@google/gemini-cli-core 0.10.0-nightly.20250926.1487841d → 0.10.0-nightly.20251009.ae02236c

package/README.md

@@ -7,16 +7,21 @@
 
 ![Gemini CLI Screenshot](./docs/assets/gemini-screenshot.png)
 
-Gemini CLI is an open-source AI agent that brings the power of Gemini directly into your terminal. It provides lightweight access to Gemini, giving you the most direct path from your prompt to our model.
+Gemini CLI is an open-source AI agent that brings the power of Gemini directly
+into your terminal. It provides lightweight access to Gemini, giving you the
+most direct path from your prompt to our model.
 
 ## 🚀 Why Gemini CLI?
 
-- **🎯 Free tier**: 60 requests/min and 1,000 requests/day with personal Google account
-- **🧠 Powerful Gemini 2.5 Pro**: Access to 1M token context window
-- **🔧 Built-in tools**: Google Search grounding, file operations, shell commands, web fetching
-- **🔌 Extensible**: MCP (Model Context Protocol) support for custom integrations
-- **💻 Terminal-first**: Designed for developers who live in the command line
-- **🛡️ Open source**: Apache 2.0 licensed
+- **🎯 Free tier**: 60 requests/min and 1,000 requests/day with personal Google
+  account.
+- **🧠 Powerful Gemini 2.5 Pro**: Access to 1M token context window.
+- **🔧 Built-in tools**: Google Search grounding, file operations, shell
+  commands, web fetching.
+- **🔌 Extensible**: MCP (Model Context Protocol) support for custom
+  integrations.
+- **💻 Terminal-first**: Designed for developers who live in the command line.
+- **🛡️ Open source**: Apache 2.0 licensed.
 
 ## 📦 Installation
 
@@ -52,7 +57,9 @@ See [Releases](./docs/releases.md) for more details.
 
 ### Preview
 
-New preview releases will be published each week at UTC 2359 on Tuesdays. These releases will not have been fully vetted and may contain regressions or other outstanding issues. Please help us test and install with `preview` tag.
+New preview releases will be published each week at UTC 2359 on Tuesdays. These
+releases will not have been fully vetted and may contain regressions or other
+outstanding issues. Please help us test and install with `preview` tag.
 
 ```bash
 npm install -g @google/gemini-cli@preview
@@ -60,7 +67,9 @@ npm install -g @google/gemini-cli@preview
 
 ### Stable
 
-- New stable releases will be published each week at UTC 2000 on Tuesdays, this will be the full promotion of last week's `preview` release + any bug fixes and validations. Use `latest` tag.
+- New stable releases will be published each week at UTC 2000 on Tuesdays, this
+  will be the full promotion of last week's `preview` release + any bug fixes
+  and validations. Use `latest` tag.
 
 ```bash
 npm install -g @google/gemini-cli@latest
@@ -68,7 +77,9 @@ npm install -g @google/gemini-cli@latest
 
 ### Nightly
 
-- New releases will be published each week at UTC 0000 each day, This will be all changes from the main branch as represented at time of release. It should be assumed there are pending validations and issues. Use `nightly` tag.
+- New releases will be published each week at UTC 0000 each day, This will be
+  all changes from the main branch as represented at time of release. It should
+  be assumed there are pending validations and issues. Use `nightly` tag.
 
 ```bash
 npm install -g @google/gemini-cli@nightly
@@ -84,24 +95,33 @@ npm install -g @google/gemini-cli@nightly
 
 ### Automation & Integration
 
-- Automate operational tasks like querying pull requests or handling complex rebases
-- Use MCP servers to connect new capabilities, including [media generation with Imagen, Veo or Lyria](https://github.com/GoogleCloudPlatform/vertex-ai-creative-studio/tree/main/experiments/mcp-genmedia)
+- Automate operational tasks like querying pull requests or handling complex
+  rebases
+- Use MCP servers to connect new capabilities, including
+  [media generation with Imagen, Veo or Lyria](https://github.com/GoogleCloudPlatform/vertex-ai-creative-studio/tree/main/experiments/mcp-genmedia)
 - Run non-interactively in scripts for workflow automation
 
 ### Advanced Capabilities
 
-- Ground your queries with built-in [Google Search](https://ai.google.dev/gemini-api/docs/grounding) for real-time information
+- Ground your queries with built-in
+  [Google Search](https://ai.google.dev/gemini-api/docs/grounding) for real-time
+  information
 - Conversation checkpointing to save and resume complex sessions
 - Custom context files (GEMINI.md) to tailor behavior for your projects
 
 ### GitHub Integration
 
-Integrate Gemini CLI directly into your GitHub workflows with [**Gemini CLI GitHub Action**](https://github.com/google-github-actions/run-gemini-cli):
+Integrate Gemini CLI directly into your GitHub workflows with
+[**Gemini CLI GitHub Action**](https://github.com/google-github-actions/run-gemini-cli):
 
-- **Pull Request Reviews**: Automated code review with contextual feedback and suggestions
-- **Issue Triage**: Automated labeling and prioritization of GitHub issues based on content analysis
-- **On-demand Assistance**: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation
-- **Custom Workflows**: Build automated, scheduled and on-demand workflows tailored to your team's needs
+- **Pull Request Reviews**: Automated code review with contextual feedback and
+  suggestions
+- **Issue Triage**: Automated labeling and prioritization of GitHub issues based
+  on content analysis
+- **On-demand Assistance**: Mention `@gemini-cli` in issues and pull requests
+  for help with debugging, explanations, or task delegation
+- **Custom Workflows**: Build automated, scheduled and on-demand workflows
+  tailored to your team's needs
 
 ## 🔐 Authentication Options
 
@@ -109,20 +129,17 @@ Choose the authentication method that best fits your needs:
 
 ### Option 1: Login with Google (OAuth login using your Google Account)
 
-**✨ Best for:**
-
-- Individual developers.
-- Google AI Pro and AI Ultra subscribers.
-- Anyone who has a Gemini Code Assist license.
-
-_See [quota limits and terms of service](https://cloud.google.com/gemini/docs/quotas) for details._
+**✨ Best for:** Individual developers as well as anyone who has a Gemini Code
+Assist License. (see
+[quota limits and terms of service](https://cloud.google.com/gemini/docs/quotas)
+for details)
 
 **Benefits:**
 
-- **Free tier** with 60 requests/min and 1,000 requests/day
-- **Gemini 2.5 Pro and Flash** with 1M token context window
+- **Free tier**: 60 requests/min and 1,000 requests/day
+- **Gemini 2.5 Pro** with 1M token context window
 - **No API key management** - just sign in with your Google account
-- **Automatic updates** to our latest models
+- **Automatic updates** to latest models
 
 #### Start Gemini CLI, then choose _Login with Google_ and follow the browser authentication flow when prompted
 
@@ -134,7 +151,7 @@ gemini
 
 ```bash
 # Set your Google Cloud Project
-export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_NAME"
+export GOOGLE_CLOUD_PROJECT="YOUR_PROJECT_ID"
 gemini
 ```
 
@@ -171,7 +188,8 @@ export GOOGLE_GENAI_USE_VERTEXAI=true
 gemini
 ```
 
-For Google Workspace accounts and other authentication methods, see the [authentication guide](./docs/cli/authentication.md).
+For Google Workspace accounts and other authentication methods, see the
+[authentication guide](./docs/get-started/authentication.md).
 
 ## 🚀 Getting Started
 
@@ -233,17 +251,26 @@ gemini
 
 ### Getting Started
 
-- [**Quickstart Guide**](./docs/cli/index.md) - Get up and running quickly
-- [**Authentication Setup**](./docs/cli/authentication.md) - Detailed auth configuration
-- [**Configuration Guide**](./docs/cli/configuration.md) - Settings and customization
-- [**Keyboard Shortcuts**](./docs/keyboard-shortcuts.md) - Productivity tips
+- [**Quickstart Guide**](./docs/get-started/index.md) - Get up and running
+  quickly.
+- [**Authentication Setup**](./docs/get-started/authentication.md) - Detailed
+  auth configuration.
+- [**Configuration Guide**](./docs/get-started/configuration.md) - Settings and
+  customization.
+- [**Keyboard Shortcuts**](./docs/cli/keyboard-shortcuts.md) - Productivity
+  tips.
 
 ### Core Features
 
-- [**Commands Reference**](./docs/cli/commands.md) - All slash commands (`/help`, `/chat`, `/mcp`, etc.)
-- [**Checkpointing**](./docs/checkpointing.md) - Save and resume conversations
-- [**Memory Management**](./docs/tools/memory.md) - Using GEMINI.md context files
-- [**Token Caching**](./docs/cli/token-caching.md) - Optimize token usage
+- [**Commands Reference**](./docs/cli/commands.md) - All slash commands
+  (`/help`, `/chat`, etc).
+- [**Custom Commands**](./docs/cli/custom-commands.md) - Create your own
+  reusable commands.
+- [**Context Files (GEMINI.md)**](./docs/cli/gemini-md.md) - Provide persistent
+  context to Gemini CLI.
+- [**Checkpointing**](./docs/cli/checkpointing.md) - Save and resume
+  conversations.
+- [**Token Caching**](./docs/cli/token-caching.md) - Optimize token usage.
 
 ### Tools & Extensions
 
@@ -251,35 +278,37 @@ gemini
   - [File System Operations](./docs/tools/file-system.md)
   - [Shell Commands](./docs/tools/shell.md)
   - [Web Fetch & Search](./docs/tools/web-fetch.md)
-  - [Multi-file Operations](./docs/tools/multi-file.md)
-- [**MCP Server Integration**](./docs/tools/mcp-server.md) - Extend with custom tools
-- [**Custom Extensions**](./docs/extension.md) - Build your own commands
+- [**MCP Server Integration**](./docs/tools/mcp-server.md) - Extend with custom
+  tools.
+- [**Custom Extensions**](./docs/extensions/index.md) - Build and share your own
+  commands.
 
 ### Advanced Topics
 
-- [**Architecture Overview**](./docs/architecture.md) - How Gemini CLI works
-- [**IDE Integration**](./docs/ide-integration.md) - VS Code companion
-- [**Sandboxing & Security**](./docs/sandbox.md) - Safe execution environments
-- [**Enterprise Deployment**](./docs/deployment.md) - Docker, system-wide config
-- [**Telemetry & Monitoring**](./docs/telemetry.md) - Usage tracking
-- [**Tools API Development**](./docs/core/tools-api.md) - Create custom tools
-
-### Configuration & Customization
-
-- [**Settings Reference**](./docs/cli/configuration.md) - All configuration options
-- [**Theme Customization**](./docs/cli/themes.md) - Visual customization
-- [**.gemini Directory**](./docs/gemini-ignore.md) - Project-specific settings
-- [**Environment Variables**](./docs/cli/configuration.md#environment-variables)
+- [**Headless Mode (Scripting)**](./docs/cli/headless.md) - Use Gemini CLI in
+  automated workflows.
+- [**Architecture Overview**](./docs/architecture.md) - How Gemini CLI works.
+- [**IDE Integration**](./docs/ide-integration/index.md) - VS Code companion.
+- [**Sandboxing & Security**](./docs/cli/sandbox.md) - Safe execution
+  environments.
+- [**Trusted Folders**](./docs/cli/trusted-folders.md) - Control execution
+  policies by folder.
+- [**Enterprise Guide**](./docs/cli/enterprise.md) - Deploy and manage in a
+  corporate environment.
+- [**Telemetry & Monitoring**](./docs/cli/telemetry.md) - Usage tracking.
+- [**Tools API Development**](./docs/core/tools-api.md) - Create custom tools.
 
 ### Troubleshooting & Support
 
-- [**Troubleshooting Guide**](./docs/troubleshooting.md) - Common issues and solutions
-- [**FAQ**](./docs/troubleshooting.md#frequently-asked-questions) - Quick answers
-- Use `/bug` command to report issues directly from the CLI
+- [**Troubleshooting Guide**](./docs/troubleshooting.md) - Common issues and
+  solutions.
+- [**FAQ**](./docs/faq.md) - Frequently asked questions.
+- Use `/bug` command to report issues directly from the CLI.
 
 ### Using MCP Servers
 
-Configure MCP servers in `~/.gemini/settings.json` to extend Gemini CLI with custom tools:
+Configure MCP servers in `~/.gemini/settings.json` to extend Gemini CLI with
+custom tools:
 
 ```text
 > @github List my open pull requests
@@ -287,31 +316,39 @@ Configure MCP servers in `~/.gemini/settings.json` to extend Gemini CLI with cus
 > @database Run a query to find inactive users
 ```
 
-See the [MCP Server Integration guide](./docs/tools/mcp-server.md) for setup instructions.
+See the [MCP Server Integration guide](./docs/tools/mcp-server.md) for setup
+instructions.
 
 ## 🤝 Contributing
 
-We welcome contributions! Gemini CLI is fully open source (Apache 2.0), and we encourage the community to:
+We welcome contributions! Gemini CLI is fully open source (Apache 2.0), and we
+encourage the community to:
 
-- Report bugs and suggest features
-- Improve documentation
-- Submit code improvements
-- Share your MCP servers and extensions
+- Report bugs and suggest features.
+- Improve documentation.
+- Submit code improvements.
+- Share your MCP servers and extensions.
 
-See our [Contributing Guide](./CONTRIBUTING.md) for development setup, coding standards, and how to submit pull requests.
+See our [Contributing Guide](./CONTRIBUTING.md) for development setup, coding
+standards, and how to submit pull requests.
 
-Check our [Official Roadmap](https://github.com/orgs/google-gemini/projects/11/) for planned features and priorities.
+Check our [Official Roadmap](https://github.com/orgs/google-gemini/projects/11)
+for planned features and priorities.
 
 ## 📖 Resources
 
-- **[Official Roadmap](./ROADMAP.md)** - See what's coming next
-- **[NPM Package](https://www.npmjs.com/package/@google/gemini-cli)** - Package registry
-- **[GitHub Issues](https://github.com/google-gemini/gemini-cli/issues)** - Report bugs or request features
-- **[Security Advisories](https://github.com/google-gemini/gemini-cli/security/advisories)** - Security updates
+- **[Official Roadmap](./ROADMAP.md)** - See what's coming next.
+- **[Changelog](./docs/changelogs/index.md)** - See recent notable updates.
+- **[NPM Package](https://www.npmjs.com/package/@google/gemini-cli)** - Package
+  registry.
+- **[GitHub Issues](https://github.com/google-gemini/gemini-cli/issues)** -
+  Report bugs or request features.
+- **[Security Advisories](https://github.com/google-gemini/gemini-cli/security/advisories)** -
+  Security updates.
 
 ### Uninstall
 
-See the [Uninstall Guide](docs/Uninstall.md) for removal instructions.
+See the [Uninstall Guide](docs/cli/uninstall.md) for removal instructions.
 
 ## 📄 Legal
 

package/dist/index.d.ts

@@ -15,3 +15,5 @@ export { makeFakeConfig } from './src/test-utils/config.js';
 export * from './src/utils/pathReader.js';
 export { ClearcutLogger } from './src/telemetry/clearcut-logger/clearcut-logger.js';
 export { logModelSlashCommand } from './src/telemetry/loggers.js';
+export * from './src/utils/googleQuotaErrors.js';
+export type { GoogleApiError } from './src/utils/googleErrors.js';

package/dist/index.js

@@ -15,4 +15,5 @@ export { makeFakeConfig } from './src/test-utils/config.js';
 export * from './src/utils/pathReader.js';
 export { ClearcutLogger } from './src/telemetry/clearcut-logger/clearcut-logger.js';
 export { logModelSlashCommand } from './src/telemetry/loggers.js';
+export * from './src/utils/googleQuotaErrors.js';
 //# sourceMappingURL=index.js.map

package/dist/index.js.map

@@ -1 +1 @@
-{"version":3,"file":"index.js","sourceRoot":"","sources":["../index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,cAAc,gBAAgB,CAAC;AAC/B,OAAO,EAAE,OAAO,EAAE,MAAM,yBAAyB,CAAC;AAClD,OAAO,EACL,oBAAoB,EACpB,yBAAyB,EACzB,0BAA0B,EAC1B,+BAA+B,EAC/B,8BAA8B,GAC/B,MAAM,wBAAwB,CAAC;AAChC,OAAO,EACL,yBAAyB,GAI1B,MAAM,mCAAmC,CAAC;AAC3C,OAAO,EACL,kCAAkC,EAClC,sCAAsC,GACvC,MAAM,wBAAwB,CAAC;AAChC,OAAO,EAAE,gBAAgB,EAAE,MAAM,yBAAyB,CAAC;AAC3D,OAAO,EACL,kBAAkB,EAClB,gBAAgB,EAChB,mBAAmB,GACpB,MAAM,4BAA4B,CAAC;AAEpC,OAAO,EACL,kBAAkB,EAClB,iBAAiB,EACjB,qBAAqB,EACrB,qBAAqB,EACrB,oBAAoB,EACpB,uBAAuB,EACvB,sBAAsB,GACvB,MAAM,0BAA0B,CAAC;AAClC,OAAO,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAC;AAC5D,cAAc,2BAA2B,CAAC;AAC1C,OAAO,EAAE,cAAc,EAAE,MAAM,oDAAoD,CAAC;AACpF,OAAO,EAAE,oBAAoB,EAAE,MAAM,4BAA4B,CAAC"}
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,cAAc,gBAAgB,CAAC;AAC/B,OAAO,EAAE,OAAO,EAAE,MAAM,yBAAyB,CAAC;AAClD,OAAO,EACL,oBAAoB,EACpB,yBAAyB,EACzB,0BAA0B,EAC1B,+BAA+B,EAC/B,8BAA8B,GAC/B,MAAM,wBAAwB,CAAC;AAChC,OAAO,EACL,yBAAyB,GAI1B,MAAM,mCAAmC,CAAC;AAC3C,OAAO,EACL,kCAAkC,EAClC,sCAAsC,GACvC,MAAM,wBAAwB,CAAC;AAChC,OAAO,EAAE,gBAAgB,EAAE,MAAM,yBAAyB,CAAC;AAC3D,OAAO,EACL,kBAAkB,EAClB,gBAAgB,EAChB,mBAAmB,GACpB,MAAM,4BAA4B,CAAC;AAEpC,OAAO,EACL,kBAAkB,EAClB,iBAAiB,EACjB,qBAAqB,EACrB,qBAAqB,EACrB,oBAAoB,EACpB,uBAAuB,EACvB,sBAAsB,GACvB,MAAM,0BAA0B,CAAC;AAClC,OAAO,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAC;AAC5D,cAAc,2BAA2B,CAAC;AAC1C,OAAO,EAAE,cAAc,EAAE,MAAM,oDAAoD,CAAC;AACpF,OAAO,EAAE,oBAAoB,EAAE,MAAM,4BAA4B,CAAC;AAClE,cAAc,kCAAkC,CAAC"}

package/dist/src/agents/codebase-investigator.d.ts

@@ -0,0 +1,46 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+import type { AgentDefinition } from './types.js';
+import { z } from 'zod';
+declare const CodebaseInvestigationReportSchema: z.ZodObject<{
+    SummaryOfFindings: z.ZodString;
+    ExplorationTrace: z.ZodArray<z.ZodString, "many">;
+    RelevantLocations: z.ZodArray<z.ZodObject<{
+        FilePath: z.ZodString;
+        Reasoning: z.ZodString;
+        KeySymbols: z.ZodArray<z.ZodString, "many">;
+    }, "strip", z.ZodTypeAny, {
+        FilePath: string;
+        Reasoning: string;
+        KeySymbols: string[];
+    }, {
+        FilePath: string;
+        Reasoning: string;
+        KeySymbols: string[];
+    }>, "many">;
+}, "strip", z.ZodTypeAny, {
+    SummaryOfFindings: string;
+    ExplorationTrace: string[];
+    RelevantLocations: {
+        FilePath: string;
+        Reasoning: string;
+        KeySymbols: string[];
+    }[];
+}, {
+    SummaryOfFindings: string;
+    ExplorationTrace: string[];
+    RelevantLocations: {
+        FilePath: string;
+        Reasoning: string;
+        KeySymbols: string[];
+    }[];
+}>;
+/**
+ * A Proof-of-Concept subagent specialized in analyzing codebase structure,
+ * dependencies, and technologies.
+ */
+export declare const CodebaseInvestigatorAgent: AgentDefinition<typeof CodebaseInvestigationReportSchema>;
+export {};

package/dist/src/agents/codebase-investigator.js

@@ -0,0 +1,136 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+import { LSTool } from '../tools/ls.js';
+import { ReadFileTool } from '../tools/read-file.js';
+import { GLOB_TOOL_NAME } from '../tools/tool-names.js';
+import { GrepTool } from '../tools/grep.js';
+import { DEFAULT_GEMINI_MODEL } from '../config/models.js';
+import { z } from 'zod';
+// Define a type that matches the outputConfig schema for type safety.
+const CodebaseInvestigationReportSchema = z.object({
+    SummaryOfFindings: z
+        .string()
+        .describe("A summary of the investigation's conclusions and insights for the main agent."),
+    ExplorationTrace: z
+        .array(z.string())
+        .describe('A step-by-step list of actions and tools used during the investigation.'),
+    RelevantLocations: z
+        .array(z.object({
+        FilePath: z.string(),
+        Reasoning: z.string(),
+        KeySymbols: z.array(z.string()),
+    }))
+        .describe('A list of relevant files and the key symbols within them.'),
+});
+/**
+ * A Proof-of-Concept subagent specialized in analyzing codebase structure,
+ * dependencies, and technologies.
+ */
+export const CodebaseInvestigatorAgent = {
+    name: 'codebase_investigator',
+    displayName: 'Codebase Investigator Agent',
+    description: `Your primary tool for multifile search tasks and codebase exploration. 
+    Invoke this tool to delegate search tasks to an autonomous subagent. 
+    Use this to find features, understand context, or locate specific files, functions, or symbols. 
+    Returns a structured Json report with key file paths, symbols, architectural map and insights to solve a task or answer questions`,
+    inputConfig: {
+        inputs: {
+            objective: {
+                description: `A comprehensive and detailed description of the user's ultimate goal. 
+          You must include original user's objective as well as questions and any extra context and questions you may have.`,
+                type: 'string',
+                required: true,
+            },
+        },
+    },
+    outputConfig: {
+        outputName: 'report',
+        description: 'The final investigation report as a JSON object.',
+        schema: CodebaseInvestigationReportSchema,
+    },
+    // The 'output' parameter is now strongly typed as CodebaseInvestigationReportSchema
+    processOutput: (output) => JSON.stringify(output, null, 2),
+    modelConfig: {
+        model: DEFAULT_GEMINI_MODEL,
+        temp: 0.1,
+        top_p: 0.95,
+        thinkingBudget: -1,
+    },
+    runConfig: {
+        max_time_minutes: 5,
+        max_turns: 15,
+    },
+    toolConfig: {
+        // Grant access only to read-only tools.
+        tools: [LSTool.Name, ReadFileTool.Name, GLOB_TOOL_NAME, GrepTool.Name],
+    },
+    promptConfig: {
+        query: `Your task is to do a deep investigation of the codebase to find all relevant files, code locations, architectural mental map and insights to solve  for the following user objective:
+<objective>
+\${objective}
+</objective>`,
+        systemPrompt: `You are **Codebase Investigator**, a hyper-specialized AI agent and an expert in reverse-engineering complex software projects. You are a sub-agent within a larger development system.
+Your **SOLE PURPOSE** is to build a complete mental model of the code relevant to a given investigation. You must identify all relevant files, understand their roles, and foresee the direct architectural consequences of potential changes.
+You are a sub-agent in a larger system. Your only responsibility is to provide deep, actionable context.
+- **DO:** Find the key modules, classes, and functions that are part of the problem and its solution.
+- **DO:** Understand *why* the code is written the way it is. Question everything.
+- **DO:** Foresee the ripple effects of a change. If \`function A\` is modified, you must check its callers. If a data structure is altered, you must identify where its type definitions need to be updated.
+- **DO:** provide a conclusion and insights to the main agent that invoked you. If the agent is trying to solve a bug, you should provide the root cause of the bug, its impacts, how to fix it etc. If it's a new feature, you should provide insights on where to implement it, what chagnes are necessary etc. 
+- **DO NOT:** Write the final implementation code yourself.
+- **DO NOT:** Stop at the first relevant file. Your goal is a comprehensive understanding of the entire relevant subsystem.
+You operate in a non-interactive loop and must reason based on the information provided and the output of your tools.
+---
+## Core Directives
+<RULES>
+1.  **DEEP ANALYSIS, NOT JUST FILE FINDING:** Your goal is to understand the *why* behind the code. Don't just list files; explain their purpose and the role of their key components. Your final report should empower another agent to make a correct and complete fix.
+2.  **SYSTEMATIC & CURIOUS EXPLORATION:** Start with high-value clues (like tracebacks or ticket numbers) and broaden your search as needed. Think like a senior engineer doing a code review. An initial file contains clues (imports, function calls, puzzling logic). **If you find something you don't understand, you MUST prioritize investigating it until it is clear.** Treat confusion as a signal to dig deeper.
+3.  **HOLISTIC & PRECISE:** Your goal is to find the complete and minimal set of locations that need to be understood or changed. Do not stop until you are confident you have considered the side effects of a potential fix (e.g., type errors, breaking changes to callers, opportunities for code reuse).
+4.  **Web Search:** You are allowed to use the \`web_fetch\` tool to research libraries, language features, or concepts you don't understand (e.g., "what does gettext.translation do with localedir=None?").
+</RULES>
+---
+## Scratchpad Management
+**This is your most critical function. Your scratchpad is your memory and your plan.**
+1.  **Initialization:** On your very first turn, you **MUST** create the \`<scratchpad>\` section. Analyze the \`task\` and create an initial \`Checklist\` of investigation goals and a \`Questions to Resolve\` section for any initial uncertainties.
+2.  **Constant Updates:** After **every** \`<OBSERVATION>\`, you **MUST** update the scratchpad.
+    * Mark checklist items as complete: \`[x]\`.
+    * Add new checklist items as you trace the architecture.
+    * **Explicitly log questions in \`Questions to Resolve\`** (e.g., \`[ ] What is the purpose of the 'None' element in this list?\`). Do not consider your investigation complete until this list is empty.
+    * Record \`Key Findings\` with file paths and notes about their purpose and relevance.
+    * Update \`Irrelevant Paths to Ignore\` to avoid re-investigating dead ends.
+3.  **Thinking on Paper:** The scratchpad must show your reasoning process, including how you resolve your questions.
+---
+## Termination
+Your mission is complete **ONLY** when your \`Questions to Resolve\` list is empty and you have identified all files and necessary change *considerations*.
+When you are finished, you **MUST** call the \`complete_task\` tool. The \`report\` argument for this tool **MUST** be a valid JSON object containing your findings.
+
+**Example of the final report**
+\`\`\`json
+{
+  "SummaryOfFindings": "The core issue is a race condition in the \`updateUser\` function. The function reads the user's state, performs an asynchronous operation, and then writes the state back. If another request modifies the user state during the async operation, that change will be overwritten. The fix requires implementing a transactional read-modify-write pattern, potentially using a database lock or a versioning system.",
+  "ExplorationTrace": [
+    "Used \`grep\` to search for \`updateUser\` to locate the primary function.",
+    "Read the file \`src/controllers/userController.js\` to understand the function's logic.",
+    "Used \`ls -R\` to look for related files, such as services or database models.",
+    "Read \`src/services/userService.js\` and \`src/models/User.js\` to understand the data flow and how state is managed."
+  ],
+  "RelevantLocations": [
+    {
+      "FilePath": "src/controllers/userController.js",
+      "Reasoning": "This file contains the \`updateUser\` function which has the race condition. It's the entry point for the problematic logic.",
+      "KeySymbols": ["updateUser", "getUser", "saveUser"]
+    },
+    {
+      "FilePath": "src/services/userService.js",
+      "Reasoning": "This service is called by the controller and handles the direct interaction with the data layer. Any locking mechanism would likely be implemented here.",
+      "KeySymbols": ["updateUserData"]
+    }
+  ]
+}
+\`\`\`
+`,
+    },
+};
+//# sourceMappingURL=codebase-investigator.js.map

package/dist/src/agents/codebase-investigator.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"codebase-investigator.js","sourceRoot":"","sources":["../../../src/agents/codebase-investigator.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAGH,OAAO,EAAE,MAAM,EAAE,MAAM,gBAAgB,CAAC;AACxC,OAAO,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAC;AACrD,OAAO,EAAE,cAAc,EAAE,MAAM,wBAAwB,CAAC;AACxD,OAAO,EAAE,QAAQ,EAAE,MAAM,kBAAkB,CAAC;AAC5C,OAAO,EAAE,oBAAoB,EAAE,MAAM,qBAAqB,CAAC;AAC3D,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAExB,sEAAsE;AACtE,MAAM,iCAAiC,GAAG,CAAC,CAAC,MAAM,CAAC;IACjD,iBAAiB,EAAE,CAAC;SACjB,MAAM,EAAE;SACR,QAAQ,CACP,+EAA+E,CAChF;IACH,gBAAgB,EAAE,CAAC;SAChB,KAAK,CAAC,CAAC,CAAC,MAAM,EAAE,CAAC;SACjB,QAAQ,CACP,yEAAyE,CAC1E;IACH,iBAAiB,EAAE,CAAC;SACjB,KAAK,CACJ,CAAC,CAAC,MAAM,CAAC;QACP,QAAQ,EAAE,CAAC,CAAC,MAAM,EAAE;QACpB,SAAS,EAAE,CAAC,CAAC,MAAM,EAAE;QACrB,UAAU,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,MAAM,EAAE,CAAC;KAChC,CAAC,CACH;SACA,QAAQ,CAAC,2DAA2D,CAAC;CACzE,CAAC,CAAC;AAEH;;;GAGG;AACH,MAAM,CAAC,MAAM,yBAAyB,GAElC;IACF,IAAI,EAAE,uBAAuB;IAC7B,WAAW,EAAE,6BAA6B;IAC1C,WAAW,EAAE;;;sIAGuH;IACpI,WAAW,EAAE;QACX,MAAM,EAAE;YACN,SAAS,EAAE;gBACT,WAAW,EAAE;4HACuG;gBACpH,IAAI,EAAE,QAAQ;gBACd,QAAQ,EAAE,IAAI;aACf;SACF;KACF;IACD,YAAY,EAAE;QACZ,UAAU,EAAE,QAAQ;QACpB,WAAW,EAAE,kDAAkD;QAC/D,MAAM,EAAE,iCAAiC;KAC1C;IAED,oFAAoF;IACpF,aAAa,EAAE,CAAC,MAAM,EAAE,EAAE,CAAC,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC;IAE1D,WAAW,EAAE;QACX,KAAK,EAAE,oBAAoB;QAC3B,IAAI,EAAE,GAAG;QACT,KAAK,EAAE,IAAI;QACX,cAAc,EAAE,CAAC,CAAC;KACnB;IAED,SAAS,EAAE;QACT,gBAAgB,EAAE,CAAC;QACnB,SAAS,EAAE,EAAE;KACd;IAED,UAAU,EAAE;QACV,wCAAwC;QACxC,KAAK,EAAE,CAAC,MAAM,CAAC,IAAI,EAAE,YAAY,CAAC,IAAI,EAAE,cAAc,EAAE,QAAQ,CAAC,IAAI,CAAC;KACvE;IAED,YAAY,EAAE;QACZ,KAAK,EAAE;;;aAGE;QACT,YAAY,EAAE;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA0DjB;KACE;CACF,CAAC"}

package/dist/src/agents/executor.d.ts

@@ -0,0 +1,92 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+import type { Config } from '../config/config.js';
+import type { AgentDefinition, AgentInputs, OutputObject, SubagentActivityEvent } from './types.js';
+import { type z } from 'zod';
+/** A callback function to report on agent activity. */
+export type ActivityCallback = (activity: SubagentActivityEvent) => void;
+/**
+ * Executes an agent loop based on an {@link AgentDefinition}.
+ *
+ * This executor runs the agent in a loop, calling tools until it calls the
+ * mandatory `complete_task` tool to signal completion.
+ */
+export declare class AgentExecutor<TOutput extends z.ZodTypeAny> {
+    readonly definition: AgentDefinition<TOutput>;
+    private readonly agentId;
+    private readonly toolRegistry;
+    private readonly runtimeContext;
+    private readonly onActivity?;
+    /**
+     * Creates and validates a new `AgentExecutor` instance.
+     *
+     * This method ensures that all tools specified in the agent's definition are
+     * safe for non-interactive use before creating the executor.
+     *
+     * @param definition The definition object for the agent.
+     * @param runtimeContext The global runtime configuration.
+     * @param onActivity An optional callback to receive activity events.
+     * @returns A promise that resolves to a new `AgentExecutor` instance.
+     */
+    static create<TOutput extends z.ZodTypeAny>(definition: AgentDefinition<TOutput>, runtimeContext: Config, onActivity?: ActivityCallback): Promise<AgentExecutor<TOutput>>;
+    /**
+     * Constructs a new AgentExecutor instance.
+     *
+     * @private This constructor is private. Use the static `create` method to
+     * instantiate the class.
+     */
+    private constructor();
+    /**
+     * Runs the agent.
+     *
+     * @param inputs The validated input parameters for this invocation.
+     * @param signal An `AbortSignal` for cancellation.
+     * @returns A promise that resolves to the agent's final output.
+     */
+    run(inputs: AgentInputs, signal: AbortSignal): Promise<OutputObject>;
+    /**
+     * Calls the generative model with the current context and tools.
+     *
+     * @returns The model's response, including any tool calls or text.
+     */
+    private callModel;
+    /** Initializes a `GeminiChat` instance for the agent run. */
+    private createChatObject;
+    /**
+     * Executes function calls requested by the model and returns the results.
+     *
+     * @returns A new `Content` object for history, any submitted output, and completion status.
+     */
+    private processFunctionCalls;
+    /**
+     * Prepares the list of tool function declarations to be sent to the model.
+     */
+    private prepareToolsList;
+    /** Builds the system prompt from the agent definition and inputs. */
+    private buildSystemPrompt;
+    /**
+     * Applies template strings to initial messages.
+     *
+     * @param initialMessages The initial messages from the prompt config.
+     * @param inputs The validated input parameters for this invocation.
+     * @returns A new array of `Content` with templated strings.
+     */
+    private applyTemplateToInitialMessages;
+    /**
+     * Validates that all tools in a registry are safe for non-interactive use.
+     *
+     * @throws An error if a tool is not on the allow-list for non-interactive execution.
+     */
+    private static validateTools;
+    /**
+     * Checks if the agent should terminate due to exceeding configured limits.
+     *
+     * @returns The reason for termination, or `null` if execution can continue.
+     */
+    private checkTermination;
+    /** Emits an activity event to the configured callback. */
+    private emitActivity;
+}