Complete guide to Gemini Code Assist: features, editions, and what's new

Informatec Digital » Artificial Intelligence » Complete guide to Gemini Code Assist: features, editions, and what's new

Gemini Code Assist has become one of Google Cloud's most talked-about programming assistants, with versions for both individual and enterprise users. Although it's an evolving technology, it already allows Complete, generate, transform, and review code directly from your IDE, with contextual chat and smart actions that reduce effort on repetitive tasks.

Beyond the classic auto-complete functions, the service incorporates Code transformation with diff view, remote repository context, and an agent mode to solve complex problems step by step. And, for those who want to get started for free, there's an Individual Edition with very generous usage limits for Visual Studio Code and JetBrains IDEs.

What is Gemini Code Assist and who is it for?

Gemini Code Assist is an AI-powered collaborator built into the editor, designed to empower developers of all skill levels. work faster without losing control over the codeIt's inspired by the older "Duet AI for Developers" and expands its capabilities to perform code generation, explanation, refactoring, and documentation tasks in real time.

There are three main approaches: the Individual Edition (free), the Standard Edition, and the Enterprise Edition. The first allows you to start without a credit card and offers High limits: up to 6.000 autocompletes per day, 240 daily chat interactions, and code reviewsAdditionally, chat supports a large context window with up to 128.000 input tokens, enough to handle large files and take into account a good portion of your local database.

For organizations, Standard and Enterprise focus on Security, data governance, and extensions in Google Cloud. Enterprise adds code customization to tailor suggestions to private repositories, as well as more enterprise cloud integrations and options like VPC-SC or Private Google Access.

In large-scale scenarios, some Gemini ecosystem capabilities have demonstrated context windows of up to one million tokens in certain flows, useful for understanding large projects or extensive documentation. In any case, it's always a good idea to verify the validity of each answer: the tool itself warns that it may generate plausible but incorrect outputs.

Main functions in the IDE

As you type, Gemini Code Assist suggests online completions that you can accept or ignore instantlyThis behavior, known as code completion, speeds up repetitive tasks and helps maintain style consistency. If you prefer, you can disable autocompletion from the plugin settings. If the default shortcut for generating code doesn't work for you, you can remap the key combination in your editor.

Another key piece is code transformation. With commands or natural language in menus like "Quick Pick," you can ask specific file modifications and review a diff before applying changesThis approach minimizes errors, as the flow shows you the proposed adjustments and allows you to approve or reject each block.

The integrated chat works as a copilot with context from the editor. You can select a snippet and request assistance: from "Function to create a Cloud Storage bucket" to "Help me debug my code." or "Write unit tests for my code.”. The tool processes your request, cites sources where appropriate and submits commented proposals, with the possibility of inserting the result into the active file.

When an error is detected, the wizard offers you a quick fix with code transformationYou'll see a diff with the suggested solution, and you'll have full control to apply, edit, or discard it. This pattern reduces back-and-forth between the IDE and the documentation, and cuts debugging time.

An important note: if you use other plugins that capture the same shortcuts or APIs from the IDE, the behavior of generation, autocompletion and transformations can be non-deterministicIf you notice inconsistencies, check for shortcut conflicts and extension settings in your environment.

Advanced Context: Remote Repositories and Customization

If your work revolves around specific microservices, libraries, or modules, you can ask Gemini to focus on specific remote repositories. To do this, you must first index and configure repos in code customization (required for Enterprise) and then invoke them in chat with “@”.

The flow is simple: you open the IDE chat, start the instruction with “@”, you select one or more repositories from the list and finish writing the request. With that, the system prioritizes the context of the chosen repos and generates more relevant responses. It's especially useful for aligning with your team's own patterns, conventions, and practices.

Some useful queries with remote repositories are: understand the repo structure ( "@REPOSITORY_NAME What is the overall structure of this repository?”), ask for a refactor towards the project conventions (“@REPOSITORY_NAME Refactor the following code to follow the conventions in the selected repository.") either generate tests adapted to existing examples ( "@UNIT_TEST_FILE_NAME Generate unit tests for module-x based on the examples in the selected file.").

You can also orchestrate specific actions on built-in tools with the “@” symbol followed by the name, for example: “@GitHub get issues assigned to me”. And, if you need to fine-tune things even further, the model supports style requests “Use the library-x in @REPOSITORY_A_NAME-A and implement the function-x" for rely on specific components of the ecosystem that your organization already uses.

To protect the privacy of the local context, Gemini Code Assist respects the “.aiexclude"And".gitignore”, preventing its content from being used in autocomplete, generation, transformations, or chat. Additionally, you can disable suggestions that match cited sources, so that the wizard doesn't suggest snippets that reproduce external code with added quotes.

Editions: Individual, Standard and Enterprise

The Individual Edition is designed for those who want to get started right away, without any costs or friction: no card required and lets you explore key features in VS Code and JetBrains with generous limits. Google notes that it offers up to “90 times more completions per month” than other popular free assistants, and chat with up to 128.000 entry tokens for understand long files and more local context.

In addition to completion and generation, chat helps you document features, write comments, or create tests from requirements, with support for natural language in multiple languagesEveryday examples include “create an HTML form with a name, email, and message,” “write a script that sends a daily email over time,” or “explain a Python snippet and detect errors.”

In the Standard edition, the focus shifts to safe operation at scale, with Robust data governance, secure infrastructure, and compensation for code suggestions. Includes chat support, simplified IDE integration, local codebase awareness, and Google Cloud extensions like Firebase, Colab Enterprise, BigQuery (data insights), Cloud Run, and Database Studio.

Enterprise adds all of the above and, in addition, customization with private codebases (GitHub, GitLab, Bitbucket) to accelerate development in accordance with internal practices. It also expands integrations with Google Cloud (Apigee, Application Integration, Gemini Cloud Assist) and makes it easier for cloud teams design, operate, and optimize applications and infrastructure more effectively.

In both paid editions, there are compliance capabilities such as Source citations in the IDE and console, network controls (VPC-SC, Private Google Access) and a catalog of functions by area (code and chat, CLI, smart actions, external tools) that can be mapped to the specific needs of each team.

Integrations and capabilities outside the IDE in Google Cloud

Gemini Code Assist's reach goes beyond the editor. With Gemini Cloud Assist In the Google Cloud Console, teams get generative support for operations and configuration, with a feature set available to all users and expanded for those using Enterprise.

In API development, Gemini on Apigee provides help within the IDE and console, speeding up design and debugging tasks. In Application Integration, AI guides the composition of integrations from the console, reducing implementation times and configuration errors.

In BigQuery Studio, the Data insights They offer a library of queries generated from your table metadata, which are very useful for quickly exploring datasets and finding patterns. This contextual help speeds up the creation of dashboards and ad hoc analyses.

In databases, the tool can generate SQL statements in natural language, adapt queries to the real schema, and optimize or explain existing queries. This democratizes data access and avoids friction between technical and business profiles.

What's New: Agent Mode, IDE and Gemini CLI Improvements

One of the big news is the Agent Mode, an agentic approach that solves complex, multi-step tasks with a plan that you review before touching the code. For example, “refactoring the model, view, and controller” of a shopping cart to display applied discount coupons would involve multiple files; the agent proposes a detailed plan, waits for your approval and implements changes in a controlled manner.

In VS Code, Agent Mode was initially released in the Insiders channel and is now available in Preview for everyone. Goes beyond command-response chat with Gemini CLI integration: supports Multiple file edits, full project context, integrated tools, and MCP support (with human in the loop to review).

Recent improvements to Agent Mode in VS Code include: visual editing with integrated inline diff, diffs within the chat to clarify proposals, persistence of agent mode in the history, clearer quota updates, real-time output of shell commands, batch approvals of tool calls, and a faster UI. Even the status of the agent mode toggle persists across IDE restarts.

In IntelliJ, Agent Mode is now available. stable version. You can review everything before applying changes, request modifications to the plan, approve or reject steps, and activate a mode of self-approval so the agent can act on your behalf. When you're done, you can review and reverse anything you see fit.

Additionally, the team has polished the overall IDE experience: you can now stop chat responses in progress to cut off long or devious outputs, and “thinking tokens” have been added in IntelliJ to provide reasoning cues before the final answer. Performance and quality of the answers have also been improved. autocomplete suggestions in VS Code, and several features that were in preview have been made generally available.

In the productivity line, Gemini CLI has grown a lot. It was released Gemini CLI GitHub Actions As a free repository partner, capable of acting autonomously on routine tasks or collaborating on demand. Key use cases include: intelligent triage of issues, accelerated pull request reviews, and timely collaboration when you need it.

The CLI is also integrated Go deeper with VS Code, becoming aware of open files and selected text to give more relevant suggestions. With Native diffs in the editorYou can view proposed changes side-by-side and edit them before accepting. To use it, install version 0.1.20 or higher and run an initial configuration command.

Other improvements include Custom Slash Commands to define reusable prompts and a public roadmap for v1 of the CLI. The goal is clear: to offer a more consistent, secure, and private development flow, with frequent, community-based iterations.

Basic setup and interaction

Getting started is simple: after installing the Gemini Code Assist extension on VS Code or in the JetBrains IDEs, you can activate the chat from the assistant icon and request help in two main ways: receive completed or generate code directly in the editor, and chat in the sidebar with your questions or by selecting code to provide context.

Some prompts that work well on a daily basis: “Write unit tests for my code.","Make my code more readable." or "Help me debug my code.”. If you work with indexed remote repositories, remember the “@” prefix to orient context to one or more specific sources, and filter the list by typing the name of the repo.

For teams on Google Cloud, you can also explore Gemini Code Assist at Cloud Shell Editor, Cloud Workstations and Android Studio. In all cases, please refer to the detailed configuration guide if you need to integrate Single Sign-On, restrict access by perimeters (VPC-SC) or define exclusion rules with “.aiexclude".

If you want to prevent the wizard from suggesting snippets that match code of cited sources (e.g., open source), there is an option to disable those suggestions. And, if you encounter strange behavior, remember that There may be conflicts with other plugins that use the same shortcuts or APIs of the IDE.

Good practices, limits and responsibility

As an early-stage technology, Gemini Code Assist may generate plausible outputs that are not correct. Therefore, it is advisable validate and test any changes before integrating it into production. The tool includes a citation system when reusing long passages from other sources and provides documentation on how and when you cite.

On the security and compliance front, the Standard and Enterprise editions rely on secure infrastructure, data governance, and network controls, along with IP compensation on suggestions. Enterprise also enables the customization with private codebases, which not only improves the relevance of the responses, but also helps reflect the organization's internal standards.

To preserve privacy, use “.aiexclude"And".gitignore” to exclude sensitive files from the local context used by the wizard. And if you detect a false positive in completions or transformations, You can always check the diff and not apply the proposed changes.

The individual edition is free and offers generous daily limits: 6.000 completed, 240 chats and code reviews. This range is perfect for students, freelancers, or developers who want to evaluate the tool without worrying about early caps, with a chat context of up to 128.000 tokens to cover large files.

Finally, the team encourages send feedback from within the IDE itself to refine experiences. There are also sections dedicated to known issues and release notes, where advancements such as Agent Mode, performance improvements in completion, and new features in the CLI and its integrations.

With this entire set of features — code completion, generation and transformation, Chat with local and remote context, enterprise customization, and Google Cloud integrations—, Gemini Code Assist is shaping up to be a powerful companion for coding with less friction, maintaining control over every change and scaling from a personal project to a complex organization.

Related article:

Gemini Code Assist: AI assistant for programmers is now available for free