Update website issue template to pre-fill title.

Update configuration.md to remove subagents YOLO mode warning based on https://github.com/google-gemini/gemini-cli/pull/22386

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

@@ -71,12 +71,44 @@ accessible.
   tables).
 - **Media:** Use lowercase hyphenated filenames. Provide descriptive alt text
   for all images.
+- **Details section:** Use the `<details>` tag to create a collapsible section.
+  This is useful for supplementary or data-heavy information that isn't critical
+  to the main flow.
+
+  Example:
+
+  <details>
+  <summary>Title</summary>
+
+  - First entry
+  - Second entry
+
+  </details>
+
+- **Callouts**: Use GitHub-flavored markdown alerts to highlight important
+  information. To ensure the formatting is preserved by `npm run format`, place
+  an empty line, then the `<!-- prettier-ignore -->` comment directly before
+  the callout block. The callout type (`[!TYPE]`) should be on the first line,
+  followed by a newline, and then the content, with each subsequent line of
+  content starting with `>`. Available types are `NOTE`, `TIP`, `IMPORTANT`,
+  `WARNING`, and `CAUTION`.
+
+  Example:
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an example of a multi-line note that will be preserved
+> by Prettier.
 
 ### Structure
 - **BLUF:** Start with an introduction explaining what to expect.
 - **Experimental features:** If a feature is clearly noted as experimental,
-add the following note immediately after the introductory paragraph:
-  `> **Note:** This is a preview feature currently under active development.`
+  add the following note immediately after the introductory paragraph:
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an experimental feature currently under active development.
+
 - **Headings:** Use hierarchical headings to support the user journey.
 - **Procedures:** 
   - Introduce lists of steps with a complete sentence.
@@ -85,8 +117,7 @@ add the following note immediately after the introductory paragraph:
   - Put conditions before instructions (e.g., "On the Settings page, click...").
   - Provide clear context for where the action takes place.
   - Indicate optional steps clearly (e.g., "Optional: ...").
-- **Elements:** Use bullet lists, tables, notes (`> **Note:**`), and warnings 
-  (`> **Warning:**`).
+- **Elements:** Use bullet lists, tables, details, and callouts.
 - **Avoid using a table of contents:** If a table of contents is present, remove
   it.
 - **Next steps:** Conclude with a "Next steps" section if applicable.

.github/ISSUE_TEMPLATE/website_issue.yml

@@ -1,7 +1,9 @@
 name: 'Website issue'
 description: 'Report an issue with the Gemini CLI Website and Gemini CLI Extensions Gallery'
+title: "GeminiCLI.com Feedback: [ISSUE]"
 labels:
   - 'area/extensions'
+  - 'area/documentation'
 body:
   - type: 'markdown'
     attributes:

docs/cli/checkpointing.md

@@ -39,7 +39,9 @@ file in your project's temporary directory, typically located at
 The Checkpointing feature is disabled by default. To enable it, you need to edit
 your `settings.json` file.
 
-> **Note:** The `--checkpointing` command-line flag was removed in version
+<!-- prettier-ignore -->
+> [!CAUTION]
+> The `--checkpointing` command-line flag was removed in version
 > 0.11.0. Checkpointing can now only be enabled through the `settings.json`
 > configuration file.
 

docs/cli/custom-commands.md

@@ -30,7 +30,9 @@ separator (`/` or `\`) being converted to a colon (`:`).
 - A file at `<project>/.gemini/commands/git/commit.toml` becomes the namespaced
   command `/git:commit`.
 
-> [!TIP] After creating or modifying `.toml` command files, run
+<!-- prettier-ignore -->
+> [!TIP]
+> After creating or modifying `.toml` command files, run
 > `/commands reload` to pick up your changes without restarting the CLI.
 
 ## TOML file format (v1)
@@ -177,10 +179,10 @@ ensure that only intended commands can be run.
     automatically shell-escaped (see
     [Context-Aware Injection](#1-context-aware-injection-with-args) above).
 3.  **Robust parsing:** The parser correctly handles complex shell commands that
-    include nested braces, such as JSON payloads. **Note:** The content inside
-    `!{...}` must have balanced braces (`{` and `}`). If you need to execute a
-    command containing unbalanced braces, consider wrapping it in an external
-    script file and calling the script within the `!{...}` block.
+    include nested braces, such as JSON payloads. The content inside `!{...}`
+    must have balanced braces (`{` and `}`). If you need to execute a command
+    containing unbalanced braces, consider wrapping it in an external script
+    file and calling the script within the `!{...}` block.
 4.  **Security check and confirmation:** The CLI performs a security check on
     the final, resolved command (after arguments are escaped and substituted). A
     dialog will appear showing the exact command(s) to be executed.

docs/cli/enterprise.md

@@ -5,9 +5,11 @@ and managing Gemini CLI in an enterprise environment. By leveraging system-level
 settings, administrators can enforce security policies, manage tool access, and
 ensure a consistent experience for all users.
 
-> **A note on security:** The patterns described in this document are intended
-> to help administrators create a more controlled and secure environment for
-> using Gemini CLI. However, they should not be considered a foolproof security
+<!-- prettier-ignore -->
+> [!WARNING]
+> The patterns described in this document are intended to help
+> administrators create a more controlled and secure environment for using
+> Gemini CLI. However, they should not be considered a foolproof security
 > boundary. A determined user with sufficient privileges on their local machine
 > may still be able to circumvent these configurations. These measures are
 > designed to prevent accidental misuse and enforce corporate policy in a
@@ -280,10 +282,12 @@ environment to a blocklist.
 }
 ```
 
-**Security note:** Blocklisting with `excludeTools` is less secure than
-allowlisting with `coreTools`, as it relies on blocking known-bad commands, and
-clever users may find ways to bypass simple string-based blocks. **Allowlisting
-is the recommended approach.**
+<!-- prettier-ignore -->
+> [!WARNING]
+> Blocklisting with `excludeTools` is less secure than
+> allowlisting with `coreTools`, as it relies on blocking known-bad commands,
+> and clever users may find ways to bypass simple string-based blocks.
+> **Allowlisting is the recommended approach.**
 
 ### Disabling YOLO mode
 
@@ -494,8 +498,10 @@ other events. For more information, see the
 }
 ```
 
-**Note:** Ensure that `logPrompts` is set to `false` in an enterprise setting to
-avoid collecting potentially sensitive information from user prompts.
+<!-- prettier-ignore -->
+> [!NOTE]
+> Ensure that `logPrompts` is set to `false` in an enterprise setting to
+> avoid collecting potentially sensitive information from user prompts.
 
 ## Authentication
 

docs/cli/model-steering.md

@@ -4,9 +4,10 @@ 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`.
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an experimental feature currently under active development and
+> 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

docs/cli/model.md

@@ -5,7 +5,9 @@ used by Gemini CLI, giving you more control over your results. Use **Pro**
 models for complex tasks and reasoning, **Flash** models for high speed results,
 or the (recommended) **Auto** setting to choose the best model for your tasks.
 
-> **Note:** The `/model` command (and the `--model` flag) does not override the
+<!-- prettier-ignore -->
+> [!NOTE]
+> The `/model` command (and the `--model` flag) does not override the
 > model used by sub-agents. Consequently, even when using the `/model` flag you
 > may see other models used in your model usage reports.
 

docs/cli/notifications.md

@@ -4,9 +4,10 @@ Gemini CLI can send system notifications to alert you when a session completes
 or when it needs your attention, such as when it's waiting for you to approve a
 tool call.
 
-> **Note:** This is a preview feature currently under active development.
-> Preview features may be available on the **Preview** channel or may need to be
-> enabled under `/settings`.
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an experimental feature currently under active development and
+> may need to be enabled under `/settings`.
 
 Notifications are particularly useful when running long-running tasks or using
 [Plan Mode](./plan-mode.md), letting you switch to other windows while Gemini

docs/cli/plan-mode.md

@@ -35,19 +35,17 @@ To launch Gemini CLI in Plan Mode once:
 To start Plan Mode while using Gemini CLI:
 
 - **Keyboard shortcut:** Press `Shift+Tab` to cycle through approval modes
-  (`Default` -> `Auto-Edit` -> `Plan`).
-
-  > **Note:** Plan Mode is automatically removed from the rotation when Gemini
-  > CLI is actively processing or showing confirmation dialogs.
+  (`Default` -> `Auto-Edit` -> `Plan`). Plan Mode is automatically removed from
+  the rotation when Gemini CLI is actively processing or showing confirmation
+  dialogs.
 
 - **Command:** Type `/plan` in the input box.
 
 - **Natural Language:** Ask Gemini CLI to "start a plan for...". Gemini CLI
   calls the
   [`enter_plan_mode`](../tools/planning.md#1-enter_plan_mode-enterplanmode) tool
-  to switch modes.
-  > **Note:** This tool is not available when Gemini CLI is in
-  > [YOLO mode](../reference/configuration.md#command-line-arguments).
+  to switch modes. This tool is not available when Gemini CLI is in
+  [YOLO mode](../reference/configuration.md#command-line-arguments).
 
 ## How to use Plan Mode
 
@@ -407,7 +405,9 @@ To build a custom planning workflow, you can use:
   [custom plan directories](#custom-plan-directory-and-policies) and
   [custom policies](#custom-policies).
 
-> **Note:** Use [Conductor] as a reference when building your own custom
+<!-- prettier-ignore -->
+> [!TIP]
+> Use [Conductor] as a reference when building your own custom
 > planning workflow.
 
 By using Plan Mode as its execution environment, your custom methodology can

docs/cli/sandbox.md

@@ -253,9 +253,11 @@ $env:SANDBOX_SET_UID_GID="false"  # Disable UID/GID mapping
 DEBUG=1 gemini -s -p "debug command"
 ```
 
-**Note:** If you have `DEBUG=true` in a project's `.env` file, it won't affect
-gemini-cli due to automatic exclusion. Use `.gemini/.env` files for gemini-cli
-specific debug settings.
+<!-- prettier-ignore -->
+> [!NOTE]
+> If you have `DEBUG=true` in a project's `.env` file, it won't affect
+> gemini-cli due to automatic exclusion. Use `.gemini/.env` files for
+> gemini-cli specific debug settings.
 
 ### Inspect sandbox
 

docs/cli/settings.md

@@ -11,7 +11,9 @@ locations:
 - **User settings**: `~/.gemini/settings.json`
 - **Workspace settings**: `your-project/.gemini/settings.json`
 
-Note: Workspace settings override user settings.
+<!-- prettier-ignore -->
+> [!IMPORTANT]
+> Workspace settings override user settings.
 
 ## Settings reference
 

docs/cli/skills.md

@@ -63,8 +63,10 @@ Use the `/skills` slash command to view and manage available expertise:
 - `/skills enable <name>`: Re-enables a disabled skill.
 - `/skills reload`: Refreshes the list of discovered skills from all tiers.
 
-_Note: `/skills disable` and `/skills enable` default to the `user` scope. Use
-`--scope workspace` to manage workspace-specific settings._
+<!-- prettier-ignore -->
+> [!NOTE]
+> `/skills disable` and `/skills enable` default to the `user` scope. Use
+> `--scope workspace` to manage workspace-specific settings.
 
 ### From the Terminal
 

docs/cli/system-prompt.md

@@ -14,7 +14,9 @@ core instructions will apply unless you include them yourself.
 This feature is intended for advanced users who need to enforce strict,
 project-specific behavior or create a customized persona.
 
-> Tip: You can export the current default system prompt to a file first, review
+<!-- prettier-ignore -->
+> [!TIP]
+> You can export the current default system prompt to a file first, review
 > it, and then selectively modify or replace it (see
 > [“Export the default prompt”](#export-the-default-prompt-recommended)).
 

docs/cli/telemetry.md

@@ -125,9 +125,11 @@ You must complete several setup steps before enabling Google Cloud telemetry.
       }
       ```
 
-      > **Note:** This setting requires **Direct export** (in-process exporters)
-      > and cannot be used when `useCollector` is `true`. If both are enabled,
-      > telemetry will be disabled.
+<!-- prettier-ignore -->
+> [!NOTE]
+> This setting requires **Direct export** (in-process exporters)
+> and cannot be used when `useCollector` is `true`. If both are enabled,
+> telemetry will be disabled.
 
 3.  Ensure your account or service account has these IAM roles:
     - Cloud Trace Agent

docs/cli/themes.md

@@ -36,9 +36,11 @@ using the `/theme` command within Gemini CLI:
     preview or highlight as you select.
 4.  Confirm your selection to apply the theme.
 
-**Note:** If a theme is defined in your `settings.json` file (either by name or
-by a file path), you must remove the `"theme"` setting from the file before you
-can change the theme using the `/theme` command.
+<!-- prettier-ignore -->
+> [!NOTE]
+> If a theme is defined in your `settings.json` file (either by name or
+> by a file path), you must remove the `"theme"` setting from the file before
+> you can change the theme using the `/theme` command.
 
 ### Theme persistence
 
@@ -179,11 +181,13 @@ custom theme defined in `settings.json`.
 }
 ```
 
-**Security note:** For your safety, Gemini CLI will only load theme files that
-are located within your home directory. If you attempt to load a theme from
-outside your home directory, a warning will be displayed and the theme will not
-be loaded. This is to prevent loading potentially malicious theme files from
-untrusted sources.
+<!-- prettier-ignore -->
+> [!WARNING]
+> For your safety, Gemini CLI will only load theme files that
+> are located within your home directory. If you attempt to load a theme from
+> outside your home directory, a warning will be displayed and the theme will
+> not be loaded. This is to prevent loading potentially malicious theme files
+> from untrusted sources.
 
 ### Example custom theme
 

docs/cli/tutorials/file-management.md

@@ -62,7 +62,9 @@ structure. It will return the specific path (e.g.,
 `src/components/UserProfile.tsx`), which you can then use with `@` in your next
 turn.
 
-> **Tip:** You can also ask for lists of files, like "Show me all the TypeScript
+<!-- prettier-ignore -->
+> [!TIP]
+> You can also ask for lists of files, like "Show me all the TypeScript
 > configuration files in the root directory."
 
 ## How to modify code

docs/cli/tutorials/mcp-setup.md

@@ -62,8 +62,10 @@ You tell Gemini about new servers by editing your `settings.json`.
 }
 ```
 
-> **Note:** The `command` is `docker`, and the rest are arguments passed to it.
-> We map the local environment variable into the container so your secret isn't
+<!-- prettier-ignore -->
+> [!NOTE]
+> The `command` is `docker`, and the rest are arguments passed to it. We
+> map the local environment variable into the container so your secret isn't
 > hardcoded in the config file.
 
 ## How to verify the connection

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

@@ -5,9 +5,10 @@ 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`.
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an experimental feature currently under active development and
+> may need to be enabled under `/settings`.
 
 ## Prerequisites
 

docs/core/remote-agents.md

@@ -10,7 +10,9 @@ agents in the following repositories:
 - [ADK Samples (Python)](https://github.com/google/adk-samples/tree/main/python)
 - [ADK Python Contributing Samples](https://github.com/google/adk-python/tree/main/contributing/samples)
 
-> **Note: Remote subagents are currently an experimental feature.**
+<!-- prettier-ignore -->
+> [!NOTE]
+> Remote subagents are currently an experimental feature.
 
 ## Configuration
 
@@ -82,7 +84,8 @@ Markdown file.
 ---
 ```
 
-> **Note:** Mixed local and remote agents, or multiple local agents, are not
+<!-- prettier-ignore -->
+> [!NOTE] Mixed local and remote agents, or multiple local agents, are not
 > supported in a single file; the list format is currently remote-only.
 
 ## Authentication
@@ -362,5 +365,7 @@ Users can manage subagents using the following commands within the Gemini CLI:
 - `/agents enable <agent_name>`: Enables a specific subagent.
 - `/agents disable <agent_name>`: Disables a specific subagent.
 
-> **Tip:** You can use the `@cli_help` agent within Gemini CLI for assistance
+<!-- prettier-ignore -->
+> [!TIP]
+> You can use the `@cli_help` agent within Gemini CLI for assistance
 > with configuring subagents.

docs/core/subagents.md

@@ -5,16 +5,18 @@ session. They are designed to handle specific, complex tasks—like deep codebas
 analysis, documentation lookup, or domain-specific reasoning—without cluttering
 the main agent's context or toolset.
 
-> **Note: Subagents are currently an experimental feature.**
->
-> To use custom subagents, you must ensure they are enabled in your
-> `settings.json` (enabled by default):
->
-> ```json
-> {
->   "experimental": { "enableAgents": true }
-> }
-> ```
+<!-- prettier-ignore -->
+> [!NOTE]
+> Subagents are currently an experimental feature.
+> 
+To use custom subagents, you must ensure they are enabled in your
+`settings.json` (enabled by default):
+
+```json
+{
+  "experimental": { "enableAgents": true }
+}
+```
 
 ## What are subagents?
 
@@ -114,7 +116,9 @@ Gemini CLI comes with the following built-in subagents:
   the pricing table from this page," "Click the login button and enter my
   credentials."
 
-> **Note:** This is a preview feature currently under active development.
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is a preview feature currently under active development.
 
 #### Prerequisites
 
@@ -217,7 +221,9 @@ captures a screenshot and sends it to the vision model for analysis. The model
 returns coordinates and element descriptions that the browser agent uses with
 the `click_at` tool for precise, coordinate-based interactions.
 
-> **Note:** The visual agent requires API key or Vertex AI authentication. It is
+<!-- prettier-ignore -->
+> [!NOTE]
+> The visual agent requires API key or Vertex AI authentication. It is
 > not available when using "Sign in with Google".
 
 ## Creating custom subagents
@@ -405,7 +411,9 @@ that your subagent was called with a specific prompt and the given description.
 Gemini CLI can also delegate tasks to remote subagents using the Agent-to-Agent
 (A2A) protocol.
 
-> **Note: Remote subagents are currently an experimental feature.**
+<!-- prettier-ignore -->
+> [!NOTE]
+> Remote subagents are currently an experimental feature.
 
 See the [Remote Subagents documentation](remote-agents) for detailed
 configuration, authentication, and usage instructions.

docs/extensions/reference.md

@@ -234,7 +234,9 @@ skill definitions in a `skills/` directory. For example,
 
 ### Sub-agents
 
-> **Note:** Sub-agents are a preview feature currently under active development.
+<!-- prettier-ignore -->
+> [!NOTE]
+> Sub-agents are a preview feature currently under active development.
 
 Provide [sub-agents](../core/subagents.md) that users can delegate tasks to. Add
 agent definition files (`.md`) to an `agents/` directory in your extension root.
@@ -253,7 +255,9 @@ Rules contributed by extensions run in their own tier (tier 2), alongside
 workspace-defined policies. This tier has higher priority than the default rules
 but lower priority than user or admin policies.
 
-> **Warning:** For security, Gemini CLI ignores any `allow` decisions or `yolo`
+<!-- prettier-ignore -->
+> [!WARNING]
+> For security, Gemini CLI ignores any `allow` decisions or `yolo`
 > mode configurations in extension policies. This ensures that an extension
 > cannot automatically approve tool calls or bypass security measures without
 > your confirmation.

docs/get-started/authentication.md

@@ -4,7 +4,9 @@ To use Gemini CLI, you'll need to authenticate with Google. This guide helps you
 quickly find the best way to sign in based on your account type and how you're
 using the CLI.
 
-> **Note:** Looking for a high-level comparison of all available subscriptions?
+<!-- prettier-ignore -->
+> [!TIP]
+> Looking for a high-level comparison of all available subscriptions?
 > To compare features and find the right quota for your needs, see our
 > [Plans page](https://geminicli.com/plans/).
 
@@ -43,8 +45,8 @@ is logging in with your Google account. This method requires a web browser on a
 machine that can communicate with the terminal running Gemini CLI (e.g., your
 local machine).
 
-> **Important:** If you are a **Google AI Pro** or **Google AI Ultra**
-> subscriber, use the Google account associated with your subscription.
+If you are a **Google AI Pro** or **Google AI Ultra** subscriber, use the Google
+account associated with your subscription.
 
 To authenticate and use Gemini CLI:
 
@@ -107,7 +109,9 @@ To authenticate and use Gemini CLI with a Gemini API key:
 
 4. Select **Use Gemini API key**.
 
-> **Warning:** Treat API keys, especially for services like Gemini, as sensitive
+<!-- prettier-ignore -->
+> [!WARNING]
+> Treat API keys, especially for services like Gemini, as sensitive
 > credentials. Protect them to prevent unauthorized access and potential misuse
 > of the service under your account.
 
@@ -150,20 +154,20 @@ To make any Vertex AI environment variable settings persistent, see
 
 Consider this authentication method if you have Google Cloud CLI installed.
 
-> **Note:** If you have previously set `GOOGLE_API_KEY` or `GEMINI_API_KEY`, you
-> must unset them to use ADC:
->
-> **macOS/Linux**
->
-> ```bash
-> unset GOOGLE_API_KEY GEMINI_API_KEY
-> ```
->
-> **Windows (PowerShell)**
->
-> ```powershell
-> Remove-Item Env:\GOOGLE_API_KEY, Env:\GEMINI_API_KEY -ErrorAction Ignore
-> ```
+If you have previously set `GOOGLE_API_KEY` or `GEMINI_API_KEY`, you must unset
+them to use ADC.
+
+**macOS/Linux**
+
+```bash
+unset GOOGLE_API_KEY GEMINI_API_KEY
+```
+
+**Windows (PowerShell)**
+
+```powershell
+Remove-Item Env:\GOOGLE_API_KEY, Env:\GEMINI_API_KEY -ErrorAction Ignore
+```
 
 1. Verify you have a Google Cloud project and Vertex AI API is enabled.
 
@@ -188,20 +192,20 @@ Consider this authentication method if you have Google Cloud CLI installed.
 Consider this method of authentication in non-interactive environments, CI/CD
 pipelines, or if your organization restricts user-based ADC or API key creation.
 
-> **Note:** If you have previously set `GOOGLE_API_KEY` or `GEMINI_API_KEY`, you
-> must unset them:
->
-> **macOS/Linux**
->
-> ```bash
-> unset GOOGLE_API_KEY GEMINI_API_KEY
-> ```
->
-> **Windows (PowerShell)**
->
-> ```powershell
-> Remove-Item Env:\GOOGLE_API_KEY, Env:\GEMINI_API_KEY -ErrorAction Ignore
-> ```
+If you have previously set `GOOGLE_API_KEY` or `GEMINI_API_KEY`, you must unset
+them:
+
+**macOS/Linux**
+
+```bash
+unset GOOGLE_API_KEY GEMINI_API_KEY
+```
+
+**Windows (PowerShell)**
+
+```powershell
+Remove-Item Env:\GOOGLE_API_KEY, Env:\GEMINI_API_KEY -ErrorAction Ignore
+```
 
 1.  [Create a service account and key](https://cloud.google.com/iam/docs/keys-create-delete)
     and download the provided JSON file. Assign the "Vertex AI User" role to the
@@ -233,8 +237,11 @@ pipelines, or if your organization restricts user-based ADC or API key creation.
     ```
 
 5.  Select **Vertex AI**.
-    > **Warning:** Protect your service account key file as it gives access to
-    > your resources.
+
+<!-- prettier-ignore -->
+> [!WARNING]
+> Protect your service account key file as it gives access to
+> your resources.
 
 #### C. Vertex AI - Google Cloud API key
 
@@ -257,10 +264,9 @@ pipelines, or if your organization restricts user-based ADC or API key creation.
     $env:GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY"
     ```
 
-    > **Note:** If you see errors like
-    > `"API keys are not supported by this API..."`, your organization might
-    > restrict API key usage for this service. Try the other Vertex AI
-    > authentication methods instead.
+    If you see errors like `"API keys are not supported by this API..."`, your
+    organization might restrict API key usage for this service. Try the other
+    Vertex AI authentication methods instead.
 
 3.  [Configure your Google Cloud Project](#set-gcp).
 
@@ -274,7 +280,9 @@ pipelines, or if your organization restricts user-based ADC or API key creation.
 
 ## Set your Google Cloud project <a id="set-gcp"></a>
 
-> **Important:** Most individual Google accounts (free and paid) don't require a
+<!-- prettier-ignore -->
+> [!IMPORTANT]
+> Most individual Google accounts (free and paid) don't require a
 > Google Cloud project for authentication.
 
 When you sign in using your Google account, you may need to configure a Google
@@ -339,9 +347,11 @@ persist them with the following methods:
     . $PROFILE
     ```
 
-    > **Warning:** Be aware that when you export API keys or service account
-    > paths in your shell configuration file, any process launched from that
-    > shell can read them.
+<!-- prettier-ignore -->
+> [!WARNING]
+> Be aware that when you export API keys or service account
+> paths in your shell configuration file, any process launched from that
+> shell can read them.
 
 2.  **Use a `.env` file:** Create a `.gemini/.env` file in your project
     directory or home directory. Gemini CLI automatically loads variables from

docs/get-started/examples.md

@@ -4,7 +4,9 @@ Gemini CLI helps you automate common engineering tasks by combining AI reasoning
 with local system tools. This document provides examples of how to use the CLI
 for file management, code analysis, and data transformation.
 
-> **Note:** These examples demonstrate potential capabilities. Your actual
+<!-- prettier-ignore -->
+> [!NOTE]
+> These examples demonstrate potential capabilities. Your actual
 > results can vary based on the model used and your project environment.
 
 ## Rename your photographs based on content

docs/get-started/gemini-3.md

@@ -2,7 +2,9 @@
 
 Gemini 3 Pro and Gemini 3 Flash are available on Gemini CLI for all users!
 
-> **Note:** Gemini 3.1 Pro Preview is rolling out. To determine whether you have
+<!-- prettier-ignore -->
+> [!NOTE]
+> Gemini 3.1 Pro Preview is rolling out. To determine whether you have
 > access to Gemini 3.1, use the `/model` command and select **Manual**. If you
 > have access, you will see `gemini-3.1-pro-preview`.
 >
@@ -39,7 +41,9 @@ When you encounter that limit, you’ll be given the option to switch to Gemini
 2.5 Pro, upgrade for higher limits, or stop. You’ll also be told when your usage
 limit resets and Gemini 3 Pro can be used again.
 
-> **Note:** Looking to upgrade for higher limits? To compare subscription
+<!-- prettier-ignore -->
+> [!TIP]
+> Looking to upgrade for higher limits? To compare subscription
 > options and find the right quota for your needs, see our
 > [Plans page](https://geminicli.com/plans/).
 
@@ -52,7 +56,9 @@ There may be times when the Gemini 3 Pro model is overloaded. When that happens,
 Gemini CLI will ask you to decide whether you want to keep trying Gemini 3 Pro
 or fallback to Gemini 2.5 Pro.
 
-> **Note:** The **Keep trying** option uses exponential backoff, in which Gemini
+<!-- prettier-ignore -->
+> [!NOTE]
+> The **Keep trying** option uses exponential backoff, in which Gemini
 > CLI waits longer between each retry, when the system is busy. If the retry
 > doesn't happen immediately, please wait a few minutes for the request to
 > process.

docs/hooks/index.md

@@ -143,7 +143,9 @@ Hooks are executed with a sanitized environment.
 
 ## Security and risks
 
-> **Warning: Hooks execute arbitrary code with your user privileges.** By
+<!-- prettier-ignore -->
+> [!WARNING]
+> Hooks execute arbitrary code with your user privileges. By
 > configuring hooks, you are allowing scripts to run shell commands on your
 > machine.
 

docs/ide-integration/ide-companion-spec.md

@@ -132,9 +132,11 @@ to the CLI whenever the user's context changes.
   }
   ```
 
-  **Note:** The `openFiles` list should only include files that exist on disk.
-  Virtual files (e.g., unsaved files without a path, editor settings pages)
-  **MUST** be excluded.
+<!-- prettier-ignore -->
+> [!NOTE]
+> The `openFiles` list should only include files that exist on disk.
+> Virtual files (e.g., unsaved files without a path, editor settings pages)
+> **MUST** be excluded.
 
 ### How the CLI uses this context
 

docs/ide-integration/index.md

@@ -66,9 +66,11 @@ You can also install the extension directly from a marketplace.
   Follow your editor's instructions for installing extensions from this
   registry.
 
-> NOTE: The "Gemini CLI Companion" extension may appear towards the bottom of
-> search results. If you don't see it immediately, try scrolling down or sorting
-> by "Newly Published".
+<!-- prettier-ignore -->
+> [!NOTE]
+> The "Gemini CLI Companion" extension may appear towards the bottom of
+> search results. If you don't see it immediately, try scrolling down or
+> sorting by "Newly Published".
 >
 > After manually installing the extension, you must run `/ide enable` in the CLI
 > to activate the integration.
@@ -103,7 +105,9 @@ IDE, run:
 If connected, this command will show the IDE it's connected to and a list of
 recently opened files it is aware of.
 
-> [!NOTE] The file list is limited to 10 recently accessed files within your
+<!-- prettier-ignore -->
+> [!NOTE]
+> The file list is limited to 10 recently accessed files within your
 > workspace and only includes local files on disk.)
 
 ### Working with diffs

docs/issue-and-pr-automation.md

@@ -14,7 +14,9 @@ feature), while the PR is the "how" (the implementation). This separation helps
 us track work, prioritize features, and maintain clear historical context. Our
 automation is built around this principle.
 
-> **Note:** Issues tagged as "🔒Maintainers only" are reserved for project
+<!-- prettier-ignore -->
+> [!NOTE]
+> Issues tagged as "🔒Maintainers only" are reserved for project
 > maintainers. We will not accept pull requests related to these issues.
 
 ---

docs/local-development.md

@@ -79,7 +79,9 @@ You can view traces in the Jaeger UI for local development.
 You can use an OpenTelemetry collector to forward telemetry data to Google Cloud
 Trace for custom processing or routing.
 
-> **Warning:** Ensure you complete the
+<!-- prettier-ignore -->
+> [!WARNING]
+> Ensure you complete the
 > [Google Cloud telemetry prerequisites](./cli/telemetry.md#prerequisites)
 > (Project ID, authentication, IAM roles, and APIs) before using this method.
 

docs/reference/commands.md

@@ -60,8 +60,8 @@ Slash commands provide meta-level control over the CLI itself.
     - `list` (selecting this opens the auto-saved session browser)
   - `-- checkpoints --`
     - `list`, `save`, `resume`, `delete`, `share` (manual tagged checkpoints)
-  - **Note:** Unique prefixes (for example `/cha` or `/resum`) resolve to the
-    same grouped menu.
+  - Unique prefixes (for example `/cha` or `/resu`) resolve to the same grouped
+    menu.
 - **Sub-commands:**
   - **`debug`**
     - **Description:** Export the most recent API request as a JSON payload.

docs/reference/configuration.md

@@ -25,7 +25,9 @@ overridden by higher numbers):
 Gemini CLI uses JSON settings files for persistent configuration. There are four
 locations for these files:
 
-> **Tip:** JSON-aware editors can use autocomplete and validation by pointing to
+<!-- prettier-ignore -->
+> [!TIP]
+> JSON-aware editors can use autocomplete and validation by pointing to
 > the generated schema at `schemas/settings.schema.json` in this repository.
 > When working outside the repo, reference the hosted schema at
 > `https://raw.githubusercontent.com/google-gemini/gemini-cli/main/schemas/settings.schema.json`.
@@ -66,9 +68,9 @@ an environment variable `MY_API_TOKEN`, you could use it in `settings.json` like
 this: `"apiKey": "$MY_API_TOKEN"`. Additionally, each extension can have its own
 `.env` file in its directory, which will be loaded automatically.
 
-> **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.
+**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
 
@@ -1559,7 +1561,9 @@ 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`.
 
-> **Warning:** Avoid using underscores (`_`) in your server aliases (e.g., use
+<!-- prettier-ignore -->
+> [!WARNING]
+> Avoid using underscores (`_`) in your server aliases (e.g., use
 > `my-server` instead of `my_server`). The underlying policy engine parses Fully
 > Qualified Names (`mcp_server_tool`) using the first underscore after the
 > `mcp_` prefix. An underscore in your server alias will cause the parser to

docs/reference/policy-engine.md

@@ -113,7 +113,9 @@ There are three possible decisions a rule can enforce:
 - `ask_user`: The user is prompted to approve or deny the tool call. (In
   non-interactive mode, this is treated as `deny`.)
 
-> **Note:** The `deny` decision is the recommended way to exclude tools. The
+<!-- prettier-ignore -->
+> [!NOTE]
+> The `deny` decision is the recommended way to exclude tools. The
 > legacy `tools.exclude` setting in `settings.json` is deprecated in favor of
 > policy rules with a `deny` decision.
 
@@ -239,15 +241,17 @@ directory are **ignored**.
 - **Linux / macOS:** Must be owned by `root` (UID 0) and NOT writable by group
   or others (e.g., `chmod 755`).
 - **Windows:** Must be in `C:\ProgramData`. Standard users (`Users`, `Everyone`)
-  must NOT have `Write`, `Modify`, or `Full Control` permissions. _Tip: If you
-  see a security warning, use the folder properties to remove write permissions
-  for non-admin groups. You may need to "Disable inheritance" in Advanced
-  Security Settings._
+  must NOT have `Write`, `Modify`, or `Full Control` permissions. If you see a
+  security warning, use the folder properties to remove write permissions for
+  non-admin groups. You may need to "Disable inheritance" in Advanced Security
+  Settings.
 
-**Note:** Supplemental admin policies (provided via `--admin-policy` or
-`adminPolicyPaths` settings) are **NOT** subject to these strict ownership
-checks, as they are explicitly provided by the user or administrator in their
-current execution context.
+<!-- prettier-ignore -->
+> [!NOTE]
+> Supplemental admin policies (provided via `--admin-policy` or
+> `adminPolicyPaths` settings) are **NOT** subject to these strict ownership
+> checks, as they are explicitly provided by the user or administrator in their
+> current execution context.
 
 ### TOML rule schema
 
@@ -348,7 +352,9 @@ using the `mcpName` field. **This is the recommended approach** for defining MCP
 policies, as it is much more robust than manually writing Fully Qualified Names
 (FQNs) or string wildcards.
 
-> **Warning:** Do not use underscores (`_`) in your MCP server names (e.g., use
+<!-- prettier-ignore -->
+> [!WARNING]
+> Do not use underscores (`_`) in your MCP server names (e.g., use
 > `my-server` rather than `my_server`). The policy parser splits Fully Qualified
 > Names (`mcp_server_tool`) on the _first_ underscore following the `mcp_`
 > prefix. If your server name contains an underscore, the parser will

docs/reference/tools.md

@@ -95,7 +95,9 @@ For developers, the tool system is designed to be extensible and robust. The
 You can extend Gemini CLI with custom tools by configuring
 `tools.discoveryCommand` in your settings or by connecting to MCP servers.
 
-> **Note:** For a deep dive into the internal Tool API and how to implement your
+<!-- prettier-ignore -->
+> [!NOTE]
+> For a deep dive into the internal Tool API and how to implement your
 > own tools in the codebase, see the `packages/core/src/tools/` directory in
 > GitHub.
 

docs/release-confidence.md

@@ -21,9 +21,13 @@ All workflows in `.github/workflows/ci.yml` must pass on the `main` branch (for
 nightly) or the release branch (for preview/stable).
 
 - **Platforms:** Tests must pass on **Linux and macOS**.
-  - _Note:_ Windows tests currently run with `continue-on-error: true`. While a
-    failure here doesn't block the release technically, it should be
-    investigated.
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> Windows tests currently run with `continue-on-error: true`. While a
+> failure here doesn't block the release technically, it should be
+> investigated.
+
 - **Checks:**
   - **Linting:** No linting errors (ESLint, Prettier, etc.).
   - **Typechecking:** No TypeScript errors.

docs/releases.md

@@ -234,10 +234,12 @@ This workflow will automatically:
 Review the automatically created pull request(s) to ensure the cherry-pick was
 successful and the changes are correct. Once approved, merge the pull request.
 
-**Security note:** The `release/*` branches are protected by branch protection
-rules. A pull request to one of these branches requires at least one review from
-a code owner before it can be merged. This ensures that no unauthorized code is
-released.
+<!-- prettier-ignore -->
+> [!WARNING]
+> The `release/*` branches are protected by branch protection
+> rules. A pull request to one of these branches requires at least one review from
+> a code owner before it can be merged. This ensures that no unauthorized code is
+> released.
 
 #### 2.5. Adding multiple commits to a hotfix (advanced)
 
@@ -524,9 +526,11 @@ Notifications use
 [GitHub for Google Chat](https://workspace.google.com/marketplace/app/github_for_google_chat/536184076190).
 To modify the notifications, use `/github-settings` within the chat space.
 
-> [!WARNING] The following instructions describe a fragile workaround that
-> depends on the internal structure of the chat application's UI. It is likely
-> to break with future updates.
+<!-- prettier-ignore -->
+> [!WARNING]
+> The following instructions describe a fragile workaround that depends on the
+> internal structure of the chat application's UI. It is likely to break with
+> future updates.
 
 The list of available labels is not currently populated correctly. If you want
 to add a label that does not appear alphabetically in the first 30 labels in the

docs/resources/faq.md

@@ -58,19 +58,6 @@ your total token usage using the `/stats` command in Gemini CLI.
 
 ## Installation and updates
 
-### How do I check which version of Gemini CLI I'm currently running?
-
-You can check your current Gemini CLI version using one of these methods:
-
-- Run `gemini --version` or `gemini -v` from your terminal
-- Check the globally installed version using your package manager:
-  - npm: `npm list -g @google/gemini-cli`
-  - pnpm: `pnpm list -g @google/gemini-cli`
-  - yarn: `yarn global list @google/gemini-cli`
-  - bun: `bun pm ls -g @google/gemini-cli`
-  - homebrew: `brew list --versions gemini-cli`
-- Inside an active Gemini CLI session, use the `/about` command
-
 ### How do I update Gemini CLI to the latest version?
 
 If you installed it globally via `npm`, update it using the command

docs/resources/tos-privacy.md

@@ -16,8 +16,10 @@ account.
 Your Gemini CLI Usage Statistics are handled in accordance with Google's Privacy
 Policy.
 
-**Note:** See [quotas and pricing](quota-and-pricing.md) for the quota and
-pricing details that apply to your usage of the Gemini CLI.
+<!-- prettier-ignore -->
+> [!NOTE]
+> See [quotas and pricing](quota-and-pricing.md) for the quota and
+> pricing details that apply to your usage of the Gemini CLI.
 
 ## Supported authentication methods
 

docs/resources/troubleshooting.md

@@ -187,5 +187,7 @@ guide_, consider searching the Gemini CLI
 If you can't find an issue similar to yours, consider creating a new GitHub
 Issue with a detailed description. Pull requests are also welcome!
 
-> **Note:** Issues tagged as "🔒Maintainers only" are reserved for project
+<!-- prettier-ignore -->
+> [!NOTE]
+> Issues tagged as "🔒Maintainers only" are reserved for project
 > maintainers. We will not accept pull requests related to these issues.

docs/tools/mcp-server.md

@@ -176,8 +176,8 @@ Each server configuration supports the following properties:
   enabled by default.
 - **`excludeTools`** (string[]): 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.
+  exposed by the server. `excludeTools` takes precedence over `includeTools`. If
+  a tool is in both lists, it will be excluded.
 - **`targetAudience`** (string): The OAuth Client ID allowlisted on the
   IAP-protected application you are trying to access. Used with
   `authProviderType: 'service_account_impersonation'`.
@@ -238,7 +238,9 @@ This follows the security principle that if a variable is explicitly configured
 by the user for a specific server, it constitutes informed consent to share that
 specific data with that server.
 
-> **Note:** Even when explicitly defined, you should avoid hardcoding secrets.
+<!-- prettier-ignore -->
+> [!NOTE]
+> Even when explicitly defined, you should avoid hardcoding secrets.
 > Instead, use environment variable expansion (e.g., `"MY_KEY": "$MY_KEY"`) to
 > securely pull the value from your host environment at runtime.
 
@@ -283,10 +285,12 @@ When connecting to an OAuth-enabled server:
 
 #### Browser redirect requirements
 
-**Important:** OAuth authentication requires that your local machine can:
-
-- Open a web browser for authentication
-- Receive redirects on `http://localhost:7777/oauth/callback`
+<!-- prettier-ignore -->
+> [!IMPORTANT]
+> OAuth authentication requires that your local machine can:
+>
+> - Open a web browser for authentication
+> - Receive redirects on `http://localhost:7777/oauth/callback`
 
 This feature will not work in:
 
@@ -577,7 +581,9 @@ every discovered MCP tool is assigned a strict namespace.
    [Special syntax for MCP tools](../reference/policy-engine.md#special-syntax-for-mcp-tools)
    in the Policy Engine documentation.
 
-> **Warning:** Do not use underscores (`_`) in your MCP server names (e.g., use
+<!-- prettier-ignore -->
+> [!WARNING]
+> Do not use underscores (`_`) in your MCP server names (e.g., use
 > `my-server` rather than `my_server`). The policy parser splits Fully Qualified
 > Names (`mcp_server_tool`) on the _first_ underscore following the `mcp_`
 > prefix. If your server name contains an underscore, the parser will
@@ -1116,7 +1122,9 @@ command has no flags.
 gemini mcp list
 ```
 
-> **Note on Trust:** For security, `stdio` MCP servers (those using the
+<!-- prettier-ignore -->
+> [!NOTE]
+> For security, `stdio` MCP servers (those using the
 > `command` property) are only tested and displayed as "Connected" if the
 > current folder is trusted. If the folder is untrusted, they will show as
 > "Disconnected". Use `gemini trust` to trust the current folder.

docs/tools/planning.md

@@ -11,7 +11,9 @@ by the agent when you ask it to "start a plan" using natural language. In this
 mode, the agent is restricted to read-only tools to allow for safe exploration
 and planning.
 
-> **Note:** This tool is not available when the CLI is in YOLO mode.
+<!-- prettier-ignore -->
+> [!NOTE]
+> This tool is not available when the CLI is in YOLO mode.
 
 - **Tool name:** `enter_plan_mode`
 - **Display name:** Enter Plan Mode

docs/tools/shell.md

@@ -57,8 +57,8 @@ implementation, which does not support interactive commands.
 ### Showing color in output
 
 To show color in the shell output, you need to set the `tools.shell.showColor`
-setting to `true`. **Note: This setting only applies when
-`tools.shell.enableInteractiveShell` is enabled.**
+setting to `true`. This setting only applies when
+`tools.shell.enableInteractiveShell` is enabled.
 
 **Example `settings.json`:**
 
@@ -75,8 +75,8 @@ setting to `true`. **Note: This setting only applies when
 ### Setting the pager
 
 You can set a custom pager for the shell output by setting the
-`tools.shell.pager` setting. The default pager is `cat`. **Note: This setting
-only applies when `tools.shell.enableInteractiveShell` is enabled.**
+`tools.shell.pager` setting. The default pager is `cat`. This setting only
+applies when `tools.shell.enableInteractiveShell` is enabled.
 
 **Example `settings.json`:**
 

package-lock.json

@@ -80,7 +80,7 @@
         "@lydell/node-pty-win32-arm64": "1.1.0",
         "@lydell/node-pty-win32-x64": "1.1.0",
         "keytar": "^7.9.0",
-        "node-pty": "^1.1.0"
+        "node-pty": "^1.0.0"
       }
     },
     "node_modules/@agentclientprotocol/sdk": {
@@ -4906,6 +4906,53 @@
         "url": "https://opencollective.com/vitest"
       }
     },
+    "node_modules/@vscode/vsce": {
+      "version": "3.6.0",
+      "resolved": "https://registry.npmjs.org/@vscode/vsce/-/vsce-3.6.0.tgz",
+      "integrity": "sha512-u2ZoMfymRNJb14aHNawnXJtXHLXDVKc1oKZaH4VELKT/9iWKRVgtQOdwxCgtwSxJoqYvuK4hGlBWQJ05wxADhg==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@azure/identity": "^4.1.0",
+        "@secretlint/node": "^10.1.1",
+        "@secretlint/secretlint-formatter-sarif": "^10.1.1",
+        "@secretlint/secretlint-rule-no-dotenv": "^10.1.1",
+        "@secretlint/secretlint-rule-preset-recommend": "^10.1.1",
+        "@vscode/vsce-sign": "^2.0.0",
+        "azure-devops-node-api": "^12.5.0",
+        "chalk": "^4.1.2",
+        "cheerio": "^1.0.0-rc.9",
+        "cockatiel": "^3.1.2",
+        "commander": "^12.1.0",
+        "form-data": "^4.0.0",
+        "glob": "^11.0.0",
+        "hosted-git-info": "^4.0.2",
+        "jsonc-parser": "^3.2.0",
+        "leven": "^3.1.0",
+        "markdown-it": "^14.1.0",
+        "mime": "^1.3.4",
+        "minimatch": "^3.0.3",
+        "parse-semver": "^1.1.1",
+        "read": "^1.0.7",
+        "secretlint": "^10.1.1",
+        "semver": "^7.5.2",
+        "tmp": "^0.2.3",
+        "typed-rest-client": "^1.8.4",
+        "url-join": "^4.0.1",
+        "xml2js": "^0.5.0",
+        "yauzl": "^2.3.1",
+        "yazl": "^2.2.2"
+      },
+      "bin": {
+        "vsce": "vsce"
+      },
+      "engines": {
+        "node": ">= 20"
+      },
+      "optionalDependencies": {
+        "keytar": "^7.7.0"
+      }
+    },
     "node_modules/@vscode/vsce-sign": {
       "version": "2.0.6",
       "resolved": "https://registry.npmjs.org/@vscode/vsce-sign/-/vsce-sign-2.0.6.tgz",
@@ -5051,6 +5098,52 @@
         "win32"
       ]
     },
+    "node_modules/@vscode/vsce/node_modules/hosted-git-info": {
+      "version": "4.1.0",
+      "resolved": "https://registry.npmjs.org/hosted-git-info/-/hosted-git-info-4.1.0.tgz",
+      "integrity": "sha512-kyCuEOWjJqZuDbRHzL8V93NzQhwIB71oFWSyzVo+KPZI+pnQPPxucdkrOZvkLRnrf5URsQM+IJ09Dw29cRALIA==",
+      "dev": true,
+      "license": "ISC",
+      "dependencies": {
+        "lru-cache": "^6.0.0"
+      },
+      "engines": {
+        "node": ">=10"
+      }
+    },
+    "node_modules/@vscode/vsce/node_modules/lru-cache": {
+      "version": "6.0.0",
+      "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-6.0.0.tgz",
+      "integrity": "sha512-Jo6dJ04CmSjuznwJSS3pUeWmd/H0ffTlkXXgwZi+eq1UCmqQwCh+eLsYOYCwY991i2Fah4h1BEMCx4qThGbsiA==",
+      "dev": true,
+      "license": "ISC",
+      "dependencies": {
+        "yallist": "^4.0.0"
+      },
+      "engines": {
+        "node": ">=10"
+      }
+    },
+    "node_modules/@vscode/vsce/node_modules/mime": {
+      "version": "1.6.0",
+      "resolved": "https://registry.npmjs.org/mime/-/mime-1.6.0.tgz",
+      "integrity": "sha512-x0Vn8spI+wuJ1O6S7gnbaQg8Pxh4NNHb7KSINmEWKiPE4RKOplvijn+NkmYmmRgP68mc70j2EbeTFRsrswaQeg==",
+      "dev": true,
+      "license": "MIT",
+      "bin": {
+        "mime": "cli.js"
+      },
+      "engines": {
+        "node": ">=4"
+      }
+    },
+    "node_modules/@vscode/vsce/node_modules/yallist": {
+      "version": "4.0.0",
+      "resolved": "https://registry.npmjs.org/yallist/-/yallist-4.0.0.tgz",
+      "integrity": "sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A==",
+      "dev": true,
+      "license": "ISC"
+    },
     "node_modules/@vue/compiler-core": {
       "version": "3.5.26",
       "resolved": "https://registry.npmjs.org/@vue/compiler-core/-/compiler-core-3.5.26.tgz",
@@ -6562,13 +6655,6 @@
         "url": "https://github.com/sponsors/sindresorhus"
       }
     },
-    "node_modules/concat-map": {
-      "version": "0.0.1",
-      "resolved": "https://registry.npmjs.org/concat-map/-/concat-map-0.0.1.tgz",
-      "integrity": "sha512-/Srv4dswyQNBfohGpz9o6Yb3Gz3SrUDqBH5rTuhGR7ahtlbYKnVxw2bCFMRljaA7EXHaXZ8wsHdodFvbkhKmqg==",
-      "dev": true,
-      "license": "MIT"
-    },
     "node_modules/config-chain": {
       "version": "1.1.13",
       "resolved": "https://registry.npmjs.org/config-chain/-/config-chain-1.1.13.tgz",
@@ -12107,6 +12193,13 @@
         "node": "^18.17.0 || >=20.5.0"
       }
     },
+    "node_modules/nan": {
+      "version": "2.23.0",
+      "resolved": "https://registry.npmjs.org/nan/-/nan-2.23.0.tgz",
+      "integrity": "sha512-1UxuyYGdoQHcGg87Lkqm3FzefucTa0NAiOcuRsDmysep3c1LVCRK2krrUDafMWtjSG04htvAmvg96+SDknOmgQ==",
+      "license": "MIT",
+      "optional": true
+    },
     "node_modules/nano-spawn": {
       "version": "1.0.3",
       "resolved": "https://registry.npmjs.org/nano-spawn/-/nano-spawn-1.0.3.tgz",
@@ -12250,23 +12343,16 @@
       }
     },
     "node_modules/node-pty": {
-      "version": "1.1.0",
-      "resolved": "https://registry.npmjs.org/node-pty/-/node-pty-1.1.0.tgz",
-      "integrity": "sha512-20JqtutY6JPXTUnL0ij1uad7Qe1baT46lyolh2sSENDd4sTzKZ4nmAFkeAARDKwmlLjPx6XKRlwRUxwjOy+lUg==",
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/node-pty/-/node-pty-1.0.0.tgz",
+      "integrity": "sha512-wtBMWWS7dFZm/VgqElrTvtfMq4GzJ6+edFI0Y0zyzygUSZMgZdraDUMUhCIvkjhJjme15qWmbyJbtAx4ot4uZA==",
       "hasInstallScript": true,
       "license": "MIT",
       "optional": true,
       "dependencies": {
-        "node-addon-api": "^7.1.0"
+        "nan": "^2.17.0"
       }
     },
-    "node_modules/node-pty/node_modules/node-addon-api": {
-      "version": "7.1.1",
-      "resolved": "https://registry.npmjs.org/node-addon-api/-/node-addon-api-7.1.1.tgz",
-      "integrity": "sha512-5m3bsyrjFWE1xf7nz7YXdN4udnVtXK6/Yfgn5qnahL6bCkf2yKt4k3nuTKAtT4r3IG8JNR2ncsIMdZuAzJjHQQ==",
-      "license": "MIT",
-      "optional": true
-    },
     "node_modules/node-sarif-builder": {
       "version": "3.2.0",
       "resolved": "https://registry.npmjs.org/node-sarif-builder/-/node-sarif-builder-3.2.0.tgz",
@@ -17910,23 +17996,6 @@
         "node": ">=20"
       }
     },
-    "packages/snake-game": {
-      "name": "@google/gemini-cli-snake-game",
-      "version": "0.1.0",
-      "extraneous": true,
-      "license": "Apache-2.0",
-      "dependencies": {
-        "lucide-react": "^0.471.0"
-      },
-      "devDependencies": {
-        "@types/react": "^19.2.0",
-        "@types/react-dom": "^19.2.0",
-        "esbuild": "^0.25.0",
-        "react": "^19.2.0",
-        "react-dom": "^19.2.0",
-        "typescript": "^5.7.3"
-      }
-    },
     "packages/test-utils": {
       "name": "@google/gemini-cli-test-utils",
       "version": "0.36.0-nightly.20260317.2f90b4653",
@@ -17961,7 +18030,7 @@
         "@types/vscode": "^1.99.0",
         "@typescript-eslint/eslint-plugin": "^8.31.1",
         "@typescript-eslint/parser": "^8.31.1",
-        "@vscode/vsce": "^3.7.1",
+        "@vscode/vsce": "^3.6.0",
         "esbuild": "^0.25.3",
         "eslint": "^9.25.1",
         "npm-run-all2": "^8.0.2",
@@ -17978,155 +18047,6 @@
       "integrity": "sha512-30sjmas1hQ0gVbX68LAWlm/YYlEqUErunPJJKLpEl+xhK0mKn+jyzlCOpsdTwfkZfPy4U6CDkmygBLC3AB8W9Q==",
       "dev": true,
       "license": "MIT"
-    },
-    "packages/vscode-ide-companion/node_modules/@vscode/vsce": {
-      "version": "3.7.1",
-      "resolved": "https://registry.npmjs.org/@vscode/vsce/-/vsce-3.7.1.tgz",
-      "integrity": "sha512-OTm2XdMt2YkpSn2Nx7z2EJtSuhRHsTPYsSK59hr3v8jRArK+2UEoju4Jumn1CmpgoBLGI6ReHLJ/czYltNUW3g==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "@azure/identity": "^4.1.0",
-        "@secretlint/node": "^10.1.2",
-        "@secretlint/secretlint-formatter-sarif": "^10.1.2",
-        "@secretlint/secretlint-rule-no-dotenv": "^10.1.2",
-        "@secretlint/secretlint-rule-preset-recommend": "^10.1.2",
-        "@vscode/vsce-sign": "^2.0.0",
-        "azure-devops-node-api": "^12.5.0",
-        "chalk": "^4.1.2",
-        "cheerio": "^1.0.0-rc.9",
-        "cockatiel": "^3.1.2",
-        "commander": "^12.1.0",
-        "form-data": "^4.0.0",
-        "glob": "^11.0.0",
-        "hosted-git-info": "^4.0.2",
-        "jsonc-parser": "^3.2.0",
-        "leven": "^3.1.0",
-        "markdown-it": "^14.1.0",
-        "mime": "^1.3.4",
-        "minimatch": "^3.0.3",
-        "parse-semver": "^1.1.1",
-        "read": "^1.0.7",
-        "secretlint": "^10.1.2",
-        "semver": "^7.5.2",
-        "tmp": "^0.2.3",
-        "typed-rest-client": "^1.8.4",
-        "url-join": "^4.0.1",
-        "xml2js": "^0.5.0",
-        "yauzl": "^2.3.1",
-        "yazl": "^2.2.2"
-      },
-      "bin": {
-        "vsce": "vsce"
-      },
-      "engines": {
-        "node": ">= 20"
-      },
-      "optionalDependencies": {
-        "keytar": "^7.7.0"
-      }
-    },
-    "packages/vscode-ide-companion/node_modules/@vscode/vsce/node_modules/minimatch": {
-      "version": "3.1.5",
-      "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.5.tgz",
-      "integrity": "sha512-VgjWUsnnT6n+NUk6eZq77zeFdpW2LWDzP6zFGrCbHXiYNul5Dzqk2HHQ5uFH2DNW5Xbp8+jVzaeNt94ssEEl4w==",
-      "dev": true,
-      "license": "ISC",
-      "dependencies": {
-        "brace-expansion": "^1.1.7"
-      },
-      "engines": {
-        "node": "*"
-      }
-    },
-    "packages/vscode-ide-companion/node_modules/balanced-match": {
-      "version": "1.0.2",
-      "resolved": "https://registry.npmjs.org/balanced-match/-/balanced-match-1.0.2.tgz",
-      "integrity": "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw==",
-      "dev": true,
-      "license": "MIT"
-    },
-    "packages/vscode-ide-companion/node_modules/brace-expansion": {
-      "version": "1.1.12",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
-      "integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
-      "dev": true,
-      "license": "MIT",
-      "dependencies": {
-        "balanced-match": "^1.0.0",
-        "concat-map": "0.0.1"
-      }
-    },
-    "packages/vscode-ide-companion/node_modules/glob": {
-      "version": "11.1.0",
-      "resolved": "https://registry.npmjs.org/glob/-/glob-11.1.0.tgz",
-      "integrity": "sha512-vuNwKSaKiqm7g0THUBu2x7ckSs3XJLXE+2ssL7/MfTGPLLcrJQ/4Uq1CjPTtO5cCIiRxqvN6Twy1qOwhL0Xjcw==",
-      "deprecated": "Old versions of glob are not supported, and contain widely publicized security vulnerabilities, which have been fixed in the current version. Please update. Support for old versions may be purchased (at exorbitant rates) by contacting i@izs.me",
-      "dev": true,
-      "license": "BlueOak-1.0.0",
-      "dependencies": {
-        "foreground-child": "^3.3.1",
-        "jackspeak": "^4.1.1",
-        "minimatch": "^10.1.1",
-        "minipass": "^7.1.2",
-        "package-json-from-dist": "^1.0.0",
-        "path-scurry": "^2.0.0"
-      },
-      "bin": {
-        "glob": "dist/esm/bin.mjs"
-      },
-      "engines": {
-        "node": "20 || >=22"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/isaacs"
-      }
-    },
-    "packages/vscode-ide-companion/node_modules/hosted-git-info": {
-      "version": "4.1.0",
-      "resolved": "https://registry.npmjs.org/hosted-git-info/-/hosted-git-info-4.1.0.tgz",
-      "integrity": "sha512-kyCuEOWjJqZuDbRHzL8V93NzQhwIB71oFWSyzVo+KPZI+pnQPPxucdkrOZvkLRnrf5URsQM+IJ09Dw29cRALIA==",
-      "dev": true,
-      "license": "ISC",
-      "dependencies": {
-        "lru-cache": "^6.0.0"
-      },
-      "engines": {
-        "node": ">=10"
-      }
-    },
-    "packages/vscode-ide-companion/node_modules/lru-cache": {
-      "version": "6.0.0",
-      "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-6.0.0.tgz",
-      "integrity": "sha512-Jo6dJ04CmSjuznwJSS3pUeWmd/H0ffTlkXXgwZi+eq1UCmqQwCh+eLsYOYCwY991i2Fah4h1BEMCx4qThGbsiA==",
-      "dev": true,
-      "license": "ISC",
-      "dependencies": {
-        "yallist": "^4.0.0"
-      },
-      "engines": {
-        "node": ">=10"
-      }
-    },
-    "packages/vscode-ide-companion/node_modules/mime": {
-      "version": "1.6.0",
-      "resolved": "https://registry.npmjs.org/mime/-/mime-1.6.0.tgz",
-      "integrity": "sha512-x0Vn8spI+wuJ1O6S7gnbaQg8Pxh4NNHb7KSINmEWKiPE4RKOplvijn+NkmYmmRgP68mc70j2EbeTFRsrswaQeg==",
-      "dev": true,
-      "license": "MIT",
-      "bin": {
-        "mime": "cli.js"
-      },
-      "engines": {
-        "node": ">=4"
-      }
-    },
-    "packages/vscode-ide-companion/node_modules/yallist": {
-      "version": "4.0.0",
-      "resolved": "https://registry.npmjs.org/yallist/-/yallist-4.0.0.tgz",
-      "integrity": "sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A==",
-      "dev": true,
-      "license": "ISC"
     }
   }
 }

package.json

@@ -150,7 +150,7 @@
     "@lydell/node-pty-win32-arm64": "1.1.0",
     "@lydell/node-pty-win32-x64": "1.1.0",
     "keytar": "^7.9.0",
-    "node-pty": "^1.1.0"
+    "node-pty": "^1.0.0"
   },
   "lint-staged": {
     "*.{js,jsx,ts,tsx}": [

packages/cli/src/acp/acpClient.test.ts

@@ -894,9 +894,6 @@ describe('Session', () => {
         update: expect.objectContaining({
           sessionUpdate: 'tool_call_update',
           status: 'completed',
-          title: 'Test Tool',
-          locations: [],
-          kind: 'read',
         }),
       }),
     );
@@ -1309,18 +1306,6 @@ describe('Session', () => {
     expect(path.resolve).toHaveBeenCalled();
     expect(fs.stat).toHaveBeenCalled();
 
-    expect(mockConnection.sessionUpdate).toHaveBeenCalledWith(
-      expect.objectContaining({
-        update: expect.objectContaining({
-          sessionUpdate: 'tool_call_update',
-          status: 'completed',
-          title: 'Read files',
-          locations: [],
-          kind: 'read',
-        }),
-      }),
-    );
-
     // Verify ReadManyFilesTool was used (implicitly by checking if sendMessageStream was called with resolved content)
     // Since we mocked ReadManyFilesTool to return specific content, we can check the args passed to sendMessageStream
     expect(mockChat.sendMessageStream).toHaveBeenCalledWith(
@@ -1336,65 +1321,6 @@ describe('Session', () => {
     );
   });
 
-  it('should handle @path resolution error', async () => {
-    (path.resolve as unknown as Mock).mockReturnValue('/tmp/error.txt');
-    (fs.stat as unknown as Mock).mockResolvedValue({
-      isDirectory: () => false,
-    });
-    (isWithinRoot as unknown as Mock).mockReturnValue(true);
-
-    const MockReadManyFilesTool = ReadManyFilesTool as unknown as Mock;
-    MockReadManyFilesTool.mockImplementationOnce(() => ({
-      name: 'read_many_files',
-      kind: 'read',
-      build: vi.fn().mockReturnValue({
-        getDescription: () => 'Read files',
-        toolLocations: () => [],
-        execute: vi.fn().mockRejectedValue(new Error('File read failed')),
-      }),
-    }));
-
-    const stream = createMockStream([
-      {
-        type: StreamEventType.CHUNK,
-        value: { candidates: [] },
-      },
-    ]);
-    mockChat.sendMessageStream.mockResolvedValue(stream);
-
-    await expect(
-      session.prompt({
-        sessionId: 'session-1',
-        prompt: [
-          { type: 'text', text: 'Read' },
-          {
-            type: 'resource_link',
-            uri: 'file://error.txt',
-            mimeType: 'text/plain',
-            name: 'error.txt',
-          },
-        ],
-      }),
-    ).rejects.toThrow('File read failed');
-
-    expect(mockConnection.sessionUpdate).toHaveBeenCalledWith(
-      expect.objectContaining({
-        update: expect.objectContaining({
-          sessionUpdate: 'tool_call_update',
-          status: 'failed',
-          content: expect.arrayContaining([
-            expect.objectContaining({
-              content: expect.objectContaining({
-                text: expect.stringMatching(/File read failed/),
-              }),
-            }),
-          ]),
-          kind: 'read',
-        }),
-      }),
-    );
-  });
-
   it('should handle cancellation during prompt', async () => {
     let streamController: ReadableStreamDefaultController<unknown>;
     const stream = new ReadableStream({
@@ -1508,7 +1434,6 @@ describe('Session', () => {
               content: expect.objectContaining({ text: 'Tool failed' }),
             }),
           ]),
-          kind: 'read',
         }),
       }),
     );

packages/cli/src/acp/acpClient.ts

@@ -966,10 +966,7 @@ export class Session {
         sessionUpdate: 'tool_call_update',
         toolCallId: callId,
         status: 'completed',
-        title: invocation.getDescription(),
         content: content ? [content] : [],
-        locations: invocation.toolLocations(),
-        kind: toAcpToolKind(tool.kind),
       });
 
       const durationMs = Date.now() - startTime;
@@ -1033,7 +1030,6 @@ export class Session {
         content: [
           { type: 'content', content: { type: 'text', text: error.message } },
         ],
-        kind: toAcpToolKind(tool.kind),
       });
 
       this.chat.recordCompletedToolCalls(this.config.getActiveModel(), [
@@ -1328,10 +1324,7 @@ export class Session {
           sessionUpdate: 'tool_call_update',
           toolCallId: callId,
           status: 'completed',
-          title: invocation.getDescription(),
           content: content ? [content] : [],
-          locations: invocation.toolLocations(),
-          kind: toAcpToolKind(readManyFilesTool.kind),
         });
         if (Array.isArray(result.llmContent)) {
           const fileContentRegex = /^--- (.*?) ---\n\n([\s\S]*?)\n\n$/;
@@ -1375,7 +1368,6 @@ export class Session {
               },
             },
           ],
-          kind: toAcpToolKind(readManyFilesTool.kind),
         });
 
         throw error;

packages/cli/src/config/config.ts

@@ -97,7 +97,6 @@ export interface CliArgs {
   rawOutput: boolean | undefined;
   acceptRawOutputRisk: boolean | undefined;
   isCommand: boolean | undefined;
-  simulateUser: boolean | undefined;
 }
 
 /**
@@ -299,11 +298,6 @@ export async function parseArguments(
         .option('accept-raw-output-risk', {
           type: 'boolean',
           description: 'Suppress the security warning when using --raw-output.',
-        })
-        .option('simulate-user', {
-          type: 'boolean',
-          description:
-            'Run the user simulation agent in the background for evaluation purposes.',
         }),
     )
     // Register MCP subcommands
@@ -805,7 +799,6 @@ export async function loadCliConfig(
     approvalMode,
     disableYoloMode:
       settings.security?.disableYoloMode || settings.admin?.secureModeEnabled,
-    simulateUser: !!argv.simulateUser,
     disableAlwaysAllow:
       settings.security?.disableAlwaysAllow ||
       settings.admin?.secureModeEnabled,

packages/cli/src/gemini.test.tsx

@@ -513,7 +513,6 @@ describe('gemini.tsx main function kitty protocol', () => {
       rawOutput: undefined,
       acceptRawOutputRisk: undefined,
       isCommand: undefined,
-      simulateUser: undefined,
     });
 
     await act(async () => {

packages/cli/src/interactiveCli.tsx

@@ -9,15 +9,7 @@ import { render } from 'ink';
 import { basename } from 'node:path';
 import { AppContainer } from './ui/AppContainer.js';
 import { ConsolePatcher } from './ui/utils/ConsolePatcher.js';
-import { UserSimulator } from './services/UserSimulator.js';
 import { registerCleanup, setupTtyCheck } from './utils/cleanup.js';
-import { PassThrough } from 'node:stream';
-
-interface RenderMetrics {
-  renderTime: number;
-  output: string;
-  staticOutput?: string;
-}
 import {
   type StartupWarning,
   type Config,
@@ -140,11 +132,6 @@ export async function startInteractiveUI(
     await new Promise((resolve) => setTimeout(resolve, 100));
   }
 
-  const simulateUser = config.getSimulateUser();
-  const simulatedStdin = new PassThrough({ encoding: 'utf8' });
-
-  let lastFrame: string | undefined;
-  const staticHistory: string[] = [];
   const instance = render(
     process.env['DEBUG'] ? (
       <React.StrictMode>
@@ -156,20 +143,12 @@ export async function startInteractiveUI(
     {
       stdout: inkStdout,
       stderr: inkStderr,
-      // eslint-disable-next-line @typescript-eslint/no-explicit-any, @typescript-eslint/no-unsafe-type-assertion, @typescript-eslint/no-unsafe-assignment
-      stdin: (simulateUser ? simulatedStdin : process.stdin) as any,
+      stdin: process.stdin,
       exitOnCtrlC: false,
       isScreenReaderEnabled: config.getScreenReader(),
-      onRender: (metrics: RenderMetrics) => {
-        lastFrame = metrics.output;
-        if (metrics.staticOutput) {
-          staticHistory.push(metrics.staticOutput);
-          if (staticHistory.length > 50) {
-            staticHistory.shift();
-          }
-        }
-        if (metrics.renderTime > SLOW_RENDER_MS) {
-          recordSlowRender(config, metrics.renderTime);
+      onRender: ({ renderTime }: { renderTime: number }) => {
+        if (renderTime > SLOW_RENDER_MS) {
+          recordSlowRender(config, renderTime);
         }
         profiler.reportFrameRendered();
       },
@@ -200,21 +179,6 @@ export async function startInteractiveUI(
       }
     });
 
-  if (simulateUser) {
-    const simulator = new UserSimulator(
-      config,
-      () => {
-        if (lastFrame === undefined) return undefined;
-        // Combine history with latest frame for the simulator
-        const historyText = staticHistory.join('\n');
-        return historyText ? `${historyText}\n${lastFrame}` : lastFrame;
-      },
-      simulatedStdin,
-    );
-    simulator.start();
-    registerCleanup(() => simulator.stop());
-  }
-
   registerCleanup(() => instance.unmount());
 
   registerCleanup(setupTtyCheck());

packages/cli/src/services/UserSimulator.ts

@@ -1,213 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-import type { Config } from '@google/gemini-cli-core';
-import {
-  debugLogger,
-  LlmRole,
-  PREVIEW_GEMINI_FLASH_MODEL,
-  resolveModel,
-} from '@google/gemini-cli-core';
-import type { Writable } from 'node:stream';
-import * as fs from 'node:fs';
-
-export class UserSimulator {
-  private isRunning = false;
-  private timer: NodeJS.Timeout | null = null;
-  private lastScreenContent = '';
-  private isProcessing = false;
-  private interactionsFile: string | null = null;
-  private actionHistory: string[] = [];
-
-  constructor(
-    private readonly config: Config,
-    private readonly getScreen: () => string | undefined,
-    private readonly stdinBuffer: Writable,
-  ) {}
-
-  start() {
-    if (!this.config.getSimulateUser()) {
-      return;
-    }
-    this.interactionsFile = `interactions_${Date.now()}.txt`;
-    this.isRunning = true;
-    this.timer = setInterval(() => this.tick(), 3000);
-  }
-
-  stop() {
-    this.isRunning = false;
-    if (this.timer) {
-      clearInterval(this.timer);
-      this.timer = null;
-    }
-    debugLogger.log('User simulator stopped');
-  }
-
-  private async tick() {
-    if (!this.isRunning || this.isProcessing) return;
-
-    try {
-      this.isProcessing = true;
-      const screen = this.getScreen();
-      if (!screen) return;
-
-      const strippedScreen = screen
-        .replace(
-          // eslint-disable-next-line no-control-regex
-          /[\u001b\u009b][[()#;?]*(?:[0-9]{1,4}(?:;[0-9]{0,4})*)?[0-9A-ORZcf-nqry=><]/g,
-          '',
-        )
-        .replace(/\n([ \t]*\n)+/g, '\n\n');
-
-      const normalizedScreen = strippedScreen
-        .replace(/[⠋⠙⠹⠸⠼⠴⠦⠧⠇⠏]/g, '')
-        .replace(/\[?\s*\b\d+(\.\d+)?s\b\s*\]?/g, '')
-        .trim();
-
-      if (normalizedScreen === this.lastScreenContent) return;
-
-      debugLogger.log(
-        `[SIMULATOR] Screen Content Seen:\n---\n${strippedScreen}\n---`,
-      );
-      if (this.interactionsFile) {
-        fs.appendFileSync(
-          this.interactionsFile,
-          `[LOG] [SIMULATOR] Screen Content Seen:\n---\n${strippedScreen}\n---\n\n`,
-        );
-      }
-
-      const contentGenerator = this.config.getContentGenerator();
-      if (!contentGenerator) return;
-
-      const originalGoal = this.config.getQuestion();
-      const goalInstruction = originalGoal
-        ? `\nThe original goal was: "${originalGoal}"\n`
-        : '';
-
-      const historyInstruction =
-        this.actionHistory.length > 0
-          ? `\nYou have previously taken the following actions (in order):\n${this.actionHistory.map((a, i) => `${i + 1}. ${JSON.stringify(a)}`).join('\n')}\nPay close attention to whether you have already asked for the original goal. If you have already submitted the original goal, DO NOT repeat it verbatim. If the UI shows your typed text but hasn't submitted it yet, just output \\r to press Enter.\n`
-          : '';
-
-      const prompt = `You are evaluating a CLI agent by simulating a user sitting at the terminal.
-Look carefully at the screen and determine the CLI's current state:
-
-STATE 1: The agent is busy (e.g., streaming a response, showing a spinner, running a tool, or displaying a timer like "7s"). It is actively working and NOT waiting for text input.
-- In this case, you MUST output exactly: <WAIT>
-
-STATE 2: The agent is waiting for you to authorize a tool, confirm an action, or answer a specific multi-choice question (e.g., "Action Required", "Allow execution", numbered options).
-- In this case, you MUST output the exact raw characters to select the option and submit it (e.g., 1\\r, 2\\r, y\\r, n\\r, or just \\r if the default option is acceptable). Do NOT output <DONE> or "Thank you". You must unblock the agent and allow it to run the tool.
-
-STATE 3: The agent has finished its current thought process AND is idle, waiting for a NEW general text prompt (usually indicated by a "> Type your message" prompt).
-- First, verify that the ACTUAL task is fully complete based on your original goal. Do not stop at intermediate steps like planning or syntax checking.
-- If the task is indeed fully complete, output "Thank you\\r" to graciously finish the simulation.
-- If you have already said thank you, output exactly: <DONE>
-- If the agent is waiting at a general text prompt but the original task is NOT complete, provide text instructions to continue what is missing. DO NOT repeat the original goal if it has already been provided once. Ask it to continue or provide feedback based on the current state or send <DONE> if you think the task is completed.
-
-STATE 4: Any other situation where the agent is waiting for text input or needs to press Enter.
-- Output the raw characters you would type, followed by \\r. For just an Enter key press, output \\r.
-
-CRITICAL RULES:
-- RULE 1: If there is ANY active spinner (e.g., ⠋, ⠙, ⠹, ⠸, ⠼, ⠴, ⠧) or an elapsed time indicator (e.g., "0s", "7s") anywhere on the screen, the agent is STILL WORKING. You MUST output <WAIT>. Do NOT issue commands, even if a text prompt is visible below it.
-- RULE 2: If there is an "Action Required" or confirmation prompt on the screen, YOU MUST HANDLE IT (State 2). This takes precedence over everything else.
-- RULE 3: Output ONLY the raw characters to send, <WAIT>, or <DONE>.
-- RULE 4: Do NOT output markdown, explanations of your thought process, or quotes.
-${goalInstruction}${historyInstruction}
-
-Here is the current terminal screen output:
-
-<screen>
-${strippedScreen}
-</screen>`;
-
-      if (this.interactionsFile) {
-        fs.appendFileSync(
-          this.interactionsFile,
-          `[LOG] [SIMULATOR] Prompt Used:\n---\n${prompt}\n---\n\n`,
-        );
-      }
-
-      const model = resolveModel(
-        PREVIEW_GEMINI_FLASH_MODEL,
-        false, // useGemini3_1
-        false, // useCustomToolModel
-        this.config.getHasAccessToPreviewModel?.() ?? true,
-        this.config,
-      );
-
-      const response = await contentGenerator.generateContent(
-        {
-          model,
-          contents: [
-            {
-              role: 'user',
-              parts: [{ text: prompt }],
-            },
-          ],
-        },
-        'simulator-prompt',
-        LlmRole.UTILITY_SIMULATOR,
-      );
-
-      const responseText = (response.text || '').replace(
-        /^[`"']+|[`"']+$/g,
-        '',
-      );
-      const trimmedResponse = responseText.trim();
-
-      debugLogger.log(
-        `[SIMULATOR] Raw model response: ${JSON.stringify(response.text)}`,
-      );
-      if (this.interactionsFile) {
-        fs.appendFileSync(
-          this.interactionsFile,
-          `[LOG] [SIMULATOR] Raw model response: ${JSON.stringify(response.text)}\n\n`,
-        );
-      }
-      debugLogger.log(
-        `[SIMULATOR] Processed response: ${JSON.stringify(responseText)}`,
-      );
-
-      if (trimmedResponse === '<DONE>') {
-        const msg = '[SIMULATOR] Terminating simulation: Task is completed.';
-        debugLogger.log(msg);
-        if (this.interactionsFile) {
-          fs.appendFileSync(this.interactionsFile, `[LOG] ${msg}\n\n`);
-        }
-        // eslint-disable-next-line no-console
-        console.log(`\n${msg}`);
-        this.stop();
-        process.exit(0);
-      }
-
-      if (trimmedResponse === '<WAIT>') {
-        debugLogger.log(
-          '[SIMULATOR] Skipping action (model decided to <WAIT>)',
-        );
-        this.lastScreenContent = normalizedScreen;
-        return;
-      }
-
-      if (responseText) {
-        const keys = responseText.replace(/\\n/g, '\r').replace(/\\r/g, '\r');
-        const readableAction = trimmedResponse.replace(/\\r/g, '[ENTER]');
-        this.actionHistory.push(readableAction);
-
-        debugLogger.log(
-          `[SIMULATOR] Sending to stdin: ${JSON.stringify(keys)}`,
-        );
-        this.stdinBuffer.write(keys);
-        this.lastScreenContent = normalizedScreen;
-      } else {
-        debugLogger.log('[SIMULATOR] Skipping (empty response)');
-        this.lastScreenContent = normalizedScreen;
-      }
-    } catch (e: unknown) {
-      debugLogger.error('UserSimulator tick failed', e);
-    } finally {
-      this.isProcessing = false;
-    }
-  }
-}

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

@@ -62,7 +62,6 @@ export const createMockConfig = (overrides: Partial<Config> = {}): Config =>
     getGeminiMdFileCount: vi.fn(() => 0),
     getDeferredCommand: vi.fn(() => undefined),
     getFileSystemService: vi.fn(() => ({})),
-    getSimulateUser: vi.fn(() => false),
     clientVersion: '1.0.0',
     getModel: vi.fn().mockReturnValue('gemini-pro'),
     getWorkingDir: vi.fn().mockReturnValue('/mock/cwd'),

packages/cli/src/utils/handleAutoUpdate.test.ts

@@ -202,12 +202,7 @@ describe('handleAutoUpdate', () => {
     expect(mockSpawn).not.toHaveBeenCalled();
   });
 
-  it.each([
-    PackageManager.NPX,
-    PackageManager.PNPX,
-    PackageManager.BUNX,
-    PackageManager.BINARY,
-  ])(
+  it.each([PackageManager.NPX, PackageManager.PNPX, PackageManager.BUNX])(
     'should suppress update notifications when running via %s',
     (packageManager) => {
       mockGetInstallationInfo.mockReturnValue({

packages/cli/src/utils/handleAutoUpdate.ts

@@ -87,12 +87,9 @@ export function handleAutoUpdate(
   );
 
   if (
-    [
-      PackageManager.NPX,
-      PackageManager.PNPX,
-      PackageManager.BUNX,
-      PackageManager.BINARY,
-    ].includes(installationInfo.packageManager)
+    [PackageManager.NPX, PackageManager.PNPX, PackageManager.BUNX].includes(
+      installationInfo.packageManager,
+    )
   ) {
     return;
   }

packages/cli/src/utils/installationInfo.test.ts

@@ -58,19 +58,6 @@ describe('getInstallationInfo', () => {
     process.argv = originalArgv;
   });
 
-  it('should detect running as a standalone binary', () => {
-    vi.stubEnv('IS_BINARY', 'true');
-    process.argv[1] = '/path/to/binary';
-    const info = getInstallationInfo(projectRoot, true);
-    expect(info.packageManager).toBe(PackageManager.BINARY);
-    expect(info.isGlobal).toBe(true);
-    expect(info.updateMessage).toBe(
-      'Running as a standalone binary. Please update by downloading the latest version from GitHub.',
-    );
-    expect(info.updateCommand).toBeUndefined();
-    vi.unstubAllEnvs();
-  });
-
   it('should return UNKNOWN when cliPath is not available', () => {
     process.argv[1] = '';
     const info = getInstallationInfo(projectRoot, true);

packages/cli/src/utils/installationInfo.ts

@@ -21,7 +21,6 @@ export enum PackageManager {
   BUNX = 'bunx',
   HOMEBREW = 'homebrew',
   NPX = 'npx',
-  BINARY = 'binary',
   UNKNOWN = 'unknown',
 }
 
@@ -42,16 +41,6 @@ export function getInstallationInfo(
   }
 
   try {
-    // Check for standalone binary first
-    if (process.env['IS_BINARY'] === 'true') {
-      return {
-        packageManager: PackageManager.BINARY,
-        isGlobal: true,
-        updateMessage:
-          'Running as a standalone binary. Please update by downloading the latest version from GitHub.',
-      };
-    }
-
     // Normalize path separators to forward slashes for consistent matching.
     const realPath = fs.realpathSync(cliPath).replace(/\\/g, '/');
     const normalizedProjectRoot = projectRoot?.replace(/\\/g, '/');

packages/core/src/agent/content-utils.test.ts

@@ -1,258 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import { describe, expect, it } from 'vitest';
-import {
-  geminiPartsToContentParts,
-  contentPartsToGeminiParts,
-  toolResultDisplayToContentParts,
-  buildToolResponseData,
-} from './content-utils.js';
-import type { Part } from '@google/genai';
-import type { ContentPart } from './types.js';
-
-describe('geminiPartsToContentParts', () => {
-  it('converts text parts', () => {
-    const parts: Part[] = [{ text: 'hello' }];
-    expect(geminiPartsToContentParts(parts)).toEqual([
-      { type: 'text', text: 'hello' },
-    ]);
-  });
-
-  it('converts thought parts', () => {
-    const parts: Part[] = [
-      { text: 'thinking...', thought: true, thoughtSignature: 'sig123' },
-    ];
-    expect(geminiPartsToContentParts(parts)).toEqual([
-      {
-        type: 'thought',
-        thought: 'thinking...',
-        thoughtSignature: 'sig123',
-      },
-    ]);
-  });
-
-  it('converts thought parts without signature', () => {
-    const parts: Part[] = [{ text: 'thinking...', thought: true }];
-    expect(geminiPartsToContentParts(parts)).toEqual([
-      { type: 'thought', thought: 'thinking...' },
-    ]);
-  });
-
-  it('converts inlineData parts to media', () => {
-    const parts: Part[] = [
-      { inlineData: { data: 'base64data', mimeType: 'image/png' } },
-    ];
-    expect(geminiPartsToContentParts(parts)).toEqual([
-      { type: 'media', data: 'base64data', mimeType: 'image/png' },
-    ]);
-  });
-
-  it('converts fileData parts to media', () => {
-    const parts: Part[] = [
-      {
-        fileData: {
-          fileUri: 'gs://bucket/file.pdf',
-          mimeType: 'application/pdf',
-        },
-      },
-    ];
-    expect(geminiPartsToContentParts(parts)).toEqual([
-      {
-        type: 'media',
-        uri: 'gs://bucket/file.pdf',
-        mimeType: 'application/pdf',
-      },
-    ]);
-  });
-
-  it('skips functionCall parts', () => {
-    const parts: Part[] = [
-      { functionCall: { name: 'myFunc', args: { key: 'value' } } },
-    ];
-    const result = geminiPartsToContentParts(parts);
-    expect(result).toEqual([]);
-  });
-
-  it('skips functionResponse parts', () => {
-    const parts: Part[] = [
-      {
-        functionResponse: {
-          name: 'myFunc',
-          response: { output: 'result' },
-        },
-      },
-    ];
-    const result = geminiPartsToContentParts(parts);
-    expect(result).toEqual([]);
-  });
-
-  it('serializes unknown part types to text with _meta', () => {
-    const parts: Part[] = [{ unknownField: 'data' } as Part];
-    const result = geminiPartsToContentParts(parts);
-    expect(result).toHaveLength(1);
-    expect(result[0]?.type).toBe('text');
-    expect(result[0]?._meta).toEqual({ partType: 'unknown' });
-  });
-
-  it('handles empty array', () => {
-    expect(geminiPartsToContentParts([])).toEqual([]);
-  });
-
-  it('handles mixed parts', () => {
-    const parts: Part[] = [
-      { text: 'hello' },
-      { inlineData: { data: 'img', mimeType: 'image/jpeg' } },
-      { text: 'thought', thought: true },
-    ];
-    const result = geminiPartsToContentParts(parts);
-    expect(result).toHaveLength(3);
-    expect(result[0]?.type).toBe('text');
-    expect(result[1]?.type).toBe('media');
-    expect(result[2]?.type).toBe('thought');
-  });
-});
-
-describe('contentPartsToGeminiParts', () => {
-  it('converts text ContentParts', () => {
-    const content: ContentPart[] = [{ type: 'text', text: 'hello' }];
-    expect(contentPartsToGeminiParts(content)).toEqual([{ text: 'hello' }]);
-  });
-
-  it('converts thought ContentParts', () => {
-    const content: ContentPart[] = [
-      { type: 'thought', thought: 'thinking...', thoughtSignature: 'sig' },
-    ];
-    expect(contentPartsToGeminiParts(content)).toEqual([
-      { text: 'thinking...', thought: true, thoughtSignature: 'sig' },
-    ]);
-  });
-
-  it('converts thought ContentParts without signature', () => {
-    const content: ContentPart[] = [
-      { type: 'thought', thought: 'thinking...' },
-    ];
-    expect(contentPartsToGeminiParts(content)).toEqual([
-      { text: 'thinking...', thought: true },
-    ]);
-  });
-
-  it('converts media ContentParts with data to inlineData', () => {
-    const content: ContentPart[] = [
-      { type: 'media', data: 'base64', mimeType: 'image/png' },
-    ];
-    expect(contentPartsToGeminiParts(content)).toEqual([
-      { inlineData: { data: 'base64', mimeType: 'image/png' } },
-    ]);
-  });
-
-  it('converts media ContentParts with uri to fileData', () => {
-    const content: ContentPart[] = [
-      { type: 'media', uri: 'gs://bucket/file', mimeType: 'application/pdf' },
-    ];
-    expect(contentPartsToGeminiParts(content)).toEqual([
-      {
-        fileData: { fileUri: 'gs://bucket/file', mimeType: 'application/pdf' },
-      },
-    ]);
-  });
-
-  it('converts reference ContentParts to text', () => {
-    const content: ContentPart[] = [{ type: 'reference', text: '@file.ts' }];
-    expect(contentPartsToGeminiParts(content)).toEqual([{ text: '@file.ts' }]);
-  });
-
-  it('handles empty array', () => {
-    expect(contentPartsToGeminiParts([])).toEqual([]);
-  });
-
-  it('skips media parts with no data or uri', () => {
-    const content: ContentPart[] = [{ type: 'media', mimeType: 'image/png' }];
-    expect(contentPartsToGeminiParts(content)).toEqual([]);
-  });
-
-  it('defaults mimeType for media with data but no mimeType', () => {
-    const content: ContentPart[] = [{ type: 'media', data: 'base64data' }];
-    const result = contentPartsToGeminiParts(content);
-    expect(result).toEqual([
-      {
-        inlineData: {
-          data: 'base64data',
-          mimeType: 'application/octet-stream',
-        },
-      },
-    ]);
-  });
-
-  it('serializes unknown ContentPart variants', () => {
-    // Force an unknown variant past the type system
-    const content = [
-      { type: 'custom_widget', payload: 123 },
-    ] as unknown as ContentPart[];
-    const result = contentPartsToGeminiParts(content);
-    expect(result).toHaveLength(1);
-    expect(result[0]).toEqual({
-      text: JSON.stringify({ type: 'custom_widget', payload: 123 }),
-    });
-  });
-});
-
-describe('toolResultDisplayToContentParts', () => {
-  it('returns undefined for undefined', () => {
-    expect(toolResultDisplayToContentParts(undefined)).toBeUndefined();
-  });
-
-  it('returns undefined for null', () => {
-    expect(toolResultDisplayToContentParts(null)).toBeUndefined();
-  });
-
-  it('handles string resultDisplay as-is', () => {
-    const result = toolResultDisplayToContentParts('File written');
-    expect(result).toEqual([{ type: 'text', text: 'File written' }]);
-  });
-
-  it('stringifies object resultDisplay', () => {
-    const display = { type: 'FileDiff', oldPath: 'a.ts', newPath: 'b.ts' };
-    const result = toolResultDisplayToContentParts(display);
-    expect(result).toEqual([{ type: 'text', text: JSON.stringify(display) }]);
-  });
-});
-
-describe('buildToolResponseData', () => {
-  it('preserves outputFile and contentLength', () => {
-    const result = buildToolResponseData({
-      outputFile: '/tmp/result.txt',
-      contentLength: 256,
-    });
-    expect(result).toEqual({
-      outputFile: '/tmp/result.txt',
-      contentLength: 256,
-    });
-  });
-
-  it('returns undefined for empty response', () => {
-    const result = buildToolResponseData({});
-    expect(result).toBeUndefined();
-  });
-
-  it('includes errorType when present', () => {
-    const result = buildToolResponseData({
-      errorType: 'permission_denied',
-    });
-    expect(result).toEqual({ errorType: 'permission_denied' });
-  });
-
-  it('merges data with other fields', () => {
-    const result = buildToolResponseData({
-      data: { custom: 'value' },
-      outputFile: '/tmp/file.txt',
-    });
-    expect(result).toEqual({
-      custom: 'value',
-      outputFile: '/tmp/file.txt',
-    });
-  });
-});

packages/core/src/agent/content-utils.ts

@@ -1,139 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import type { Part } from '@google/genai';
-import type { ContentPart } from './types.js';
-
-/**
- * Converts Gemini API Part objects to framework-agnostic ContentPart objects.
- * Handles text, thought, inlineData, fileData parts and serializes unknown
- * part types to text to avoid silent data loss.
- */
-export function geminiPartsToContentParts(parts: Part[]): ContentPart[] {
-  const result: ContentPart[] = [];
-  for (const part of parts) {
-    if ('text' in part && part.text !== undefined) {
-      if ('thought' in part && part.thought) {
-        result.push({
-          type: 'thought',
-          thought: part.text,
-          ...(part.thoughtSignature
-            ? { thoughtSignature: part.thoughtSignature }
-            : {}),
-        });
-      } else {
-        result.push({ type: 'text', text: part.text });
-      }
-    } else if ('inlineData' in part && part.inlineData) {
-      result.push({
-        type: 'media',
-        data: part.inlineData.data,
-        mimeType: part.inlineData.mimeType,
-      });
-    } else if ('fileData' in part && part.fileData) {
-      result.push({
-        type: 'media',
-        uri: part.fileData.fileUri,
-        mimeType: part.fileData.mimeType,
-      });
-    } else if ('functionCall' in part && part.functionCall) {
-      continue; // Skip function calls, they are emitted as distinct tool_request events
-    } else if ('functionResponse' in part && part.functionResponse) {
-      continue; // Skip function responses, they are tied to tool_response events
-    } else {
-      // Fallback: serialize any unrecognized part type to text
-      result.push({
-        type: 'text',
-        text: JSON.stringify(part),
-        _meta: { partType: 'unknown' },
-      });
-    }
-  }
-  return result;
-}
-
-/**
- * Converts framework-agnostic ContentPart objects to Gemini API Part objects.
- */
-export function contentPartsToGeminiParts(content: ContentPart[]): Part[] {
-  const result: Part[] = [];
-  for (const part of content) {
-    switch (part.type) {
-      case 'text':
-        result.push({ text: part.text });
-        break;
-      case 'thought':
-        result.push({
-          text: part.thought,
-          thought: true,
-          ...(part.thoughtSignature
-            ? { thoughtSignature: part.thoughtSignature }
-            : {}),
-        });
-        break;
-      case 'media':
-        if (part.data) {
-          result.push({
-            inlineData: {
-              data: part.data,
-              mimeType: part.mimeType ?? 'application/octet-stream',
-            },
-          });
-        } else if (part.uri) {
-          result.push({
-            fileData: { fileUri: part.uri, mimeType: part.mimeType },
-          });
-        }
-        break;
-      case 'reference':
-        // References are converted to text for the model
-        result.push({ text: part.text });
-        break;
-      default:
-        // Serialize unknown ContentPart variants instead of dropping them
-        result.push({ text: JSON.stringify(part) });
-        break;
-    }
-  }
-  return result;
-}
-
-/**
- * Converts a ToolCallResponseInfo.resultDisplay value into ContentPart[].
- * Handles string, object-valued (FileDiff, SubagentProgress, etc.),
- * and undefined resultDisplay consistently.
- */
-export function toolResultDisplayToContentParts(
-  resultDisplay: unknown,
-): ContentPart[] | undefined {
-  if (resultDisplay === undefined || resultDisplay === null) {
-    return undefined;
-  }
-  const text =
-    typeof resultDisplay === 'string'
-      ? resultDisplay
-      : JSON.stringify(resultDisplay);
-  return [{ type: 'text', text }];
-}
-
-/**
- * Builds the data record for a tool_response AgentEvent, preserving
- * all available metadata from the ToolCallResponseInfo.
- */
-export function buildToolResponseData(response: {
-  data?: Record<string, unknown>;
-  errorType?: string;
-  outputFile?: string;
-  contentLength?: number;
-}): Record<string, unknown> | undefined {
-  const parts: Record<string, unknown> = {};
-  if (response.data) Object.assign(parts, response.data);
-  if (response.errorType) parts['errorType'] = response.errorType;
-  if (response.outputFile) parts['outputFile'] = response.outputFile;
-  if (response.contentLength !== undefined)
-    parts['contentLength'] = response.contentLength;
-  return Object.keys(parts).length > 0 ? parts : undefined;
-}

packages/core/src/agents/local-executor.test.ts

@@ -91,18 +91,9 @@ import {
   type LocalAgentDefinition,
   type SubagentActivityEvent,
   type OutputConfig,
-  SubagentActivityErrorType,
 } from './types.js';
-import {
-  ToolConfirmationOutcome,
-  type AnyDeclarativeTool,
-  type AnyToolInvocation,
-} from '../tools/tools.js';
-import {
-  type ToolCallRequestInfo,
-  CoreToolCallStatus,
-} from '../scheduler/types.js';
-
+import type { AnyDeclarativeTool, AnyToolInvocation } from '../tools/tools.js';
+import type { ToolCallRequestInfo } from '../scheduler/types.js';
 import { CompressionStatus } from '../core/turn.js';
 import { ChatCompressionService } from '../services/chatCompressionService.js';
 import type {
@@ -1022,7 +1013,6 @@ describe('LocalAgentExecutor', () => {
           data: expect.objectContaining({
             context: 'protocol_violation',
             error: expectedError,
-            errorType: SubagentActivityErrorType.GENERIC,
           }),
         }),
       );
@@ -1068,7 +1058,6 @@ describe('LocalAgentExecutor', () => {
             context: 'tool_call',
             name: TASK_COMPLETE_TOOL_NAME,
             error: expectedError,
-            errorType: SubagentActivityErrorType.GENERIC,
           }),
         }),
       );
@@ -1172,7 +1161,7 @@ describe('LocalAgentExecutor', () => {
               if (callsStarted === 2) resolveCalls();
               await vi.advanceTimersByTimeAsync(100);
               return {
-                status: CoreToolCallStatus.Success,
+                status: 'success',
                 request: reqInfo,
                 tool: {} as AnyDeclarativeTool,
                 invocation: {} as AnyToolInvocation,
@@ -1190,7 +1179,7 @@ describe('LocalAgentExecutor', () => {
                   ],
                   error: undefined,
                   errorType: undefined,
-                  contentLength: 0,
+                  contentLength: undefined,
                 },
               };
             }),
@@ -1228,10 +1217,10 @@ describe('LocalAgentExecutor', () => {
       expect(parts).toEqual(
         expect.arrayContaining([
           expect.objectContaining({
-            functionResponse: expect.objectContaining({ name: LS_TOOL_NAME }),
+            functionResponse: expect.objectContaining({ id: 'c1' }),
           }),
           expect.objectContaining({
-            functionResponse: expect.objectContaining({ name: LS_TOOL_NAME }),
+            functionResponse: expect.objectContaining({ id: 'c2' }),
           }),
         ]),
       );
@@ -1302,7 +1291,6 @@ describe('LocalAgentExecutor', () => {
           data: expect.objectContaining({
             context: 'tool_call_unauthorized',
             name: READ_FILE_TOOL_NAME,
-            errorType: SubagentActivityErrorType.GENERIC,
           }),
         }),
       );
@@ -1356,7 +1344,6 @@ describe('LocalAgentExecutor', () => {
             context: 'tool_call',
             name: TASK_COMPLETE_TOOL_NAME,
             error: expect.stringContaining('Output validation failed'),
-            errorType: SubagentActivityErrorType.GENERIC,
           }),
         }),
       );
@@ -1403,7 +1390,6 @@ describe('LocalAgentExecutor', () => {
           type: 'ERROR',
           data: expect.objectContaining({
             error: `Error: Failed to create chat object: ${getErrorMessage(initError)}`,
-            errorType: SubagentActivityErrorType.GENERIC,
           }),
         }),
       );
@@ -1432,7 +1418,7 @@ describe('LocalAgentExecutor', () => {
       ]);
       mockScheduleAgentTools.mockResolvedValueOnce([
         {
-          status: CoreToolCallStatus.Error,
+          status: 'error',
           request: {
             callId: 'call1',
             name: LS_TOOL_NAME,
@@ -1483,7 +1469,6 @@ describe('LocalAgentExecutor', () => {
             context: 'tool_call',
             name: LS_TOOL_NAME,
             error: toolErrorMessage,
-            errorType: SubagentActivityErrorType.GENERIC,
           }),
         }),
       );
@@ -1506,157 +1491,6 @@ describe('LocalAgentExecutor', () => {
       expect(output.terminate_reason).toBe(AgentTerminateMode.GOAL);
       expect(output.result).toBe('Aborted due to tool failure.');
     });
-
-    it('should handle a soft tool rejection (outcome: Cancel) and provide direct instructions to the model', async () => {
-      const definition = createTestDefinition([LS_TOOL_NAME]);
-      const executor = await LocalAgentExecutor.create(
-        definition,
-        mockConfig,
-        onActivity,
-      );
-
-      // Turn 1: Model calls a tool that will be rejected
-      mockModelResponse([
-        { name: LS_TOOL_NAME, args: { path: '/secret' }, id: 'call1' },
-      ]);
-      mockScheduleAgentTools.mockResolvedValueOnce([
-        {
-          status: 'cancelled',
-          request: {
-            callId: 'call1',
-            name: LS_TOOL_NAME,
-            args: { path: '/secret' },
-            isClientInitiated: false,
-            prompt_id: 'test-prompt',
-          },
-          tool: {} as AnyDeclarativeTool,
-          invocation: {} as AnyToolInvocation,
-          outcome: ToolConfirmationOutcome.Cancel, // Soft rejection
-          response: {
-            callId: 'call1',
-            resultDisplay: '',
-            responseParts: [
-              {
-                functionResponse: {
-                  name: LS_TOOL_NAME,
-                  response: {
-                    error:
-                      '[Operation Cancelled] Reason: User denied execution.',
-                  },
-                  id: 'call1',
-                },
-              },
-            ],
-            error: undefined,
-            errorType: undefined,
-            contentLength: 0,
-          },
-        },
-      ]);
-
-      // Turn 2: Model sees the rejection + consolidated instructions and completes
-      mockModelResponse([
-        {
-          name: TASK_COMPLETE_TOOL_NAME,
-          args: { finalResult: 'User rejected access to /secret.' },
-          id: 'call2',
-        },
-      ]);
-
-      const output = await executor.run(
-        { goal: 'Soft rejection test' },
-        signal,
-      );
-
-      // Verify the activity stream reported the consolidated instruction
-      expect(activities).toContainEqual(
-        expect.objectContaining({
-          type: 'ERROR',
-          data: expect.objectContaining({
-            context: 'tool_call',
-            name: LS_TOOL_NAME,
-            error: expect.stringContaining('User rejected this operation'),
-            errorType: SubagentActivityErrorType.REJECTED,
-          }),
-        }),
-      );
-
-      // Verify the instruction was sent back to the model as the tool error
-      const turn2Params = getMockMessageParams(1);
-      const parts = turn2Params.message as Part[];
-      const errorMsg = parts[0].functionResponse?.response?.['error'];
-      expect(typeof errorMsg).toBe('string');
-      if (typeof errorMsg === 'string') {
-        expect(errorMsg).toContain('User rejected this operation');
-        expect(errorMsg).toContain('acknowledge this, rethink your strategy');
-      }
-
-      expect(output.terminate_reason).toBe(AgentTerminateMode.GOAL);
-      expect(output.result).toBe('User rejected access to /secret.');
-    });
-
-    it('should handle a hard tool abort (cancelled with no outcome) and terminate the agent', async () => {
-      const definition = createTestDefinition([LS_TOOL_NAME]);
-      const executor = await LocalAgentExecutor.create(
-        definition,
-        mockConfig,
-        onActivity,
-      );
-
-      // Turn 1: Model calls a tool that will be aborted (e.g. Ctrl+C)
-      mockModelResponse([
-        { name: LS_TOOL_NAME, args: { path: '/secret' }, id: 'call1' },
-      ]);
-      mockScheduleAgentTools.mockResolvedValueOnce([
-        {
-          status: 'cancelled',
-          request: {
-            callId: 'call1',
-            name: LS_TOOL_NAME,
-            args: { path: '/secret' },
-            isClientInitiated: false,
-            prompt_id: 'test-prompt',
-          },
-          tool: {} as AnyDeclarativeTool,
-          invocation: {} as AnyToolInvocation,
-          outcome: undefined, // Hard abort
-          response: {
-            callId: 'call1',
-            resultDisplay: '',
-            responseParts: [
-              {
-                functionResponse: {
-                  name: LS_TOOL_NAME,
-                  response: { error: 'Request cancelled.' },
-                  id: 'call1',
-                },
-              },
-            ],
-            error: undefined,
-            errorType: undefined,
-            contentLength: 0,
-          },
-        },
-      ]);
-
-      const output = await executor.run({ goal: 'Hard abort test' }, signal);
-
-      // Verify the activity stream reported the cancellation
-      expect(activities).toContainEqual(
-        expect.objectContaining({
-          type: 'ERROR',
-          data: expect.objectContaining({
-            context: 'tool_call',
-            name: LS_TOOL_NAME,
-            error: 'Request cancelled.',
-            errorType: SubagentActivityErrorType.CANCELLED,
-          }),
-        }),
-      );
-
-      // Agent should terminate with ABORTED status
-      expect(output.terminate_reason).toBe(AgentTerminateMode.ABORTED);
-    });
   });
 
   describe('Model Routing', () => {
@@ -1851,7 +1685,6 @@ describe('LocalAgentExecutor', () => {
           data: expect.objectContaining({
             context: 'timeout',
             error: 'Agent timed out after 0.5 minutes.',
-            errorType: SubagentActivityErrorType.GENERIC,
           }),
         }),
       );
@@ -2040,7 +1873,6 @@ describe('LocalAgentExecutor', () => {
           data: expect.objectContaining({
             context: 'recovery_turn',
             error: 'Graceful recovery attempt failed. Reason: stop',
-            errorType: SubagentActivityErrorType.GENERIC,
           }),
         }),
       );
@@ -2124,7 +1956,6 @@ describe('LocalAgentExecutor', () => {
           data: expect.objectContaining({
             context: 'recovery_turn',
             error: 'Graceful recovery attempt failed. Reason: stop',
-            errorType: SubagentActivityErrorType.GENERIC,
           }),
         }),
       );
@@ -2246,7 +2077,6 @@ describe('LocalAgentExecutor', () => {
           data: expect.objectContaining({
             context: 'recovery_turn',
             error: 'Graceful recovery attempt failed. Reason: stop',
-            errorType: SubagentActivityErrorType.GENERIC,
           }),
         }),
       );

packages/core/src/agents/local-executor.ts

@@ -18,10 +18,7 @@ import {
 import { ToolRegistry } from '../tools/tool-registry.js';
 import { PromptRegistry } from '../prompts/prompt-registry.js';
 import { ResourceRegistry } from '../resources/resource-registry.js';
-import {
-  type AnyDeclarativeTool,
-  ToolConfirmationOutcome,
-} from '../tools/tools.js';
+import { type AnyDeclarativeTool } from '../tools/tools.js';
 import {
   DiscoveredMCPTool,
   isMcpToolName,
@@ -49,9 +46,6 @@ import {
   DEFAULT_QUERY_STRING,
   DEFAULT_MAX_TURNS,
   DEFAULT_MAX_TIME_MINUTES,
-  SubagentActivityErrorType,
-  SUBAGENT_REJECTED_ERROR_PREFIX,
-  SUBAGENT_CANCELLED_ERROR_MESSAGE,
   type LocalAgentDefinition,
   type AgentInputs,
   type OutputObject,
@@ -344,7 +338,6 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
       this.emitActivity('ERROR', {
         error: `Agent stopped calling tools but did not call '${TASK_COMPLETE_TOOL_NAME}' to finalize the session.`,
         context: 'protocol_violation',
-        errorType: SubagentActivityErrorType.GENERIC,
       });
       return {
         status: 'stop',
@@ -478,7 +471,6 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
       this.emitActivity('ERROR', {
         error: `Graceful recovery attempt failed. Reason: ${turnResult.status}`,
         context: 'recovery_turn',
-        errorType: SubagentActivityErrorType.GENERIC,
       });
       return null;
     } catch (error) {
@@ -486,7 +478,6 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
       this.emitActivity('ERROR', {
         error: `Graceful recovery attempt failed: ${String(error)}`,
         context: 'recovery_turn',
-        errorType: SubagentActivityErrorType.GENERIC,
       });
       return null;
     } finally {
@@ -692,14 +683,12 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
             this.emitActivity('ERROR', {
               error: finalResult,
               context: 'timeout',
-              errorType: SubagentActivityErrorType.GENERIC,
             });
           } else if (terminateReason === AgentTerminateMode.MAX_TURNS) {
             finalResult = `Agent reached max turns limit (${maxTurns}).`;
             this.emitActivity('ERROR', {
               error: finalResult,
               context: 'max_turns',
-              errorType: SubagentActivityErrorType.GENERIC,
             });
           } else if (
             terminateReason === AgentTerminateMode.ERROR_NO_COMPLETE_TASK_CALL
@@ -711,7 +700,6 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
             this.emitActivity('ERROR', {
               error: finalResult,
               context: 'protocol_violation',
-              errorType: SubagentActivityErrorType.GENERIC,
             });
           }
         }
@@ -766,7 +754,6 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
         this.emitActivity('ERROR', {
           error: finalResult,
           context: 'timeout',
-          errorType: SubagentActivityErrorType.GENERIC,
         });
         return {
           result: finalResult,
@@ -774,10 +761,7 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
         };
       }
 
-      this.emitActivity('ERROR', {
-        error: String(error),
-        errorType: SubagentActivityErrorType.GENERIC,
-      });
+      this.emitActivity('ERROR', { error: String(error) });
       throw error; // Re-throw other errors or external aborts.
     } finally {
       deadlineTimer.abort();
@@ -1046,7 +1030,6 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
             context: 'tool_call',
             name: toolName,
             error,
-            errorType: SubagentActivityErrorType.GENERIC,
           });
           continue;
         }
@@ -1074,7 +1057,6 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
                 context: 'tool_call',
                 name: toolName,
                 error,
-                errorType: SubagentActivityErrorType.GENERIC,
               });
               continue;
             }
@@ -1117,7 +1099,6 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
               name: toolName,
               callId,
               error,
-              errorType: SubagentActivityErrorType.GENERIC,
             });
           }
         } else {
@@ -1161,7 +1142,6 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
               name: toolName,
               callId,
               error,
-              errorType: SubagentActivityErrorType.GENERIC,
             });
           }
         }
@@ -1186,7 +1166,6 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
           name: toolName,
           callId,
           error,
-          errorType: SubagentActivityErrorType.GENERIC,
         });
 
         continue;
@@ -1234,46 +1213,18 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
             name: toolName,
             callId: call.request.callId,
             error: call.response.error?.message || 'Unknown error',
-            errorType: SubagentActivityErrorType.GENERIC,
           });
         } else if (call.status === 'cancelled') {
-          const isSoftRejection =
-            call.outcome === ToolConfirmationOutcome.Cancel;
-
-          if (isSoftRejection) {
-            const error = `${SUBAGENT_REJECTED_ERROR_PREFIX} Please acknowledge this, rethink your strategy, and try a different approach. If you cannot proceed without the rejected operation, summarize the issue and use \`${TASK_COMPLETE_TOOL_NAME}\` to report your findings and the blocker.`;
-            this.emitActivity('ERROR', {
-              context: 'tool_call',
-              name: toolName,
-              callId: call.request.callId,
-              error,
-              errorType: SubagentActivityErrorType.REJECTED,
-            });
-            // Soft rejection: we do NOT set aborted=true, allowing the agent to rethink.
-
-            // Provide the direct instruction to the model as the tool error response.
-            syncResults.set(call.request.callId, {
-              functionResponse: {
-                name: toolName,
-                id: call.request.callId,
-                response: { error },
-              },
-            });
-            continue; // Skip the generic syncResults.set below
-          } else {
-            // Hard abort (Ctrl+C)
-            this.emitActivity('ERROR', {
-              context: 'tool_call',
-              name: toolName,
-              callId: call.request.callId,
-              error: SUBAGENT_CANCELLED_ERROR_MESSAGE,
-              errorType: SubagentActivityErrorType.CANCELLED,
-            });
-            aborted = true;
-          }
+          this.emitActivity('ERROR', {
+            context: 'tool_call',
+            name: toolName,
+            callId: call.request.callId,
+            error: 'Request cancelled.',
+          });
+          aborted = true;
         }
 
-        // Add result to syncResults for other statuses (success, error, hard abort)
+        // Add result to syncResults to preserve order later
         syncResults.set(call.request.callId, call.response.responseParts[0]);
       }
     }
@@ -1384,8 +1335,7 @@ export class LocalAgentExecutor<TOutput extends z.ZodTypeAny> {
 Important Rules:
 * You are running in a non-interactive mode. You CANNOT ask the user for input or clarification.
 * Work systematically using available tools to complete your task.
-* Always use absolute paths for file operations. Construct them using the provided "Environment Context".
-* If a tool call is rejected by the user, acknowledge the rejection, rethink your strategy, and try a different approach. Do not repeatedly attempt the same rejected operation.`;
+* Always use absolute paths for file operations. Construct them using the provided "Environment Context".`;
 
     if (this.definition.outputConfig) {
       finalPrompt += `

packages/core/src/agents/local-invocation.test.ts

@@ -19,8 +19,6 @@ import {
   type SubagentActivityEvent,
   type AgentInputs,
   type SubagentProgress,
-  SubagentActivityErrorType,
-  SUBAGENT_REJECTED_ERROR_PREFIX,
 } from './types.js';
 import { LocalSubagentInvocation } from './local-invocation.js';
 import { LocalAgentExecutor } from './local-executor.js';
@@ -305,48 +303,6 @@ describe('LocalSubagentInvocation', () => {
       );
     });
 
-    it('should reflect tool rejections in the activity stream as cancelled but not abort the agent', async () => {
-      mockExecutorInstance.run.mockImplementation(async () => {
-        const onActivity = MockLocalAgentExecutor.create.mock.calls[0][2];
-
-        if (onActivity) {
-          onActivity({
-            isSubagentActivityEvent: true,
-            agentName: 'MockAgent',
-            type: 'TOOL_CALL_START',
-            data: { name: 'ls', args: {}, callId: 'call1' },
-          } as SubagentActivityEvent);
-          onActivity({
-            isSubagentActivityEvent: true,
-            agentName: 'MockAgent',
-            type: 'ERROR',
-            data: {
-              name: 'ls',
-              callId: 'call1',
-              error: `${SUBAGENT_REJECTED_ERROR_PREFIX} Please acknowledge this, rethink your strategy, and try a different approach. If you cannot proceed without the rejected operation, summarize the issue and use \`complete_task\` to report your findings and the blocker.`,
-              errorType: SubagentActivityErrorType.REJECTED,
-            },
-          } as SubagentActivityEvent);
-        }
-        return {
-          result: 'Rethinking...',
-          terminate_reason: AgentTerminateMode.GOAL,
-        };
-      });
-
-      await invocation.execute(signal, updateOutput);
-
-      expect(updateOutput).toHaveBeenCalledTimes(4);
-      const lastCall = updateOutput.mock.calls[3][0] as SubagentProgress;
-      expect(lastCall.recentActivity).toContainEqual(
-        expect.objectContaining({
-          type: 'tool_call',
-          content: 'ls',
-          status: 'cancelled',
-        }),
-      );
-    });
-
     it('should run successfully without an updateOutput callback', async () => {
       mockExecutorInstance.run.mockImplementation(async () => {
         const onActivity = MockLocalAgentExecutor.create.mock.calls[0][2];

packages/core/src/agents/local-invocation.ts

@@ -18,9 +18,6 @@ import {
   type SubagentProgress,
   type SubagentActivityItem,
   AgentTerminateMode,
-  SubagentActivityErrorType,
-  SUBAGENT_REJECTED_ERROR_PREFIX,
-  SUBAGENT_CANCELLED_ERROR_MESSAGE,
 } from './types.js';
 import { randomUUID } from 'node:crypto';
 import type { MessageBus } from '../confirmation-bus/message-bus.js';
@@ -174,19 +171,12 @@ export class LocalSubagentInvocation extends BaseToolInvocation<
           }
           case 'ERROR': {
             const error = String(activity.data['error']);
-            const errorType = activity.data['errorType'];
-            const isCancellation =
-              errorType === SubagentActivityErrorType.CANCELLED ||
-              error === SUBAGENT_CANCELLED_ERROR_MESSAGE;
-            const isRejection =
-              errorType === SubagentActivityErrorType.REJECTED ||
-              error.startsWith(SUBAGENT_REJECTED_ERROR_PREFIX);
-
+            const isCancellation = error === 'Request cancelled.';
             const toolName = activity.data['name']
               ? String(activity.data['name'])
               : undefined;
 
-            if (toolName && (isCancellation || isRejection)) {
+            if (toolName && isCancellation) {
               for (let i = recentActivity.length - 1; i >= 0; i--) {
                 if (
                   recentActivity[i].type === 'tool_call' &&
@@ -198,27 +188,13 @@ export class LocalSubagentInvocation extends BaseToolInvocation<
                   break;
                 }
               }
-            } else if (toolName) {
-              // Mark non-rejection/non-cancellation errors as 'error'
-              for (let i = recentActivity.length - 1; i >= 0; i--) {
-                if (
-                  recentActivity[i].type === 'tool_call' &&
-                  recentActivity[i].content === toolName &&
-                  recentActivity[i].status === 'running'
-                ) {
-                  recentActivity[i].status = 'error';
-                  updated = true;
-                  break;
-                }
-              }
             }
 
             recentActivity.push({
               id: randomUUID(),
-              type: 'thought',
-              content:
-                isCancellation || isRejection ? error : `Error: ${error}`,
-              status: isCancellation || isRejection ? 'cancelled' : 'error',
+              type: 'thought', // Treat errors as thoughts for now, or add an error type
+              content: isCancellation ? error : `Error: ${error}`,
+              status: isCancellation ? 'cancelled' : 'error',
             });
             updated = true;
             break;

packages/core/src/agents/types.ts

@@ -65,18 +65,6 @@ export type RemoteAgentInputs = { query: string };
 /**
  * Structured events emitted during subagent execution for user observability.
  */
-export enum SubagentActivityErrorType {
-  REJECTED = 'REJECTED',
-  CANCELLED = 'CANCELLED',
-  GENERIC = 'GENERIC',
-}
-
-/**
- * Standard error messages for subagent activities.
- */
-export const SUBAGENT_REJECTED_ERROR_PREFIX = 'User rejected this operation.';
-export const SUBAGENT_CANCELLED_ERROR_MESSAGE = 'Request cancelled.';
-
 export interface SubagentActivityEvent {
   isSubagentActivityEvent: true;
   agentName: string;

packages/core/src/config/config.ts

@@ -649,7 +649,6 @@ export interface ConfigParameters {
   billing?: {
     overageStrategy?: OverageStrategy;
   };
-  simulateUser?: boolean;
 }
 
 export class Config implements McpContext, AgentLoopContext {
@@ -867,7 +866,6 @@ export class Config implements McpContext, AgentLoopContext {
   private lastModeSwitchTime: number = performance.now();
   readonly injectionService: InjectionService;
   private approvedPlanPath: string | undefined;
-  private readonly simulateUser: boolean;
 
   constructor(params: ConfigParameters) {
     this._sessionId = params.sessionId;
@@ -1097,7 +1095,6 @@ export class Config implements McpContext, AgentLoopContext {
     this.fileExclusions = new FileExclusions(this);
     this.eventEmitter = params.eventEmitter;
     this.enableConseca = params.enableConseca ?? false;
-    this.simulateUser = params.simulateUser ?? false;
 
     // Initialize Safety Infrastructure
     const contextBuilder = new ContextBuilder(this);
@@ -2512,10 +2509,6 @@ export class Config implements McpContext, AgentLoopContext {
     return this.usageStatisticsEnabled;
   }
 
-  getSimulateUser(): boolean {
-    return this.simulateUser;
-  }
-
   getAcpMode(): boolean {
     return this.acpMode;
   }

packages/core/src/config/defaultModelConfigs.ts

@@ -277,7 +277,7 @@ export const DEFAULT_MODEL_CONFIGS: ModelConfigServiceConfig = {
       family: 'gemini-3',
       isPreview: true,
       isVisible: true,
-      features: { thinking: true, multimodalToolUse: true },
+      features: { thinking: false, multimodalToolUse: true },
     },
     'gemini-2.5-pro': {
       tier: 'pro',

packages/core/src/core/contentGenerator.test.ts

@@ -725,26 +725,6 @@ describe('createContentGeneratorConfig', () => {
     expect(config.apiKey).toBeUndefined();
     expect(config.vertexai).toBeUndefined();
   });
-  it('should configure for GATEWAY using dummy placeholder if GEMINI_API_KEY is set', async () => {
-    vi.stubEnv('GEMINI_API_KEY', 'env-gemini-key');
-    const config = await createContentGeneratorConfig(
-      mockConfig,
-      AuthType.GATEWAY,
-    );
-    expect(config.apiKey).toBe('gateway-placeholder-key');
-    expect(config.vertexai).toBe(false);
-  });
-
-  it('should configure for GATEWAY using dummy placeholder if GEMINI_API_KEY is not set', async () => {
-    vi.stubEnv('GEMINI_API_KEY', '');
-    vi.mocked(loadApiKey).mockResolvedValue(null);
-    const config = await createContentGeneratorConfig(
-      mockConfig,
-      AuthType.GATEWAY,
-    );
-    expect(config.apiKey).toBe('gateway-placeholder-key');
-    expect(config.vertexai).toBe(false);
-  });
 });
 
 describe('validateBaseUrl', () => {

packages/core/src/core/contentGenerator.ts

@@ -150,13 +150,6 @@ export async function createContentGeneratorConfig(
     return contentGeneratorConfig;
   }
 
-  if (authType === AuthType.GATEWAY) {
-    contentGeneratorConfig.apiKey = apiKey || 'gateway-placeholder-key';
-    contentGeneratorConfig.vertexai = false;
-
-    return contentGeneratorConfig;
-  }
-
   return contentGeneratorConfig;
 }
 

packages/core/src/telemetry/llmRole.ts

@@ -16,5 +16,4 @@ export enum LlmRole {
   UTILITY_EDIT_CORRECTOR = 'utility_edit_corrector',
   UTILITY_AUTOCOMPLETE = 'utility_autocomplete',
   UTILITY_FAST_ACK_HELPER = 'utility_fast_ack_helper',
-  UTILITY_SIMULATOR = 'utility_simulator',
 }

packages/dd.md

@@ -1,72 +0,0 @@
-# User Simulation Feature - Design Document
-
-*Branch: `user-simulation`*
-
-## 1. Overview
-The User Simulation feature enables an autonomous LLM-driven agent to act as a realistic user in interactive terminal sessions. It aims to support integration testing, evaluation, and background evaluation of system capabilities by effectively observing the terminal interface and supplying contextual standard input (stdin). 
-
-This is accomplished by adding a `--simulate-user` option to the CLI, intercepting terminal updates via a simulated stdout reader, computing appropriate responses via an LLM, and piping these directly into a `PassThrough` stream masquerading as `process.stdin`.
-
-## 2. Core Architecture
-
-### 2.1 Configurations and Triggers
-**Affected Files:**
-- `packages/cli/src/config/config.ts`
-- `packages/core/src/config/config.ts`
-- `packages/cli/src/interactiveCli.tsx`
-
-**Implementation:**
-The feature is controlled via the explicit CLI argument `--simulate-user`. When supplied, the argument flows through the `Config` interface (`config.getSimulateUser()`), modifying how the interactive CLI bootstraps.
-- Instead of attaching the raw `process.stdin` directly to the `ink` render environment, the UI engine binds to a Node.js `PassThrough` stream if simulation is enabled.
-- The Interactive CLI session begins by initiating the `UserSimulator`, providing it access to the `Config`, the `simulatedStdin` buffer, and an observable snapshot of the `lastFrame` (the current state of the UI render).
-
-### 2.2 The `UserSimulator` Service
-**Affected Files:**
-- `packages/cli/src/services/UserSimulator.ts`
-
-**Implementation:**
-The `UserSimulator` class governs the core observation and input loops. It handles interactions asynchronously outside of the primary command execution flow.
-
-#### Loop Execution
-The simulator runs via a repeating timer (3-second intervals `setInterval`), checking `tick()`. It ensures only one evaluation happens sequentially using a mutex lock (`this.isProcessing`).
-
-#### Screen Processing and Environment Context
-The engine receives the rendered terminal snapshot (`lastFrame`) and applies sanitizations:
-- Removes ANSI terminal colors and cursor properties using regex filtering.
-- Strips variable UI animation symbols (Spinners like ⠋, ⠙) and time indicators (e.g., `[ 7s ]`).
-These visual stability checks allow the simulator to detect meaningful frame changes instead of being repeatedly triggered by minor clock updates.
-
-#### Simulation Brain & LLM Integration
-The simulator utilizes `PREVIEW_GEMINI_FLASH_MODEL`, leveraging the newly configured `thinking: true` capacity (`packages/core/src/config/defaultModelConfigs.ts`) for better reasoning, operating under the distinct telemetry role `LlmRole.UTILITY_SIMULATOR`.
-
-The LLM is provided an extensive context schema encapsulating:
-- **Terminal output:** Current stripped terminal representation.
-- **Original task objective:** The intention of the CLI session.
-- **Action Memory:** A tracked sequence (`actionHistory`) of previously executed actions to avoid getting stuck in inquiry loops.
-
-#### State Machine Interpretation
-The model translates the screen context into specific behavioral states:
-- **STATE 1 (WAIT):** Triggered if any indication of internal "thinking" or processing exists (active spinners/timers). Returns `<WAIT>`.
-- **STATE 2 (ACTION/AUTHORIZATION):** Prompt requests an approval (e.g., "Allow execution"). Supplies strict raw choice input.
-- **STATE 3 (DONE):** Fully idle string detection paired with task completion fulfillment. Gracefully types `Thank you\r` and eventually exits indicating `<DONE>`.
-- **STATE 4 (INPUT):** Idle state where continuation text instruction is needed, supplying direct commands injected to stdin.
-
-#### Safeguards and Debugging
-- **Anti-Stall Mechanism:** The simulator tracks repetitive actions. If the LLM repeats the exact same non-empty interaction `MAX_REPEATS` (3) times, it terminates the process abruptly to prevent infinite loops.
-- **Interaction Transcripts:** Binds an audit log, dumping each parsed `[SIMULATOR] Screen Content Seen` block, the constructed `Prompt Used`, and `Raw model response` to discrete contextual `interactions_<timestamp>.txt` files, making it traceable.
-
-### 2.3 Required Ecosystem Changes
-- `packages/core/src/telemetry/llmRole.ts`: A new internal trace role `UTILITY_SIMULATOR` has been appended to separate evaluation events from main-thread generations.
-- `packages/core/src/config/defaultModelConfigs.ts`: Added dynamic thought logic parameter (`thinking: true`) for `gemini-3-flash-preview` to enhance the simulation depth reasoning.
-- Unit Testing Mocks: Updated dummy interface `mockConfig.ts` to ensure compatibility by safely mocking `getSimulateUser`.
-
-## 3. Workflow Summary
-1. The user launches `gemini --simulate-user`.
-2. Interactive UI bindings swap `process.stdin` for a readable `PassThrough` stream.
-3. Every 3 seconds, `UserSimulator.tick()` accesses the newest render frame. 
-4. The frame is stripped of unstable metrics/spinners. If the clean frame is unchanged since the last tick, it waits.
-5. If changed, the simulator invokes Gemini Flash Preview (Thinking).
-6. Gemini observes the state—emitting `<WAIT>` if busy, action keys for selections, `<DONE>` if completed, or commands to be resolved.
-7. Return text is piped cleanly back to `simulatedStdin`—advancing the ink render state.
-
-*This design effectively encapsulates the user interface flow without imposing side-effects on standard operations.*

packages/vscode-ide-companion/package.json

@@ -129,7 +129,7 @@
     "@types/vscode": "^1.99.0",
     "@typescript-eslint/eslint-plugin": "^8.31.1",
     "@typescript-eslint/parser": "^8.31.1",
-    "@vscode/vsce": "^3.7.1",
+    "@vscode/vsce": "^3.6.0",
     "esbuild": "^0.25.3",
     "eslint": "^9.25.1",
     "npm-run-all2": "^8.0.2",