: !!confirmationRequest || shouldShowActionRequiredTitle,
+      isConfirming:
+        !!commandConfirmationRequest || shouldShowActionRequiredTitle,
       isSilentWorking: shouldShowSilentWorkingTitle,
       folderName: basename(config.getTargetDir()),
       showThoughts: !!settings.merged.ui.showStatusInTitle,
@@ -1602,7 +1633,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
   }, [
     streamingState,
     thought,
-    confirmationRequest,
+    commandConfirmationRequest,
     shouldShowActionRequiredTitle,
     shouldShowSilentWorkingTitle,
     settings.merged.ui.showStatusInTitle,
@@ -1678,11 +1709,11 @@ Logging in with Google... Restarting Gemini CLI to continue.
   const nightly = props.version.includes('nightly');
 
   const dialogsVisible =
-    !!askUserRequest ||
     shouldShowIdePrompt ||
     isFolderTrustDialogOpen ||
     adminSettingsChanged ||
-    !!confirmationRequest ||
+    !!commandConfirmationRequest ||
+    !!authConsentRequest ||
     !!customDialog ||
     confirmUpdateExtensionRequests.length > 0 ||
     !!loopDetectionConfirmationRequest ||
@@ -1792,7 +1823,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
       slashCommands,
       pendingSlashCommandHistoryItems,
       commandContext,
-      confirmationRequest,
+      commandConfirmationRequest,
+      authConsentRequest,
       confirmUpdateExtensionRequests,
       loopDetectionConfirmationRequest,
       geminiMdFileCount,
@@ -1853,6 +1885,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
       isRestarting,
       extensionsUpdateState,
       activePtyId,
+      backgroundShellCount,
+      isBackgroundShellVisible,
       embeddedShellFocused,
       showDebugProfiler,
       customDialog,
@@ -1862,6 +1896,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
       bannerVisible,
       terminalBackgroundColor: config.getTerminalBackground(),
       settingsNonce,
+      backgroundShells,
+      activeBackgroundShellPid,
+      backgroundShellHeight,
+      isBackgroundShellListOpen,
       adminSettingsChanged,
       newAgents,
     }),
@@ -1890,7 +1928,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
       slashCommands,
       pendingSlashCommandHistoryItems,
       commandContext,
-      confirmationRequest,
+      commandConfirmationRequest,
+      authConsentRequest,
       confirmUpdateExtensionRequests,
       loopDetectionConfirmationRequest,
       geminiMdFileCount,
@@ -1951,6 +1990,8 @@ Logging in with Google... Restarting Gemini CLI to continue.
       currentModel,
       extensionsUpdateState,
       activePtyId,
+      backgroundShellCount,
+      isBackgroundShellVisible,
       historyManager,
       embeddedShellFocused,
       showDebugProfiler,
@@ -1963,6 +2004,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
       bannerVisible,
       config,
       settingsNonce,
+      backgroundShellHeight,
+      isBackgroundShellListOpen,
+      activeBackgroundShellPid,
+      backgroundShells,
       adminSettingsChanged,
       newAgents,
     ],
@@ -2010,7 +2055,11 @@ Logging in with Google... Restarting Gemini CLI to continue.
       handleApiKeySubmit,
       handleApiKeyCancel,
       setBannerVisible,
+      handleWarning,
       setEmbeddedShellFocused,
+      dismissBackgroundShell,
+      setActiveBackgroundShellPid,
+      setIsBackgroundShellListOpen,
       setAuthContext,
       handleRestart: async () => {
         if (process.send) {
@@ -2082,7 +2131,11 @@ Logging in with Google... Restarting Gemini CLI to continue.
       handleApiKeySubmit,
       handleApiKeyCancel,
       setBannerVisible,
+      handleWarning,
       setEmbeddedShellFocused,
+      dismissBackgroundShell,
+      setActiveBackgroundShellPid,
+      setIsBackgroundShellListOpen,
       setAuthContext,
       newAgents,
       config,
@@ -2113,15 +2166,9 @@ Logging in with Google... Restarting Gemini CLI to continue.
             }}
           >
             <ToolActionsProvider config={config} toolCalls={allToolCalls}>
-              <AskUserActionsProvider
-                request={askUserRequest}
-                onSubmit={handleAskUserSubmit}
-                onCancel={handleAskUserCancel}
-              >
-                <ShellFocusContext.Provider value={isFocused}>
-                  <App />
-                </ShellFocusContext.Provider>
-              </AskUserActionsProvider>
+              <ShellFocusContext.Provider value={isFocused}>
+                <App />
+              </ShellFocusContext.Provider>
             </ToolActionsProvider>
           </AppContext.Provider>
         </ConfigContext.Provider>

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

@@ -125,7 +125,7 @@ Tips for getting started:
 4. /help for more information.
 HistoryItemDisplay
 ╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
-│ Action Required                                                                                               1 of 1 │
+│ Action Required                                                                                                      │
 │                                                                                                                      │
 │ ?  ls list directory                                                                                                 │
 │                                                                                                                      │

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

@@ -86,6 +86,11 @@ describe('directoryCommand', () => {
         settings: {
           merged: {
             memoryDiscoveryMaxDirs: 1000,
+            security: {
+              folderTrust: {
+                enabled: false,
+              },
+            },
           },
         },
       },

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

@@ -30,9 +30,6 @@ describe('hooksCommand', () => {
       hooksConfig?: {
         disabled?: string[];
       };
-      tools?: {
-        enableHooks?: boolean;
-      };
     };
     setValue: ReturnType<typeof vi.fn>;
     // eslint-disable-next-line @typescript-eslint/no-explicit-any
@@ -187,8 +184,8 @@ describe('hooksCommand', () => {
     it('should display panel when no hooks are configured', async () => {
       mockHookSystem.getAllHooks.mockReturnValue([]);
       (mockContext.services.settings.merged as Record<string, unknown>)[
-        'tools'
-      ] = { enableHooks: true };
+        'hooksConfig'
+      ] = { enabled: true };
 
       const panelCmd = hooksCommand.subCommands!.find(
         (cmd) => cmd.name === 'panel',
@@ -215,8 +212,8 @@ describe('hooksCommand', () => {
 
       mockHookSystem.getAllHooks.mockReturnValue(mockHooks);
       (mockContext.services.settings.merged as Record<string, unknown>)[
-        'tools'
-      ] = { enableHooks: true };
+        'hooksConfig'
+      ] = { enabled: true };
 
       const panelCmd = hooksCommand.subCommands!.find(
         (cmd) => cmd.name === 'panel',

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

@@ -10,6 +10,7 @@ import {
   type OpenCustomDialogActionReturn,
 } from './types.js';
 import { TriageDuplicates } from '../components/triage/TriageDuplicates.js';
+import { TriageIssues } from '../components/triage/TriageIssues.js';
 
 export const oncallCommand: SlashCommand = {
   name: 'oncall',
@@ -49,5 +50,63 @@ export const oncallCommand: SlashCommand = {
         };
       },
     },
+    {
+      name: 'audit',
+      description: 'Triage issues labeled as status/need-triage',
+      kind: CommandKind.BUILT_IN,
+      autoExecute: true,
+      action: async (context, args): Promise<OpenCustomDialogActionReturn> => {
+        const { config } = context.services;
+        if (!config) {
+          throw new Error('Config not available');
+        }
+
+        let limit = 100;
+        let until: string | undefined;
+
+        if (args && args.trim().length > 0) {
+          const argArray = args.trim().split(/\s+/);
+          for (let i = 0; i < argArray.length; i++) {
+            const arg = argArray[i];
+            if (arg === '--until') {
+              if (i + 1 >= argArray.length) {
+                throw new Error('Flag --until requires a value (YYYY-MM-DD).');
+              }
+              const val = argArray[i + 1];
+              if (!/^\d{4}-\d{2}-\d{2}$/.test(val)) {
+                throw new Error(
+                  `Invalid date format for --until: "${val}". Expected YYYY-MM-DD.`,
+                );
+              }
+              until = val;
+              i++;
+            } else if (arg.startsWith('--')) {
+              throw new Error(`Unknown flag: ${arg}`);
+            } else {
+              const parsedLimit = parseInt(arg, 10);
+              if (!isNaN(parsedLimit) && parsedLimit > 0) {
+                limit = parsedLimit;
+              } else {
+                throw new Error(
+                  `Invalid argument: "${arg}". Expected a positive number or --until flag.`,
+                );
+              }
+            }
+          }
+        }
+
+        return {
+          type: 'custom_dialog',
+          component: (
+            <TriageIssues
+              config={config}
+              initialLimit={limit}
+              until={until}
+              onExit={() => context.ui.removeComponent()}
+            />
+          ),
+        };
+      },
+    },
   ],
 };

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

@@ -0,0 +1,118 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, beforeEach, vi, afterEach } from 'vitest';
+import { planCommand } from './planCommand.js';
+import { type CommandContext } from './types.js';
+import { createMockCommandContext } from '../../test-utils/mockCommandContext.js';
+import { MessageType } from '../types.js';
+import {
+  ApprovalMode,
+  coreEvents,
+  processSingleFileContent,
+  type ProcessedFileReadResult,
+} from '@google/gemini-cli-core';
+
+vi.mock('@google/gemini-cli-core', async (importOriginal) => {
+  const actual =
+    await importOriginal<typeof import('@google/gemini-cli-core')>();
+  return {
+    ...actual,
+    coreEvents: {
+      emitFeedback: vi.fn(),
+    },
+    processSingleFileContent: vi.fn(),
+    partToString: vi.fn((val) => val),
+  };
+});
+
+vi.mock('node:path', async (importOriginal) => {
+  const actual = await importOriginal<typeof import('node:path')>();
+  return {
+    ...actual,
+    default: { ...actual },
+    join: vi.fn((...args) => args.join('/')),
+  };
+});
+
+describe('planCommand', () => {
+  let mockContext: CommandContext;
+
+  beforeEach(() => {
+    mockContext = createMockCommandContext({
+      services: {
+        config: {
+          isPlanEnabled: vi.fn(),
+          setApprovalMode: vi.fn(),
+          getApprovedPlanPath: vi.fn(),
+          getApprovalMode: vi.fn(),
+          getFileSystemService: vi.fn(),
+          storage: {
+            getProjectTempPlansDir: vi.fn().mockReturnValue('/mock/plans/dir'),
+          },
+        },
+      },
+      ui: {
+        addItem: vi.fn(),
+      },
+    } as unknown as CommandContext);
+
+    vi.clearAllMocks();
+  });
+
+  afterEach(() => {
+    vi.restoreAllMocks();
+  });
+
+  it('should have the correct name and description', () => {
+    expect(planCommand.name).toBe('plan');
+    expect(planCommand.description).toBe(
+      'Switch to Plan Mode and view current plan',
+    );
+  });
+
+  it('should switch to plan mode if enabled', async () => {
+    vi.mocked(mockContext.services.config!.isPlanEnabled).mockReturnValue(true);
+    vi.mocked(mockContext.services.config!.getApprovedPlanPath).mockReturnValue(
+      undefined,
+    );
+
+    if (!planCommand.action) throw new Error('Action missing');
+    await planCommand.action(mockContext, '');
+
+    expect(mockContext.services.config!.setApprovalMode).toHaveBeenCalledWith(
+      ApprovalMode.PLAN,
+    );
+    expect(coreEvents.emitFeedback).toHaveBeenCalledWith(
+      'info',
+      'Switched to Plan Mode.',
+    );
+  });
+
+  it('should display the approved plan from config', async () => {
+    const mockPlanPath = '/mock/plans/dir/approved-plan.md';
+    vi.mocked(mockContext.services.config!.isPlanEnabled).mockReturnValue(true);
+    vi.mocked(mockContext.services.config!.getApprovedPlanPath).mockReturnValue(
+      mockPlanPath,
+    );
+    vi.mocked(processSingleFileContent).mockResolvedValue({
+      llmContent: '# Approved Plan Content',
+      returnDisplay: '# Approved Plan Content',
+    } as ProcessedFileReadResult);
+
+    if (!planCommand.action) throw new Error('Action missing');
+    await planCommand.action(mockContext, '');
+
+    expect(coreEvents.emitFeedback).toHaveBeenCalledWith(
+      'info',
+      'Approved Plan: approved-plan.md',
+    );
+    expect(mockContext.ui.addItem).toHaveBeenCalledWith({
+      type: MessageType.GEMINI,
+      text: '# Approved Plan Content',
+    });
+  });
+});

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

@@ -0,0 +1,65 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { CommandKind, type SlashCommand } from './types.js';
+import {
+  ApprovalMode,
+  coreEvents,
+  debugLogger,
+  processSingleFileContent,
+  partToString,
+} from '@google/gemini-cli-core';
+import { MessageType } from '../types.js';
+import * as path from 'node:path';
+
+export const planCommand: SlashCommand = {
+  name: 'plan',
+  description: 'Switch to Plan Mode and view current plan',
+  kind: CommandKind.BUILT_IN,
+  autoExecute: true,
+  action: async (context) => {
+    const config = context.services.config;
+    if (!config) {
+      debugLogger.debug('Plan command: config is not available in context');
+      return;
+    }
+
+    const previousApprovalMode = config.getApprovalMode();
+    config.setApprovalMode(ApprovalMode.PLAN);
+
+    if (previousApprovalMode !== ApprovalMode.PLAN) {
+      coreEvents.emitFeedback('info', 'Switched to Plan Mode.');
+    }
+
+    const approvedPlanPath = config.getApprovedPlanPath();
+
+    if (!approvedPlanPath) {
+      return;
+    }
+
+    try {
+      const content = await processSingleFileContent(
+        approvedPlanPath,
+        config.storage.getProjectTempPlansDir(),
+        config.getFileSystemService(),
+      );
+      const fileName = path.basename(approvedPlanPath);
+
+      coreEvents.emitFeedback('info', `Approved Plan: ${fileName}`);
+
+      context.ui.addItem({
+        type: MessageType.GEMINI,
+        text: partToString(content.llmContent),
+      });
+    } catch (error) {
+      coreEvents.emitFeedback(
+        'error',
+        `Failed to read approved plan at ${approvedPlanPath}: ${error}`,
+        error,
+      );
+    }
+  },
+};

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

@@ -41,6 +41,8 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
       ...actual.coreEvents,
       emitFeedback: vi.fn(),
     },
+    logRewind: vi.fn(),
+    RewindEvent: class {},
   };
 });
 

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

@@ -14,14 +14,16 @@ 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,
+import {
+  checkExhaustive,
+  coreEvents,
+  debugLogger,
+  logRewind,
+  RewindEvent,
+  type ChatRecordingService,
+  type 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.
@@ -144,6 +146,9 @@ export const rewindCommand: SlashCommand = {
             context.ui.removeComponent();
           }}
           onRewind={async (messageId, newText, outcome) => {
+            if (outcome !== RewindOutcome.Cancel) {
+              logRewind(config, new RewindEvent(outcome));
+            }
             switch (outcome) {
               case RewindOutcome.Cancel:
                 context.ui.removeComponent();

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

@@ -0,0 +1,35 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, vi } from 'vitest';
+import { shellsCommand } from './shellsCommand.js';
+import type { CommandContext } from './types.js';
+
+describe('shellsCommand', () => {
+  it('should call toggleBackgroundShell', async () => {
+    const toggleBackgroundShell = vi.fn();
+    const context = {
+      ui: {
+        toggleBackgroundShell,
+      },
+    } as unknown as CommandContext;
+
+    if (shellsCommand.action) {
+      await shellsCommand.action(context, '');
+    }
+
+    expect(toggleBackgroundShell).toHaveBeenCalled();
+  });
+
+  it('should have correct name and altNames', () => {
+    expect(shellsCommand.name).toBe('shells');
+    expect(shellsCommand.altNames).toContain('bashes');
+  });
+
+  it('should auto-execute', () => {
+    expect(shellsCommand.autoExecute).toBe(true);
+  });
+});

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

@@ -0,0 +1,18 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { CommandKind, type SlashCommand } from './types.js';
+
+export const shellsCommand: SlashCommand = {
+  name: 'shells',
+  altNames: ['bashes'],
+  kind: CommandKind.BUILT_IN,
+  description: 'Toggle background shells view',
+  autoExecute: true,
+  action: async (context) => {
+    context.ui.toggleBackgroundShell();
+  },
+};

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

@@ -17,6 +17,27 @@ import {
   type MergedSettings,
 } from '../../config/settings.js';
 
+vi.mock('../../utils/skillUtils.js', async (importOriginal) => {
+  const actual =
+    await importOriginal<typeof import('../../utils/skillUtils.js')>();
+  return {
+    ...actual,
+    linkSkill: vi.fn(),
+  };
+});
+
+vi.mock('../../config/extensions/consent.js', async (importOriginal) => {
+  const actual =
+    await importOriginal<typeof import('../../config/extensions/consent.js')>();
+  return {
+    ...actual,
+    requestConsentInteractive: vi.fn().mockResolvedValue(true),
+    skillsConsentString: vi.fn().mockResolvedValue('Mock Consent'),
+  };
+});
+
+import { linkSkill } from '../../utils/skillUtils.js';
+
 vi.mock('../../config/settings.js', async (importOriginal) => {
   const actual =
     await importOriginal<typeof import('../../config/settings.js')>();
@@ -58,6 +79,7 @@ describe('skillsCommand', () => {
                 (name: string) => skills.find((s) => s.name === name) ?? null,
               ),
           }),
+          getContentGenerator: vi.fn(),
         } as unknown as Config,
         settings: {
           merged: createTestMergedSettings({ skills: { disabled: [] } }),
@@ -184,6 +206,80 @@ describe('skillsCommand', () => {
     expect(lastCall.skills).toHaveLength(2);
   });
 
+  describe('link', () => {
+    it('should link a skill successfully', async () => {
+      const linkCmd = skillsCommand.subCommands!.find(
+        (s) => s.name === 'link',
+      )!;
+      vi.mocked(linkSkill).mockResolvedValue([
+        { name: 'test-skill', location: '/path' },
+      ]);
+
+      await linkCmd.action!(context, '/some/path');
+
+      expect(linkSkill).toHaveBeenCalledWith(
+        '/some/path',
+        'user',
+        expect.any(Function),
+        expect.any(Function),
+      );
+      expect(context.ui.addItem).toHaveBeenCalledWith(
+        expect.objectContaining({
+          type: MessageType.INFO,
+          text: 'Successfully linked skills from "/some/path" (user).',
+        }),
+      );
+    });
+
+    it('should link a skill with workspace scope', async () => {
+      const linkCmd = skillsCommand.subCommands!.find(
+        (s) => s.name === 'link',
+      )!;
+      vi.mocked(linkSkill).mockResolvedValue([
+        { name: 'test-skill', location: '/path' },
+      ]);
+
+      await linkCmd.action!(context, '/some/path --scope workspace');
+
+      expect(linkSkill).toHaveBeenCalledWith(
+        '/some/path',
+        'workspace',
+        expect.any(Function),
+        expect.any(Function),
+      );
+    });
+
+    it('should show error if link fails', async () => {
+      const linkCmd = skillsCommand.subCommands!.find(
+        (s) => s.name === 'link',
+      )!;
+      vi.mocked(linkSkill).mockRejectedValue(new Error('Link failed'));
+
+      await linkCmd.action!(context, '/some/path');
+
+      expect(context.ui.addItem).toHaveBeenCalledWith(
+        expect.objectContaining({
+          type: MessageType.ERROR,
+          text: 'Failed to link skills: Link failed',
+        }),
+      );
+    });
+
+    it('should show error if path is missing', async () => {
+      const linkCmd = skillsCommand.subCommands!.find(
+        (s) => s.name === 'link',
+      )!;
+      await linkCmd.action!(context, '');
+
+      expect(context.ui.addItem).toHaveBeenCalledWith(
+        expect.objectContaining({
+          type: MessageType.ERROR,
+          text: 'Usage: /skills link <path> [--scope user|workspace]',
+        }),
+      );
+    });
+  });
+
   describe('disable/enable', () => {
     beforeEach(() => {
       (
@@ -367,7 +463,7 @@ describe('skillsCommand', () => {
       expect(context.ui.addItem).toHaveBeenCalledWith(
         expect.objectContaining({
           type: MessageType.ERROR,
-          text: 'Agent skills are disabled by your admin.',
+          text: 'Agent skills is disabled by your administrator. To enable it, please request an update to the settings at: https://goo.gle/manage-gemini-cli',
         }),
         expect.any(Number),
       );
@@ -385,7 +481,7 @@ describe('skillsCommand', () => {
       expect(context.ui.addItem).toHaveBeenCalledWith(
         expect.objectContaining({
           type: MessageType.ERROR,
-          text: 'Agent skills are disabled by your admin.',
+          text: 'Agent skills is disabled by your administrator. To enable it, please request an update to the settings at: https://goo.gle/manage-gemini-cli',
         }),
         expect.any(Number),
       );

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

@@ -11,13 +11,23 @@ import {
   CommandKind,
 } from './types.js';
 import {
-  MessageType,
-  type HistoryItemSkillsList,
   type HistoryItemInfo,
+  type HistoryItemSkillsList,
+  MessageType,
 } from '../types.js';
+import { disableSkill, enableSkill } from '../../utils/skillSettings.js';
+import { getErrorMessage } from '../../utils/errors.js';
+
+import { getAdminErrorMessage } from '@google/gemini-cli-core';
+import {
+  linkSkill,
+  renderSkillActionFeedback,
+} from '../../utils/skillUtils.js';
 import { SettingScope } from '../../config/settings.js';
-import { enableSkill, disableSkill } from '../../utils/skillSettings.js';
-import { renderSkillActionFeedback } from '../../utils/skillUtils.js';
+import {
+  requestConsentInteractive,
+  skillsConsentString,
+} from '../../config/extensions/consent.js';
 
 async function listAction(
   context: CommandContext,
@@ -66,6 +76,69 @@ async function listAction(
   context.ui.addItem(skillsListItem);
 }
 
+async function linkAction(
+  context: CommandContext,
+  args: string,
+): Promise<void | SlashCommandActionReturn> {
+  const parts = args.trim().split(/\s+/);
+  const sourcePath = parts[0];
+
+  if (!sourcePath) {
+    context.ui.addItem({
+      type: MessageType.ERROR,
+      text: 'Usage: /skills link <path> [--scope user|workspace]',
+    });
+    return;
+  }
+
+  let scopeArg = 'user';
+  if (parts.length >= 3 && parts[1] === '--scope') {
+    scopeArg = parts[2];
+  } else if (parts.length >= 2 && parts[1].startsWith('--scope=')) {
+    scopeArg = parts[1].split('=')[1];
+  }
+
+  const scope = scopeArg === 'workspace' ? 'workspace' : 'user';
+
+  try {
+    await linkSkill(
+      sourcePath,
+      scope,
+      (msg) =>
+        context.ui.addItem({
+          type: MessageType.INFO,
+          text: msg,
+        }),
+      async (skills, targetDir) => {
+        const consentString = await skillsConsentString(
+          skills,
+          sourcePath,
+          targetDir,
+          true,
+        );
+        return requestConsentInteractive(
+          consentString,
+          context.ui.setConfirmationRequest.bind(context.ui),
+        );
+      },
+    );
+
+    context.ui.addItem({
+      type: MessageType.INFO,
+      text: `Successfully linked skills from "${sourcePath}" (${scope}).`,
+    });
+
+    if (context.services.config) {
+      await context.services.config.reloadSkills();
+    }
+  } catch (error) {
+    context.ui.addItem({
+      type: MessageType.ERROR,
+      text: `Failed to link skills: ${getErrorMessage(error)}`,
+    });
+  }
+}
+
 async function disableAction(
   context: CommandContext,
   args: string,
@@ -83,7 +156,10 @@ async function disableAction(
     context.ui.addItem(
       {
         type: MessageType.ERROR,
-        text: 'Agent skills are disabled by your admin.',
+        text: getAdminErrorMessage(
+          'Agent skills',
+          context.services.config ?? undefined,
+        ),
       },
       Date.now(),
     );
@@ -141,7 +217,10 @@ async function enableAction(
     context.ui.addItem(
       {
         type: MessageType.ERROR,
-        text: 'Agent skills are disabled by your admin.',
+        text: getAdminErrorMessage(
+          'Agent skills',
+          context.services.config ?? undefined,
+        ),
       },
       Date.now(),
     );
@@ -293,6 +372,13 @@ export const skillsCommand: SlashCommand = {
       kind: CommandKind.BUILT_IN,
       action: listAction,
     },
+    {
+      name: 'link',
+      description:
+        'Link an agent skill from a local path. Usage: /skills link <path> [--scope user|workspace]',
+      kind: CommandKind.BUILT_IN,
+      action: linkAction,
+    },
     {
       name: 'disable',
       description: 'Disable a skill by name. Usage: /skills disable <name>',

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

@@ -83,7 +83,14 @@ export interface CommandContext {
     extensionsUpdateState: Map<string, ExtensionUpdateStatus>;
     dispatchExtensionStateUpdate: (action: ExtensionUpdateAction) => void;
     addConfirmUpdateExtensionRequest: (value: ConfirmationRequest) => void;
+    /**
+     * Sets a confirmation request to be displayed to the user.
+     *
+     * @param value The confirmation request details.
+     */
+    setConfirmationRequest: (value: ConfirmationRequest) => void;
     removeComponent: () => void;
+    toggleBackgroundShell: () => void;
   };
   // Session-specific data
   session: {

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

@@ -7,6 +7,7 @@
 import { Box } from 'ink';
 import { Header } from './Header.js';
 import { Tips } from './Tips.js';
+import { UserIdentity } from './UserIdentity.js';
 import { useSettings } from '../contexts/SettingsContext.js';
 import { useConfig } from '../contexts/ConfigContext.js';
 import { useUIState } from '../contexts/UIStateContext.js';
@@ -40,6 +41,9 @@ export const AppHeader = ({ version }: AppHeaderProps) => {
           )}
         </>
       )}
+      {settings.merged.ui.showUserIdentity !== false && (
+        <UserIdentity config={config} />
+      )}
       {!(settings.merged.ui.hideTips || config.getScreenReader()) &&
         showTips && <Tips config={config} />}
     </Box>

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

@@ -10,6 +10,8 @@ import { renderWithProviders } from '../../test-utils/render.js';
 import { waitFor } from '../../test-utils/async.js';
 import { AskUserDialog } from './AskUserDialog.js';
 import { QuestionType, type Question } from '@google/gemini-cli-core';
+import chalk from 'chalk';
+import { UIStateContext, type UIState } from '../contexts/UIStateContext.js';
 
 // Helper to write to stdin with proper act() wrapping
 const writeKey = (stdin: { write: (data: string) => void }, key: string) => {
@@ -41,6 +43,7 @@ describe('AskUserDialog', () => {
         questions={authQuestion}
         onSubmit={vi.fn()}
         onCancel={vi.fn()}
+        width={120}
       />,
       { width: 120 },
     );
@@ -105,6 +108,7 @@ describe('AskUserDialog', () => {
           questions={questions}
           onSubmit={onSubmit}
           onCancel={vi.fn()}
+          width={120}
         />,
         { width: 120 },
       );
@@ -124,6 +128,7 @@ describe('AskUserDialog', () => {
         questions={authQuestion}
         onSubmit={onSubmit}
         onCancel={vi.fn()}
+        width={120}
       />,
       { width: 120 },
     );
@@ -153,12 +158,57 @@ describe('AskUserDialog', () => {
     });
   });
 
+  describe.each([
+    { useAlternateBuffer: true, expectedArrows: false },
+    { useAlternateBuffer: false, expectedArrows: true },
+  ])(
+    'Scroll Arrows (useAlternateBuffer: $useAlternateBuffer)',
+    ({ useAlternateBuffer, expectedArrows }) => {
+      it(`shows scroll arrows correctly when useAlternateBuffer is ${useAlternateBuffer}`, async () => {
+        const questions: Question[] = [
+          {
+            question: 'Choose an option',
+            header: 'Scroll Test',
+            options: Array.from({ length: 15 }, (_, i) => ({
+              label: `Option ${i + 1}`,
+              description: `Description ${i + 1}`,
+            })),
+            multiSelect: false,
+          },
+        ];
+
+        const { lastFrame } = renderWithProviders(
+          <AskUserDialog
+            questions={questions}
+            onSubmit={vi.fn()}
+            onCancel={vi.fn()}
+            width={80}
+            availableHeight={10} // Small height to force scrolling
+          />,
+          { useAlternateBuffer },
+        );
+
+        await waitFor(() => {
+          if (expectedArrows) {
+            expect(lastFrame()).toContain('▲');
+            expect(lastFrame()).toContain('▼');
+          } else {
+            expect(lastFrame()).not.toContain('▲');
+            expect(lastFrame()).not.toContain('▼');
+          }
+          expect(lastFrame()).toMatchSnapshot();
+        });
+      });
+    },
+  );
+
   it('navigates to custom option when typing unbound characters (Type-to-Jump)', async () => {
     const { stdin, lastFrame } = renderWithProviders(
       <AskUserDialog
         questions={authQuestion}
         onSubmit={vi.fn()}
         onCancel={vi.fn()}
+        width={120}
       />,
       { width: 120 },
     );
@@ -209,6 +259,7 @@ describe('AskUserDialog', () => {
         questions={multiQuestions}
         onSubmit={vi.fn()}
         onCancel={vi.fn()}
+        width={120}
       />,
       { width: 120 },
     );
@@ -222,6 +273,7 @@ describe('AskUserDialog', () => {
         questions={authQuestion}
         onSubmit={vi.fn()}
         onCancel={vi.fn()}
+        width={120}
       />,
       { width: 120 },
     );
@@ -235,6 +287,7 @@ describe('AskUserDialog', () => {
         questions={authQuestion}
         onSubmit={vi.fn()}
         onCancel={vi.fn()}
+        width={120}
       />,
       { width: 120 },
     );
@@ -265,6 +318,7 @@ describe('AskUserDialog', () => {
         questions={multiQuestions}
         onSubmit={vi.fn()}
         onCancel={vi.fn()}
+        width={120}
       />,
       { width: 120 },
     );
@@ -306,6 +360,7 @@ describe('AskUserDialog', () => {
         questions={multiQuestions}
         onSubmit={onSubmit}
         onCancel={vi.fn()}
+        width={120}
       />,
       { width: 120 },
     );
@@ -373,6 +428,7 @@ describe('AskUserDialog', () => {
         questions={multiQuestions}
         onSubmit={vi.fn()}
         onCancel={vi.fn()}
+        width={120}
       />,
       { width: 120 },
     );
@@ -401,6 +457,7 @@ describe('AskUserDialog', () => {
         questions={multiQuestions}
         onSubmit={vi.fn()}
         onCancel={vi.fn()}
+        width={120}
       />,
       { width: 120 },
     );
@@ -445,6 +502,7 @@ describe('AskUserDialog', () => {
         questions={multiQuestions}
         onSubmit={vi.fn()}
         onCancel={vi.fn()}
+        width={120}
       />,
       { width: 120 },
     );
@@ -480,6 +538,7 @@ describe('AskUserDialog', () => {
         questions={multiQuestions}
         onSubmit={onSubmit}
         onCancel={vi.fn()}
+        width={120}
       />,
       { width: 120 },
     );
@@ -512,6 +571,7 @@ describe('AskUserDialog', () => {
           questions={textQuestion}
           onSubmit={vi.fn()}
           onCancel={vi.fn()}
+          width={120}
         />,
         { width: 120 },
       );
@@ -533,6 +593,7 @@ describe('AskUserDialog', () => {
           questions={textQuestion}
           onSubmit={vi.fn()}
           onCancel={vi.fn()}
+          width={120}
         />,
         { width: 120 },
       );
@@ -554,6 +615,7 @@ describe('AskUserDialog', () => {
           questions={textQuestion}
           onSubmit={vi.fn()}
           onCancel={vi.fn()}
+          width={120}
         />,
         { width: 120 },
       );
@@ -588,6 +650,7 @@ describe('AskUserDialog', () => {
           questions={textQuestion}
           onSubmit={vi.fn()}
           onCancel={vi.fn()}
+          width={120}
         />,
         { width: 120 },
       );
@@ -618,6 +681,7 @@ describe('AskUserDialog', () => {
           questions={mixedQuestions}
           onSubmit={vi.fn()}
           onCancel={vi.fn()}
+          width={120}
         />,
         { width: 120 },
       );
@@ -664,6 +728,7 @@ describe('AskUserDialog', () => {
           questions={mixedQuestions}
           onSubmit={onSubmit}
           onCancel={vi.fn()}
+          width={120}
         />,
         { width: 120 },
       );
@@ -713,6 +778,7 @@ describe('AskUserDialog', () => {
           questions={textQuestion}
           onSubmit={onSubmit}
           onCancel={vi.fn()}
+          width={120}
         />,
         { width: 120 },
       );
@@ -738,6 +804,7 @@ describe('AskUserDialog', () => {
           questions={textQuestion}
           onSubmit={vi.fn()}
           onCancel={onCancel}
+          width={120}
         />,
         { width: 120 },
       );
@@ -783,6 +850,7 @@ describe('AskUserDialog', () => {
           questions={multiQuestions}
           onSubmit={vi.fn()}
           onCancel={vi.fn()}
+          width={120}
         />,
         { width: 120 },
       );
@@ -841,6 +909,7 @@ describe('AskUserDialog', () => {
           questions={multiQuestions}
           onSubmit={onSubmit}
           onCancel={vi.fn()}
+          width={120}
         />,
         { width: 120 },
       );
@@ -872,4 +941,258 @@ describe('AskUserDialog', () => {
       });
     });
   });
+
+  describe('Markdown rendering', () => {
+    it('auto-bolds plain single-line questions', async () => {
+      const questions: Question[] = [
+        {
+          question: 'Which option do you prefer?',
+          header: 'Test',
+          options: [{ label: 'Yes', description: '' }],
+          multiSelect: false,
+        },
+      ];
+
+      const { lastFrame } = renderWithProviders(
+        <AskUserDialog
+          questions={questions}
+          onSubmit={vi.fn()}
+          onCancel={vi.fn()}
+          width={120}
+          availableHeight={40}
+        />,
+        { width: 120 },
+      );
+
+      await waitFor(() => {
+        const frame = lastFrame();
+        // Plain text should be rendered as bold
+        expect(frame).toContain(chalk.bold('Which option do you prefer?'));
+      });
+    });
+
+    it('does not auto-bold questions that already have markdown', async () => {
+      const questions: Question[] = [
+        {
+          question: 'Is **this** working?',
+          header: 'Test',
+          options: [{ label: 'Yes', description: '' }],
+          multiSelect: false,
+        },
+      ];
+
+      const { lastFrame } = renderWithProviders(
+        <AskUserDialog
+          questions={questions}
+          onSubmit={vi.fn()}
+          onCancel={vi.fn()}
+          width={120}
+          availableHeight={40}
+        />,
+        { width: 120 },
+      );
+
+      await waitFor(() => {
+        const frame = lastFrame();
+        // Should NOT have double-bold (the whole question bolded AND "this" bolded)
+        // "Is " should not be bold, only "this" should be bold
+        expect(frame).toContain('Is ');
+        expect(frame).toContain(chalk.bold('this'));
+        expect(frame).not.toContain('**this**');
+      });
+    });
+
+    it('renders bold markdown in question', async () => {
+      const questions: Question[] = [
+        {
+          question: 'Is **this** working?',
+          header: 'Test',
+          options: [{ label: 'Yes', description: '' }],
+          multiSelect: false,
+        },
+      ];
+
+      const { lastFrame } = renderWithProviders(
+        <AskUserDialog
+          questions={questions}
+          onSubmit={vi.fn()}
+          onCancel={vi.fn()}
+          width={120}
+          availableHeight={40}
+        />,
+        { width: 120 },
+      );
+
+      await waitFor(() => {
+        const frame = lastFrame();
+        // Check for chalk.bold('this') - asterisks should be gone, text should be bold
+        expect(frame).toContain(chalk.bold('this'));
+        expect(frame).not.toContain('**this**');
+      });
+    });
+
+    it('renders inline code markdown in question', async () => {
+      const questions: Question[] = [
+        {
+          question: 'Run `npm start`?',
+          header: 'Test',
+          options: [{ label: 'Yes', description: '' }],
+          multiSelect: false,
+        },
+      ];
+
+      const { lastFrame } = renderWithProviders(
+        <AskUserDialog
+          questions={questions}
+          onSubmit={vi.fn()}
+          onCancel={vi.fn()}
+          width={120}
+          availableHeight={40}
+        />,
+        { width: 120 },
+      );
+
+      await waitFor(() => {
+        const frame = lastFrame();
+        // Backticks should be removed
+        expect(frame).toContain('npm start');
+        expect(frame).not.toContain('`npm start`');
+      });
+    });
+  });
+
+  it('uses availableTerminalHeight from UIStateContext if availableHeight prop is missing', () => {
+    const questions: Question[] = [
+      {
+        question: 'Choose an option',
+        header: 'Context Test',
+        options: Array.from({ length: 10 }, (_, i) => ({
+          label: `Option ${i + 1}`,
+          description: `Description ${i + 1}`,
+        })),
+        multiSelect: false,
+      },
+    ];
+
+    const mockUIState = {
+      availableTerminalHeight: 5, // Small height to force scroll arrows
+    } as UIState;
+
+    const { lastFrame } = renderWithProviders(
+      <UIStateContext.Provider value={mockUIState}>
+        <AskUserDialog
+          questions={questions}
+          onSubmit={vi.fn()}
+          onCancel={vi.fn()}
+          width={80}
+        />
+      </UIStateContext.Provider>,
+      { useAlternateBuffer: false },
+    );
+
+    // With height 5 and alternate buffer disabled, it should show scroll arrows (▲)
+    expect(lastFrame()).toContain('▲');
+    expect(lastFrame()).toContain('▼');
+  });
+
+  it('does NOT truncate the question when in alternate buffer mode even with small height', () => {
+    const longQuestion =
+      'This is a very long question ' + 'with many words '.repeat(10);
+    const questions: Question[] = [
+      {
+        question: longQuestion,
+        header: 'Alternate Buffer Test',
+        options: [{ label: 'Option 1', description: 'Desc 1' }],
+        multiSelect: false,
+      },
+    ];
+
+    const mockUIState = {
+      availableTerminalHeight: 5,
+    } as UIState;
+
+    const { lastFrame } = renderWithProviders(
+      <UIStateContext.Provider value={mockUIState}>
+        <AskUserDialog
+          questions={questions}
+          onSubmit={vi.fn()}
+          onCancel={vi.fn()}
+          width={40} // Small width to force wrapping
+        />
+      </UIStateContext.Provider>,
+      { useAlternateBuffer: true },
+    );
+
+    // Should NOT contain the truncation message
+    expect(lastFrame()).not.toContain('hidden ...');
+    // Should contain the full long question (or at least its parts)
+    expect(lastFrame()).toContain('This is a very long question');
+  });
+
+  describe('Choice question placeholder', () => {
+    it('uses placeholder for "Other" option when provided', async () => {
+      const questions: Question[] = [
+        {
+          question: 'Select your preferred language:',
+          header: 'Language',
+          options: [
+            { label: 'TypeScript', description: '' },
+            { label: 'JavaScript', description: '' },
+          ],
+          placeholder: 'Type another language...',
+          multiSelect: false,
+        },
+      ];
+
+      const { stdin, lastFrame } = renderWithProviders(
+        <AskUserDialog
+          questions={questions}
+          onSubmit={vi.fn()}
+          onCancel={vi.fn()}
+          width={80}
+        />,
+        { width: 80 },
+      );
+
+      // Navigate to the "Other" option
+      writeKey(stdin, '\x1b[B'); // Down
+      writeKey(stdin, '\x1b[B'); // Down to Other
+
+      await waitFor(() => {
+        expect(lastFrame()).toMatchSnapshot();
+      });
+    });
+
+    it('uses default placeholder when not provided', async () => {
+      const questions: Question[] = [
+        {
+          question: 'Select your preferred language:',
+          header: 'Language',
+          options: [
+            { label: 'TypeScript', description: '' },
+            { label: 'JavaScript', description: '' },
+          ],
+          multiSelect: false,
+        },
+      ];
+
+      const { stdin, lastFrame } = renderWithProviders(
+        <AskUserDialog
+          questions={questions}
+          onSubmit={vi.fn()}
+          onCancel={vi.fn()}
+          width={80}
+        />,
+        { width: 80 },
+      );
+
+      // Navigate to the "Other" option
+      writeKey(stdin, '\x1b[B'); // Down
+      writeKey(stdin, '\x1b[B'); // Down to Other
+
+      await waitFor(() => {
+        expect(lastFrame()).toMatchSnapshot();
+      });
+    });
+  });
 });

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

@@ -21,13 +21,65 @@ import type { SelectionListItem } from '../hooks/useSelectionList.js';
 import { TabHeader, type Tab } from './shared/TabHeader.js';
 import { useKeypress, type Key } from '../hooks/useKeypress.js';
 import { keyMatchers, Command } from '../keyMatchers.js';
-import { checkExhaustive } from '../../utils/checks.js';
+import { checkExhaustive } from '@google/gemini-cli-core';
 import { TextInput } from './shared/TextInput.js';
 import { useTextBuffer } from './shared/text-buffer.js';
-import { UIStateContext } from '../contexts/UIStateContext.js';
 import { getCachedStringWidth } from '../utils/textUtils.js';
 import { useTabbedNavigation } from '../hooks/useTabbedNavigation.js';
 import { DialogFooter } from './shared/DialogFooter.js';
+import { MarkdownDisplay } from '../utils/MarkdownDisplay.js';
+import { RenderInline } from '../utils/InlineMarkdownRenderer.js';
+import { MaxSizedBox } from './shared/MaxSizedBox.js';
+import { UIStateContext } from '../contexts/UIStateContext.js';
+import { useAlternateBuffer } from '../hooks/useAlternateBuffer.js';
+
+/** Padding for dialog content to prevent text from touching edges. */
+const DIALOG_PADDING = 4;
+
+/**
+ * Checks if text is a single line without markdown identifiers.
+ */
+function isPlainSingleLine(text: string): boolean {
+  // Must be a single line (no newlines)
+  if (text.includes('\n') || text.includes('\r')) {
+    return false;
+  }
+
+  // Check for common markdown identifiers
+  const markdownPatterns = [
+    /^#{1,6}\s/, // Headers
+    /^[`~]{3,}/, // Code fences
+    /^[-*+]\s/, // Unordered lists
+    /^\d+\.\s/, // Ordered lists
+    /^[-*_]{3,}$/, // Horizontal rules
+    /\|/, // Tables
+    /\*\*|__/, // Bold
+    /(?<!\*)\*(?!\*)/, // Italic (single asterisk not part of bold)
+    /(?<!_)_(?!_)/, // Italic (single underscore not part of bold)
+    /`[^`]+`/, // Inline code
+    /\[.*?\]\(.*?\)/, // Links
+    /!\[/, // Images
+  ];
+
+  for (const pattern of markdownPatterns) {
+    if (pattern.test(text)) {
+      return false;
+    }
+  }
+
+  return true;
+}
+
+/**
+ * Auto-bolds plain single-line text by wrapping in **.
+ * Returns the text unchanged if it already contains markdown.
+ */
+function autoBoldIfPlain(text: string): string {
+  if (isPlainSingleLine(text)) {
+    return `**${text}**`;
+  }
+  return text;
+}
 
 interface AskUserDialogState {
   answers: { [key: string]: string };
@@ -121,6 +173,14 @@ interface AskUserDialogProps {
    * Useful for managing global keypress handlers.
    */
   onActiveTextInputChange?: (active: boolean) => void;
+  /**
+   * Width of the dialog.
+   */
+  width: number;
+  /**
+   * Height constraint for scrollable content.
+   */
+  availableHeight?: number;
 }
 
 interface ReviewViewProps {
@@ -152,12 +212,7 @@ const ReviewView: React.FC<ReviewViewProps> = ({
   );
 
   return (
-    <Box
-      flexDirection="column"
-      borderStyle="round"
-      paddingX={1}
-      borderColor={theme.border.default}
-    >
+    <Box flexDirection="column">
       {progressHeader}
       <Box marginBottom={1}>
         <Text bold color={theme.text.primary}>
@@ -174,15 +229,19 @@ const ReviewView: React.FC<ReviewViewProps> = ({
         </Box>
       )}
 
-      {questions.map((q, i) => (
-        <Box key={i} marginBottom={0}>
-          <Text color={theme.text.secondary}>{q.header}</Text>
-          <Text color={theme.text.secondary}> → </Text>
-          <Text color={answers[i] ? theme.text.primary : theme.status.warning}>
-            {answers[i] || '(not answered)'}
-          </Text>
-        </Box>
-      ))}
+      <Box flexDirection="column">
+        {questions.map((q, i) => (
+          <Box key={i} marginBottom={0}>
+            <Text color={theme.text.secondary}>{q.header}</Text>
+            <Text color={theme.text.secondary}> → </Text>
+            <Text
+              color={answers[i] ? theme.text.primary : theme.status.warning}
+            >
+              {answers[i] || '(not answered)'}
+            </Text>
+          </Box>
+        ))}
+      </Box>
       <DialogFooter
         primaryAction="Enter to submit"
         navigationActions="Tab/Shift+Tab to edit answers"
@@ -199,6 +258,7 @@ interface TextQuestionViewProps {
   onSelectionChange?: (answer: string) => void;
   onEditingCustomOption?: (editing: boolean) => void;
   availableWidth: number;
+  availableHeight?: number;
   initialAnswer?: string;
   progressHeader?: React.ReactNode;
   keyboardHints?: React.ReactNode;
@@ -210,12 +270,14 @@ const TextQuestionView: React.FC<TextQuestionViewProps> = ({
   onSelectionChange,
   onEditingCustomOption,
   availableWidth,
+  availableHeight,
   initialAnswer,
   progressHeader,
   keyboardHints,
 }) => {
+  const isAlternateBuffer = useAlternateBuffer();
   const prefix = '> ';
-  const horizontalPadding = 4 + 1; // Padding from Box (2) and border (2) + 1 for cursor
+  const horizontalPadding = 1; // 1 for cursor
   const bufferWidth =
     availableWidth - getCachedStringWidth(prefix) - horizontalPadding;
 
@@ -241,12 +303,15 @@ const TextQuestionView: React.FC<TextQuestionViewProps> = ({
   const handleExtraKeys = useCallback(
     (key: Key) => {
       if (keyMatchers[Command.QUIT](key)) {
+        if (textValue === '') {
+          return false;
+        }
         buffer.setText('');
         return true;
       }
       return false;
     },
-    [buffer],
+    [buffer, textValue],
   );
 
   useKeypress(handleExtraKeys, { isActive: true, priority: true });
@@ -270,18 +335,30 @@ const TextQuestionView: React.FC<TextQuestionViewProps> = ({
 
   const placeholder = question.placeholder || 'Enter your response';
 
+  const HEADER_HEIGHT = progressHeader ? 2 : 0;
+  const INPUT_HEIGHT = 2; // TextInput + margin
+  const FOOTER_HEIGHT = 2; // DialogFooter + margin
+  const overhead = HEADER_HEIGHT + INPUT_HEIGHT + FOOTER_HEIGHT;
+  const questionHeight =
+    availableHeight && !isAlternateBuffer
+      ? Math.max(1, availableHeight - overhead)
+      : undefined;
+
   return (
-    <Box
-      flexDirection="column"
-      borderStyle="round"
-      paddingX={1}
-      borderColor={theme.border.default}
-    >
+    <Box flexDirection="column">
       {progressHeader}
       <Box marginBottom={1}>
-        <Text bold color={theme.text.primary}>
-          {question.question}
-        </Text>
+        <MaxSizedBox
+          maxHeight={questionHeight}
+          maxWidth={availableWidth}
+          overflowDirection="bottom"
+        >
+          <MarkdownDisplay
+            text={autoBoldIfPlain(question.question)}
+            terminalWidth={availableWidth - DIALOG_PADDING}
+            isPending={false}
+          />
+        </MaxSizedBox>
       </Box>
 
       <Box flexDirection="row" marginBottom={1}>
@@ -381,6 +458,7 @@ interface ChoiceQuestionViewProps {
   onSelectionChange?: (answer: string) => void;
   onEditingCustomOption?: (editing: boolean) => void;
   availableWidth: number;
+  availableHeight?: number;
   initialAnswer?: string;
   progressHeader?: React.ReactNode;
   keyboardHints?: React.ReactNode;
@@ -391,14 +469,13 @@ const ChoiceQuestionView: React.FC<ChoiceQuestionViewProps> = ({
   onAnswer,
   onSelectionChange,
   onEditingCustomOption,
+  availableWidth,
+  availableHeight,
   initialAnswer,
   progressHeader,
   keyboardHints,
 }) => {
-  const uiState = useContext(UIStateContext);
-  const terminalWidth = uiState?.terminalWidth ?? 80;
-  const availableWidth = terminalWidth;
-
+  const isAlternateBuffer = useAlternateBuffer();
   const numOptions =
     (question.options?.length ?? 0) + (question.type !== 'yesno' ? 1 : 0);
   const numLen = String(numOptions).length;
@@ -407,15 +484,9 @@ const ChoiceQuestionView: React.FC<ChoiceQuestionViewProps> = ({
   const checkboxWidth = question.multiSelect ? 4 : 1; // "[x] " or " "
   const checkmarkWidth = question.multiSelect ? 0 : 2; // "" or " ✓"
   const cursorPadding = 1; // Extra character for cursor at end of line
-  const outerBoxPadding = 4; // border (2) + paddingX (2)
 
   const horizontalPadding =
-    outerBoxPadding +
-    radioWidth +
-    numberWidth +
-    checkboxWidth +
-    checkmarkWidth +
-    cursorPadding;
+    radioWidth + numberWidth + checkboxWidth + checkmarkWidth + cursorPadding;
 
   const bufferWidth = availableWidth - horizontalPadding;
 
@@ -544,6 +615,9 @@ const ChoiceQuestionView: React.FC<ChoiceQuestionViewProps> = ({
     (key: Key) => {
       // If focusing custom option, handle Ctrl+C
       if (isCustomOptionFocused && keyMatchers[Command.QUIT](key)) {
+        if (customOptionText === '') {
+          return false;
+        }
         customBuffer.setText('');
         return true;
       }
@@ -586,7 +660,12 @@ const ChoiceQuestionView: React.FC<ChoiceQuestionViewProps> = ({
       }
       return false;
     },
-    [isCustomOptionFocused, customBuffer, onEditingCustomOption],
+    [
+      isCustomOptionFocused,
+      customBuffer,
+      onEditingCustomOption,
+      customOptionText,
+    ],
   );
 
   useKeypress(handleExtraKeys, { isActive: true, priority: true });
@@ -698,31 +777,53 @@ const ChoiceQuestionView: React.FC<ChoiceQuestionViewProps> = ({
     }
   }, [customOptionText, isCustomOptionSelected, question.multiSelect]);
 
+  const HEADER_HEIGHT = progressHeader ? 2 : 0;
+  const TITLE_MARGIN = 1;
+  const FOOTER_HEIGHT = 2; // DialogFooter + margin
+  const overhead = HEADER_HEIGHT + TITLE_MARGIN + FOOTER_HEIGHT;
+  const listHeight = availableHeight
+    ? Math.max(1, availableHeight - overhead)
+    : undefined;
+  const questionHeight =
+    listHeight && !isAlternateBuffer
+      ? Math.min(15, Math.max(1, listHeight - DIALOG_PADDING))
+      : undefined;
+  const maxItemsToShow =
+    listHeight && questionHeight
+      ? Math.max(1, Math.floor((listHeight - questionHeight) / 2))
+      : selectionItems.length;
+
   return (
-    <Box
-      flexDirection="column"
-      borderStyle="round"
-      paddingX={1}
-      borderColor={theme.border.default}
-    >
+    <Box flexDirection="column">
       {progressHeader}
-      <Box marginBottom={1}>
-        <Text bold color={theme.text.primary}>
-          {question.question}
-        </Text>
+      <Box marginBottom={TITLE_MARGIN}>
+        <MaxSizedBox
+          maxHeight={questionHeight}
+          maxWidth={availableWidth}
+          overflowDirection="bottom"
+        >
+          <Box flexDirection="column">
+            <MarkdownDisplay
+              text={autoBoldIfPlain(question.question)}
+              terminalWidth={availableWidth - DIALOG_PADDING}
+              isPending={false}
+            />
+            {question.multiSelect && (
+              <Text color={theme.text.secondary} italic>
+                (Select all that apply)
+              </Text>
+            )}
+          </Box>
+        </MaxSizedBox>
       </Box>
-      {question.multiSelect && (
-        <Text color={theme.text.secondary} italic>
-          {' '}
-          (Select all that apply)
-        </Text>
-      )}
 
       <BaseSelectionList<OptionItem>
         items={selectionItems}
         onSelect={handleSelect}
         onHighlight={handleHighlight}
         focusKey={isCustomOptionFocused ? 'other' : undefined}
+        maxItemsToShow={maxItemsToShow}
+        showScrollArrows={true}
         renderItem={(item, context) => {
           const optionItem = item.value;
           const isChecked =
@@ -734,7 +835,7 @@ const ChoiceQuestionView: React.FC<ChoiceQuestionViewProps> = ({
 
           // Render inline text input for custom option
           if (optionItem.type === 'other') {
-            const placeholder = 'Enter a custom value';
+            const placeholder = question.placeholder || 'Enter a custom value';
             return (
               <Box flexDirection="row">
                 {showCheck && (
@@ -787,7 +888,10 @@ const ChoiceQuestionView: React.FC<ChoiceQuestionViewProps> = ({
               {optionItem.description && (
                 <Text color={theme.text.secondary} wrap="wrap">
                   {' '}
-                  {optionItem.description}
+                  <RenderInline
+                    text={optionItem.description}
+                    defaultColor={theme.text.secondary}
+                  />
                 </Text>
               )}
             </Box>
@@ -804,14 +908,19 @@ export const AskUserDialog: React.FC<AskUserDialogProps> = ({
   onSubmit,
   onCancel,
   onActiveTextInputChange,
+  width,
+  availableHeight: availableHeightProp,
 }) => {
+  const uiState = useContext(UIStateContext);
+  const availableHeight =
+    availableHeightProp ??
+    (uiState?.constrainHeight !== false
+      ? uiState?.availableTerminalHeight
+      : undefined);
+
   const [state, dispatch] = useReducer(askUserDialogReducerLogic, initialState);
   const { answers, isEditingCustomOption, submitted } = state;
 
-  const uiState = useContext(UIStateContext);
-  const terminalWidth = uiState?.terminalWidth ?? 80;
-  const availableWidth = terminalWidth;
-
   const reviewTabIndex = questions.length;
   const tabCount =
     questions.length > 1 ? questions.length + 1 : questions.length;
@@ -842,9 +951,12 @@ export const AskUserDialog: React.FC<AskUserDialogProps> = ({
       if (keyMatchers[Command.ESCAPE](key)) {
         onCancel();
         return true;
-      } else if (keyMatchers[Command.QUIT](key) && !isEditingCustomOption) {
-        onCancel();
-        return true;
+      } else if (keyMatchers[Command.QUIT](key)) {
+        if (!isEditingCustomOption) {
+          onCancel();
+        }
+        // Return false to let ctrl-C bubble up to AppContainer for exit flow
+        return false;
       }
       return false;
     },
@@ -1021,7 +1133,8 @@ export const AskUserDialog: React.FC<AskUserDialogProps> = ({
         onAnswer={handleAnswer}
         onSelectionChange={handleSelectionChange}
         onEditingCustomOption={handleEditingCustomOption}
-        availableWidth={availableWidth}
+        availableWidth={width}
+        availableHeight={availableHeight}
         initialAnswer={answers[currentQuestionIndex]}
         progressHeader={progressHeader}
         keyboardHints={keyboardHints}
@@ -1033,7 +1146,8 @@ export const AskUserDialog: React.FC<AskUserDialogProps> = ({
         onAnswer={handleAnswer}
         onSelectionChange={handleSelectionChange}
         onEditingCustomOption={handleEditingCustomOption}
-        availableWidth={availableWidth}
+        availableWidth={width}
+        availableHeight={availableHeight}
         initialAnswer={answers[currentQuestionIndex]}
         progressHeader={progressHeader}
         keyboardHints={keyboardHints}
@@ -1043,7 +1157,7 @@ export const AskUserDialog: React.FC<AskUserDialogProps> = ({
   return (
     <Box
       flexDirection="column"
-      width={availableWidth}
+      width={width}
       aria-label={`Question ${currentQuestionIndex + 1} of ${questions.length}: ${currentQuestion.question}`}
     >
       {questionView}

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

@@ -0,0 +1,459 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { render } from '../../test-utils/render.js';
+import { describe, it, expect, vi, beforeEach } from 'vitest';
+import { BackgroundShellDisplay } from './BackgroundShellDisplay.js';
+import { type BackgroundShell } from '../hooks/shellCommandProcessor.js';
+import { ShellExecutionService } from '@google/gemini-cli-core';
+import { act } from 'react';
+import { type Key, type KeypressHandler } from '../contexts/KeypressContext.js';
+import { ScrollProvider } from '../contexts/ScrollProvider.js';
+import { Box } from 'ink';
+
+const delay = (ms: number) => new Promise((resolve) => setTimeout(resolve, ms));
+
+// Mock dependencies
+const mockDismissBackgroundShell = vi.fn();
+const mockSetActiveBackgroundShellPid = vi.fn();
+const mockSetIsBackgroundShellListOpen = vi.fn();
+const mockHandleWarning = vi.fn();
+const mockSetEmbeddedShellFocused = vi.fn();
+
+vi.mock('../contexts/UIActionsContext.js', () => ({
+  useUIActions: () => ({
+    dismissBackgroundShell: mockDismissBackgroundShell,
+    setActiveBackgroundShellPid: mockSetActiveBackgroundShellPid,
+    setIsBackgroundShellListOpen: mockSetIsBackgroundShellListOpen,
+    handleWarning: mockHandleWarning,
+    setEmbeddedShellFocused: mockSetEmbeddedShellFocused,
+  }),
+}));
+
+vi.mock('@google/gemini-cli-core', async (importOriginal) => {
+  const actual =
+    await importOriginal<typeof import('@google/gemini-cli-core')>();
+  return {
+    ...actual,
+    ShellExecutionService: {
+      resizePty: vi.fn(),
+      subscribe: vi.fn(() => vi.fn()),
+    },
+  };
+});
+
+// Mock AnsiOutputText since it's a complex component
+vi.mock('./AnsiOutput.js', () => ({
+  AnsiOutputText: ({ data }: { data: string | unknown }) => {
+    if (typeof data === 'string') return <>{data}</>;
+    // Simple serialization for object data
+    return <>{JSON.stringify(data)}</>;
+  },
+}));
+
+// Mock useKeypress
+let keypressHandlers: Array<{ handler: KeypressHandler; isActive: boolean }> =
+  [];
+vi.mock('../hooks/useKeypress.js', () => ({
+  useKeypress: vi.fn((handler, { isActive }) => {
+    keypressHandlers.push({ handler, isActive });
+  }),
+}));
+
+const simulateKey = (key: Partial<Key>) => {
+  const fullKey: Key = createMockKey(key);
+  keypressHandlers.forEach(({ handler, isActive }) => {
+    if (isActive) {
+      handler(fullKey);
+    }
+  });
+};
+
+vi.mock('../contexts/MouseContext.js', () => ({
+  useMouseContext: vi.fn(() => ({
+    subscribe: vi.fn(),
+    unsubscribe: vi.fn(),
+  })),
+  useMouse: vi.fn(),
+}));
+
+// Mock ScrollableList
+vi.mock('./shared/ScrollableList.js', () => ({
+  SCROLL_TO_ITEM_END: 999999,
+  ScrollableList: vi.fn(
+    ({
+      data,
+      renderItem,
+    }: {
+      data: BackgroundShell[];
+      renderItem: (props: {
+        item: BackgroundShell;
+        index: number;
+      }) => React.ReactNode;
+    }) => (
+      <Box flexDirection="column">
+        {data.map((item: BackgroundShell, index: number) => (
+          <Box key={index}>{renderItem({ item, index })}</Box>
+        ))}
+      </Box>
+    ),
+  ),
+}));
+
+const createMockKey = (overrides: Partial<Key>): Key => ({
+  name: '',
+  ctrl: false,
+  alt: false,
+  cmd: false,
+  shift: false,
+  insertable: false,
+  sequence: '',
+  ...overrides,
+});
+
+describe('<BackgroundShellDisplay />', () => {
+  const mockShells = new Map<number, BackgroundShell>();
+  const shell1: BackgroundShell = {
+    pid: 1001,
+    command: 'npm start',
+    output: 'Starting server...',
+    isBinary: false,
+    binaryBytesReceived: 0,
+    status: 'running',
+  };
+  const shell2: BackgroundShell = {
+    pid: 1002,
+    command: 'tail -f log.txt',
+    output: 'Log entry 1',
+    isBinary: false,
+    binaryBytesReceived: 0,
+    status: 'running',
+  };
+
+  beforeEach(() => {
+    vi.clearAllMocks();
+    mockShells.clear();
+    mockShells.set(shell1.pid, shell1);
+    mockShells.set(shell2.pid, shell2);
+    keypressHandlers = [];
+  });
+
+  it('renders the output of the active shell', async () => {
+    const { lastFrame } = render(
+      <ScrollProvider>
+        <BackgroundShellDisplay
+          shells={mockShells}
+          activePid={shell1.pid}
+          width={80}
+          height={24}
+          isFocused={false}
+          isListOpenProp={false}
+        />
+      </ScrollProvider>,
+    );
+    await act(async () => {
+      await delay(0);
+    });
+
+    expect(lastFrame()).toMatchSnapshot();
+  });
+
+  it('renders tabs for multiple shells', async () => {
+    const { lastFrame } = render(
+      <ScrollProvider>
+        <BackgroundShellDisplay
+          shells={mockShells}
+          activePid={shell1.pid}
+          width={100}
+          height={24}
+          isFocused={false}
+          isListOpenProp={false}
+        />
+      </ScrollProvider>,
+    );
+    await act(async () => {
+      await delay(0);
+    });
+
+    expect(lastFrame()).toMatchSnapshot();
+  });
+
+  it('highlights the focused state', async () => {
+    const { lastFrame } = render(
+      <ScrollProvider>
+        <BackgroundShellDisplay
+          shells={mockShells}
+          activePid={shell1.pid}
+          width={80}
+          height={24}
+          isFocused={true} // Focused
+          isListOpenProp={false}
+        />
+      </ScrollProvider>,
+    );
+    await act(async () => {
+      await delay(0);
+    });
+
+    expect(lastFrame()).toMatchSnapshot();
+  });
+
+  it('resizes the PTY on mount and when dimensions change', async () => {
+    const { rerender } = render(
+      <ScrollProvider>
+        <BackgroundShellDisplay
+          shells={mockShells}
+          activePid={shell1.pid}
+          width={80}
+          height={24}
+          isFocused={false}
+          isListOpenProp={false}
+        />
+      </ScrollProvider>,
+    );
+    await act(async () => {
+      await delay(0);
+    });
+
+    expect(ShellExecutionService.resizePty).toHaveBeenCalledWith(
+      shell1.pid,
+      76,
+      21,
+    );
+
+    rerender(
+      <ScrollProvider>
+        <BackgroundShellDisplay
+          shells={mockShells}
+          activePid={shell1.pid}
+          width={100}
+          height={30}
+          isFocused={false}
+          isListOpenProp={false}
+        />
+      </ScrollProvider>,
+    );
+    await act(async () => {
+      await delay(0);
+    });
+
+    expect(ShellExecutionService.resizePty).toHaveBeenCalledWith(
+      shell1.pid,
+      96,
+      27,
+    );
+  });
+
+  it('renders the process list when isListOpenProp is true', async () => {
+    const { lastFrame } = render(
+      <ScrollProvider>
+        <BackgroundShellDisplay
+          shells={mockShells}
+          activePid={shell1.pid}
+          width={80}
+          height={24}
+          isFocused={true}
+          isListOpenProp={true}
+        />
+      </ScrollProvider>,
+    );
+    await act(async () => {
+      await delay(0);
+    });
+
+    expect(lastFrame()).toMatchSnapshot();
+  });
+
+  it('selects the current process and closes the list when Ctrl+L is pressed in list view', async () => {
+    render(
+      <ScrollProvider>
+        <BackgroundShellDisplay
+          shells={mockShells}
+          activePid={shell1.pid}
+          width={80}
+          height={24}
+          isFocused={true}
+          isListOpenProp={true}
+        />
+      </ScrollProvider>,
+    );
+    await act(async () => {
+      await delay(0);
+    });
+
+    // Simulate down arrow to select the second process (handled by RadioButtonSelect)
+    act(() => {
+      simulateKey({ name: 'down' });
+    });
+
+    // Simulate Ctrl+L (handled by BackgroundShellDisplay)
+    act(() => {
+      simulateKey({ name: 'l', ctrl: true });
+    });
+
+    expect(mockSetActiveBackgroundShellPid).toHaveBeenCalledWith(shell2.pid);
+    expect(mockSetIsBackgroundShellListOpen).toHaveBeenCalledWith(false);
+  });
+
+  it('kills the highlighted process when Ctrl+K is pressed in list view', async () => {
+    render(
+      <ScrollProvider>
+        <BackgroundShellDisplay
+          shells={mockShells}
+          activePid={shell1.pid}
+          width={80}
+          height={24}
+          isFocused={true}
+          isListOpenProp={true}
+        />
+      </ScrollProvider>,
+    );
+    await act(async () => {
+      await delay(0);
+    });
+
+    // Initial state: shell1 (active) is highlighted
+
+    // Move to shell2
+    act(() => {
+      simulateKey({ name: 'down' });
+    });
+
+    // Press Ctrl+K
+    act(() => {
+      simulateKey({ name: 'k', ctrl: true });
+    });
+
+    expect(mockDismissBackgroundShell).toHaveBeenCalledWith(shell2.pid);
+  });
+
+  it('kills the active process when Ctrl+K is pressed in output view', async () => {
+    render(
+      <ScrollProvider>
+        <BackgroundShellDisplay
+          shells={mockShells}
+          activePid={shell1.pid}
+          width={80}
+          height={24}
+          isFocused={true}
+          isListOpenProp={false}
+        />
+      </ScrollProvider>,
+    );
+    await act(async () => {
+      await delay(0);
+    });
+
+    act(() => {
+      simulateKey({ name: 'k', ctrl: true });
+    });
+
+    expect(mockDismissBackgroundShell).toHaveBeenCalledWith(shell1.pid);
+  });
+
+  it('scrolls to active shell when list opens', async () => {
+    // shell2 is active
+    const { lastFrame } = render(
+      <ScrollProvider>
+        <BackgroundShellDisplay
+          shells={mockShells}
+          activePid={shell2.pid}
+          width={80}
+          height={24}
+          isFocused={true}
+          isListOpenProp={true}
+        />
+      </ScrollProvider>,
+    );
+    await act(async () => {
+      await delay(0);
+    });
+
+    expect(lastFrame()).toMatchSnapshot();
+  });
+
+  it('keeps exit code status color even when selected', async () => {
+    const exitedShell: BackgroundShell = {
+      pid: 1003,
+      command: 'exit 0',
+      output: '',
+      isBinary: false,
+      binaryBytesReceived: 0,
+      status: 'exited',
+      exitCode: 0,
+    };
+    mockShells.set(exitedShell.pid, exitedShell);
+
+    const { lastFrame } = render(
+      <ScrollProvider>
+        <BackgroundShellDisplay
+          shells={mockShells}
+          activePid={exitedShell.pid}
+          width={80}
+          height={24}
+          isFocused={true}
+          isListOpenProp={true}
+        />
+      </ScrollProvider>,
+    );
+    await act(async () => {
+      await delay(0);
+    });
+
+    expect(lastFrame()).toMatchSnapshot();
+  });
+
+  it('unfocuses the shell when Shift+Tab is pressed', async () => {
+    render(
+      <ScrollProvider>
+        <BackgroundShellDisplay
+          shells={mockShells}
+          activePid={shell1.pid}
+          width={80}
+          height={24}
+          isFocused={true}
+          isListOpenProp={false}
+        />
+      </ScrollProvider>,
+    );
+    await act(async () => {
+      await delay(0);
+    });
+
+    act(() => {
+      simulateKey({ name: 'tab', shift: true });
+    });
+
+    expect(mockSetEmbeddedShellFocused).toHaveBeenCalledWith(false);
+  });
+
+  it('shows a warning when Tab is pressed', async () => {
+    render(
+      <ScrollProvider>
+        <BackgroundShellDisplay
+          shells={mockShells}
+          activePid={shell1.pid}
+          width={80}
+          height={24}
+          isFocused={true}
+          isListOpenProp={false}
+        />
+      </ScrollProvider>,
+    );
+    await act(async () => {
+      await delay(0);
+    });
+
+    act(() => {
+      simulateKey({ name: 'tab' });
+    });
+
+    expect(mockHandleWarning).toHaveBeenCalledWith(
+      'Press Shift+Tab to focus out.',
+    );
+    expect(mockSetEmbeddedShellFocused).not.toHaveBeenCalled();
+  });
+});

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

@@ -0,0 +1,460 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { Box, Text } from 'ink';
+import { useEffect, useState, useRef } from 'react';
+import { useUIActions } from '../contexts/UIActionsContext.js';
+import { theme } from '../semantic-colors.js';
+import {
+  ShellExecutionService,
+  type AnsiOutput,
+  type AnsiLine,
+  type AnsiToken,
+} from '@google/gemini-cli-core';
+import { cpLen, cpSlice, getCachedStringWidth } from '../utils/textUtils.js';
+import { type BackgroundShell } from '../hooks/shellCommandProcessor.js';
+import { Command, keyMatchers } from '../keyMatchers.js';
+import { useKeypress } from '../hooks/useKeypress.js';
+import { commandDescriptions } from '../../config/keyBindings.js';
+import {
+  ScrollableList,
+  type ScrollableListRef,
+} from './shared/ScrollableList.js';
+
+import { SCROLL_TO_ITEM_END } from './shared/VirtualizedList.js';
+
+import {
+  RadioButtonSelect,
+  type RadioSelectItem,
+} from './shared/RadioButtonSelect.js';
+
+interface BackgroundShellDisplayProps {
+  shells: Map<number, BackgroundShell>;
+  activePid: number;
+  width: number;
+  height: number;
+  isFocused: boolean;
+  isListOpenProp: boolean;
+}
+
+const CONTENT_PADDING_X = 1;
+const BORDER_WIDTH = 2; // Left and Right border
+const HEADER_HEIGHT = 3; // 2 for border, 1 for header
+const TAB_DISPLAY_HORIZONTAL_PADDING = 4;
+
+const formatShellCommandForDisplay = (command: string, maxWidth: number) => {
+  const commandFirstLine = command.split('\n')[0];
+  return cpLen(commandFirstLine) > maxWidth
+    ? `${cpSlice(commandFirstLine, 0, maxWidth - 3)}...`
+    : commandFirstLine;
+};
+
+export const BackgroundShellDisplay = ({
+  shells,
+  activePid,
+  width,
+  height,
+  isFocused,
+  isListOpenProp,
+}: BackgroundShellDisplayProps) => {
+  const {
+    dismissBackgroundShell,
+    setActiveBackgroundShellPid,
+    setIsBackgroundShellListOpen,
+    handleWarning,
+    setEmbeddedShellFocused,
+  } = useUIActions();
+  const activeShell = shells.get(activePid);
+  const [output, setOutput] = useState<string | AnsiOutput>(
+    activeShell?.output || '',
+  );
+  const [highlightedPid, setHighlightedPid] = useState<number | null>(
+    activePid,
+  );
+  const outputRef = useRef<ScrollableListRef<AnsiLine | string>>(null);
+  const subscribedRef = useRef(false);
+
+  useEffect(() => {
+    if (!activePid) return;
+
+    const ptyWidth = Math.max(1, width - BORDER_WIDTH - CONTENT_PADDING_X * 2);
+    const ptyHeight = Math.max(1, height - HEADER_HEIGHT);
+    ShellExecutionService.resizePty(activePid, ptyWidth, ptyHeight);
+  }, [activePid, width, height]);
+
+  useEffect(() => {
+    if (!activePid) {
+      setOutput('');
+      return;
+    }
+
+    // Set initial output from the shell object
+    const shell = shells.get(activePid);
+    if (shell) {
+      setOutput(shell.output);
+    }
+
+    subscribedRef.current = false;
+
+    // Subscribe to live updates for the active shell
+    const unsubscribe = ShellExecutionService.subscribe(activePid, (event) => {
+      if (event.type === 'data') {
+        if (typeof event.chunk === 'string') {
+          if (!subscribedRef.current) {
+            // Initial synchronous update contains full history
+            setOutput(event.chunk);
+          } else {
+            // Subsequent updates are deltas for child_process
+            setOutput((prev) =>
+              typeof prev === 'string' ? prev + event.chunk : event.chunk,
+            );
+          }
+        } else {
+          // PTY always sends full AnsiOutput
+          setOutput(event.chunk);
+        }
+      }
+    });
+
+    subscribedRef.current = true;
+
+    return () => {
+      unsubscribe();
+      subscribedRef.current = false;
+    };
+  }, [activePid, shells]);
+
+  // Sync highlightedPid with activePid when list opens
+  useEffect(() => {
+    if (isListOpenProp) {
+      setHighlightedPid(activePid);
+    }
+  }, [isListOpenProp, activePid]);
+
+  useKeypress(
+    (key) => {
+      if (!activeShell) return;
+
+      // Handle Shift+Tab or Tab (in list) to focus out
+      if (
+        keyMatchers[Command.UNFOCUS_BACKGROUND_SHELL](key) ||
+        (isListOpenProp &&
+          keyMatchers[Command.UNFOCUS_BACKGROUND_SHELL_LIST](key))
+      ) {
+        setEmbeddedShellFocused(false);
+        return true;
+      }
+
+      // Handle Tab to warn but propagate
+      if (
+        !isListOpenProp &&
+        keyMatchers[Command.SHOW_BACKGROUND_SHELL_UNFOCUS_WARNING](key)
+      ) {
+        handleWarning(
+          `Press ${commandDescriptions[Command.UNFOCUS_BACKGROUND_SHELL]} to focus out.`,
+        );
+        // Fall through to allow Tab to be sent to the shell
+      }
+
+      if (isListOpenProp) {
+        // Navigation (Up/Down/Enter) is handled by RadioButtonSelect
+        // We only handle special keys not consumed by RadioButtonSelect or overriding them if needed
+        // RadioButtonSelect handles Enter -> onSelect
+
+        if (keyMatchers[Command.BACKGROUND_SHELL_ESCAPE](key)) {
+          setIsBackgroundShellListOpen(false);
+          return true;
+        }
+
+        if (keyMatchers[Command.KILL_BACKGROUND_SHELL](key)) {
+          if (highlightedPid) {
+            dismissBackgroundShell(highlightedPid);
+            // If we killed the active one, the list might update via props
+          }
+          return true;
+        }
+
+        if (keyMatchers[Command.TOGGLE_BACKGROUND_SHELL_LIST](key)) {
+          if (highlightedPid) {
+            setActiveBackgroundShellPid(highlightedPid);
+          }
+          setIsBackgroundShellListOpen(false);
+          return true;
+        }
+        return false;
+      }
+
+      if (keyMatchers[Command.TOGGLE_BACKGROUND_SHELL](key)) {
+        return true;
+      }
+
+      if (keyMatchers[Command.KILL_BACKGROUND_SHELL](key)) {
+        dismissBackgroundShell(activeShell.pid);
+        return true;
+      }
+
+      if (keyMatchers[Command.TOGGLE_BACKGROUND_SHELL_LIST](key)) {
+        setIsBackgroundShellListOpen(true);
+        return true;
+      }
+
+      if (keyMatchers[Command.BACKGROUND_SHELL_SELECT](key)) {
+        ShellExecutionService.writeToPty(activeShell.pid, '\r');
+        return true;
+      } else if (keyMatchers[Command.DELETE_CHAR_LEFT](key)) {
+        ShellExecutionService.writeToPty(activeShell.pid, '\b');
+        return true;
+      } else if (key.sequence) {
+        ShellExecutionService.writeToPty(activeShell.pid, key.sequence);
+        return true;
+      }
+      return false;
+    },
+    { isActive: isFocused && !!activeShell },
+  );
+
+  const helpText = `${commandDescriptions[Command.TOGGLE_BACKGROUND_SHELL]} Hide | ${commandDescriptions[Command.KILL_BACKGROUND_SHELL]} Kill | ${commandDescriptions[Command.TOGGLE_BACKGROUND_SHELL_LIST]} List`;
+
+  const renderTabs = () => {
+    const shellList = Array.from(shells.values()).filter(
+      (s) => s.status === 'running',
+    );
+
+    const pidInfoWidth = getCachedStringWidth(
+      ` (PID: ${activePid}) ${isFocused ? '(Focused)' : ''}`,
+    );
+
+    const availableWidth =
+      width -
+      TAB_DISPLAY_HORIZONTAL_PADDING -
+      getCachedStringWidth(helpText) -
+      pidInfoWidth;
+
+    let currentWidth = 0;
+    const tabs = [];
+
+    for (let i = 0; i < shellList.length; i++) {
+      const shell = shellList[i];
+      // Account for " i: " (length 4 if i < 9) and spaces (length 2)
+      const labelOverhead = 4 + (i + 1).toString().length;
+      const maxTabLabelLength = Math.max(
+        1,
+        Math.floor(availableWidth / shellList.length) - labelOverhead,
+      );
+      const truncatedCommand = formatShellCommandForDisplay(
+        shell.command,
+        maxTabLabelLength,
+      );
+      const label = ` ${i + 1}: ${truncatedCommand} `;
+      const labelWidth = getCachedStringWidth(label);
+
+      // If this is the only shell, we MUST show it (truncated if necessary)
+      // even if it exceeds availableWidth, as there are no alternatives.
+      if (i > 0 && currentWidth + labelWidth > availableWidth) {
+        break;
+      }
+
+      const isActive = shell.pid === activePid;
+
+      tabs.push(
+        <Text
+          key={shell.pid}
+          color={isActive ? theme.text.primary : theme.text.secondary}
+          bold={isActive}
+        >
+          {label}
+        </Text>,
+      );
+      currentWidth += labelWidth;
+    }
+
+    if (shellList.length > tabs.length && !isListOpenProp) {
+      const overflowLabel = ` ... (${commandDescriptions[Command.TOGGLE_BACKGROUND_SHELL_LIST]}) `;
+      const overflowWidth = getCachedStringWidth(overflowLabel);
+
+      // If we only have one tab, ensure we don't show the overflow if it's too cramped
+      // We want at least 10 chars for the overflow or we favor the first tab.
+      const shouldShowOverflow =
+        tabs.length > 1 || availableWidth - currentWidth >= overflowWidth;
+
+      if (shouldShowOverflow) {
+        tabs.push(
+          <Text key="overflow" color={theme.status.warning} bold>
+            {overflowLabel}
+          </Text>,
+        );
+      }
+    }
+
+    return tabs;
+  };
+
+  const renderProcessList = () => {
+    const maxCommandLength = Math.max(
+      0,
+      width - BORDER_WIDTH - CONTENT_PADDING_X * 2 - 10,
+    );
+
+    const items: Array<RadioSelectItem<number>> = Array.from(
+      shells.values(),
+    ).map((shell, index) => {
+      const truncatedCommand = formatShellCommandForDisplay(
+        shell.command,
+        maxCommandLength,
+      );
+
+      let label = `${index + 1}: ${truncatedCommand} (PID: ${shell.pid})`;
+      if (shell.status === 'exited') {
+        label += ` (Exit Code: ${shell.exitCode})`;
+      }
+
+      return {
+        key: shell.pid.toString(),
+        value: shell.pid,
+        label,
+      };
+    });
+
+    const initialIndex = items.findIndex((item) => item.value === activePid);
+
+    return (
+      <Box flexDirection="column" height="100%" width="100%">
+        <Box flexShrink={0} marginBottom={1} paddingTop={1}>
+          <Text bold>
+            {`Select Process (${commandDescriptions[Command.BACKGROUND_SHELL_SELECT]} to select, ${commandDescriptions[Command.BACKGROUND_SHELL_ESCAPE]} to cancel):`}
+          </Text>
+        </Box>
+        <Box flexGrow={1} width="100%">
+          <RadioButtonSelect
+            items={items}
+            initialIndex={initialIndex >= 0 ? initialIndex : 0}
+            onSelect={(pid) => {
+              setActiveBackgroundShellPid(pid);
+              setIsBackgroundShellListOpen(false);
+            }}
+            onHighlight={(pid) => setHighlightedPid(pid)}
+            isFocused={isFocused}
+            maxItemsToShow={Math.max(1, height - HEADER_HEIGHT - 3)} // Adjust for header
+            renderItem={(
+              item,
+              { isSelected: _isSelected, titleColor: _titleColor },
+            ) => {
+              // Custom render to handle exit code coloring if needed,
+              // or just use default. The default RadioButtonSelect renderer
+              // handles standard label.
+              // But we want to color exit code differently?
+              // The previous implementation colored exit code green/red.
+              // Let's reimplement that.
+
+              // We need access to shell details here.
+              // We can put shell details in the item or lookup.
+              // Lookup from shells map.
+              const shell = shells.get(item.value);
+              if (!shell) return <Text>{item.label}</Text>;
+
+              const truncatedCommand = formatShellCommandForDisplay(
+                shell.command,
+                maxCommandLength,
+              );
+
+              return (
+                <Text>
+                  {truncatedCommand} (PID: {shell.pid})
+                  {shell.status === 'exited' ? (
+                    <Text
+                      color={
+                        shell.exitCode === 0
+                          ? theme.status.success
+                          : theme.status.error
+                      }
+                    >
+                      {' '}
+                      (Exit Code: {shell.exitCode})
+                    </Text>
+                  ) : null}
+                </Text>
+              );
+            }}
+          />
+        </Box>
+      </Box>
+    );
+  };
+
+  const renderOutput = () => {
+    const lines = typeof output === 'string' ? output.split('\n') : output;
+
+    return (
+      <ScrollableList
+        ref={outputRef}
+        data={lines}
+        renderItem={({ item: line, index }) => {
+          if (typeof line === 'string') {
+            return <Text key={index}>{line}</Text>;
+          }
+          return (
+            <Text key={index} wrap="truncate">
+              {line.length > 0
+                ? line.map((token: AnsiToken, tokenIndex: number) => (
+                    <Text
+                      key={tokenIndex}
+                      color={token.fg}
+                      backgroundColor={token.bg}
+                      inverse={token.inverse}
+                      dimColor={token.dim}
+                      bold={token.bold}
+                      italic={token.italic}
+                      underline={token.underline}
+                    >
+                      {token.text}
+                    </Text>
+                  ))
+                : null}
+            </Text>
+          );
+        }}
+        estimatedItemHeight={() => 1}
+        keyExtractor={(_, index) => index.toString()}
+        hasFocus={isFocused}
+        initialScrollIndex={SCROLL_TO_ITEM_END}
+      />
+    );
+  };
+
+  return (
+    <Box
+      flexDirection="column"
+      height="100%"
+      width="100%"
+      borderStyle="single"
+      borderColor={isFocused ? theme.border.focused : undefined}
+    >
+      <Box
+        flexDirection="row"
+        justifyContent="space-between"
+        borderStyle="single"
+        borderBottom={false}
+        borderLeft={false}
+        borderRight={false}
+        borderTop={false}
+        paddingX={1}
+        borderColor={isFocused ? theme.border.focused : undefined}
+      >
+        <Box flexDirection="row">
+          {renderTabs()}
+          <Text bold>
+            {' '}
+            (PID: {activeShell?.pid}) {isFocused ? '(Focused)' : ''}
+          </Text>
+        </Box>
+        <Text color={theme.text.accent}>{helpText}</Text>
+      </Box>
+      <Box flexGrow={1} overflow="hidden" paddingX={CONTENT_PADDING_X}>
+        {isListOpenProp ? renderProcessList() : renderOutput()}
+      </Box>
+    </Box>
+  );
+};

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

@@ -34,6 +34,8 @@ describe('Key Bubbling Regression', () => {
         questions={choiceQuestion}
         onSubmit={vi.fn()}
         onCancel={vi.fn()}
+        width={120}
+        availableHeight={20}
       />,
       { width: 120 },
     );

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

@@ -7,7 +7,7 @@
 import type React from 'react';
 import { Box, Text } from 'ink';
 import { theme } from '../semantic-colors.js';
-import { checkExhaustive } from '../../utils/checks.js';
+import { checkExhaustive } from '@google/gemini-cli-core';
 
 export type ChecklistStatus =
   | 'pending'

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

@@ -4,10 +4,8 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-import {
-  renderWithProviders,
-  createMockSettings,
-} from '../../test-utils/render.js';
+import { renderWithProviders } from '../../test-utils/render.js';
+import { createMockSettings } from '../../test-utils/settings.js';
 import { CliSpinner } from './CliSpinner.js';
 import { debugState } from '../debug.js';
 import { describe, it, expect, beforeEach } from 'vitest';

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

@@ -15,16 +15,16 @@ import {
 } from '../contexts/UIActionsContext.js';
 import { ConfigContext } from '../contexts/ConfigContext.js';
 import { SettingsContext } from '../contexts/SettingsContext.js';
+import { createMockSettings } from '../../test-utils/settings.js';
 // Mock VimModeContext hook
 vi.mock('../contexts/VimModeContext.js', () => ({
   useVimMode: vi.fn(() => ({
     vimEnabled: false,
-    vimMode: 'NORMAL',
+    vimMode: 'INSERT',
   })),
 }));
 import { ApprovalMode } from '@google/gemini-cli-core';
 import { StreamingState } from '../types.js';
-import { mergeSettings } from '../../config/settings.js';
 
 // Mock child components
 vi.mock('./LoadingIndicator.js', () => ({
@@ -54,7 +54,9 @@ vi.mock('./DetailedMessagesDisplay.js', () => ({
 }));
 
 vi.mock('./InputPrompt.js', () => ({
-  InputPrompt: () => <Text>InputPrompt</Text>,
+  InputPrompt: ({ placeholder }: { placeholder?: string }) => (
+    <Text>InputPrompt: {placeholder}</Text>
+  ),
   calculatePromptWidths: vi.fn(() => ({
     inputWidth: 80,
     suggestionsWidth: 40,
@@ -131,6 +133,8 @@ const createMockUIState = (overrides: Partial<UIState> = {}): UIState =>
     nightly: false,
     isTrustedFolder: true,
     activeHooks: [],
+    isBackgroundShellVisible: false,
+    embeddedShellFocused: false,
     ...overrides,
   }) as UIState;
 
@@ -164,21 +168,6 @@ const createMockConfig = (overrides = {}) => ({
   ...overrides,
 });
 
-const createMockSettings = (merged = {}) => {
-  const defaultMergedSettings = mergeSettings({}, {}, {}, {}, true);
-  return {
-    merged: {
-      ...defaultMergedSettings,
-      ui: {
-        ...defaultMergedSettings.ui,
-        hideFooter: false,
-        showMemoryUsage: false,
-        ...merged,
-      },
-    },
-  };
-};
-
 /* eslint-disable @typescript-eslint/no-explicit-any */
 const renderComposer = (
   uiState: UIState,
@@ -203,7 +192,7 @@ describe('Composer', () => {
   describe('Footer Display Settings', () => {
     it('renders Footer by default when hideFooter is false', () => {
       const uiState = createMockUIState();
-      const settings = createMockSettings({ hideFooter: false });
+      const settings = createMockSettings({ ui: { hideFooter: false } });
 
       const { lastFrame } = renderComposer(uiState, settings);
 
@@ -212,7 +201,7 @@ describe('Composer', () => {
 
     it('does NOT render Footer when hideFooter is true', () => {
       const uiState = createMockUIState();
-      const settings = createMockSettings({ hideFooter: true });
+      const settings = createMockSettings({ ui: { hideFooter: true } });
 
       const { lastFrame } = renderComposer(uiState, settings);
 
@@ -241,8 +230,10 @@ describe('Composer', () => {
         getDebugMode: vi.fn(() => true),
       });
       const settings = createMockSettings({
-        hideFooter: false,
-        showMemoryUsage: true,
+        ui: {
+          hideFooter: false,
+          showMemoryUsage: true,
+        },
       });
       // Mock vim mode for this test
       const { useVimMode } = await import('../contexts/VimModeContext.js');
@@ -308,6 +299,32 @@ describe('Composer', () => {
       expect(output).toContain('LoadingIndicator');
       expect(output).not.toContain('Should not show during confirmation');
     });
+
+    it('renders LoadingIndicator when embedded shell is focused but background shell is visible', () => {
+      const uiState = createMockUIState({
+        streamingState: StreamingState.Responding,
+        embeddedShellFocused: true,
+        isBackgroundShellVisible: true,
+      });
+
+      const { lastFrame } = renderComposer(uiState);
+
+      const output = lastFrame();
+      expect(output).toContain('LoadingIndicator');
+    });
+
+    it('does NOT render LoadingIndicator when embedded shell is focused and background shell is NOT visible', () => {
+      const uiState = createMockUIState({
+        streamingState: StreamingState.Responding,
+        embeddedShellFocused: true,
+        isBackgroundShellVisible: false,
+      });
+
+      const { lastFrame } = renderComposer(uiState);
+
+      const output = lastFrame();
+      expect(output).not.toContain('LoadingIndicator');
+    });
   });
 
   describe('Message Queue Display', () => {
@@ -487,4 +504,40 @@ describe('Composer', () => {
       expect(lastFrame()).not.toContain('DetailedMessagesDisplay');
     });
   });
+
+  describe('Vim Mode Placeholders', () => {
+    it('shows correct placeholder in INSERT mode', async () => {
+      const uiState = createMockUIState({ isInputActive: true });
+      const { useVimMode } = await import('../contexts/VimModeContext.js');
+      vi.mocked(useVimMode).mockReturnValue({
+        vimEnabled: true,
+        vimMode: 'INSERT',
+        toggleVimEnabled: vi.fn(),
+        setVimMode: vi.fn(),
+      });
+
+      const { lastFrame } = renderComposer(uiState);
+
+      expect(lastFrame()).toContain(
+        "InputPrompt:   Press 'Esc' for NORMAL mode.",
+      );
+    });
+
+    it('shows correct placeholder in NORMAL mode', async () => {
+      const uiState = createMockUIState({ isInputActive: true });
+      const { useVimMode } = await import('../contexts/VimModeContext.js');
+      vi.mocked(useVimMode).mockReturnValue({
+        vimEnabled: true,
+        vimMode: 'NORMAL',
+        toggleVimEnabled: vi.fn(),
+        setVimMode: vi.fn(),
+      });
+
+      const { lastFrame } = renderComposer(uiState);
+
+      expect(lastFrame()).toContain(
+        "InputPrompt:   Press 'i' for INSERT mode.",
+      );
+    });
+  });
 });

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

@@ -35,7 +35,7 @@ export const Composer = ({ isFocused = true }: { isFocused?: boolean }) => {
   const isScreenReaderEnabled = useIsScreenReaderEnabled();
   const uiState = useUIState();
   const uiActions = useUIActions();
-  const { vimEnabled } = useVimMode();
+  const { vimEnabled, vimMode } = useVimMode();
   const terminalWidth = process.stdout.columns;
   const isNarrow = isNarrowWidth(terminalWidth);
   const debugConsoleMaxHeight = Math.floor(Math.max(terminalWidth * 0.2, 5));
@@ -54,7 +54,7 @@ export const Composer = ({ isFocused = true }: { isFocused?: boolean }) => {
       flexGrow={0}
       flexShrink={0}
     >
-      {!uiState.embeddedShellFocused && (
+      {(!uiState.embeddedShellFocused || uiState.isBackgroundShellVisible) && (
         <LoadingIndicator
           thought={
             uiState.streamingState === StreamingState.WaitingForConfirmation ||
@@ -143,7 +143,9 @@ export const Composer = ({ isFocused = true }: { isFocused?: boolean }) => {
           popAllMessages={uiActions.popAllMessages}
           placeholder={
             vimEnabled
-              ? "  Press 'i' for INSERT mode and 'Esc' for NORMAL mode."
+              ? vimMode === 'INSERT'
+                ? "  Press 'Esc' for NORMAL mode."
+                : "  Press 'i' for INSERT mode."
               : uiState.shellModeActive
                 ? '  Type your shell command'
                 : '  Type your message or @path/to/file'

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

@@ -18,6 +18,7 @@ interface ContextSummaryDisplayProps {
   blockedMcpServers?: Array<{ name: string; extensionName: string }>;
   ideContext?: IdeContext;
   skillCount: number;
+  backgroundProcessCount?: number;
 }
 
 export const ContextSummaryDisplay: React.FC<ContextSummaryDisplayProps> = ({
@@ -27,6 +28,7 @@ export const ContextSummaryDisplay: React.FC<ContextSummaryDisplayProps> = ({
   blockedMcpServers,
   ideContext,
   skillCount,
+  backgroundProcessCount = 0,
 }) => {
   const { columns: terminalWidth } = useTerminalSize();
   const isNarrow = isNarrowWidth(terminalWidth);
@@ -39,7 +41,8 @@ export const ContextSummaryDisplay: React.FC<ContextSummaryDisplayProps> = ({
     mcpServerCount === 0 &&
     blockedMcpServerCount === 0 &&
     openFileCount === 0 &&
-    skillCount === 0
+    skillCount === 0 &&
+    backgroundProcessCount === 0
   ) {
     return <Text> </Text>; // Render an empty space to reserve height
   }
@@ -93,9 +96,22 @@ export const ContextSummaryDisplay: React.FC<ContextSummaryDisplayProps> = ({
     return `${skillCount} skill${skillCount > 1 ? 's' : ''}`;
   })();
 
-  const summaryParts = [openFilesText, geminiMdText, mcpText, skillText].filter(
-    Boolean,
-  );
+  const backgroundText = (() => {
+    if (backgroundProcessCount === 0) {
+      return '';
+    }
+    return `${backgroundProcessCount} Background process${
+      backgroundProcessCount > 1 ? 'es' : ''
+    }`;
+  })();
+
+  const summaryParts = [
+    openFilesText,
+    geminiMdText,
+    mcpText,
+    skillText,
+    backgroundText,
+  ].filter(Boolean);
 
   if (isNarrow) {
     return (