@google/gemini-cli-core 0.34.0-preview.3 → 0.35.0-nightly.20260314.3038fdce2

package/dist/docs/cli/model-routing.md

@@ -26,6 +26,20 @@ policies.
     the CLI will use an available fallback model for the current turn or the
     remainder of the session.
 
+### Local Model Routing (Experimental)
+
+Gemini CLI supports using a local model for routing decisions. When configured,
+Gemini CLI will use a locally-running **Gemma** model to make routing decisions
+(instead of sending routing decisions to a hosted model). This feature can help
+reduce costs associated with hosted model usage while offering similar routing
+decision latency and quality.
+
+In order to use this feature, the local Gemma model **must** be served behind a
+Gemini API and accessible via HTTP at an endpoint configured in `settings.json`.
+
+For more details on how to configure local model routing, see
+[Local Model Routing](../core/local-model-routing.md).
+
 ### Model selection precedence
 
 The model used by Gemini CLI is determined by the following order of precedence:
@@ -38,5 +52,8 @@ The model used by Gemini CLI is determined by the following order of precedence:
 3.  **`model.name` in `settings.json`:** If neither of the above are set, the
     model specified in the `model.name` property of your `settings.json` file
     will be used.
-4.  **Default model:** If none of the above are set, the default model will be
+4.  **Local model (experimental):** If the Gemma local model router is enabled
+    in your `settings.json` file, the CLI will use the local Gemma model
+    (instead of Gemini models) to route the request to an appropriate model.
+5.  **Default model:** If none of the above are set, the default model will be
     used. The default model is `auto`

package/dist/docs/cli/model-steering.md

@@ -0,0 +1,79 @@
+# Model steering (experimental)
+
+Model steering lets you provide real-time guidance and feedback to Gemini CLI
+while it is actively executing a task. This lets you correct course, add missing
+context, or skip unnecessary steps without having to stop and restart the agent.
+
+> **Note:** This is a preview feature under active development. Preview features
+> may only be available in the **Preview** channel or may need to be enabled
+> under `/settings`.
+
+Model steering is particularly useful during complex [Plan Mode](./plan-mode.md)
+workflows or long-running subagent executions where you want to ensure the agent
+stays on the right track.
+
+## Enabling model steering
+
+Model steering is an experimental feature and is disabled by default. You can
+enable it using the `/settings` command or by updating your `settings.json`
+file.
+
+1.  Type `/settings` in the Gemini CLI.
+2.  Search for **Model Steering**.
+3.  Set the value to **true**.
+
+Alternatively, add the following to your `settings.json`:
+
+```json
+{
+  "experimental": {
+    "modelSteering": true
+  }
+}
+```
+
+## Using model steering
+
+When model steering is enabled, Gemini CLI treats any text you type while the
+agent is working as a steering hint.
+
+1.  Start a task (for example, "Refactor the database service").
+2.  While the agent is working (the spinner is visible), type your feedback in
+    the input box.
+3.  Press **Enter**.
+
+Gemini CLI acknowledges your hint with a brief message and injects it directly
+into the model's context for the very next turn. The model then re-evaluates its
+current plan and adjusts its actions accordingly.
+
+### Common use cases
+
+You can use steering hints to guide the model in several ways:
+
+- **Correcting a path:** "Actually, the utilities are in `src/common/utils`."
+- **Skipping a step:** "Skip the unit tests for now and just focus on the
+  implementation."
+- **Adding context:** "The `User` type is defined in `packages/core/types.ts`."
+- **Redirecting the effort:** "Stop searching the codebase and start drafting
+  the plan now."
+- **Handling ambiguity:** "Use the existing `Logger` class instead of creating a
+  new one."
+
+## How it works
+
+When you submit a steering hint, Gemini CLI performs the following actions:
+
+1.  **Immediate acknowledgment:** It uses a small, fast model to generate a
+    one-sentence acknowledgment so you know your hint was received.
+2.  **Context injection:** It prepends an internal instruction to your hint that
+    tells the main agent to:
+    - Re-evaluate the active plan.
+    - Classify the update (for example, as a new task or extra context).
+    - Apply minimal-diff changes to affected tasks.
+3.  **Real-time update:** The hint is delivered to the agent at the beginning of
+    its next turn, ensuring the most immediate course correction possible.
+
+## Next steps
+
+- Tackle complex tasks with [Plan Mode](./plan-mode.md).
+- Build custom [Agent Skills](./skills.md).

package/dist/docs/cli/plan-mode.md

@@ -61,20 +61,44 @@ Gemini CLI takes action.
     [`ask_user`](../tools/ask-user.md). Provide your preferences to help guide
     the design.
 3.  **Review the plan:** Once Gemini CLI has a proposed strategy, it creates a
-    detailed implementation plan as a Markdown file in your plans directory. You
-    can open and read this file to understand the proposed changes.
+    detailed implementation plan as a Markdown file in your plans directory.
+    - **View:** You can open and read this file to understand the proposed
+      changes.
+    - **Edit:** Press `Ctrl+X` to open the plan directly in your configured
+      external editor.
+
 4.  **Approve or iterate:** Gemini CLI will present the finalized plan for your
     approval.
     - **Approve:** If you're satisfied with the plan, approve it to start the
       implementation immediately: **Yes, automatically accept edits** or **Yes,
       manually accept edits**.
-    - **Iterate:** If the plan needs adjustments, provide feedback. Gemini CLI
-      will refine the strategy and update the plan.
+    - **Iterate:** If the plan needs adjustments, provide feedback in the input
+      box or [edit the plan file directly](#collaborative-plan-editing). Gemini
+      CLI will refine the strategy and update the plan.
     - **Cancel:** You can cancel your plan with `Esc`.
 
 For more complex or specialized planning tasks, you can
 [customize the planning workflow with skills](#custom-planning-with-skills).
 
+### Collaborative plan editing
+
+You can collaborate with Gemini CLI by making direct changes or leaving comments
+in the implementation plan. This is often faster and more precise than
+describing complex changes in natural language.
+
+1.  **Open the plan:** Press `Ctrl+X` when Gemini CLI presents a plan for
+    review.
+2.  **Edit or comment:** The plan opens in your configured external editor (for
+    example, VS Code or Vim). You can:
+    - **Modify steps:** Directly reorder, delete, or rewrite implementation
+      steps.
+    - **Leave comments:** Add inline questions or feedback (for example, "Wait,
+      shouldn't we use the existing `Logger` class here?").
+3.  **Save and close:** Save your changes and close the editor.
+4.  **Review and refine:** Gemini CLI automatically detects the changes, reviews
+    your comments, and adjusts the implementation strategy. It then presents the
+    refined plan for your final approval.
+
 ## How to exit Plan Mode
 
 You can exit Plan Mode at any time, whether you have finalized a plan or want to
@@ -85,16 +109,6 @@ switch back to another mode.
 - **Keyboard shortcut:** Press `Shift+Tab` to cycle to the desired mode.
 - **Natural language:** Ask Gemini CLI to "exit plan mode" or "stop planning."
 
-## Customization and best practices
-
-Plan Mode is secure by default, but you can adapt it to fit your specific
-workflows. You can customize how Gemini CLI plans by using skills, adjusting
-safety policies, or changing where plans are stored.
-
-## Commands
-
-- **`/plan copy`**: Copy the currently approved plan to your clipboard.
-
 ## Tool Restrictions
 
 Plan Mode enforces strict safety policies to prevent accidental changes.
@@ -122,6 +136,12 @@ These are the only allowed tools:
 - **Skills:** [`activate_skill`](../cli/skills.md) (allows loading specialized
   instructions and resources in a read-only manner)
 
+## Customization and best practices
+
+Plan Mode is secure by default, but you can adapt it to fit your specific
+workflows. You can customize how Gemini CLI plans by using skills, adjusting
+safety policies, changing where plans are stored, or adding hooks.
+
 ### Custom planning with skills
 
 You can use [Agent Skills](../cli/skills.md) to customize how Gemini CLI
@@ -270,6 +290,71 @@ modes = ["plan"]
 argsPattern = "\"file_path\":\"[^\"]+[\\\\/]+\\.gemini[\\\\/]+plans[\\\\/]+[\\w-]+\\.md\""
 ```
 
+### Using hooks with Plan Mode
+
+You can use the [hook system](../hooks/writing-hooks.md) to automate parts of
+the planning workflow or enforce additional checks when Gemini CLI transitions
+into or out of Plan Mode.
+
+Hooks such as `BeforeTool` or `AfterTool` can be configured to intercept the
+`enter_plan_mode` and `exit_plan_mode` tool calls.
+
+> [!WARNING] When hooks are triggered by **tool executions**, they do **not**
+> run when you manually toggle Plan Mode using the `/plan` command or the
+> `Shift+Tab` keyboard shortcut. If you need hooks to execute on mode changes,
+> ensure the transition is initiated by the agent (e.g., by asking "start a plan
+> for...").
+
+#### Example: Archive approved plans to GCS (`AfterTool`)
+
+If your organizational policy requires a record of all execution plans, you can
+use an `AfterTool` hook to securely copy the plan artifact to Google Cloud
+Storage whenever Gemini CLI exits Plan Mode to start the implementation.
+
+**`.gemini/hooks/archive-plan.sh`:**
+
+```bash
+#!/usr/bin/env bash
+# Extract the plan path from the tool input JSON
+plan_path=$(jq -r '.tool_input.plan_path // empty')
+
+if [ -f "$plan_path" ]; then
+  # Generate a unique filename using a timestamp
+  filename="$(date +%s)_$(basename "$plan_path")"
+
+  # Upload the plan to GCS in the background so it doesn't block the CLI
+  gsutil cp "$plan_path" "gs://my-audit-bucket/gemini-plans/$filename" > /dev/null 2>&1 &
+fi
+
+# AfterTool hooks should generally allow the flow to continue
+echo '{"decision": "allow"}'
+```
+
+To register this `AfterTool` hook, add it to your `settings.json`:
+
+```json
+{
+  "hooks": {
+    "AfterTool": [
+      {
+        "matcher": "exit_plan_mode",
+        "hooks": [
+          {
+            "name": "archive-plan",
+            "type": "command",
+            "command": "./.gemini/hooks/archive-plan.sh"
+          }
+        ]
+      }
+    ]
+  }
+}
+```
+
+## Commands
+
+- **`/plan copy`**: Copy the currently approved plan to your clipboard.
+
 ## Planning workflows
 
 Plan Mode provides building blocks for structured research and design. These are

package/dist/docs/cli/settings.md

@@ -22,18 +22,19 @@ they appear in the UI.
 
 ### General
 
-| UI Label                | Setting                            | Description                                                                                                                                                                    | Default     |
-| ----------------------- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------- |
-| Vim Mode                | `general.vimMode`                  | Enable Vim keybindings                                                                                                                                                         | `false`     |
-| Default Approval Mode   | `general.defaultApprovalMode`      | The default approval mode for tool execution. 'default' prompts for approval, 'auto_edit' auto-approves edit tools, and 'plan' is read-only mode. 'yolo' is not supported yet. | `"default"` |
-| Enable Auto Update      | `general.enableAutoUpdate`         | Enable automatic updates.                                                                                                                                                      | `true`      |
-| Enable Notifications    | `general.enableNotifications`      | Enable run-event notifications for action-required prompts and session completion. Currently macOS only.                                                                       | `false`     |
-| Plan Directory          | `general.plan.directory`           | The directory where planning artifacts are stored. If not specified, defaults to the system temporary directory.                                                               | `undefined` |
-| Plan Model Routing      | `general.plan.modelRouting`        | Automatically switch between Pro and Flash models based on Plan Mode status. Uses Pro for the planning phase and Flash for the implementation phase.                           | `true`      |
-| Max Chat Model Attempts | `general.maxAttempts`              | Maximum number of attempts for requests to the main chat model. Cannot exceed 10.                                                                                              | `10`        |
-| Debug Keystroke Logging | `general.debugKeystrokeLogging`    | Enable debug logging of keystrokes to the console.                                                                                                                             | `false`     |
-| Enable Session Cleanup  | `general.sessionRetention.enabled` | Enable automatic session cleanup                                                                                                                                               | `true`      |
-| Keep chat history       | `general.sessionRetention.maxAge`  | Automatically delete chats older than this time period (e.g., "30d", "7d", "24h", "1w")                                                                                        | `"30d"`     |
+| UI Label                | Setting                            | Description                                                                                                                                                                                                                                                   | Default     |
+| ----------------------- | ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
+| Vim Mode                | `general.vimMode`                  | Enable Vim keybindings                                                                                                                                                                                                                                        | `false`     |
+| Default Approval Mode   | `general.defaultApprovalMode`      | The default approval mode for tool execution. 'default' prompts for approval, 'auto_edit' auto-approves edit tools, and 'plan' is read-only mode. YOLO mode (auto-approve all actions) can only be enabled via command line (--yolo or --approval-mode=yolo). | `"default"` |
+| Enable Auto Update      | `general.enableAutoUpdate`         | Enable automatic updates.                                                                                                                                                                                                                                     | `true`      |
+| Enable Notifications    | `general.enableNotifications`      | Enable run-event notifications for action-required prompts and session completion. Currently macOS only.                                                                                                                                                      | `false`     |
+| Plan Directory          | `general.plan.directory`           | The directory where planning artifacts are stored. If not specified, defaults to the system temporary directory.                                                                                                                                              | `undefined` |
+| Plan Model Routing      | `general.plan.modelRouting`        | Automatically switch between Pro and Flash models based on Plan Mode status. Uses Pro for the planning phase and Flash for the implementation phase.                                                                                                          | `true`      |
+| Retry Fetch Errors      | `general.retryFetchErrors`         | Retry on "exception TypeError: fetch failed sending request" errors.                                                                                                                                                                                          | `true`      |
+| Max Chat Model Attempts | `general.maxAttempts`              | Maximum number of attempts for requests to the main chat model. Cannot exceed 10.                                                                                                                                                                             | `10`        |
+| Debug Keystroke Logging | `general.debugKeystrokeLogging`    | Enable debug logging of keystrokes to the console.                                                                                                                                                                                                            | `false`     |
+| Enable Session Cleanup  | `general.sessionRetention.enabled` | Enable automatic session cleanup                                                                                                                                                                                                                              | `true`      |
+| Keep chat history       | `general.sessionRetention.maxAge`  | Automatically delete chats older than this time period (e.g., "30d", "7d", "24h", "1w")                                                                                                                                                                       | `"30d"`     |
 
 ### Output
 
@@ -54,6 +55,7 @@ they appear in the UI.
 | Show Home Directory Warning          | `ui.showHomeDirectoryWarning`          | Show a warning when running Gemini CLI in the home directory.                                                                                                     | `true`   |
 | Show Compatibility Warnings          | `ui.showCompatibilityWarnings`         | Show warnings about terminal or OS compatibility issues.                                                                                                          | `true`   |
 | Hide Tips                            | `ui.hideTips`                          | Hide helpful tips in the UI                                                                                                                                       | `false`  |
+| Escape Pasted @ Symbols              | `ui.escapePastedAtSymbols`             | When enabled, @ symbols in pasted text are escaped to prevent unintended @path expansion.                                                                         | `false`  |
 | Show Shortcuts Hint                  | `ui.showShortcutsHint`                 | Show the "? for shortcuts" hint above the input.                                                                                                                  | `true`   |
 | Hide Banner                          | `ui.hideBanner`                        | Hide the application banner                                                                                                                                       | `false`  |
 | Hide Context Summary                 | `ui.hideContextSummary`                | Hide the context summary (GEMINI.md, MCP servers) above the input.                                                                                                | `false`  |

package/dist/docs/cli/telemetry.md

@@ -45,6 +45,7 @@ Environment variables can override these settings.
 | `logPrompts`   | `GEMINI_TELEMETRY_LOG_PROMPTS`   | Include prompts in telemetry logs                   | `true`/`false`    | `true`                  |
 | `useCollector` | `GEMINI_TELEMETRY_USE_COLLECTOR` | Use external OTLP collector (advanced)              | `true`/`false`    | `false`                 |
 | `useCliAuth`   | `GEMINI_TELEMETRY_USE_CLI_AUTH`  | Use CLI credentials for telemetry (GCP target only) | `true`/`false`    | `false`                 |
+| -              | `GEMINI_CLI_SURFACE`             | Optional custom label for traffic reporting         | string            | -                       |
 
 **Note on boolean environment variables:** For boolean settings like `enabled`,
 setting the environment variable to `true` or `1` enables the feature.
@@ -216,6 +217,50 @@ recommend using file-based output for local development.
 For advanced local telemetry setups (such as Jaeger or Genkit), see the
 [Local development guide](../local-development.md#viewing-traces).
 
+## Client identification
+
+Gemini CLI includes identifiers in its `User-Agent` header to help you
+differentiate and report on API traffic from different environments (for
+example, identifying calls from Gemini Code Assist versus a standard terminal).
+
+### Automatic identification
+
+Most integrated environments are identified automatically without additional
+configuration. The identifier is included as a prefix to the `User-Agent` and as
+a "surface" tag in the parenthetical metadata.
+
+| Environment                         | User-Agent Prefix            | Surface Tag |
+| :---------------------------------- | :--------------------------- | :---------- |
+| **Gemini Code Assist (Agent Mode)** | `GeminiCLI-a2a-server`       | `vscode`    |
+| **Zed (via ACP)**                   | `GeminiCLI-acp-zed`          | `zed`       |
+| **XCode (via ACP)**                 | `GeminiCLI-acp-xcode`        | `xcode`     |
+| **IntelliJ IDEA (via ACP)**         | `GeminiCLI-acp-intellijidea` | `jetbrains` |
+| **Standard Terminal**               | `GeminiCLI`                  | `terminal`  |
+
+**Example User-Agent:**
+`GeminiCLI-a2a-server/0.34.0/gemini-pro (linux; x64; vscode)`
+
+### Custom identification
+
+You can provide a custom identifier for your own scripts or automation by
+setting the `GEMINI_CLI_SURFACE` environment variable. This is useful for
+tracking specific internal tools or distribution channels in your GCP logs.
+
+**macOS/Linux**
+
+```bash
+export GEMINI_CLI_SURFACE="my-custom-tool"
+```
+
+**Windows (PowerShell)**
+
+```powershell
+$env:GEMINI_CLI_SURFACE="my-custom-tool"
+```
+
+When set, the value appears at the end of the `User-Agent` parenthetical:
+`GeminiCLI/0.34.0/gemini-pro (linux; x64; my-custom-tool)`
+
 ## Logs, metrics, and traces
 
 This section describes the structure of logs, metrics, and traces generated by

package/dist/docs/cli/tutorials/plan-mode-steering.md

@@ -0,0 +1,89 @@
+# Use Plan Mode with model steering for complex tasks
+
+Architecting a complex solution requires precision. By combining Plan Mode's
+structured environment with model steering's real-time feedback, you can guide
+Gemini CLI through the research and design phases to ensure the final
+implementation plan is exactly what you need.
+
+> **Note:** This is a preview feature under active development. Preview features
+> may only be available in the **Preview** channel or may need to be enabled
+> under `/settings`.
+
+## Prerequisites
+
+- Gemini CLI installed and authenticated.
+- [Plan Mode](../plan-mode.md) enabled in your settings.
+- [Model steering](../model-steering.md) enabled in your settings.
+
+## Why combine Plan Mode and model steering?
+
+[Plan Mode](../plan-mode.md) typically follows a linear path: research, propose,
+and draft. Adding model steering lets you:
+
+1.  **Direct the research:** Correct the agent if it's looking in the wrong
+    directory or missing a key dependency.
+2.  **Iterate mid-draft:** Suggest a different architectural pattern while the
+    agent is still writing the plan.
+3.  **Speed up the loop:** Avoid waiting for a full research turn to finish
+    before providing critical context.
+
+## Step 1: Start a complex task
+
+Enter Plan Mode and start a task that requires research.
+
+**Prompt:** `/plan I want to implement a new notification service using Redis.`
+
+Gemini CLI enters Plan Mode and starts researching your existing codebase to
+identify where the new service should live.
+
+## Step 2: Steer the research phase
+
+As you see the agent calling tools like `list_directory` or `grep_search`, you
+might realize it's missing the relevant context.
+
+**Action:** While the spinner is active, type your hint:
+`"Don't forget to check packages/common/queues for the existing Redis config."`
+
+**Result:** Gemini CLI acknowledges your hint and immediately incorporates it
+into its research. You'll see it start exploring the directory you suggested in
+its very next turn.
+
+## Step 3: Refine the design mid-turn
+
+After research, the agent starts drafting the implementation plan. If you notice
+it's proposing a design that doesn't align with your goals, steer it.
+
+**Action:** Type:
+`"Actually, let's use a Publisher/Subscriber pattern instead of a simple queue for this service."`
+
+**Result:** The agent stops drafting the current version of the plan,
+re-evaluates the design based on your feedback, and starts a new draft that uses
+the Pub/Sub pattern.
+
+## Step 4: Approve and implement
+
+Once the agent has used your hints to craft the perfect plan, review the final
+`.md` file.
+
+**Action:** Type: `"Looks perfect. Let's start the implementation."`
+
+Gemini CLI exits Plan Mode and transitions to the implementation phase. Because
+the plan was refined in real-time with your feedback, the agent can now execute
+each step with higher confidence and fewer errors.
+
+## Tips for effective steering
+
+- **Be specific:** Instead of "do it differently," try "use the existing
+  `Logger` class in `src/utils`."
+- **Steer early:** Providing feedback during the research phase is more
+  efficient than waiting for the final plan to be drafted.
+- **Use for context:** Steering is a great way to provide knowledge that might
+  not be obvious from reading the code (e.g., "We are planning to deprecate this
+  module next month").
+
+## Next steps
+
+- Explore [Agent Skills](../skills.md) to add specialized expertise to your
+  planning turns.
+- See the [Model steering reference](../model-steering.md) for technical
+  details.

package/dist/docs/core/index.md

@@ -15,6 +15,8 @@ requests sent from `packages/cli`. For a general overview of Gemini CLI, see 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.
+- **[Local Model Routing (experimental)](./local-model-routing.md):** Learn how
+  to enable use of a local Gemma model for model routing decisions.
 
 ## Role of the core
 

package/dist/docs/core/local-model-routing.md

@@ -0,0 +1,193 @@
+# Local Model Routing (experimental)
+
+Gemini CLI supports using a local model for
+[routing decisions](../cli/model-routing.md). When configured, Gemini CLI will
+use a locally-running **Gemma** model to make routing decisions (instead of
+sending routing decisions to a hosted model).
+
+This feature can help reduce costs associated with hosted model usage while
+offering similar routing decision latency and quality.
+
+> **Note: Local model routing is currently an experimental feature.**
+
+## Setup
+
+Using a Gemma model for routing decisions requires that an implementation of a
+Gemma model be running locally on your machine, served behind an HTTP endpoint
+and accessed via the Gemini API.
+
+To serve the Gemma model, follow these steps:
+
+### Download the LiteRT-LM runtime
+
+The [LiteRT-LM](https://github.com/google-ai-edge/LiteRT-LM) runtime offers
+pre-built binaries for locally-serving models. Download the binary appropriate
+for your system.
+
+#### Windows
+
+1. Download
+   [lit.windows_x86_64.exe](https://github.com/google-ai-edge/LiteRT-LM/releases/download/v0.9.0-alpha03/lit.windows_x86_64.exe).
+2. Using GPU on Windows requires the DirectXShaderCompiler. Download the
+   [dxc zip from the latest release](https://github.com/microsoft/DirectXShaderCompiler/releases/download/v1.8.2505.1/dxc_2025_07_14.zip).
+   Unzip the archive and from the architecture-appropriate `bin\` directory, and
+   copy the `dxil.dll` and `dxcompiler.dll` into the same location as you saved
+   `lit.windows_x86_64.exe`.
+3. (Optional) Test starting the runtime:
+   `.\lit.windows_x86_64.exe serve --verbose`
+
+#### Linux
+
+1. Download
+   [lit.linux_x86_64](https://github.com/google-ai-edge/LiteRT-LM/releases/download/v0.9.0-alpha03/lit.linux_x86_64).
+2. Ensure the binary is executable: `chmod a+x lit.linux_x86_64`
+3. (Optional) Test starting the runtime: `./lit.linux_x86_64 serve --verbose`
+
+#### MacOS
+
+1. Download
+   [lit-macos-arm64](https://github.com/google-ai-edge/LiteRT-LM/releases/download/v0.9.0-alpha03/lit.macos_arm64).
+2. Ensure the binary is executable: `chmod a+x lit.macos_arm64`
+3. (Optional) Test starting the runtime: `./lit.macos_arm64 serve --verbose`
+
+> **Note**: MacOS can be configured to only allows binaries from "App Store &
+> Known Developers". If you encounter an error message when attempting to run
+> the binary, you will need to allow the application. One option is to visit
+> `System Settings -> Privacy & Security`, scroll to `Security`, and click
+> `"Allow Anyway"` for `"lit.macos_arm64"`. Another option is to run
+> `xattr -d com.apple.quarantine lit.macos_arm64` from the commandline.
+
+### Download the Gemma Model
+
+Before using Gemma, you will need to download the model (and agree to the Terms
+of Service).
+
+This can be done via the LiteRT-LM runtime.
+
+#### Windows
+
+```bash
+$ .\lit.windows_x86_64.exe pull gemma3-1b-gpu-custom
+
+[Legal] The model you are about to download is governed by
+the Gemma Terms of Use and Prohibited Use Policy. Please review these terms and ensure you agree before continuing.
+
+Full Terms: https://ai.google.dev/gemma/terms
+Prohibited Use Policy: https://ai.google.dev/gemma/prohibited_use_policy
+
+Do you accept these terms? (Y/N): Y
+
+Terms accepted.
+Downloading model 'gemma3-1b-gpu-custom' ...
+Downloading... 968.6 MB
+Download complete.
+```
+
+#### Linux
+
+```bash
+$ ./lit.linux_x86_64 pull gemma3-1b-gpu-custom
+
+[Legal] The model you are about to download is governed by
+the Gemma Terms of Use and Prohibited Use Policy. Please review these terms and ensure you agree before continuing.
+
+Full Terms: https://ai.google.dev/gemma/terms
+Prohibited Use Policy: https://ai.google.dev/gemma/prohibited_use_policy
+
+Do you accept these terms? (Y/N): Y
+
+Terms accepted.
+Downloading model 'gemma3-1b-gpu-custom' ...
+Downloading... 968.6 MB
+Download complete.
+```
+
+#### MacOS
+
+```bash
+$ ./lit.lit.macos_arm64 pull gemma3-1b-gpu-custom
+
+[Legal] The model you are about to download is governed by
+the Gemma Terms of Use and Prohibited Use Policy. Please review these terms and ensure you agree before continuing.
+
+Full Terms: https://ai.google.dev/gemma/terms
+Prohibited Use Policy: https://ai.google.dev/gemma/prohibited_use_policy
+
+Do you accept these terms? (Y/N): Y
+
+Terms accepted.
+Downloading model 'gemma3-1b-gpu-custom' ...
+Downloading... 968.6 MB
+Download complete.
+```
+
+### Start LiteRT-LM Runtime
+
+Using the command appropriate to your system, start the LiteRT-LM runtime.
+Configure the port that you want to use for your Gemma model. For the purposes
+of this document, we will use port `9379`.
+
+Example command for MacOS: `./lit.macos_arm64 serve --port=9379 --verbose`
+
+### (Optional) Verify Model Serving
+
+Send a quick prompt to the model via HTTP to validate successful model serving.
+This will cause the runtime to download the model and run it once.
+
+You should see a short joke in the server output as an indicator of success.
+
+#### Windows
+
+```
+# Run this in PowerShell to send a request to the server
+
+$uri = "http://localhost:9379/v1beta/models/gemma3-1b-gpu-custom:generateContent"
+$body = @{contents = @( @{
+  role = "user"
+  parts = @( @{ text = "Tell me a joke." } )
+})} | ConvertTo-Json -Depth 10
+
+Invoke-RestMethod -Uri $uri -Method Post -Body $body -ContentType "application/json"
+```
+
+#### Linux/MacOS
+
+```bash
+$ curl "http://localhost:9379/v1beta/models/gemma3-1b-gpu-custom:generateContent" \
+  -H 'Content-Type: application/json' \
+  -X POST \
+  -d '{"contents":[{"role":"user","parts":[{"text":"Tell me a joke."}]}]}'
+```
+
+## Configuration
+
+To use a local Gemma model for routing, you must explicitly enable it in your
+`settings.json`:
+
+```json
+{
+  "experimental": {
+    "gemmaModelRouter": {
+      "enabled": true,
+      "classifier": {
+        "host": "http://localhost:9379",
+        "model": "gemma3-1b-gpu-custom"
+      }
+    }
+  }
+}
+```
+
+> Use the port you started your LiteRT-LM runtime on in the setup steps.
+
+### Configuration schema
+
+| Field              | Type    | Required | Description                                                                                |
+| :----------------- | :------ | :------- | :----------------------------------------------------------------------------------------- |
+| `enabled`          | boolean | Yes      | Must be `true` to enable the feature.                                                      |
+| `classifier`       | object  | Yes      | The configuration for the local model endpoint. It includes the host and model specifiers. |
+| `classifier.host`  | string  | Yes      | The URL to the local model server. Should be `http://localhost:<port>`.                    |
+| `classifier.model` | string  | Yes      | The model name to use for decisions. Must be `"gemma3-1b-gpu-custom"`.                     |
+
+> **Note: You will need to restart after configuration changes for local model
+> routing to take effect.**