Update links to outdated index file.

outdated clone of docs/index.

CONTRIBUTING.md

@@ -546,7 +546,7 @@ Before submitting your documentation pull request, please:
 
 If you have questions about contributing documentation:
 
-- Check our [FAQ](/docs/faq.md).
+- Check our [FAQ](/docs/resources/faq).
 - Review existing documentation for examples.
 - Open [an issue](https://github.com/google-gemini/gemini-cli/issues) to discuss
   your proposed changes.

docs/architecture.md

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

docs/changelogs/index.md

@@ -276,7 +276,8 @@ on GitHub.
 - **Experimental permission improvements:** We are now experimenting with a new
   policy engine in Gemini CLI. This allows users and administrators to create
   fine-grained policy for tool calls. Currently behind a flag. See
-  [policy engine documentation](../core/policy-engine.md) for more information.
+  [policy engine documentation](../reference/policy-engine.md) for more
+  information.
   - Blog:
     [https://allen.hutchison.org/2025/11/26/the-guardrails-of-autonomy/](https://allen.hutchison.org/2025/11/26/the-guardrails-of-autonomy/)
 - **Gemini 3 support for paid:** Gemini 3 support has been rolled out to all API

docs/cli/cli-reference.md

@@ -26,29 +26,29 @@ and parameters.
 
 ## CLI Options
 
-| Option                           | Alias | Type    | Default   | Description                                                                                                                                                       |
-| -------------------------------- | ----- | ------- | --------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `--debug`                        | `-d`  | boolean | `false`   | Run in debug mode with verbose logging                                                                                                                            |
-| `--version`                      | `-v`  | -       | -         | Show CLI version number and exit                                                                                                                                  |
-| `--help`                         | `-h`  | -       | -         | Show help information                                                                                                                                             |
-| `--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                                                                                                                   |
-| `--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.                                                                                     |
-| `--experimental-acp`             | -     | boolean | -         | Start in ACP (Agent Code Pilot) mode. **Experimental feature.**                                                                                                   |
-| `--experimental-zed-integration` | -     | boolean | -         | Run in Zed editor integration mode. **Experimental feature.**                                                                                                     |
-| `--allowed-mcp-server-names`     | -     | array   | -         | Allowed MCP server names (comma-separated or multiple flags)                                                                                                      |
-| `--allowed-tools`                | -     | array   | -         | **Deprecated.** Use the [Policy Engine](../core/policy-engine.md) instead. Tools that are allowed to run without confirmation (comma-separated or multiple flags) |
-| `--extensions`                   | `-e`  | array   | -         | List of extensions to use. If not provided, all extensions are enabled (comma-separated or multiple flags)                                                        |
-| `--list-extensions`              | `-l`  | boolean | -         | List all available extensions and exit                                                                                                                            |
-| `--resume`                       | `-r`  | string  | -         | Resume a previous session. Use `"latest"` for most recent or index number (e.g. `--resume 5`)                                                                     |
-| `--list-sessions`                | -     | boolean | -         | List available sessions for the current project and exit                                                                                                          |
-| `--delete-session`               | -     | string  | -         | Delete a session by index number (use `--list-sessions` to see available sessions)                                                                                |
-| `--include-directories`          | -     | array   | -         | Additional directories to include in the workspace (comma-separated or multiple flags)                                                                            |
-| `--screen-reader`                | -     | boolean | -         | Enable screen reader mode for accessibility                                                                                                                       |
-| `--output-format`                | `-o`  | string  | `text`    | The format of the CLI output. Choices: `text`, `json`, `stream-json`                                                                                              |
+| Option                           | Alias | Type    | Default   | Description                                                                                                                                                            |
+| -------------------------------- | ----- | ------- | --------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `--debug`                        | `-d`  | boolean | `false`   | Run in debug mode with verbose logging                                                                                                                                 |
+| `--version`                      | `-v`  | -       | -         | Show CLI version number and exit                                                                                                                                       |
+| `--help`                         | `-h`  | -       | -         | Show help information                                                                                                                                                  |
+| `--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                                                                                                                        |
+| `--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.                                                                                          |
+| `--experimental-acp`             | -     | boolean | -         | Start in ACP (Agent Code Pilot) mode. **Experimental feature.**                                                                                                        |
+| `--experimental-zed-integration` | -     | boolean | -         | Run in Zed editor integration mode. **Experimental feature.**                                                                                                          |
+| `--allowed-mcp-server-names`     | -     | array   | -         | Allowed MCP server names (comma-separated or multiple flags)                                                                                                           |
+| `--allowed-tools`                | -     | array   | -         | **Deprecated.** Use the [Policy Engine](../reference/policy-engine.md) instead. Tools that are allowed to run without confirmation (comma-separated or multiple flags) |
+| `--extensions`                   | `-e`  | array   | -         | List of extensions to use. If not provided, all extensions are enabled (comma-separated or multiple flags)                                                             |
+| `--list-extensions`              | `-l`  | boolean | -         | List all available extensions and exit                                                                                                                                 |
+| `--resume`                       | `-r`  | string  | -         | Resume a previous session. Use `"latest"` for most recent or index number (e.g. `--resume 5`)                                                                          |
+| `--list-sessions`                | -     | boolean | -         | List available sessions for the current project and exit                                                                                                               |
+| `--delete-session`               | -     | string  | -         | Delete a session by index number (use `--list-sessions` to see available sessions)                                                                                     |
+| `--include-directories`          | -     | array   | -         | Additional directories to include in the workspace (comma-separated or multiple flags)                                                                                 |
+| `--screen-reader`                | -     | boolean | -         | Enable screen reader mode for accessibility                                                                                                                            |
+| `--output-format`                | `-o`  | string  | `text`    | The format of the CLI output. Choices: `text`, `json`, `stream-json`                                                                                                   |
 
 ## Model selection
 

docs/cli/enterprise.md

@@ -20,7 +20,7 @@ The most powerful tools for enterprise administration are the system-wide
 settings files. These files allow you to define a baseline configuration
 (`system-defaults.json`) and a set of overrides (`settings.json`) that apply to
 all users on a machine. For a complete overview of configuration options, see
-the [Configuration documentation](../get-started/configuration.md).
+the [Configuration documentation](../reference/configuration.md).
 
 Settings are merged from four files. The precedence order for single-value
 settings (like `theme`) is:
@@ -224,8 +224,8 @@ gemini
 
 You can significantly enhance security by controlling which tools the Gemini
 model can use. This is achieved through the `tools.core` setting and the
-[Policy Engine](../core/policy-engine.md). For a list of available tools, see
-the [Tools documentation](../tools/index.md).
+[Policy Engine](../reference/policy-engine.md). For a list of available tools,
+see the [Tools documentation](../tools/index.md).
 
 ### Allowlisting with `coreTools`
 
@@ -245,8 +245,8 @@ on the approved list.
 
 ### Blocklisting with `excludeTools` (Deprecated)
 
-> **Deprecated:** Use the [Policy Engine](../core/policy-engine.md) for more
-> robust control.
+> **Deprecated:** Use the [Policy Engine](../reference/policy-engine.md) for
+> more robust control.
 
 Alternatively, you can add specific tools that are considered dangerous in your
 environment to a blocklist.
@@ -289,8 +289,8 @@ unintended tool execution.
 ## Managing custom tools (MCP servers)
 
 If your organization uses custom tools via
-[Model-Context Protocol (MCP) servers](../core/tools-api.md), it is crucial to
-understand how server configurations are managed to apply security policies
+[Model-Context Protocol (MCP) servers](../reference/tools-api.md), it is crucial
+to understand how server configurations are managed to apply security policies
 effectively.
 
 ### How MCP server configurations are merged

docs/cli/gemini-md.md

@@ -88,7 +88,7 @@ More content here.
 @../shared/style-guide.md
 ```
 
-For more details, see the [Memory Import Processor](../core/memport.md)
+For more details, see the [Memory Import Processor](../reference/memport.md)
 documentation.
 
 ## Customize the context file name

docs/cli/index.md

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

docs/cli/model.md

@@ -39,7 +39,7 @@ To enable Gemini 3 Pro and Gemini 3 Flash (if available), enable
 
 You can also use the `--model` flag to specify a particular Gemini model on
 startup. For more details, refer to the
-[configuration documentation](../get-started/configuration.md).
+[configuration documentation](../reference/configuration.md).
 
 Changes to these settings will be applied to all subsequent interactions with
 Gemini CLI.

docs/cli/plan-mode.md

@@ -184,7 +184,7 @@ Guide].
 [MCP tools]: /docs/tools/mcp-server.md
 [`activate_skill`]: /docs/cli/skills.md
 [experimental research sub-agents]: /docs/core/subagents.md
-[Policy Engine Guide]: /docs/core/policy-engine.md
+[Policy Engine Guide]: /docs/reference/policy-engine.md
 [`enter_plan_mode`]: /docs/tools/planning.md#1-enter_plan_mode-enterplanmode
 [`exit_plan_mode`]: /docs/tools/planning.md#2-exit_plan_mode-exitplanmode
 [`ask_user`]: /docs/tools/ask-user.md

docs/cli/sandbox.md

@@ -167,6 +167,6 @@ gemini -s -p "run shell command: mount | grep workspace"
 
 ## Related documentation
 
-- [Configuration](../get-started/configuration.md): Full configuration options.
-- [Commands](./commands.md): Available commands.
-- [Troubleshooting](../troubleshooting.md): General troubleshooting.
+- [Configuration](../reference/configuration.md): Full configuration options.
+- [Commands](../reference/commands.md): Available commands.
+- [Troubleshooting](../resources/troubleshooting.md): General troubleshooting.

docs/cli/telemetry.md

@@ -93,7 +93,7 @@ Environment variables can be used to override the settings in the file.
 `true` or `1` will enable the feature. Any other value will disable it.
 
 For detailed information about all configuration options, see the
-[Configuration guide](../get-started/configuration.md).
+[Configuration guide](../reference/configuration.md).
 
 ## Google Cloud telemetry
 

docs/cli/themes.md

@@ -41,8 +41,8 @@ can change the theme using the `/theme` command.
 ### Theme persistence
 
 Selected themes are saved in Gemini CLI's
-[configuration](../get-started/configuration.md) so your preference is
-remembered across sessions.
+[configuration](../reference/configuration.md) so your preference is remembered
+across sessions.
 
 ---
 
@@ -194,7 +194,7 @@ untrusted sources.
 - Or, set it as the default by adding `"theme": "MyCustomTheme"` to the `ui`
   object in your `settings.json`.
 - Custom themes can be set at the user, project, or system level, and follow the
-  same [configuration precedence](../get-started/configuration.md) as other
+  same [configuration precedence](../reference/configuration.md) as other
   settings.
 
 ### Themes from extensions

docs/cli/tutorials/memory-management.md

@@ -121,6 +121,6 @@ immediately. Force a reload with:
 
 - Learn about [Session management](session-management.md) to see how short-term
   history works.
-- Explore the [Command reference](../../cli/commands.md) for more `/memory`
-  options.
+- Explore the [Command reference](../../reference/commands.md) for more
+  `/memory` options.
 - Read the technical spec for [Project context](../../cli/gemini-md.md).

docs/cli/tutorials/session-management.md

@@ -101,5 +101,5 @@ This creates a new branch of history without losing your original work.
 - Learn about [Checkpointing](../../cli/checkpointing.md) to understand the
   underlying safety mechanism.
 - Explore [Task planning](task-planning.md) to keep complex sessions organized.
-- See the [Command reference](../../cli/commands.md) for all `/chat` and
+- See the [Command reference](../../reference/commands.md) for all `/chat` and
   `/resume` options.

docs/core/concepts.md

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

docs/core/index.md

@@ -9,11 +9,11 @@ requests sent from `packages/cli`. For a general overview of Gemini CLI, see the
 
 - **[Sub-agents (experimental)](./subagents.md):** Learn how to create and use
   specialized sub-agents for complex tasks.
-- **[Core tools API](./tools-api.md):** Information on how tools are defined,
-  registered, and used by the core.
-- **[Memory Import Processor](./memport.md):** Documentation for the modular
-  GEMINI.md import feature using @file.md syntax.
-- **[Policy Engine](./policy-engine.md):** Use the Policy Engine for
+- **[Core tools API](../reference/tools-api.md):** Information on how tools are
+  defined, registered, and used by the core.
+- **[Memory Import Processor](../reference/memport.md):** Documentation for the
+  modular GEMINI.md import feature using @file.md syntax.
+- **[Policy Engine](../reference/policy-engine.md):** Use the Policy Engine for
   fine-grained control over tool execution.
 
 ## Role of the core
@@ -92,8 +92,8 @@ This allows you to have global, project-level, and component-level context
 files, which are all combined to provide the model with the most relevant
 information.
 
-You can use the [`/memory` command](../cli/commands.md) to `show`, `add`, and
-`refresh` the content of loaded `GEMINI.md` files.
+You can use the [`/memory` command](../reference/commands.md) to `show`, `add`,
+and `refresh` the content of loaded `GEMINI.md` files.
 
 ## Citations
 

docs/core/subagents.md

@@ -17,7 +17,7 @@ the main agent's context or toolset.
 > ```
 >
 > **Warning:** Sub-agents currently operate in
-> ["YOLO mode"](../get-started/configuration.md#command-line-arguments), meaning
+> ["YOLO mode"](../reference/configuration.md#command-line-arguments), meaning
 > they may execute tools without individual user confirmation for each step.
 > Proceed with caution when defining agents with powerful tools like
 > `run_shell_command` or `write_file`.

docs/extensions/reference.md

@@ -130,7 +130,7 @@ The manifest file defines the extension's behavior and configuration.
 - `description`: A short summary shown in the extension gallery.
 - <a id="mcp-servers"></a>`mcpServers`: A map of Model Context Protocol (MCP)
   servers. Extension servers follow the same format as standard
-  [CLI configuration](../get-started/configuration.md).
+  [CLI configuration](../reference/configuration.md).
 - `contextFileName`: The name of the context file (defaults to `GEMINI.md`). Can
   also be an array of strings to load multiple context files.
 - `excludeTools`: An array of tools to block from the model. You can restrict

docs/get-started/authentication.md

@@ -22,8 +22,8 @@ Select the authentication method that matches your situation in the table below:
 ### What is my Google account type?
 
 - **Individual Google accounts:** Includes all
-  [free tier accounts](../quota-and-pricing/#free-usage) such as Gemini Code
-  Assist for individuals, as well as paid subscriptions for
+  [free tier accounts](../resources/quota-and-pricing.md#free-usage) such as
+  Gemini Code Assist for individuals, as well as paid subscriptions for
   [Google AI Pro and Ultra](https://gemini.google/subscriptions/).
 
 - **Organization accounts:** Accounts using paid licenses through an
@@ -317,5 +317,5 @@ configure authentication using environment variables:
 Your authentication method affects your quotas, pricing, Terms of Service, and
 privacy notices. Review the following pages to learn more:
 
-- [Gemini CLI: Quotas and Pricing](../quota-and-pricing.md).
-- [Gemini CLI: Terms of Service and Privacy Notice](../tos-privacy.md).
+- [Gemini CLI: Quotas and Pricing](../resources/quota-and-pricing.md).
+- [Gemini CLI: Terms of Service and Privacy Notice](../resources/tos-privacy.md).

docs/get-started/configuration-v1.md

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

docs/get-started/examples.md

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

docs/get-started/index.md

@@ -54,7 +54,7 @@ Gemini CLI offers several ways to configure its behavior, including environment
 variables, command-line arguments, and settings files.
 
 To explore your configuration options, see
-[Gemini CLI Configuration](./configuration.md).
+[Gemini CLI Configuration](../reference/configuration.md).
 
 ## Use
 
@@ -70,4 +70,3 @@ To explore the power of Gemini CLI, see [Gemini CLI examples](./examples.md).
   start working with your codebase.
 - See [Shell commands](../cli/tutorials/shell-commands.md) to learn about
   terminal integration.
-- Explore the full range of [User guides](../cli/index.md#user-guides).

docs/hooks/best-practices.md

@@ -420,7 +420,7 @@ When you open a project with hooks defined in `.gemini/settings.json`:
 
 Hooks inherit the environment of the Gemini CLI process, which may include
 sensitive API keys. Gemini CLI provides a
-[redaction system](/docs/get-started/configuration#environment-variable-redaction)
+[redaction system](/docs/reference/configuration#environment-variable-redaction)
 that automatically filters variables matching sensitive patterns (e.g., `KEY`,
 `TOKEN`).
 

docs/index.md

@@ -12,8 +12,7 @@ npm install -g @google/gemini-cli
 
 ## Get started
 
-Jump in to Gemini CLI.
-
+- **[Overview](./index.md):** An overview of Gemini CLI and its features.
 - **[Quickstart](./get-started/index.md):** Your first session with Gemini CLI.
 - **[Installation](./get-started/installation.md):** How to install Gemini CLI
   on your system.
@@ -21,13 +20,13 @@ Jump in to Gemini CLI.
   personal and enterprise accounts.
 - **[Examples](./get-started/examples.md):** Practical examples of Gemini CLI in
   action.
-- **[Cheatsheet](./cli/cli-reference.md):** A quick reference for common
+- **[CLI cheatsheet](./cli/cli-reference.md):** A quick reference for common
   commands and options.
+- **[Gemini 3 on Gemini CLI](./get-started/gemini-3.md):** Learn how to use
+  Gemini 3 with Gemini CLI.
 
 ## Use Gemini CLI
 
-User-focused guides and tutorials for daily development workflows.
-
 - **[File management](./cli/tutorials/file-management.md):** How to work with
   local files and directories.
 - **[Manage context and memory](./cli/tutorials/memory-management.md):**
@@ -42,105 +41,119 @@ User-focused guides and tutorials for daily development workflows.
   fetching content from the web.
 - **[Get started with skills](./cli/tutorials/skills-getting-started.md):**
   Getting started with specialized expertise.
+- **[Set up an MCP server](./cli/tutorials/mcp-setup.md):** Learn how to set up
+  a Model-Context Protocol server.
+- **[Automate tasks](./cli/tutorials/automation.md):** Automate common
+  development tasks.
 
 ## Features
 
-Technical reference documentation for each capability of Gemini CLI.
-
-- **[/about](./cli/commands.md#about):** About Gemini CLI.
-- **[/auth](./get-started/authentication.md):** Authentication.
-- **[/bug](./cli/commands.md#bug):** Report a bug.
-- **[/chat](./cli/commands.md#chat):** Chat history.
-- **[/clear](./cli/commands.md#clear):** Clear screen.
-- **[/compress](./cli/commands.md#compress):** Compress context.
-- **[/copy](./cli/commands.md#copy):** Copy output.
-- **[/directory](./cli/commands.md#directory-or-dir):** Manage workspace.
-- **[/docs](./cli/commands.md#docs):** Open documentation.
-- **[/editor](./cli/commands.md#editor):** Select editor.
-- **[/extensions](./extensions/index.md):** Manage extensions.
-- **[/help](./cli/commands.md#help-or):** Show help.
-- **[/hooks](./hooks/index.md):** Hooks.
-- **[/ide](./ide-integration/index.md):** IDE integration.
-- **[/init](./cli/commands.md#init):** Initialize context.
-- **[/mcp](./tools/mcp-server.md):** MCP servers.
-- **[/memory](./cli/commands.md#memory):** Manage memory.
-- **[/model](./cli/model.md):** Model selection.
-- **[/policies](./cli/commands.md#policies):** Manage policies.
-- **[/privacy](./cli/commands.md#privacy):** Privacy notice.
-- **[/quit](./cli/commands.md#quit-or-exit):** Exit CLI.
-- **[/restore](./cli/checkpointing.md):** Restore files.
-- **[/resume](./cli/commands.md#resume):** Resume session.
-- **[/rewind](./cli/rewind.md):** Rewind.
-- **[/settings](./cli/settings.md):** Settings.
-- **[/setup-github](./cli/commands.md#setup-github):** GitHub setup.
-- **[/shells](./cli/commands.md#shells-or-bashes):** Manage processes.
-- **[/skills](./cli/skills.md):** Agent skills.
-- **[/stats](./cli/commands.md#stats):** Session statistics.
-- **[/terminal-setup](./cli/commands.md#terminal-setup):** Terminal keybindings.
-- **[/theme](./cli/themes.md):** Themes.
-- **[/tools](./cli/commands.md#tools):** List tools.
-- **[/vim](./cli/commands.md#vim):** Vim mode.
-- **[Activate skill (tool)](./tools/activate-skill.md):** Internal mechanism for
-  loading expert procedures.
-- **[Ask user (tool)](./tools/ask-user.md):** Internal dialog system for
-  clarification.
-- **[Checkpointing](./cli/checkpointing.md):** Automatic session snapshots.
-- **[File system (tool)](./tools/file-system.md):** Technical details for local
-  file operations.
-- **[Headless mode](./cli/headless.md):** Programmatic and scripting interface.
-- **[Internal documentation (tool)](./tools/internal-docs.md):** Technical
-  lookup for CLI features.
-- **[Memory (tool)](./tools/memory.md):** Storage details for persistent facts.
-- **[Model routing](./cli/model-routing.md):** Automatic fallback resilience.
-- **[Plan mode (experimental)](./cli/plan-mode.md):** Use a safe, read-only mode
-  for planning complex changes.
-- **[Sandboxing](./cli/sandbox.md):** Isolate tool execution.
-- **[Shell (tool)](./tools/shell.md):** Detailed system execution parameters.
-- **[Telemetry](./cli/telemetry.md):** Usage and performance metric details.
-- **[Todo (tool)](./tools/todos.md):** Progress tracking specification.
-- **[Token caching](./cli/token-caching.md):** Performance optimization.
-- **[Web fetch (tool)](./tools/web-fetch.md):** URL retrieval and extraction
-  details.
-- **[Web search (tool)](./tools/web-search.md):** Google Search integration
-  technicals.
+- **[Agent Skills](./cli/skills.md):** Extend the capabilities of Gemini CLI
+  with custom skills.
+- **[Authentication](./get-started/authentication.md):** Learn about the
+  different authentication methods.
+- **[Checkpointing](./cli/checkpointing.md):** Automatically save and restore
+  your sessions.
+- **[Extensions](./extensions/index.md):** Extend the functionality of Gemini
+  CLI with extensions.
+- **[Headless mode](./cli/headless.md):** Run Gemini CLI in a non-interactive
+  mode.
+- **[Hooks](./hooks/index.md):** Customize the behavior of Gemini CLI with
+  hooks.
+- **[IDE integration](./ide-integration/index.md):** Integrate Gemini CLI with
+  your favorite IDE.
+- **[MCP servers](./tools/mcp-server.md):** Connect to Model-Context Protocol
+  servers.
+- **[Model routing](./cli/model-routing.md):** Automatically route requests to
+  the best model.
+- **[Model selection](./cli/model.md):** Learn how to select the right model for
+  your task.
+- **[Plan mode (experimental)](./cli/plan-mode.md):** Plan and review changes
+  before they are executed.
+- **[Rewind](./cli/rewind.md):** Rewind the conversation to a previous point.
+- **[Sandboxing](./cli/sandbox.md):** Isolate tool execution in a sandboxed
+  environment.
+- **[Settings](./cli/settings.md):** Customize the behavior of Gemini CLI.
+- **[Telemetry](./cli/telemetry.md):** Understand the usage data that Gemini CLI
+  collects.
+- **[Token caching](./cli/token-caching.md):** Cache tokens to improve
+  performance.
 
 ## Configuration
 
-Settings and customization options for Gemini CLI.
+- **[Custom commands](./cli/custom-commands.md):** Create your own custom
+  commands.
+- **[Enterprise configuration](./cli/enterprise.md):** Configure Gemini CLI for
+  your enterprise.
+- **[Ignore files (.geminiignore)](./cli/gemini-ignore.md):** Ignore files and
+  directories.
+- **[Model configuration](./cli/generation-settings.md):** Configure the
+  generation settings for your models.
+- **[Project context (GEMINI.md)](./cli/gemini-md.md):** Provide
+  project-specific context to the model.
+- **[Settings](./cli/settings.md):** A full reference of all the available
+  settings.
+- **[System prompt override](./cli/system-prompt.md):** Override the default
+  system prompt.
+- **[Themes](./cli/themes.md):** Customize the look and feel of Gemini CLI.
+- **[Trusted folders](./cli/trusted-folders.md):** Configure trusted folders to
+  bypass security warnings.
 
-- **[Custom commands](./cli/custom-commands.md):** Personalized shortcuts.
-- **[Enterprise configuration](./cli/enterprise.md):** Professional environment
-  controls.
-- **[Ignore files (.geminiignore)](./cli/gemini-ignore.md):** Exclusion pattern
-  reference.
-- **[Model configuration](./cli/generation-settings.md):** Fine-tune generation
-  parameters like temperature and thinking budget.
-- **[Project context (GEMINI.md)](./cli/gemini-md.md):** Technical hierarchy of
-  context files.
-- **[Settings](./cli/settings.md):** Full configuration reference.
-- **[System prompt override](./cli/system-prompt.md):** Instruction replacement
-  logic.
-- **[Themes](./cli/themes.md):** UI personalization technical guide.
-- **[Trusted folders](./cli/trusted-folders.md):** Security permission logic.
+## Extensions
+
+- **[Overview](./extensions/index.md):** An overview of the extension system.
+- **[User guide: Install and manage](./extensions/index.md#manage-extensions):**
+  Learn how to install and manage extensions.
+- **[Developer guide: Build extensions](./extensions/writing-extensions.md):**
+  Learn how to build your own extensions.
+- **[Developer guide: Best practices](./extensions/best-practices.md):** Best
+  practices for writing extensions.
+- **[Developer guide: Releasing](./extensions/releasing.md):** Learn how to
+  release your extensions.
+- **[Developer guide: Reference](./extensions/reference.md):** A full reference
+  of the extension API.
+
+## Development
+
+- **[Contribution guide](/docs/contributing):** Learn how to contribute to
+  Gemini CLI.
+- **[Integration testing](./integration-tests.md):** Learn how to run the
+  integration tests.
+- **[Issue and PR automation](./issue-and-pr-automation.md):** Learn about the
+  issue and PR automation.
+- **[Local development](./local-development.md):** Learn how to set up your
+  local development environment.
+- **[NPM package structure](./npm.md):** Learn about the structure of the NPM
+  packages.
 
 ## Reference
 
-Deep technical documentation and API specifications.
-
-- **[Architecture overview](./architecture.md):** System design and components.
-- **[Command reference](./cli/commands.md):** Detailed slash command guide.
-- **[Configuration reference](./get-started/configuration.md):** Settings and
-  environment variables.
-- **[Core concepts](./core/concepts.md):** Fundamental terminology and
-  definitions.
-- **[Keyboard shortcuts](./cli/keyboard-shortcuts.md):** Productivity tips.
-- **[Policy engine](./core/policy-engine.md):** Fine-grained execution control.
+- **[Command reference](./reference/commands.md):** A full reference of all the
+  available commands.
+- **[Configuration reference](./reference/configuration.md):** A full reference
+  of all the available configuration options.
+- **[Keyboard shortcuts](./reference/keyboard-shortcuts.md):** A list of all the
+  available keyboard shortcuts.
+- **[Memory import processor](./reference/memport.md):** Learn how to use the
+  memory import processor.
+- **[Policy engine](./reference/policy-engine.md):** Learn how to use the policy
+  engine.
+- **[Tools API](./reference/tools-api.md):** Learn how to use the tools API.
 
 ## Resources
 
-Support, release history, and legal information.
+- **[Quota and pricing](./resources/quota-and-pricing.md):** Information about
+  quota and pricing.
+- **[Terms and privacy](./resources/tos-privacy.md):** The terms of service and
+  privacy policy.
+- **[FAQ](./resources/faq.md):** Frequently asked questions.
+- **[Troubleshooting](./resources/troubleshooting.md):** Troubleshooting common
+  issues.
+- **[Uninstall](./resources/uninstall.md):** How to uninstall Gemini CLI.
 
-- **[FAQ](./faq.md):** Answers to frequently asked questions.
-- **[Changelogs](./changelogs/index.md):** Highlights and notable changes.
-- **[Quota and pricing](./quota-and-pricing.md):** Limits and billing details.
-- **[Terms and privacy](./tos-privacy.md):** Official notices and terms.
+## Changelog
+
+- **[Release notes](./changelogs/index.md):** The release notes for all
+  versions.
+- **[Stable release](./changelogs/latest.md):** The latest stable release.
+- **[Preview release](./changelogs/preview.md):** The latest preview release.

docs/reference/commands.md

@@ -217,7 +217,7 @@ Slash commands provide meta-level control over the CLI itself.
       model.
   - **Note:** For more details on how `GEMINI.md` files contribute to
     hierarchical memory, see the
-    [CLI Configuration documentation](../get-started/configuration.md).
+    [CLI Configuration documentation](../reference/configuration.md).
 
 ### `/model`
 
@@ -247,7 +247,7 @@ Slash commands provide meta-level control over the CLI itself.
   checkpoints to restore from.
 - **Usage:** `/restore [tool_call_id]`
 - **Note:** Only available if checkpointing is configured via
-  [settings](../get-started/configuration.md). See
+  [settings](../reference/configuration.md). See
   [Checkpointing documentation](../cli/checkpointing.md) for more details.
 
 ### `/rewind`
@@ -286,7 +286,8 @@ Slash commands provide meta-level control over the CLI itself.
   settings that control the behavior and appearance of Gemini CLI. It is
   equivalent to manually editing the `.gemini/settings.json` file, but with
   validation and guidance to prevent errors. See the
-  [settings documentation](./settings.md) for a full list of available settings.
+  [settings documentation](../cli/settings.md) for a full list of available
+  settings.
 - **Usage:** Simply run `/settings` and the editor will open. You can then
   browse or search for specific settings, view their current values, and modify
   them as desired. Changes to some settings are applied immediately, while
@@ -373,7 +374,8 @@ Slash commands provide meta-level control over the CLI itself.
 
 Custom commands allow you to create personalized shortcuts for your most-used
 prompts. For detailed instructions on how to create, manage, and use them,
-please see the dedicated [Custom Commands documentation](./custom-commands.md).
+please see the dedicated
+[Custom Commands documentation](../cli/custom-commands.md).
 
 ## Input prompt shortcuts
 

docs/reference/configuration.md

@@ -1,16 +1,5 @@
 # Gemini CLI configuration
 
-> **Note on configuration format, 9/17/25:** The format of the `settings.json`
-> file has been updated to a new, more organized structure.
->
-> - The new format will be supported in the stable release starting
->   **[09/10/25]**.
-> - Automatic migration from the old format to the new format will begin on
->   **[09/17/25]**.
->
-> For details on the previous format, please see the
-> [v1 Configuration documentation](./configuration-v1.md).
-
 Gemini CLI offers several ways to configure its behavior, including environment
 variables, command-line arguments, and settings files. This document outlines
 the different configuration methods and available settings.
@@ -1210,8 +1199,8 @@ within your user's home folder.
 Environment variables are a common way to configure applications, especially for
 sensitive information like API keys or for settings that might change between
 environments. For authentication setup, see the
-[Authentication documentation](./authentication.md) which covers all available
-authentication methods.
+[Authentication documentation](../get-started/authentication.md) which covers
+all available authentication methods.
 
 The CLI automatically loads environment variables from an `.env` file. The
 loading order is:
@@ -1230,7 +1219,8 @@ the `advanced.excludedEnvVars` setting in your `settings.json` file.
 
 - **`GEMINI_API_KEY`**:
   - Your API key for the Gemini API.
-  - One of several available [authentication methods](./authentication.md).
+  - One of several available
+    [authentication methods](../get-started/authentication.md).
   - Set this in your shell profile (e.g., `~/.bashrc`, `~/.zshrc`) or an `.env`
     file.
 - **`GEMINI_MODEL`**:
@@ -1576,15 +1566,16 @@ conventions and context.
   about the active instructional context.
 - **Importing content:** You can modularize your context files by importing
   other Markdown files using the `@path/to/file.md` syntax. For more details,
-  see the [Memory Import Processor documentation](../core/memport.md).
+  see the [Memory Import Processor documentation](../reference/memport.md).
 - **Commands for memory management:**
   - Use `/memory refresh` to force a re-scan and reload of all context files
     from all configured locations. This updates the AI's instructional context.
   - Use `/memory show` to display the combined instructional context currently
     loaded, allowing you to verify the hierarchy and content being used by the
     AI.
-  - See the [Commands documentation](../cli/commands.md#memory) for full details
-    on the `/memory` command and its sub-commands (`show` and `refresh`).
+  - See the [Commands documentation](../reference/commands.md#memory) for full
+    details on the `/memory` command and its sub-commands (`show` and
+    `refresh`).
 
 By understanding and utilizing these configuration layers and the hierarchical
 nature of context files, you can effectively manage the AI's memory and tailor

docs/resources/faq.md

@@ -104,7 +104,7 @@ The Gemini CLI configuration is stored in two `settings.json` files:
 1.  In your home directory: `~/.gemini/settings.json`.
 2.  In your project's root directory: `./.gemini/settings.json`.
 
-Refer to [Gemini CLI Configuration](./get-started/configuration.md) for more
+Refer to [Gemini CLI Configuration](../reference/configuration.md) for more
 details.
 
 ## Google AI Pro/Ultra and subscription FAQs

docs/resources/tos-privacy.md

@@ -10,8 +10,8 @@ and Privacy Notices applicable to those services apply to such access and use.
 Your Gemini CLI Usage Statistics are handled in accordance with Google's Privacy
 Policy.
 
-**Note:** See [quotas and pricing](/docs/quota-and-pricing.md) for the quota and
-pricing details that apply to your usage of the Gemini CLI.
+**Note:** See [quotas and pricing](/docs/resources/quota-and-pricing.md) for the
+quota and pricing details that apply to your usage of the Gemini CLI.
 
 ## Supported authentication methods
 
@@ -93,4 +93,4 @@ backend, these Terms of Service and Privacy Notice documents apply:
 
 You may opt-out from sending Gemini CLI Usage Statistics to Google by following
 the instructions available here:
-[Usage Statistics Configuration](https://github.com/google-gemini/gemini-cli/blob/main/docs/get-started/configuration.md#usage-statistics).
+[Usage Statistics Configuration](https://github.com/google-gemini/gemini-cli/blob/main/docs/reference/configuration.md#usage-statistics).

docs/resources/troubleshooting.md

@@ -93,7 +93,7 @@ topics on:
   - **Cause:** When sandboxing is enabled, Gemini CLI may attempt operations
     that are restricted by your sandbox configuration, such as writing outside
     the project directory or system temp directory.
-  - **Solution:** Refer to the [Configuration: Sandboxing](./cli/sandbox.md)
+  - **Solution:** Refer to the [Configuration: Sandboxing](../cli/sandbox.md)
     documentation for more information, including how to customize your sandbox
     configuration.
 

docs/sidebar.json

@@ -1,189 +1,223 @@
 [
   {
-    "label": "Get started",
-    "items": [
-      { "label": "Overview", "slug": "docs" },
-      { "label": "Quickstart", "slug": "docs/get-started" },
-      { "label": "Installation", "slug": "docs/get-started/installation" },
-      { "label": "Authentication", "slug": "docs/get-started/authentication" },
-      { "label": "Examples", "slug": "docs/get-started/examples" },
-      { "label": "CLI cheatsheet", "slug": "docs/cli/cli-reference" },
-      { "label": "Gemini 3 on Gemini CLI", "slug": "docs/get-started/gemini-3" }
-    ]
-  },
-  {
-    "label": "Use Gemini CLI",
+    "label": "docs_tab",
     "items": [
       {
-        "label": "File management",
-        "slug": "docs/cli/tutorials/file-management"
+        "label": "Get started",
+        "items": [
+          { "label": "Overview", "slug": "docs" },
+          { "label": "Quickstart", "slug": "docs/get-started" },
+          { "label": "Installation", "slug": "docs/get-started/installation" },
+          {
+            "label": "Authentication",
+            "slug": "docs/get-started/authentication"
+          },
+          { "label": "Examples", "slug": "docs/get-started/examples" },
+          { "label": "CLI cheatsheet", "slug": "docs/cli/cli-reference" },
+          {
+            "label": "Gemini 3 on Gemini CLI",
+            "slug": "docs/get-started/gemini-3"
+          }
+        ]
       },
       {
-        "label": "Manage context and memory",
-        "slug": "docs/cli/tutorials/memory-management"
+        "label": "Use Gemini CLI",
+        "items": [
+          {
+            "label": "File management",
+            "slug": "docs/cli/tutorials/file-management"
+          },
+          {
+            "label": "Manage context and memory",
+            "slug": "docs/cli/tutorials/memory-management"
+          },
+          {
+            "label": "Execute shell commands",
+            "slug": "docs/cli/tutorials/shell-commands"
+          },
+          {
+            "label": "Manage sessions and history",
+            "slug": "docs/cli/tutorials/session-management"
+          },
+          {
+            "label": "Plan tasks with todos",
+            "slug": "docs/cli/tutorials/task-planning"
+          },
+          {
+            "label": "Web search and fetch",
+            "slug": "docs/cli/tutorials/web-tools"
+          },
+          {
+            "label": "Get started with skills",
+            "slug": "docs/cli/tutorials/skills-getting-started"
+          },
+          {
+            "label": "Set up an MCP server",
+            "slug": "docs/cli/tutorials/mcp-setup"
+          },
+          { "label": "Automate tasks", "slug": "docs/cli/tutorials/automation" }
+        ]
       },
       {
-        "label": "Execute shell commands",
-        "slug": "docs/cli/tutorials/shell-commands"
+        "label": "Features",
+        "items": [
+          { "label": "Agent Skills", "slug": "docs/cli/skills" },
+          {
+            "label": "Authentication",
+            "slug": "docs/get-started/authentication"
+          },
+          { "label": "Checkpointing", "slug": "docs/cli/checkpointing" },
+          {
+            "label": "Extensions",
+            "slug": "docs/extensions/index"
+          },
+          { "label": "Headless mode", "slug": "docs/cli/headless" },
+          { "label": "Hooks", "slug": "docs/hooks" },
+          { "label": "IDE integration", "slug": "docs/ide-integration" },
+          { "label": "MCP servers", "slug": "docs/tools/mcp-server" },
+          { "label": "Model routing", "slug": "docs/cli/model-routing" },
+          { "label": "Model selection", "slug": "docs/cli/model" },
+          { "label": "Plan mode (experimental)", "slug": "docs/cli/plan-mode" },
+          { "label": "Rewind", "slug": "docs/cli/rewind" },
+          { "label": "Sandboxing", "slug": "docs/cli/sandbox" },
+          { "label": "Settings", "slug": "docs/cli/settings" },
+          { "label": "Telemetry", "slug": "docs/cli/telemetry" },
+          { "label": "Token caching", "slug": "docs/cli/token-caching" }
+        ]
       },
       {
-        "label": "Manage sessions and history",
-        "slug": "docs/cli/tutorials/session-management"
+        "label": "Configuration",
+        "items": [
+          { "label": "Custom commands", "slug": "docs/cli/custom-commands" },
+          {
+            "label": "Enterprise configuration",
+            "slug": "docs/cli/enterprise"
+          },
+          {
+            "label": "Ignore files (.geminiignore)",
+            "slug": "docs/cli/gemini-ignore"
+          },
+          {
+            "label": "Model configuration",
+            "slug": "docs/cli/generation-settings"
+          },
+          {
+            "label": "Project context (GEMINI.md)",
+            "slug": "docs/cli/gemini-md"
+          },
+          { "label": "Settings", "slug": "docs/cli/settings" },
+          {
+            "label": "System prompt override",
+            "slug": "docs/cli/system-prompt"
+          },
+          { "label": "Themes", "slug": "docs/cli/themes" },
+          { "label": "Trusted folders", "slug": "docs/cli/trusted-folders" }
+        ]
       },
-      {
-        "label": "Plan tasks with todos",
-        "slug": "docs/cli/tutorials/task-planning"
-      },
-      {
-        "label": "Web search and fetch",
-        "slug": "docs/cli/tutorials/web-tools"
-      },
-      {
-        "label": "Get started with skills",
-        "slug": "docs/cli/tutorials/skills-getting-started"
-      },
-      {
-        "label": "Set up an MCP server",
-        "slug": "docs/cli/tutorials/mcp-setup"
-      },
-      { "label": "Automate tasks", "slug": "docs/cli/tutorials/automation" }
-    ]
-  },
-  {
-    "label": "Features",
-    "items": [
-      { "label": "Agent Skills", "slug": "docs/cli/skills" },
-      {
-        "label": "Authentication",
-        "slug": "docs/get-started/authentication"
-      },
-      { "label": "Checkpointing", "slug": "docs/cli/checkpointing" },
       {
         "label": "Extensions",
-        "slug": "docs/extensions/index"
-      },
-      { "label": "Headless mode", "slug": "docs/cli/headless" },
-      { "label": "Help", "link": "/docs/cli/commands/#help-or" },
-      { "label": "Hooks", "slug": "docs/hooks" },
-      { "label": "IDE integration", "slug": "docs/ide-integration" },
-      { "label": "MCP servers", "slug": "docs/tools/mcp-server" },
-      {
-        "label": "Memory management",
-        "link": "/docs/cli/commands/#memory"
-      },
-      { "label": "Model routing", "slug": "docs/cli/model-routing" },
-      { "label": "Model selection", "slug": "docs/cli/model" },
-      { "label": "Plan mode (experimental)", "slug": "docs/cli/plan-mode" },
-      { "label": "Rewind", "slug": "docs/cli/rewind" },
-      { "label": "Sandboxing", "slug": "docs/cli/sandbox" },
-      { "label": "Settings", "slug": "docs/cli/settings" },
-      {
-        "label": "Shell",
-        "link": "/docs/cli/commands/#shells-or-bashes"
+        "items": [
+          {
+            "label": "Overview",
+            "slug": "docs/extensions"
+          },
+          {
+            "label": "User guide: Install and manage",
+            "link": "/docs/extensions/#manage-extensions"
+          },
+          {
+            "label": "Developer guide: Build extensions",
+            "slug": "docs/extensions/writing-extensions"
+          },
+          {
+            "label": "Developer guide: Best practices",
+            "slug": "docs/extensions/best-practices"
+          },
+          {
+            "label": "Developer guide: Releasing",
+            "slug": "docs/extensions/releasing"
+          },
+          {
+            "label": "Developer guide: Reference",
+            "slug": "docs/extensions/reference"
+          }
+        ]
       },
       {
-        "label": "Stats",
-        "link": "/docs/cli/commands/#stats"
-      },
-      { "label": "Telemetry", "slug": "docs/cli/telemetry" },
-      { "label": "Token caching", "slug": "docs/cli/token-caching" },
-      { "label": "Tools", "link": "/docs/cli/commands/#tools" }
-    ]
-  },
-  {
-    "label": "Configuration",
-    "items": [
-      { "label": "Custom commands", "slug": "docs/cli/custom-commands" },
-      { "label": "Enterprise configuration", "slug": "docs/cli/enterprise" },
-      {
-        "label": "Ignore files (.geminiignore)",
-        "slug": "docs/cli/gemini-ignore"
-      },
-      {
-        "label": "Model configuration",
-        "slug": "docs/cli/generation-settings"
-      },
-      { "label": "Project context (GEMINI.md)", "slug": "docs/cli/gemini-md" },
-      { "label": "Settings", "slug": "docs/cli/settings" },
-      { "label": "System prompt override", "slug": "docs/cli/system-prompt" },
-      { "label": "Themes", "slug": "docs/cli/themes" },
-      { "label": "Trusted folders", "slug": "docs/cli/trusted-folders" }
-    ]
-  },
-  {
-    "label": "Extensions",
-    "items": [
-      {
-        "label": "Overview",
-        "slug": "docs/extensions"
-      },
-      {
-        "label": "User guide: Install and manage",
-        "link": "/docs/extensions/#manage-extensions"
-      },
-      {
-        "label": "Developer guide: Build extensions",
-        "slug": "docs/extensions/writing-extensions"
-      },
-      {
-        "label": "Developer guide: Best practices",
-        "slug": "docs/extensions/best-practices"
-      },
-      {
-        "label": "Developer guide: Releasing",
-        "slug": "docs/extensions/releasing"
-      },
-      {
-        "label": "Developer guide: Reference",
-        "slug": "docs/extensions/reference"
+        "label": "Development",
+        "items": [
+          { "label": "Contribution guide", "slug": "docs/contributing" },
+          { "label": "Integration testing", "slug": "docs/integration-tests" },
+          {
+            "label": "Issue and PR automation",
+            "slug": "docs/issue-and-pr-automation"
+          },
+          { "label": "Local development", "slug": "docs/local-development" },
+          { "label": "NPM package structure", "slug": "docs/npm" }
+        ]
       }
     ]
   },
   {
-    "label": "Reference",
+    "label": "reference_tab",
     "items": [
-      { "label": "Architecture", "slug": "docs/architecture" },
-      { "label": "Command reference", "slug": "docs/cli/commands" },
       {
-        "label": "Configuration reference",
-        "slug": "docs/get-started/configuration"
-      },
-      { "label": "Core concepts", "slug": "docs/core/concepts" },
-      { "label": "Keyboard shortcuts", "slug": "docs/cli/keyboard-shortcuts" },
-      { "label": "Memory import processor", "slug": "docs/core/memport" },
-      { "label": "Policy engine", "slug": "docs/core/policy-engine" },
-      { "label": "Tools API", "slug": "docs/core/tools-api" }
+        "label": "Reference",
+        "items": [
+          { "label": "Command reference", "slug": "docs/reference/commands" },
+          {
+            "label": "Configuration reference",
+            "slug": "docs/reference/configuration"
+          },
+          {
+            "label": "Keyboard shortcuts",
+            "slug": "docs/reference/keyboard-shortcuts"
+          },
+          {
+            "label": "Memory import processor",
+            "slug": "docs/reference/memport"
+          },
+          { "label": "Policy engine", "slug": "docs/reference/policy-engine" },
+          { "label": "Tools API", "slug": "docs/reference/tools-api" }
+        ]
+      }
     ]
   },
   {
-    "label": "Resources",
+    "label": "resources_tab",
     "items": [
-      { "label": "FAQ", "slug": "docs/faq" },
-      { "label": "Quota and pricing", "slug": "docs/quota-and-pricing" },
-      { "label": "Terms and privacy", "slug": "docs/tos-privacy" },
-      { "label": "Troubleshooting", "slug": "docs/troubleshooting" },
-      { "label": "Uninstall", "slug": "docs/cli/uninstall" }
-    ]
-  },
-  {
-    "label": "Development",
-    "items": [
-      { "label": "Contribution guide", "slug": "docs/contributing" },
-      { "label": "Integration testing", "slug": "docs/integration-tests" },
       {
-        "label": "Issue and PR automation",
-        "slug": "docs/issue-and-pr-automation"
-      },
-      { "label": "Local development", "slug": "docs/local-development" },
-      { "label": "NPM package structure", "slug": "docs/npm" }
+        "label": "Resources",
+        "items": [
+          {
+            "label": "Quota and pricing",
+            "slug": "docs/resources/quota-and-pricing"
+          },
+          {
+            "label": "Terms and privacy",
+            "slug": "docs/resources/tos-privacy"
+          },
+          { "label": "FAQ", "slug": "docs/resources/faq" },
+          {
+            "label": "Troubleshooting",
+            "slug": "docs/resources/troubleshooting"
+          },
+          { "label": "Uninstall", "slug": "docs/resources/uninstall" }
+        ]
+      }
     ]
   },
   {
-    "label": "Releases",
+    "label": "changelog_tab",
     "items": [
-      { "label": "Release notes", "slug": "docs/changelogs/" },
-      { "label": "Stable release", "slug": "docs/changelogs/latest" },
-      { "label": "Preview release", "slug": "docs/changelogs/preview" }
+      {
+        "label": "Changelog",
+        "items": [
+          { "label": "Release notes", "slug": "docs/changelogs/" },
+          { "label": "Stable release", "slug": "docs/changelogs/latest" },
+          { "label": "Preview release", "slug": "docs/changelogs/preview" }
+        ]
+      }
     ]
   }
 ]

docs/tools/index.md

@@ -98,5 +98,5 @@ Always review confirmation prompts carefully before allowing a tool to execute.
 ## Next steps
 
 - Learn how to [Provide context](../cli/gemini-md.md) to guide tool use.
-- Explore the [Command reference](../cli/commands.md) for tool-related slash
-  commands.
+- Explore the [Command reference](../reference/commands.md) for tool-related
+  slash commands.

docs/tools/internal-docs.md

@@ -40,7 +40,7 @@ Gemini CLI uses this tool to ensure technical accuracy:
 
 ## Next steps
 
-- Explore the [Command reference](../cli/commands.md) for a detailed guide to
-  slash commands.
-- See the [Configuration guide](../get-started/configuration.md) for settings
+- Explore the [Command reference](../reference/commands.md) for a detailed guide
+  to slash commands.
+- See the [Configuration guide](../reference/configuration.md) for settings
   reference.

docs/tools/shell.md

@@ -131,9 +131,9 @@ configuration file.
   commands. Including the generic `run_shell_command` acts as a wildcard,
   allowing any command not explicitly blocked.
 - `tools.exclude` [DEPRECATED]: To block specific commands, use the
-  [Policy Engine](../core/policy-engine.md). Historically, this setting allowed
-  adding entries to the `exclude` list under the `tools` category in the format
-  `run_shell_command(<command>)`. For example,
+  [Policy Engine](../reference/policy-engine.md). Historically, this setting
+  allowed adding entries to the `exclude` list under the `tools` category in the
+  format `run_shell_command(<command>)`. For example,
   `"tools": {"exclude": ["run_shell_command(rm)"]}` will block `rm` commands.
 
 The validation logic is designed to be secure and flexible:

evals/frugalReads.eval.ts

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

evals/frugalSearch.eval.ts

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

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

@@ -216,8 +216,18 @@ describe('App', () => {
 
     const stateWithConfirmingTool = {
       ...mockUIState,
-      pendingHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
-      pendingGeminiHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
+      pendingHistoryItems: [
+        {
+          type: 'tool_group',
+          tools: toolCalls,
+        },
+      ],
+      pendingGeminiHistoryItems: [
+        {
+          type: 'tool_group',
+          tools: toolCalls,
+        },
+      ],
     } as UIState;
 
     const configWithExperiment = makeFakeConfig();

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

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

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

@@ -44,8 +44,6 @@ interface HistoryItemDisplayProps {
   terminalWidth: number;
   isPending: boolean;
   commands?: readonly SlashCommand[];
-  activeShellPtyId?: number | null;
-  embeddedShellFocused?: boolean;
   availableTerminalHeightGemini?: number;
 }
 
@@ -55,8 +53,6 @@ export const HistoryItemDisplay: React.FC<HistoryItemDisplayProps> = ({
   terminalWidth,
   isPending,
   commands,
-  activeShellPtyId,
-  embeddedShellFocused,
   availableTerminalHeightGemini,
 }) => {
   const settings = useSettings();
@@ -173,12 +169,10 @@ export const HistoryItemDisplay: React.FC<HistoryItemDisplayProps> = ({
       )}
       {itemForDisplay.type === 'tool_group' && (
         <ToolGroupMessage
+          item={itemForDisplay}
           toolCalls={itemForDisplay.tools}
-          groupId={itemForDisplay.id}
           availableTerminalHeight={availableTerminalHeight}
           terminalWidth={terminalWidth}
-          activeShellPtyId={activeShellPtyId}
-          embeddedShellFocused={embeddedShellFocused}
           borderTop={itemForDisplay.borderTop}
           borderBottom={itemForDisplay.borderBottom}
         />

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

@@ -7,6 +7,7 @@
 import { renderWithProviders } from '../../test-utils/render.js';
 import { waitFor } from '../../test-utils/async.js';
 import { MainContent } from './MainContent.js';
+import { getToolGroupBorderAppearance } from '../utils/borderStyles.js';
 import { describe, it, expect, vi, beforeEach } from 'vitest';
 import { Box, Text } from 'ink';
 import { act, useState, type JSX } from 'react';
@@ -18,6 +19,7 @@ import {
   type UIState,
 } from '../contexts/UIStateContext.js';
 import { CoreToolCallStatus } from '@google/gemini-cli-core';
+import { type IndividualToolCallDisplay } from '../types.js';
 
 // Mock dependencies
 vi.mock('../contexts/SettingsContext.js', async () => {
@@ -76,6 +78,209 @@ vi.mock('./shared/ScrollableList.js', () => ({
   SCROLL_TO_ITEM_END: 0,
 }));
 
+import { theme } from '../semantic-colors.js';
+import { type BackgroundShell } from '../hooks/shellReducer.js';
+
+describe('getToolGroupBorderAppearance', () => {
+  const mockBackgroundShells = new Map<number, BackgroundShell>();
+  const activeShellPtyId = 123;
+
+  it('returns default empty values for non-tool_group items', () => {
+    const item = { type: 'user' as const, text: 'Hello', id: 1 };
+    const result = getToolGroupBorderAppearance(
+      item,
+      null,
+      false,
+      [],
+      mockBackgroundShells,
+    );
+    expect(result).toEqual({ borderColor: '', borderDimColor: false });
+  });
+
+  it('inspects only the last pending tool_group item if current has no tools', () => {
+    const item = { type: 'tool_group' as const, tools: [], id: 1 };
+    const pendingItems = [
+      {
+        type: 'tool_group' as const,
+        tools: [
+          {
+            callId: '1',
+            name: 'some_tool',
+            description: '',
+            status: CoreToolCallStatus.Executing,
+            ptyId: undefined,
+            resultDisplay: undefined,
+            confirmationDetails: undefined,
+          } as IndividualToolCallDisplay,
+        ],
+      },
+      {
+        type: 'tool_group' as const,
+        tools: [
+          {
+            callId: '2',
+            name: 'other_tool',
+            description: '',
+            status: CoreToolCallStatus.Success,
+            ptyId: undefined,
+            resultDisplay: undefined,
+            confirmationDetails: undefined,
+          } as IndividualToolCallDisplay,
+        ],
+      },
+    ];
+
+    // Only the last item (Success) should be inspected, so hasPending = false.
+    // The previous item was Executing (pending) but it shouldn't be counted.
+    const result = getToolGroupBorderAppearance(
+      item,
+      null,
+      false,
+      pendingItems,
+      mockBackgroundShells,
+    );
+    expect(result).toEqual({
+      borderColor: theme.border.default,
+      borderDimColor: false,
+    });
+  });
+
+  it('returns default border for completed normal tools', () => {
+    const item = {
+      type: 'tool_group' as const,
+      tools: [
+        {
+          callId: '1',
+          name: 'some_tool',
+          description: '',
+          status: CoreToolCallStatus.Success,
+          ptyId: undefined,
+          resultDisplay: undefined,
+          confirmationDetails: undefined,
+        } as IndividualToolCallDisplay,
+      ],
+      id: 1,
+    };
+    const result = getToolGroupBorderAppearance(
+      item,
+      null,
+      false,
+      [],
+      mockBackgroundShells,
+    );
+    expect(result).toEqual({
+      borderColor: theme.border.default,
+      borderDimColor: false,
+    });
+  });
+
+  it('returns warning border for pending normal tools', () => {
+    const item = {
+      type: 'tool_group' as const,
+      tools: [
+        {
+          callId: '1',
+          name: 'some_tool',
+          description: '',
+          status: CoreToolCallStatus.Executing,
+          ptyId: undefined,
+          resultDisplay: undefined,
+          confirmationDetails: undefined,
+        } as IndividualToolCallDisplay,
+      ],
+      id: 1,
+    };
+    const result = getToolGroupBorderAppearance(
+      item,
+      null,
+      false,
+      [],
+      mockBackgroundShells,
+    );
+    expect(result).toEqual({
+      borderColor: theme.status.warning,
+      borderDimColor: true,
+    });
+  });
+
+  it('returns symbol border for executing shell commands', () => {
+    const item = {
+      type: 'tool_group' as const,
+      tools: [
+        {
+          callId: '1',
+          name: SHELL_COMMAND_NAME,
+          description: '',
+          status: CoreToolCallStatus.Executing,
+          ptyId: activeShellPtyId,
+          resultDisplay: undefined,
+          confirmationDetails: undefined,
+        } as IndividualToolCallDisplay,
+      ],
+      id: 1,
+    };
+    // While executing shell commands, it's dim false, border symbol
+    const result = getToolGroupBorderAppearance(
+      item,
+      activeShellPtyId,
+      true,
+      [],
+      mockBackgroundShells,
+    );
+    expect(result).toEqual({
+      borderColor: theme.ui.symbol,
+      borderDimColor: false,
+    });
+  });
+
+  it('returns symbol border and dims color for background executing shell command when another shell is active', () => {
+    const item = {
+      type: 'tool_group' as const,
+      tools: [
+        {
+          callId: '1',
+          name: SHELL_COMMAND_NAME,
+          description: '',
+          status: CoreToolCallStatus.Executing,
+          ptyId: 456, // Different ptyId, not active
+          resultDisplay: undefined,
+          confirmationDetails: undefined,
+        } as IndividualToolCallDisplay,
+      ],
+      id: 1,
+    };
+    const result = getToolGroupBorderAppearance(
+      item,
+      activeShellPtyId,
+      false,
+      [],
+      mockBackgroundShells,
+    );
+    expect(result).toEqual({
+      borderColor: theme.ui.symbol,
+      borderDimColor: true,
+    });
+  });
+
+  it('handles empty tools with active shell turn (isCurrentlyInShellTurn)', () => {
+    const item = { type: 'tool_group' as const, tools: [], id: 1 };
+
+    // active shell turn
+    const result = getToolGroupBorderAppearance(
+      item,
+      activeShellPtyId,
+      true,
+      [],
+      mockBackgroundShells,
+    );
+    // Since there are no tools to inspect, it falls back to empty pending, but isCurrentlyInShellTurn=true
+    // so it counts as pending shell.
+    expect(result.borderColor).toEqual(theme.ui.symbol);
+    // It shouldn't be dim because there are no tools to say it isEmbeddedShellFocused = false
+    expect(result.borderDimColor).toBe(false);
+  });
+});
+
 describe('MainContent', () => {
   const defaultMockUiState = {
     history: [
@@ -258,7 +463,7 @@ describe('MainContent', () => {
           history: [],
           pendingHistoryItems: [
             {
-              type: 'tool_group' as const,
+              type: 'tool_group',
               id: 1,
               tools: [
                 {

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

@@ -88,8 +88,6 @@ export const MainContent = () => {
             terminalWidth={mainAreaWidth}
             item={{ ...item, id: 0 }}
             isPending={true}
-            activeShellPtyId={uiState.activePtyId}
-            embeddedShellFocused={uiState.embeddedShellFocused}
           />
         ))}
         {showConfirmationQueue && confirmingTool && (
@@ -103,8 +101,6 @@ export const MainContent = () => {
       isAlternateBuffer,
       availableTerminalHeight,
       mainAreaWidth,
-      uiState.activePtyId,
-      uiState.embeddedShellFocused,
       showConfirmationQueue,
       confirmingTool,
     ],

packages/cli/src/ui/components/messages/ShellToolMessage.test.tsx

@@ -88,20 +88,16 @@ describe('<ShellToolMessage />', () => {
           CoreToolCallStatus.Executing,
         );
         updateStatus = setStatus;
-        return (
-          <ShellToolMessage
-            {...baseProps}
-            status={status}
-            embeddedShellFocused={true}
-            activeShellPtyId={1}
-            ptyId={1}
-          />
-        );
+        return <ShellToolMessage {...baseProps} status={status} ptyId={1} />;
       };
 
       const { lastFrame } = renderWithProviders(<Wrapper />, {
         uiActions,
-        uiState: { streamingState: StreamingState.Idle },
+        uiState: {
+          streamingState: StreamingState.Idle,
+          embeddedShellFocused: true,
+          activePtyId: 1,
+        },
       });
 
       // Verify it is initially focused
@@ -143,21 +139,29 @@ describe('<ShellToolMessage />', () => {
         'renders in Alternate Buffer mode while focused',
         {
           status: CoreToolCallStatus.Executing,
-          embeddedShellFocused: true,
-          activeShellPtyId: 1,
           ptyId: 1,
         },
-        { useAlternateBuffer: true },
+        {
+          useAlternateBuffer: true,
+          uiState: {
+            embeddedShellFocused: true,
+            activePtyId: 1,
+          },
+        },
       ],
       [
         'renders in Alternate Buffer mode while unfocused',
         {
           status: CoreToolCallStatus.Executing,
-          embeddedShellFocused: false,
-          activeShellPtyId: 1,
           ptyId: 1,
         },
-        { useAlternateBuffer: true },
+        {
+          useAlternateBuffer: true,
+          uiState: {
+            embeddedShellFocused: false,
+            activePtyId: 1,
+          },
+        },
       ],
     ])('%s', async (_, props, options) => {
       const { lastFrame } = renderShell(props, options);
@@ -199,12 +203,16 @@ describe('<ShellToolMessage />', () => {
           resultDisplay: LONG_OUTPUT,
           renderOutputAsMarkdown: false,
           availableTerminalHeight,
-          activeShellPtyId: 1,
-          ptyId: focused ? 1 : 2,
+          ptyId: 1,
           status: CoreToolCallStatus.Executing,
-          embeddedShellFocused: focused,
         },
-        { useAlternateBuffer: true },
+        {
+          useAlternateBuffer: true,
+          uiState: {
+            activePtyId: focused ? 1 : 2,
+            embeddedShellFocused: focused,
+          },
+        },
       );
 
       await waitFor(() => {

packages/cli/src/ui/components/messages/ShellToolMessage.tsx

@@ -29,9 +29,9 @@ import {
 import { useAlternateBuffer } from '../../hooks/useAlternateBuffer.js';
 import { type Config, CoreToolCallStatus } from '@google/gemini-cli-core';
 
+import { useUIState } from '../../contexts/UIStateContext.js';
+
 export interface ShellToolMessageProps extends ToolMessageProps {
-  activeShellPtyId?: number | null;
-  embeddedShellFocused?: boolean;
   config?: Config;
 }
 
@@ -52,10 +52,6 @@ export const ShellToolMessage: React.FC<ShellToolMessageProps> = ({
 
   renderOutputAsMarkdown = true,
 
-  activeShellPtyId,
-
-  embeddedShellFocused,
-
   ptyId,
 
   config,
@@ -66,6 +62,7 @@ export const ShellToolMessage: React.FC<ShellToolMessageProps> = ({
 
   borderDimColor,
 }) => {
+  const { activePtyId: activeShellPtyId, embeddedShellFocused } = useUIState();
   const isAlternateBuffer = useAlternateBuffer();
   const isThisShellFocused = checkIsShellFocused(
     name,

packages/cli/src/ui/components/messages/ToolGroupMessage.test.tsx

@@ -7,7 +7,11 @@
 import { renderWithProviders } from '../../../test-utils/render.js';
 import { describe, it, expect, vi, afterEach } from 'vitest';
 import { ToolGroupMessage } from './ToolGroupMessage.js';
-import type { IndividualToolCallDisplay } from '../../types.js';
+import type {
+  HistoryItem,
+  HistoryItemWithoutId,
+  IndividualToolCallDisplay,
+} from '../../types.js';
 import { Scrollable } from '../shared/Scrollable.js';
 import {
   makeFakeConfig,
@@ -40,10 +44,17 @@ describe('<ToolGroupMessage />', () => {
   });
 
   const baseProps = {
-    groupId: 1,
     terminalWidth: 80,
   };
 
+  const createItem = (
+    tools: IndividualToolCallDisplay[],
+  ): HistoryItem | HistoryItemWithoutId => ({
+    id: 1,
+    type: 'tool_group',
+    tools,
+  });
+
   const baseMockConfig = makeFakeConfig({
     model: 'gemini-pro',
     targetDir: os.tmpdir(),
@@ -56,12 +67,18 @@ describe('<ToolGroupMessage />', () => {
   describe('Golden Snapshots', () => {
     it('renders single successful tool call', () => {
       const toolCalls = [createToolCall()];
+      const item = createItem(toolCalls);
       const { lastFrame, unmount } = renderWithProviders(
-        <ToolGroupMessage {...baseProps} toolCalls={toolCalls} />,
+        <ToolGroupMessage {...baseProps} item={item} toolCalls={toolCalls} />,
         {
           config: baseMockConfig,
           uiState: {
-            pendingHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
+            pendingHistoryItems: [
+              {
+                type: 'tool_group',
+                tools: toolCalls,
+              },
+            ],
           },
         },
       );
@@ -81,9 +98,10 @@ describe('<ToolGroupMessage />', () => {
           },
         }),
       ];
+      const item = createItem(toolCalls);
 
       const { lastFrame, unmount } = renderWithProviders(
-        <ToolGroupMessage {...baseProps} toolCalls={toolCalls} />,
+        <ToolGroupMessage {...baseProps} item={item} toolCalls={toolCalls} />,
         { config: baseMockConfig },
       );
 
@@ -113,13 +131,19 @@ describe('<ToolGroupMessage />', () => {
           status: CoreToolCallStatus.Error,
         }),
       ];
+      const item = createItem(toolCalls);
 
       const { lastFrame, unmount } = renderWithProviders(
-        <ToolGroupMessage {...baseProps} toolCalls={toolCalls} />,
+        <ToolGroupMessage {...baseProps} item={item} toolCalls={toolCalls} />,
         {
           config: baseMockConfig,
           uiState: {
-            pendingHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
+            pendingHistoryItems: [
+              {
+                type: 'tool_group',
+                tools: toolCalls,
+              },
+            ],
           },
         },
       );
@@ -153,13 +177,19 @@ describe('<ToolGroupMessage />', () => {
           status: CoreToolCallStatus.Scheduled,
         }),
       ];
+      const item = createItem(toolCalls);
 
       const { lastFrame, unmount } = renderWithProviders(
-        <ToolGroupMessage {...baseProps} toolCalls={toolCalls} />,
+        <ToolGroupMessage {...baseProps} item={item} toolCalls={toolCalls} />,
         {
           config: baseMockConfig,
           uiState: {
-            pendingHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
+            pendingHistoryItems: [
+              {
+                type: 'tool_group',
+                tools: toolCalls,
+              },
+            ],
           },
         },
       );
@@ -188,16 +218,23 @@ describe('<ToolGroupMessage />', () => {
           resultDisplay: 'More output here',
         }),
       ];
+      const item = createItem(toolCalls);
       const { lastFrame, unmount } = renderWithProviders(
         <ToolGroupMessage
           {...baseProps}
+          item={item}
           toolCalls={toolCalls}
           availableTerminalHeight={10}
         />,
         {
           config: baseMockConfig,
           uiState: {
-            pendingHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
+            pendingHistoryItems: [
+              {
+                type: 'tool_group',
+                tools: toolCalls,
+              },
+            ],
           },
         },
       );
@@ -213,16 +250,23 @@ describe('<ToolGroupMessage />', () => {
             'This is a very long description that might cause wrapping issues',
         }),
       ];
+      const item = createItem(toolCalls);
       const { lastFrame, unmount } = renderWithProviders(
         <ToolGroupMessage
           {...baseProps}
+          item={item}
           toolCalls={toolCalls}
           terminalWidth={40}
         />,
         {
           config: baseMockConfig,
           uiState: {
-            pendingHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
+            pendingHistoryItems: [
+              {
+                type: 'tool_group',
+                tools: toolCalls,
+              },
+            ],
           },
         },
       );
@@ -231,12 +275,19 @@ describe('<ToolGroupMessage />', () => {
     });
 
     it('renders empty tool calls array', () => {
+      const toolCalls: IndividualToolCallDisplay[] = [];
+      const item = createItem(toolCalls);
       const { lastFrame, unmount } = renderWithProviders(
-        <ToolGroupMessage {...baseProps} toolCalls={[]} />,
+        <ToolGroupMessage {...baseProps} item={item} toolCalls={toolCalls} />,
         {
           config: baseMockConfig,
           uiState: {
-            pendingHistoryItems: [{ type: 'tool_group', tools: [] }],
+            pendingHistoryItems: [
+              {
+                type: 'tool_group',
+                tools: [],
+              },
+            ],
           },
         },
       );
@@ -260,14 +311,20 @@ describe('<ToolGroupMessage />', () => {
           resultDisplay: 'line1\nline2',
         }),
       ];
+      const item = createItem(toolCalls);
       const { lastFrame, unmount } = renderWithProviders(
         <Scrollable height={10} hasFocus={true} scrollToBottom={true}>
-          <ToolGroupMessage {...baseProps} toolCalls={toolCalls} />
+          <ToolGroupMessage {...baseProps} item={item} toolCalls={toolCalls} />
         </Scrollable>,
         {
           config: baseMockConfig,
           uiState: {
-            pendingHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
+            pendingHistoryItems: [
+              {
+                type: 'tool_group',
+                tools: toolCalls,
+              },
+            ],
           },
         },
       );
@@ -285,12 +342,18 @@ describe('<ToolGroupMessage />', () => {
           outputFile: '/path/to/output.txt',
         }),
       ];
+      const item = createItem(toolCalls);
       const { lastFrame, unmount } = renderWithProviders(
-        <ToolGroupMessage {...baseProps} toolCalls={toolCalls} />,
+        <ToolGroupMessage {...baseProps} item={item} toolCalls={toolCalls} />,
         {
           config: baseMockConfig,
           uiState: {
-            pendingHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
+            pendingHistoryItems: [
+              {
+                type: 'tool_group',
+                tools: toolCalls,
+              },
+            ],
           },
         },
       );
@@ -307,6 +370,7 @@ describe('<ToolGroupMessage />', () => {
           resultDisplay: 'line1\nline2\nline3\nline4\nline5',
         }),
       ];
+      const item1 = createItem(toolCalls1);
       const toolCalls2 = [
         createToolCall({
           callId: '2',
@@ -315,18 +379,33 @@ describe('<ToolGroupMessage />', () => {
           resultDisplay: 'line1',
         }),
       ];
+      const item2 = createItem(toolCalls2);
 
       const { lastFrame, unmount } = renderWithProviders(
         <Scrollable height={6} hasFocus={true} scrollToBottom={true}>
-          <ToolGroupMessage {...baseProps} toolCalls={toolCalls1} />
-          <ToolGroupMessage {...baseProps} toolCalls={toolCalls2} />
+          <ToolGroupMessage
+            {...baseProps}
+            item={item1}
+            toolCalls={toolCalls1}
+          />
+          <ToolGroupMessage
+            {...baseProps}
+            item={item2}
+            toolCalls={toolCalls2}
+          />
         </Scrollable>,
         {
           config: baseMockConfig,
           uiState: {
             pendingHistoryItems: [
-              { type: 'tool_group', tools: toolCalls1 },
-              { type: 'tool_group', tools: toolCalls2 },
+              {
+                type: 'tool_group',
+                tools: toolCalls1,
+              },
+              {
+                type: 'tool_group',
+                tools: toolCalls2,
+              },
             ],
           },
         },
@@ -344,12 +423,18 @@ describe('<ToolGroupMessage />', () => {
           status: CoreToolCallStatus.Success,
         }),
       ];
+      const item = createItem(toolCalls);
       const { lastFrame, unmount } = renderWithProviders(
-        <ToolGroupMessage {...baseProps} toolCalls={toolCalls} />,
+        <ToolGroupMessage {...baseProps} item={item} toolCalls={toolCalls} />,
         {
           config: baseMockConfig,
           uiState: {
-            pendingHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
+            pendingHistoryItems: [
+              {
+                type: 'tool_group',
+                tools: toolCalls,
+              },
+            ],
           },
         },
       );
@@ -366,12 +451,18 @@ describe('<ToolGroupMessage />', () => {
           status: CoreToolCallStatus.Success,
         }),
       ];
+      const item = createItem(toolCalls);
       const { lastFrame, unmount } = renderWithProviders(
-        <ToolGroupMessage {...baseProps} toolCalls={toolCalls} />,
+        <ToolGroupMessage {...baseProps} item={item} toolCalls={toolCalls} />,
         {
           config: baseMockConfig,
           uiState: {
-            pendingHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
+            pendingHistoryItems: [
+              {
+                type: 'tool_group',
+                tools: toolCalls,
+              },
+            ],
           },
         },
       );
@@ -396,16 +487,23 @@ describe('<ToolGroupMessage />', () => {
           resultDisplay: '', // No result
         }),
       ];
+      const item = createItem(toolCalls);
       const { lastFrame, unmount } = renderWithProviders(
         <ToolGroupMessage
           {...baseProps}
+          item={item}
           toolCalls={toolCalls}
           availableTerminalHeight={20}
         />,
         {
           config: baseMockConfig,
           uiState: {
-            pendingHistoryItems: [{ type: 'tool_group', tools: toolCalls }],
+            pendingHistoryItems: [
+              {
+                type: 'tool_group',
+                tools: toolCalls,
+              },
+            ],
           },
         },
       );
@@ -453,9 +551,10 @@ describe('<ToolGroupMessage />', () => {
             resultDisplay,
           }),
         ];
+        const item = createItem(toolCalls);
 
         const { lastFrame, unmount } = renderWithProviders(
-          <ToolGroupMessage {...baseProps} toolCalls={toolCalls} />,
+          <ToolGroupMessage {...baseProps} item={item} toolCalls={toolCalls} />,
           { config: baseMockConfig },
         );
 
@@ -481,9 +580,10 @@ describe('<ToolGroupMessage />', () => {
           status: CoreToolCallStatus.Scheduled,
         }),
       ];
+      const item = createItem(toolCalls);
 
       const { lastFrame, unmount } = renderWithProviders(
-        <ToolGroupMessage {...baseProps} toolCalls={toolCalls} />,
+        <ToolGroupMessage {...baseProps} item={item} toolCalls={toolCalls} />,
         { config: baseMockConfig },
       );
 
@@ -502,10 +602,12 @@ describe('<ToolGroupMessage />', () => {
           status: CoreToolCallStatus.Executing,
         }),
       ];
+      const item = createItem(toolCalls);
 
       const { lastFrame, unmount } = renderWithProviders(
         <ToolGroupMessage
           {...baseProps}
+          item={item}
           toolCalls={toolCalls}
           borderBottom={false}
         />,
@@ -540,9 +642,10 @@ describe('<ToolGroupMessage />', () => {
           approvalMode: mode,
         }),
       ];
+      const item = createItem(toolCalls);
 
       const { lastFrame, unmount } = renderWithProviders(
-        <ToolGroupMessage {...baseProps} toolCalls={toolCalls} />,
+        <ToolGroupMessage {...baseProps} item={item} toolCalls={toolCalls} />,
         { config: baseMockConfig },
       );
 

packages/cli/src/ui/components/messages/ToolGroupMessage.tsx

@@ -7,27 +7,27 @@
 import type React from 'react';
 import { useMemo } from 'react';
 import { Box, Text } from 'ink';
-import type { IndividualToolCallDisplay } from '../../types.js';
+import type {
+  HistoryItem,
+  HistoryItemWithoutId,
+  IndividualToolCallDisplay,
+} from '../../types.js';
 import { ToolCallStatus, mapCoreStatusToDisplayStatus } from '../../types.js';
 import { ToolMessage } from './ToolMessage.js';
 import { ShellToolMessage } from './ShellToolMessage.js';
 import { theme } from '../../semantic-colors.js';
 import { useConfig } from '../../contexts/ConfigContext.js';
-import { isShellTool, isThisShellFocused } from './ToolShared.js';
-import {
-  CoreToolCallStatus,
-  shouldHideToolCall,
-} from '@google/gemini-cli-core';
+import { isShellTool } from './ToolShared.js';
+import { shouldHideToolCall } from '@google/gemini-cli-core';
 import { ShowMoreLines } from '../ShowMoreLines.js';
 import { useUIState } from '../../contexts/UIStateContext.js';
+import { getToolGroupBorderAppearance } from '../../utils/borderStyles.js';
 
 interface ToolGroupMessageProps {
-  groupId: number;
+  item: HistoryItem | HistoryItemWithoutId;
   toolCalls: IndividualToolCallDisplay[];
   availableTerminalHeight?: number;
   terminalWidth: number;
-  activeShellPtyId?: number | null;
-  embeddedShellFocused?: boolean;
   onShellInputSubmit?: (input: string) => void;
   borderTop?: boolean;
   borderBottom?: boolean;
@@ -37,11 +37,10 @@ interface ToolGroupMessageProps {
 const TOOL_MESSAGE_HORIZONTAL_MARGIN = 4;
 
 export const ToolGroupMessage: React.FC<ToolGroupMessageProps> = ({
+  item,
   toolCalls: allToolCalls,
   availableTerminalHeight,
   terminalWidth,
-  activeShellPtyId,
-  embeddedShellFocused,
   borderTop: borderTopOverride,
   borderBottom: borderBottomOverride,
 }) => {
@@ -61,7 +60,31 @@ export const ToolGroupMessage: React.FC<ToolGroupMessageProps> = ({
   );
 
   const config = useConfig();
-  const { constrainHeight } = useUIState();
+  const {
+    constrainHeight,
+    activePtyId,
+    embeddedShellFocused,
+    backgroundShells,
+    pendingHistoryItems,
+  } = useUIState();
+
+  const { borderColor, borderDimColor } = useMemo(
+    () =>
+      getToolGroupBorderAppearance(
+        item,
+        activePtyId,
+        embeddedShellFocused,
+        pendingHistoryItems,
+        backgroundShells,
+      ),
+    [
+      item,
+      activePtyId,
+      embeddedShellFocused,
+      pendingHistoryItems,
+      backgroundShells,
+    ],
+  );
 
   // We HIDE tools that are still in pre-execution states (Confirming, Pending)
   // from the History log. They live in the Global Queue or wait for their turn.
@@ -80,31 +103,6 @@ export const ToolGroupMessage: React.FC<ToolGroupMessageProps> = ({
     [toolCalls],
   );
 
-  const isEmbeddedShellFocused = visibleToolCalls.some((t) =>
-    isThisShellFocused(
-      t.name,
-      t.status,
-      t.ptyId,
-      activeShellPtyId,
-      embeddedShellFocused,
-    ),
-  );
-
-  const hasPending = !visibleToolCalls.every(
-    (t) => t.status === CoreToolCallStatus.Success,
-  );
-
-  const isShellCommand = toolCalls.some((t) => isShellTool(t.name));
-  const borderColor =
-    (isShellCommand && hasPending) || isEmbeddedShellFocused
-      ? theme.ui.symbol
-      : hasPending
-        ? theme.status.warning
-        : theme.border.default;
-
-  const borderDimColor =
-    hasPending && (!isShellCommand || !isEmbeddedShellFocused);
-
   const staticHeight = /* border */ 2 + /* marginBottom */ 1;
 
   // If all tools are filtered out (e.g., in-progress AskUser tools, confirming tools),
@@ -175,12 +173,7 @@ export const ToolGroupMessage: React.FC<ToolGroupMessageProps> = ({
             width={contentWidth}
           >
             {isShellToolCall ? (
-              <ShellToolMessage
-                {...commonProps}
-                activeShellPtyId={activeShellPtyId}
-                embeddedShellFocused={embeddedShellFocused}
-                config={config}
-              />
+              <ShellToolMessage {...commonProps} config={config} />
             ) : (
               <ToolMessage {...commonProps} />
             )}

packages/cli/src/ui/components/messages/ToolResultDisplayOverflow.test.tsx

@@ -35,7 +35,7 @@ describe('ToolResultDisplay Overflow', () => {
     const { lastFrame } = renderWithProviders(
       <OverflowProvider>
         <ToolGroupMessage
-          groupId={1}
+          item={{ id: 1, type: 'tool_group', tools: toolCalls }}
           toolCalls={toolCalls}
           availableTerminalHeight={15} // Small height to force overflow
           terminalWidth={80}

packages/cli/src/ui/components/messages/ToolStickyHeaderRegression.test.tsx

@@ -79,7 +79,7 @@ describe('ToolMessage Sticky Header Regression', () => {
           data={['item1']}
           renderItem={() => (
             <ToolGroupMessage
-              groupId={1}
+              item={{ id: 1, type: 'tool_group', tools: toolCalls }}
               toolCalls={toolCalls}
               terminalWidth={terminalWidth - 2} // Account for ScrollableList padding
             />
@@ -165,7 +165,7 @@ describe('ToolMessage Sticky Header Regression', () => {
           data={['item1']}
           renderItem={() => (
             <ToolGroupMessage
-              groupId={1}
+              item={{ id: 1, type: 'tool_group', tools: toolCalls }}
               toolCalls={toolCalls}
               terminalWidth={terminalWidth - 2}
             />

packages/cli/src/ui/hooks/atCommandProcessor.test.ts

@@ -1286,7 +1286,9 @@ describe('handleAtCommand', () => {
     // Assert
     // It SHOULD be called for the tool_group
     expect(mockAddItem).toHaveBeenCalledWith(
-      expect.objectContaining({ type: 'tool_group' }),
+      expect.objectContaining({
+        type: 'tool_group',
+      }),
       999,
     );
 
@@ -1343,7 +1345,9 @@ describe('handleAtCommand', () => {
       });
       expect(containsResourceText).toBe(true);
       expect(mockAddItem).toHaveBeenCalledWith(
-        expect.objectContaining({ type: 'tool_group' }),
+        expect.objectContaining({
+          type: 'tool_group',
+        }),
         expect.any(Number),
       );
     });

packages/cli/src/ui/hooks/toolMapping.ts

@@ -23,10 +23,15 @@ import {
  */
 export function mapToDisplay(
   toolOrTools: ToolCall[] | ToolCall,
-  options: { borderTop?: boolean; borderBottom?: boolean } = {},
+  options: {
+    borderTop?: boolean;
+    borderBottom?: boolean;
+    borderColor?: string;
+    borderDimColor?: boolean;
+  } = {},
 ): HistoryItemToolGroup {
   const toolCalls = Array.isArray(toolOrTools) ? toolOrTools : [toolOrTools];
-  const { borderTop, borderBottom } = options;
+  const { borderTop, borderBottom, borderColor, borderDimColor } = options;
 
   const toolDisplays = toolCalls.map((call): IndividualToolCallDisplay => {
     let description: string;
@@ -104,5 +109,7 @@ export function mapToDisplay(
     tools: toolDisplays,
     borderTop,
     borderBottom,
+    borderColor,
+    borderDimColor,
   };
 }

packages/cli/src/ui/hooks/useGeminiStream.test.tsx

@@ -44,6 +44,7 @@ import type { Part, PartListUnion } from '@google/genai';
 import type { UseHistoryManagerReturn } from './useHistoryManager.js';
 import type { SlashCommandProcessorResult } from '../types.js';
 import { MessageType, StreamingState } from '../types.js';
+
 import type { LoadedSettings } from '../../config/settings.js';
 
 // --- MOCKS ---

packages/cli/src/ui/hooks/useGeminiStream.ts

@@ -78,6 +78,8 @@ import {
   type TrackedWaitingToolCall,
   type TrackedExecutingToolCall,
 } from './useToolScheduler.js';
+import { theme } from '../semantic-colors.js';
+import { getToolGroupBorderAppearance } from '../utils/borderStyles.js';
 import { promises as fs } from 'node:fs';
 import path from 'node:path';
 import { useSessionStats } from '../contexts/SessionContext.js';
@@ -250,6 +252,8 @@ export const useGeminiStream = (
             mapTrackedToolCallsToDisplay(toolsToPush as TrackedToolCall[], {
               borderTop: isFirstToolInGroupRef.current,
               borderBottom: true,
+              borderColor: theme.border.default,
+              borderDimColor: false,
             }),
           );
         }
@@ -290,6 +294,45 @@ export const useGeminiStream = (
     getPreferredEditor,
   );
 
+  const activeToolPtyId = useMemo(() => {
+    const executingShellTool = toolCalls.find(
+      (tc) =>
+        tc.status === 'executing' && tc.request.name === 'run_shell_command',
+    );
+    // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
+    return (executingShellTool as TrackedExecutingToolCall | undefined)?.pid;
+  }, [toolCalls]);
+
+  const onExec = useCallback(async (done: Promise<void>) => {
+    setIsResponding(true);
+    await done;
+    setIsResponding(false);
+  }, []);
+
+  const {
+    handleShellCommand,
+    activeShellPtyId,
+    lastShellOutputTime,
+    backgroundShellCount,
+    isBackgroundShellVisible,
+    toggleBackgroundShell,
+    backgroundCurrentShell,
+    registerBackgroundShell,
+    dismissBackgroundShell,
+    backgroundShells,
+  } = useShellCommandProcessor(
+    addItem,
+    setPendingHistoryItem,
+    onExec,
+    onDebugMessage,
+    config,
+    geminiClient,
+    setShellInputFocused,
+    terminalWidth,
+    terminalHeight,
+    activeToolPtyId,
+  );
+
   const streamingState = useMemo(
     () => calculateStreamingState(isResponding, toolCalls),
     [isResponding, toolCalls],
@@ -347,6 +390,13 @@ export const useGeminiStream = (
         const historyItem = mapTrackedToolCallsToDisplay(tc, {
           borderTop: isFirst,
           borderBottom: isLastInBatch,
+          ...getToolGroupBorderAppearance(
+            { type: 'tool_group', tools: toolCalls },
+            activeShellPtyId,
+            !!isShellFocused,
+            [],
+            backgroundShells,
+          ),
         });
         addItem(historyItem);
         isFirst = false;
@@ -362,6 +412,9 @@ export const useGeminiStream = (
     setPushedToolCallIds,
     setIsFirstToolInGroup,
     addItem,
+    activeShellPtyId,
+    isShellFocused,
+    backgroundShells,
   ]);
 
   const pendingToolGroupItems = useMemo((): HistoryItemWithoutId[] => {
@@ -371,11 +424,20 @@ export const useGeminiStream = (
 
     const items: HistoryItemWithoutId[] = [];
 
+    const appearance = getToolGroupBorderAppearance(
+      { type: 'tool_group', tools: toolCalls },
+      activeShellPtyId,
+      !!isShellFocused,
+      [],
+      backgroundShells,
+    );
+
     if (remainingTools.length > 0) {
       items.push(
         mapTrackedToolCallsToDisplay(remainingTools, {
           borderTop: pushedToolCallIds.size === 0,
           borderBottom: false, // Stay open to connect with the slice below
+          ...appearance,
         }),
       );
     }
@@ -423,20 +485,18 @@ export const useGeminiStream = (
         tools: [] as IndividualToolCallDisplay[],
         borderTop: false,
         borderBottom: true,
+        ...appearance,
       });
     }
 
     return items;
-  }, [toolCalls, pushedToolCallIds]);
-
-  const activeToolPtyId = useMemo(() => {
-    const executingShellTool = toolCalls.find(
-      (tc) =>
-        tc.status === 'executing' && tc.request.name === 'run_shell_command',
-    );
-    // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
-    return (executingShellTool as TrackedExecutingToolCall | undefined)?.pid;
-  }, [toolCalls]);
+  }, [
+    toolCalls,
+    pushedToolCallIds,
+    activeShellPtyId,
+    isShellFocused,
+    backgroundShells,
+  ]);
 
   const lastQueryRef = useRef<PartListUnion | null>(null);
   const lastPromptIdRef = useRef<string | null>(null);
@@ -448,36 +508,6 @@ export const useGeminiStream = (
     onComplete: (result: { userSelection: 'disable' | 'keep' }) => void;
   } | null>(null);
 
-  const onExec = useCallback(async (done: Promise<void>) => {
-    setIsResponding(true);
-    await done;
-    setIsResponding(false);
-  }, []);
-
-  const {
-    handleShellCommand,
-    activeShellPtyId,
-    lastShellOutputTime,
-    backgroundShellCount,
-    isBackgroundShellVisible,
-    toggleBackgroundShell,
-    backgroundCurrentShell,
-    registerBackgroundShell,
-    dismissBackgroundShell,
-    backgroundShells,
-  } = useShellCommandProcessor(
-    addItem,
-    setPendingHistoryItem,
-    onExec,
-    onDebugMessage,
-    config,
-    geminiClient,
-    setShellInputFocused,
-    terminalWidth,
-    terminalHeight,
-    activeToolPtyId,
-  );
-
   const activePtyId = activeShellPtyId || activeToolPtyId;
 
   const prevActiveShellPtyIdRef = useRef<number | null>(null);

packages/cli/src/ui/types.ts

@@ -221,6 +221,8 @@ export type HistoryItemToolGroup = HistoryItemBase & {
   tools: IndividualToolCallDisplay[];
   borderTop?: boolean;
   borderBottom?: boolean;
+  borderColor?: string;
+  borderDimColor?: boolean;
 };
 
 export type HistoryItemUserShell = HistoryItemBase & {

packages/cli/src/ui/utils/borderStyles.ts

@@ -0,0 +1,123 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { CoreToolCallStatus } from '@google/gemini-cli-core';
+import { isShellTool } from '../components/messages/ToolShared.js';
+import { theme } from '../semantic-colors.js';
+import type {
+  HistoryItem,
+  HistoryItemWithoutId,
+  HistoryItemToolGroup,
+  IndividualToolCallDisplay,
+} from '../types.js';
+import type { BackgroundShell } from '../hooks/shellReducer.js';
+import type { TrackedToolCall } from '../hooks/useToolScheduler.js';
+
+function isTrackedToolCall(
+  tool: IndividualToolCallDisplay | TrackedToolCall,
+): tool is TrackedToolCall {
+  return 'request' in tool;
+}
+
+/**
+ * Calculates the border color and dimming state for a tool group message.
+ */
+export function getToolGroupBorderAppearance(
+  item:
+    | HistoryItem
+    | HistoryItemWithoutId
+    | { type: 'tool_group'; tools: TrackedToolCall[] },
+  activeShellPtyId: number | null | undefined,
+  embeddedShellFocused: boolean | undefined,
+  allPendingItems: HistoryItemWithoutId[] = [],
+  backgroundShells: Map<number, BackgroundShell> = new Map(),
+): { borderColor: string; borderDimColor: boolean } {
+  if (item.type !== 'tool_group') {
+    return { borderColor: '', borderDimColor: false };
+  }
+
+  // If this item has no tools, it's a closing slice for the current batch.
+  // We need to look at the last pending item to determine the batch's appearance.
+  const toolsToInspect: Array<IndividualToolCallDisplay | TrackedToolCall> =
+    item.tools.length > 0
+      ? item.tools
+      : allPendingItems
+          .filter(
+            (i): i is HistoryItemToolGroup =>
+              i !== null && i !== undefined && i.type === 'tool_group',
+          )
+          .slice(-1)
+          .flatMap((i) => i.tools);
+
+  const hasPending = toolsToInspect.some((t) => {
+    if (isTrackedToolCall(t)) {
+      return (
+        t.status !== 'success' &&
+        t.status !== 'error' &&
+        t.status !== 'cancelled'
+      );
+    } else {
+      return (
+        t.status !== CoreToolCallStatus.Success &&
+        t.status !== CoreToolCallStatus.Error &&
+        t.status !== CoreToolCallStatus.Cancelled
+      );
+    }
+  });
+
+  const isEmbeddedShellFocused = toolsToInspect.some((t) => {
+    if (isTrackedToolCall(t)) {
+      return (
+        isShellTool(t.request.name) &&
+        t.status === 'executing' &&
+        t.pid === activeShellPtyId &&
+        !!embeddedShellFocused
+      );
+    } else {
+      return (
+        isShellTool(t.name) &&
+        t.status === CoreToolCallStatus.Executing &&
+        t.ptyId === activeShellPtyId &&
+        !!embeddedShellFocused
+      );
+    }
+  });
+
+  const isShellCommand = toolsToInspect.some((t) => {
+    if (isTrackedToolCall(t)) {
+      return isShellTool(t.request.name);
+    } else {
+      return isShellTool(t.name);
+    }
+  });
+
+  // If we have an active PTY that isn't a background shell, then the current
+  // pending batch is definitely a shell batch.
+  const isCurrentlyInShellTurn =
+    !!activeShellPtyId && !backgroundShells.has(activeShellPtyId);
+
+  const isShell =
+    isShellCommand || (item.tools.length === 0 && isCurrentlyInShellTurn);
+  const isPending =
+    hasPending || (item.tools.length === 0 && isCurrentlyInShellTurn);
+
+  const isEffectivelyFocused =
+    isEmbeddedShellFocused ||
+    (item.tools.length === 0 &&
+      isCurrentlyInShellTurn &&
+      !!embeddedShellFocused);
+
+  const borderColor =
+    (isShell && isPending) || isEffectivelyFocused
+      ? theme.ui.symbol
+      : isPending
+        ? theme.status.warning
+        : theme.border.default;
+
+  const borderDimColor = isPending && (!isShell || !isEffectivelyFocused);
+
+  return { borderColor, borderDimColor };
+}

packages/core/src/core/__snapshots__/prompts.test.ts.snap

@@ -520,8 +520,34 @@ exports[`Core System Prompt (prompts.ts) > should append userMemory with separat
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.
@@ -649,8 +675,34 @@ exports[`Core System Prompt (prompts.ts) > should handle CodebaseInvestigator wi
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.
@@ -744,8 +796,34 @@ exports[`Core System Prompt (prompts.ts) > should handle CodebaseInvestigator wi
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.
@@ -1308,8 +1386,34 @@ exports[`Core System Prompt (prompts.ts) > should include available_skills with
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.
@@ -1433,8 +1537,34 @@ exports[`Core System Prompt (prompts.ts) > should include correct sandbox instru
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.
@@ -1549,8 +1679,34 @@ exports[`Core System Prompt (prompts.ts) > should include correct sandbox instru
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.
@@ -1665,8 +1821,34 @@ exports[`Core System Prompt (prompts.ts) > should include correct sandbox instru
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.
@@ -1777,8 +1959,34 @@ exports[`Core System Prompt (prompts.ts) > should include mandate to distinguish
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.
@@ -1889,8 +2097,34 @@ exports[`Core System Prompt (prompts.ts) > should include planning phase suggest
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.
@@ -2000,8 +2234,34 @@ exports[`Core System Prompt (prompts.ts) > should include sub-agents in XML for
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.
@@ -2351,8 +2611,34 @@ exports[`Core System Prompt (prompts.ts) > should return the base prompt when us
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.
@@ -2463,8 +2749,34 @@ exports[`Core System Prompt (prompts.ts) > should return the base prompt when us
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.
@@ -2686,8 +2998,34 @@ exports[`Core System Prompt (prompts.ts) > should use chatty system prompt for p
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.
@@ -2798,8 +3136,34 @@ exports[`Core System Prompt (prompts.ts) > should use chatty system prompt for p
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to grep_search, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like grep_search to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like read_file and grep_search.
+- read_file fails if old_string is ambiguous, causing extra turns. Take care to read enough with read_file and grep_search to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like grep_search and glob with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like grep_search with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like grep_search and/or read_file called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in \`GEMINI.md\` files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.

packages/core/src/prompts/snippets.ts

@@ -155,6 +155,10 @@ export function renderCoreMandates(options?: CoreMandatesOptions): string {
           .join(', ') + ` or \`${filenames[filenames.length - 1]}\``
       : `\`${filenames[0]}\``;
 
+  // ⚠️ IMPORTANT: the Context Efficiency changes strike a delicate balance that encourages
+  // the agent to minimize response sizes while also taking care to avoid extra turns. You
+  // must run the major benchmarks, such as SWEBench, prior to committing any changes to
+  // the Context Efficiency section to avoid regressing this behavior.
   return `
 # Core Mandates
 
@@ -163,8 +167,34 @@ export function renderCoreMandates(options?: CoreMandatesOptions): string {
 - **Source Control:** Do not stage or commit changes unless specifically requested by the user.
 
 ## Context Efficiency:
-- Always scope and limit your searches to avoid context window exhaustion and ensure high-signal results. Use include to target relevant files and strictly limit results using total_max_matches and max_matches_per_file, especially during the research phase.
-- For broad discovery, use names_only=true or max_matches_per_file=1 to identify files without retrieving their context.
+Be strategic in your use of the available tools to minimize unnecessary context usage while still
+providing the best answer that you can.
+
+Consider the following when estimating the cost of your approach:
+<estimating_context_usage>
+- The agent passes the full history with each subsequent message. The larger context is early in the session, the more expensive each subsequent turn is.
+- Unnecessary turns are generally more expensive than other types of wasted context.
+- You can reduce context usage by limiting the outputs of tools but take care not to cause more token consumption via additional turns required to recover from a tool failure or compensate for a misapplied optimization strategy.
+</estimating_context_usage>
+
+Use the following guidelines to optimize your search and read patterns.
+<guidelines>
+- Combine turns whenever possible by utilizing parallel searching and reading and by requesting enough context by passing context, before, or after to ${GREP_TOOL_NAME}, to enable you to skip using an extra turn reading the file.
+- Prefer using tools like ${GREP_TOOL_NAME} to identify points of interest instead of reading lots of files individually.
+- If you need to read multiple ranges in a file, do so parallel, in as few turns as possible.
+- It is more important to reduce extra turns, but please also try to minimize unnecessarily large file reads and search results, when doing so doesn't result in extra turns. Do this by always providing conservative limits and scopes to tools like ${READ_FILE_TOOL_NAME} and ${GREP_TOOL_NAME}.
+- ${READ_FILE_TOOL_NAME} fails if old_string is ambiguous, causing extra turns. Take care to read enough with ${READ_FILE_TOOL_NAME} and ${GREP_TOOL_NAME} to make the edit unambiguous.
+- You can compensate for the risk of missing results with scoped or limited searches by doing multiple searches in parallel.
+- Your primary goal is still to do your best quality work. Efficiency is an important, but secondary concern.
+</guidelines>
+
+<examples>
+- **Searching:** utilize search tools like ${GREP_TOOL_NAME} and ${GLOB_TOOL_NAME} with a conservative result count (\`total_max_matches\`) and a narrow scope (\`include\` and \`exclude\` parameters).
+- **Searching and editing:** utilize search tools like ${GREP_TOOL_NAME} with a conservative result count and a narrow scope. Use \`context\`, \`before\`, and/or \`after\` to request enough context to avoid the need to read the file before editing matches.
+- **Understanding:** minimize turns needed to understand a file. It's most efficient to read small files in their entirety.
+- **Large files:** utilize search tools like ${GREP_TOOL_NAME} and/or ${READ_FILE_TOOL_NAME} called in parallel with an offset and a limit to reduce the impact on context. Minmize extra turns, unless unavoidable due to the file being too large.
+- **Navigating:** read the minimum required to not require additional turns spent reading the file.
+</examples>
 
 ## Engineering Standards
 - **Contextual Precedence:** Instructions found in ${formattedFilenames} files are foundational mandates. They take absolute precedence over the general workflows and tool defaults described in this system prompt.

packages/core/src/tools/edit.test.ts

@@ -373,6 +373,182 @@ describe('EditTool', () => {
       expect(result.occurrences).toBe(1);
     });
 
+    it('should perform a fuzzy replacement when exact match fails but similarity is high', async () => {
+      const content =
+        'const myConfig = {\n  enableFeature: true,\n  retries: 3\n};';
+      // Typo: missing comma after true
+      const oldString =
+        'const myConfig = {\n  enableFeature: true\n  retries: 3\n};';
+      const newString =
+        'const myConfig = {\n  enableFeature: false,\n  retries: 5\n};';
+
+      const result = await calculateReplacement(mockConfig, {
+        params: {
+          file_path: 'config.ts',
+          instruction: 'update config',
+          old_string: oldString,
+          new_string: newString,
+        },
+        currentContent: content,
+        abortSignal,
+      });
+
+      expect(result.occurrences).toBe(1);
+      expect(result.newContent).toBe(newString);
+    });
+
+    it('should NOT perform a fuzzy replacement when similarity is below threshold', async () => {
+      const content =
+        'const myConfig = {\n  enableFeature: true,\n  retries: 3\n};';
+      // Completely different string
+      const oldString = 'function somethingElse() {\n  return false;\n}';
+      const newString =
+        'const myConfig = {\n  enableFeature: false,\n  retries: 5\n};';
+
+      const result = await calculateReplacement(mockConfig, {
+        params: {
+          file_path: 'config.ts',
+          instruction: 'update config',
+          old_string: oldString,
+          new_string: newString,
+        },
+        currentContent: content,
+        abortSignal,
+      });
+
+      expect(result.occurrences).toBe(0);
+      expect(result.newContent).toBe(content);
+    });
+
+    it('should NOT perform a fuzzy replacement when the complexity (length * size) is too high', async () => {
+      // 2000 chars
+      const longString = 'a'.repeat(2000);
+
+      // Create a file with enough lines to trigger the complexity limit
+      // Complexity = Lines * Length^2
+      // Threshold = 500,000,000
+      // 2000^2 = 4,000,000.
+      // Need > 125 lines. Let's use 200 lines.
+      const lines = Array(200).fill(longString);
+      const content = lines.join('\n');
+
+      // Mismatch at the end (making it a fuzzy match candidate)
+      const oldString = longString + 'c';
+      const newString = 'replacement';
+
+      const result = await calculateReplacement(mockConfig, {
+        params: {
+          file_path: 'test.ts',
+          instruction: 'update',
+          old_string: oldString,
+          new_string: newString,
+        },
+        currentContent: content,
+        abortSignal,
+      });
+
+      // Should return 0 occurrences because fuzzy match is skipped
+      expect(result.occurrences).toBe(0);
+      expect(result.newContent).toBe(content);
+    });
+
+    it('should perform multiple fuzzy replacements if multiple valid matches are found', async () => {
+      const content = `
+function doIt() {
+  console.log("hello");
+}
+
+function doIt() {
+  console.log("hello");
+}
+`;
+      // old_string uses single quotes, file uses double.
+      // This is a fuzzy match (quote difference).
+      const oldString = `
+function doIt() {
+  console.log('hello');
+}
+`.trim();
+
+      const newString = `
+function doIt() {
+  console.log("bye");
+}
+`.trim();
+
+      const result = await calculateReplacement(mockConfig, {
+        params: {
+          file_path: 'test.ts',
+          instruction: 'update',
+          old_string: oldString,
+          new_string: newString,
+        },
+        currentContent: content,
+        abortSignal,
+      });
+
+      expect(result.occurrences).toBe(2);
+      const expectedContent = `
+function doIt() {
+  console.log("bye");
+}
+
+function doIt() {
+  console.log("bye");
+}
+`;
+      expect(result.newContent).toBe(expectedContent);
+    });
+
+    it('should correctly rebase indentation in flexible replacement without double-indenting', async () => {
+      const content = '    if (a) {\n        foo();\n    }\n';
+      // old_string and new_string are unindented. They should be rebased to 4-space.
+      const oldString = 'if (a) {\n    foo();\n}';
+      const newString = 'if (a) {\n    bar();\n}';
+
+      const result = await calculateReplacement(mockConfig, {
+        params: {
+          file_path: 'test.ts',
+          old_string: oldString,
+          new_string: newString,
+        },
+        currentContent: content,
+        abortSignal,
+      });
+
+      expect(result.occurrences).toBe(1);
+      // foo() was at 8 spaces (4 base + 4 indent).
+      // newString has bar() at 4 spaces (0 base + 4 indent).
+      // Rebased to 4 base, it should be 4 + 4 = 8 spaces.
+      const expectedContent = '    if (a) {\n        bar();\n    }\n';
+      expect(result.newContent).toBe(expectedContent);
+    });
+
+    it('should correctly rebase indentation in fuzzy replacement without double-indenting', async () => {
+      const content =
+        '    const myConfig = {\n      enableFeature: true,\n      retries: 3\n    };';
+      // Typo: missing comma. old_string/new_string are unindented.
+      const fuzzyOld =
+        'const myConfig = {\n  enableFeature: true\n  retries: 3\n};';
+      const fuzzyNew =
+        'const myConfig = {\n  enableFeature: false,\n  retries: 5\n};';
+
+      const result = await calculateReplacement(mockConfig, {
+        params: {
+          file_path: 'test.ts',
+          old_string: fuzzyOld,
+          new_string: fuzzyNew,
+        },
+        currentContent: content,
+        abortSignal,
+      });
+
+      expect(result.strategy).toBe('fuzzy');
+      const expectedContent =
+        '    const myConfig = {\n      enableFeature: false,\n      retries: 5\n    };';
+      expect(result.newContent).toBe(expectedContent);
+    });
+
     it('should NOT insert extra newlines when replacing a block preceded by a blank line (regression)', async () => {
       const content = '\n  function oldFunc() {\n    // some code\n  }';
       const result = await calculateReplacement(mockConfig, {

packages/core/src/tools/edit.ts

@@ -49,8 +49,13 @@ import {
   EDIT_DISPLAY_NAME,
 } from './tool-names.js';
 import { debugLogger } from '../utils/debugLogger.js';
+import levenshtein from 'fast-levenshtein';
 import { EDIT_DEFINITION } from './definitions/coreTools.js';
 import { resolveToolDeclaration } from './definitions/resolver.js';
+
+const ENABLE_FUZZY_MATCH_RECOVERY = true;
+const FUZZY_MATCH_THRESHOLD = 0.1; // Allow up to 10% weighted difference
+const WHITESPACE_PENALTY_FACTOR = 0.1; // Whitespace differences cost 10% of a character difference
 interface ReplacementContext {
   params: EditToolParams;
   currentContent: string;
@@ -62,6 +67,8 @@ interface ReplacementResult {
   occurrences: number;
   finalOldString: string;
   finalNewString: string;
+  strategy?: 'exact' | 'flexible' | 'regex' | 'fuzzy';
+  matchRanges?: Array<{ start: number; end: number }>;
 }
 
 export function applyReplacement(
@@ -176,9 +183,7 @@ async function calculateFlexibleReplacement(
       const firstLineInMatch = window[0];
       const indentationMatch = firstLineInMatch.match(/^([ \t]*)/);
       const indentation = indentationMatch ? indentationMatch[1] : '';
-      const newBlockWithIndent = replaceLines.map(
-        (line: string) => `${indentation}${line}`,
-      );
+      const newBlockWithIndent = applyIndentation(replaceLines, indentation);
       sourceLines.splice(
         i,
         searchLinesStripped.length,
@@ -247,9 +252,7 @@ async function calculateRegexReplacement(
 
   const indentation = match[1] || '';
   const newLines = normalizedReplace.split('\n');
-  const newBlockWithIndent = newLines
-    .map((line) => `${indentation}${line}`)
-    .join('\n');
+  const newBlockWithIndent = applyIndentation(newLines, indentation).join('\n');
 
   // Use replace with the regex to substitute the matched content.
   // Since the regex doesn't have the 'g' flag, it will only replace the first occurrence.
@@ -305,6 +308,14 @@ export async function calculateReplacement(
     return regexResult;
   }
 
+  let fuzzyResult;
+  if (
+    ENABLE_FUZZY_MATCH_RECOVERY &&
+    (fuzzyResult = await calculateFuzzyReplacement(config, context))
+  ) {
+    return fuzzyResult;
+  }
+
   return {
     newContent: currentContent,
     occurrences: 0,
@@ -395,6 +406,8 @@ interface CalculatedEdit {
   error?: { display: string; raw: string; type: ToolErrorType };
   isNewFile: boolean;
   originalLineEnding: '\r\n' | '\n';
+  strategy?: 'exact' | 'flexible' | 'regex' | 'fuzzy';
+  matchRanges?: Array<{ start: number; end: number }>;
 }
 
 class EditToolInvocation
@@ -520,6 +533,8 @@ class EditToolInvocation
       isNewFile: false,
       error: undefined,
       originalLineEnding,
+      strategy: secondAttemptResult.strategy,
+      matchRanges: secondAttemptResult.matchRanges,
     };
   }
 
@@ -633,6 +648,8 @@ class EditToolInvocation
         isNewFile: false,
         error: undefined,
         originalLineEnding,
+        strategy: replacementResult.strategy,
+        matchRanges: replacementResult.matchRanges,
       };
     }
 
@@ -859,6 +876,10 @@ class EditToolInvocation
           ? `Created new file: ${this.params.file_path} with provided content.`
           : `Successfully modified file: ${this.params.file_path} (${editData.occurrences} replacements).`,
       ];
+      const fuzzyFeedback = getFuzzyMatchFeedback(editData);
+      if (fuzzyFeedback) {
+        llmSuccessMessageParts.push(fuzzyFeedback);
+      }
       if (this.params.modified_by_user) {
         llmSuccessMessageParts.push(
           `User modified the \`new_string\` content to be: ${this.params.new_string}.`,
@@ -1011,3 +1032,188 @@ export class EditTool
     };
   }
 }
+
+function stripWhitespace(str: string): string {
+  return str.replace(/\s/g, '');
+}
+
+/**
+ * Applies the target indentation to the lines, while preserving relative indentation.
+ * It identifies the common indentation of the provided lines and replaces it with the target indentation.
+ */
+function applyIndentation(
+  lines: string[],
+  targetIndentation: string,
+): string[] {
+  if (lines.length === 0) return [];
+
+  // Use the first line as the reference for indentation, even if it's empty/whitespace.
+  // This is because flexible/fuzzy matching identifies the indentation of the START of the match.
+  const referenceLine = lines[0];
+  const refIndentMatch = referenceLine.match(/^([ \t]*)/);
+  const refIndent = refIndentMatch ? refIndentMatch[1] : '';
+
+  return lines.map((line) => {
+    if (line.trim() === '') {
+      return '';
+    }
+    if (line.startsWith(refIndent)) {
+      return targetIndentation + line.slice(refIndent.length);
+    }
+    return targetIndentation + line.trimStart();
+  });
+}
+
+function getFuzzyMatchFeedback(editData: CalculatedEdit): string | null {
+  if (
+    editData.strategy === 'fuzzy' &&
+    editData.matchRanges &&
+    editData.matchRanges.length > 0
+  ) {
+    const ranges = editData.matchRanges
+      .map((r) => (r.start === r.end ? `${r.start}` : `${r.start}-${r.end}`))
+      .join(', ');
+    return `Applied fuzzy match at line${editData.matchRanges.length > 1 ? 's' : ''} ${ranges}.`;
+  }
+  return null;
+}
+
+async function calculateFuzzyReplacement(
+  config: Config,
+  context: ReplacementContext,
+): Promise<ReplacementResult | null> {
+  const { currentContent, params } = context;
+  const { old_string, new_string } = params;
+
+  // Pre-check: Don't fuzzy match very short strings to avoid false positives
+  if (old_string.length < 10) {
+    return null;
+  }
+
+  const normalizedCode = currentContent.replace(/\r\n/g, '\n');
+  const normalizedSearch = old_string.replace(/\r\n/g, '\n');
+  const normalizedReplace = new_string.replace(/\r\n/g, '\n');
+
+  const sourceLines = normalizedCode.match(/.*(?:\n|$)/g)?.slice(0, -1) ?? [];
+  const searchLines = normalizedSearch
+    .match(/.*(?:\n|$)/g)
+    ?.slice(0, -1)
+    .map((l) => l.trimEnd()); // Trim end of search lines to be more robust
+
+  // Limit the scope of the fuzzy match to reduce impact on responsivesness.
+  // Each comparison takes roughly O(L^2) time.
+  // We perform sourceLines.length comparisons (sliding window).
+  // Total complexity proxy: sourceLines.length * old_string.length^2
+  // Limit to 4e8 for < 1 second.
+  if (sourceLines.length * Math.pow(old_string.length, 2) > 400_000_000) {
+    return null;
+  }
+
+  if (!searchLines || searchLines.length === 0) {
+    return null;
+  }
+
+  const N = searchLines.length;
+  const candidates: Array<{ index: number; score: number }> = [];
+  const searchBlock = searchLines.join('\n');
+
+  // Sliding window
+  for (let i = 0; i <= sourceLines.length - N; i++) {
+    const windowLines = sourceLines.slice(i, i + N);
+    const windowText = windowLines.map((l) => l.trimEnd()).join('\n'); // Normalized join for comparison
+
+    // Length Heuristic Optimization
+    const lengthDiff = Math.abs(windowText.length - searchBlock.length);
+    if (
+      lengthDiff / searchBlock.length >
+      FUZZY_MATCH_THRESHOLD / WHITESPACE_PENALTY_FACTOR
+    ) {
+      continue;
+    }
+
+    // Tiered Scoring
+    const d_raw = levenshtein.get(windowText, searchBlock);
+    const d_norm = levenshtein.get(
+      stripWhitespace(windowText),
+      stripWhitespace(searchBlock),
+    );
+
+    const weightedDist = d_norm + (d_raw - d_norm) * WHITESPACE_PENALTY_FACTOR;
+    const score = weightedDist / searchBlock.length;
+
+    if (score <= FUZZY_MATCH_THRESHOLD) {
+      candidates.push({ index: i, score });
+    }
+  }
+
+  if (candidates.length === 0) {
+    return null;
+  }
+
+  // Select best non-overlapping matches
+  // Sort by score ascending. If scores equal, prefer earlier index (stable sort).
+  candidates.sort((a, b) => a.score - b.score || a.index - b.index);
+
+  const selectedMatches: Array<{ index: number; score: number }> = [];
+  for (const candidate of candidates) {
+    // Check for overlap with already selected matches
+    // Two windows overlap if their start indices are within N lines of each other
+    // (Assuming window size N. Actually overlap is |i - j| < N)
+    const overlaps = selectedMatches.some(
+      (m) => Math.abs(m.index - candidate.index) < N,
+    );
+    if (!overlaps) {
+      selectedMatches.push(candidate);
+    }
+  }
+
+  // If we found matches, apply them
+  if (selectedMatches.length > 0) {
+    const event = new EditStrategyEvent('fuzzy');
+    logEditStrategy(config, event);
+
+    // Calculate match ranges before sorting for replacement
+    // Indices in selectedMatches are 0-based line indices
+    const matchRanges = selectedMatches
+      .map((m) => ({ start: m.index + 1, end: m.index + N }))
+      .sort((a, b) => a.start - b.start);
+
+    // Sort matches by index descending to apply replacements from bottom to top
+    // so that indices remain valid
+    selectedMatches.sort((a, b) => b.index - a.index);
+
+    const newLines = normalizedReplace.split('\n');
+
+    for (const match of selectedMatches) {
+      // If we want to preserve the indentation of the first line of the match:
+      const firstLineMatch = sourceLines[match.index];
+      const indentationMatch = firstLineMatch.match(/^([ \t]*)/);
+      const indentation = indentationMatch ? indentationMatch[1] : '';
+
+      const indentedReplaceLines = applyIndentation(newLines, indentation);
+
+      let replacementText = indentedReplaceLines.join('\n');
+      // If the last line of the match had a newline, preserve it in the replacement
+      // to avoid merging with the next line or losing a blank line separator.
+      if (sourceLines[match.index + N - 1].endsWith('\n')) {
+        replacementText += '\n';
+      }
+
+      sourceLines.splice(match.index, N, replacementText);
+    }
+
+    let modifiedCode = sourceLines.join('');
+    modifiedCode = restoreTrailingNewline(currentContent, modifiedCode);
+
+    return {
+      newContent: modifiedCode,
+      occurrences: selectedMatches.length,
+      finalOldString: normalizedSearch,
+      finalNewString: normalizedReplace,
+      strategy: 'fuzzy',
+      matchRanges,
+    };
+  }
+
+  return null;
+}

packages/core/src/tools/ls.test.ts

@@ -235,8 +235,8 @@ describe('LSTool', () => {
 
       expect(entries[0]).toBe('[DIR] x-dir');
       expect(entries[1]).toBe('[DIR] y-dir');
-      expect(entries[2]).toBe('a-file.txt');
-      expect(entries[3]).toBe('b-file.txt');
+      expect(entries[2]).toBe('a-file.txt (8 bytes)');
+      expect(entries[3]).toBe('b-file.txt (8 bytes)');
     });
 
     it('should handle permission errors gracefully', async () => {

packages/core/src/tools/ls.ts

@@ -241,7 +241,12 @@ class LSToolInvocation extends BaseToolInvocation<LSToolParams, ToolResult> {
 
       // Create formatted content for LLM
       const directoryContent = entries
-        .map((entry) => `${entry.isDirectory ? '[DIR] ' : ''}${entry.name}`)
+        .map((entry) => {
+          if (entry.isDirectory) {
+            return `[DIR] ${entry.name}`;
+          }
+          return `${entry.name} (${entry.size} bytes)`;
+        })
         .join('\n');
 
       let resultMessage = `Directory listing for ${resolvedDirPath}:\n${directoryContent}`;

packages/test-utils/src/test-rig.ts

@@ -208,6 +208,7 @@ export interface ParsedLog {
     stdout?: string;
     stderr?: string;
     error?: string;
+    prompt_id?: string;
   };
   scopeMetrics?: {
     metrics: {
@@ -1051,6 +1052,7 @@ export class TestRig {
         args: string;
         success: boolean;
         duration_ms: number;
+        prompt_id?: string;
       };
     }[] = [];
 
@@ -1079,6 +1081,13 @@ export class TestRig {
         args = argsMatch[1];
       }
 
+      // Look for prompt_id in the context
+      let promptId = undefined;
+      const promptIdMatch = context.match(/prompt_id:\s*'([^']+)'/);
+      if (promptIdMatch) {
+        promptId = promptIdMatch[1];
+      }
+
       // Also try to find function_name to double-check
       // Updated regex to handle tool names with hyphens and underscores
       const nameMatch = context.match(/function_name:\s*'([\w-]+)'/);
@@ -1091,6 +1100,7 @@ export class TestRig {
           args: args,
           success: success,
           duration_ms: duration,
+          prompt_id: promptId,
         },
       });
     }
@@ -1138,6 +1148,7 @@ export class TestRig {
                       args: obj.attributes.function_args || '{}',
                       success: obj.attributes.success !== false,
                       duration_ms: obj.attributes.duration_ms || 0,
+                      prompt_id: obj.attributes.prompt_id,
                     },
                   });
                 }
@@ -1152,6 +1163,7 @@ export class TestRig {
                     args: obj.attributes.function_args,
                     success: obj.attributes.success,
                     duration_ms: obj.attributes.duration_ms,
+                    prompt_id: obj.attributes.prompt_id,
                   },
                 });
               }
@@ -1242,6 +1254,7 @@ export class TestRig {
         args: string;
         success: boolean;
         duration_ms: number;
+        prompt_id?: string;
       };
     }[] = [];
 
@@ -1258,6 +1271,7 @@ export class TestRig {
             args: logData.attributes.function_args ?? '{}',
             success: logData.attributes.success ?? false,
             duration_ms: logData.attributes.duration_ms ?? 0,
+            prompt_id: logData.attributes.prompt_id,
           },
         });
       }

scripts/generate-keybindings-doc.ts

@@ -22,7 +22,7 @@ import {
 
 const START_MARKER = '<!-- KEYBINDINGS-AUTOGEN:START -->';
 const END_MARKER = '<!-- KEYBINDINGS-AUTOGEN:END -->';
-const OUTPUT_RELATIVE_PATH = ['docs', 'cli', 'keyboard-shortcuts.md'];
+const OUTPUT_RELATIVE_PATH = ['docs', 'reference', 'keyboard-shortcuts.md'];
 
 const KEY_NAME_OVERRIDES: Record<string, string> = {
   return: 'Enter',

scripts/generate-settings-doc.ts

@@ -47,7 +47,7 @@ export async function main(argv = process.argv.slice(2)) {
     path.dirname(fileURLToPath(import.meta.url)),
     '..',
   );
-  const docPath = path.join(repoRoot, 'docs/get-started/configuration.md');
+  const docPath = path.join(repoRoot, 'docs/reference/configuration.md');
   const cliSettingsDocPath = path.join(repoRoot, 'docs/cli/settings.md');
 
   const { getSettingsSchema } = await loadSettingsSchemaModule();