With Sourcegraph 6.0, we're updating the chat experience by introducing a unified interface that combines AI-powered chat and code search into a single, seamless UI. This update helps you search, understand, and create code faster and more efficiently, whether you're in VS Code, JetBrains IDEs, or using Sourcegraph on the web.

What's new:

Sourcegraph is industrializing enterprise software development with the introduction of AI agents, designed to automate repetitive, time-consuming tasks and accelerate how enterprises build software.

The first available agent, the Code Review Agent, is now in Early Access, with additional agents for code migration, testing, documentation, and notifications coming soon. These agents are customizable, enabling enterprises to address bottlenecks and accelerate progress across large, complex codebases. This allows AI to impact and scale beyond individual developers and across the whole company.

Formerly Cody Analytics, Sourcegraph Analytics now provides customers with aggregate and product-specific metrics for Code Search, Batch Changes, and Code Insights, in addition to the Cody metrics that were previously available. The change in name reflects the new metrics that provide insight into how your developers are interacting with features across the entire Sourcegraph platform, and can help you understand ROI.

Sourcegraph Analytics also includes a CSV export with key metrics like number of searches, chats, autocomplete suggestions, completion acceptance rate (CAR %), and more, by user, day, client, and language — perfect for automating retrieval and analyzing data in ways that make the most sense to your organization.

We're introducing agentic chat to Cody users—a transformative upgrade that makes Cody smarter and more autonomous.

With agentic chat, Cody proactively gathers, reviews, and refines context from your codebase, shell, and the web to deliver high-quality, context-rich responses. Whether generating accurate unit tests, answering complex questions, or retrieving the latest API docs, agentic chat eliminates the need for manual context input, saving time and ensuring precision.

The Prompt Library is getting a major update for teams: the ability to embed specific files, repositories, and other context directly into prompts. This feature enables teams to create precise, reusable prompts tailored to their unique workflows, helping ensure collaboration, consistency, and high-quality outputs across their team.

We're excited to introduce auto-edit, an experimental feature now available in Cody for VS Code. Auto-edit goes beyond traditional autocomplete by analyzing recent edits and suggesting context-aware changes, enabling a seamless, non-linear coding experience.

Prompts provide Cody users the ability to create and share actions that can be tailored specifically to their development workflow. In this month's release, Enterprise users can now add tags to prompts, making it easier to group, organize, and filter prompts for easier discovery in the Prompt Library.

Gemini 2.0 Flash Experimental was announced last week, and we're happy to announce support for Google's latest model across all plans for Cody chat. Google indicates Gemini 2.0 Flash outperforms Gemini 1.5 Pro on key benchmarks at twice the speed, with promising improvements across developer-related benchmarks.

Cody users will now see Gemini 2.0 Flash Experimental in the model selection list for them to use when using chat, and the model is available in the latest versions of Cody for VS Code, JetBrains, and Cody Web. For Cody Enterprise customers, the new model is only available via Cody Gateway. These customers will need to upgrade to the latest release (5.11) and use modelConfig to access the model.

We're excited to announce the release of Cody for Eclipse! Eclipse devs can now natively work with Cody in their editor, including users on all Cody plans (Free, Pro, and Enterprise). This release is experimental, and it includes Cody's chat and Prompts functions.

Ask questions about your code, generate code, and fix code all through Cody chat. You can also automate your work with the Prompt Library. Autocomplete and inline editing capabilities will come in a future release.

While Cody primarily lives in your editor, the broadly trained LLMs it uses under the hood let it answer a wide range of questions beyond just coding. We're introducing a new feature for Cody Enterprise that allows teams to give Cody more prescriptive guidance on what kinds of questions it can answer.

Admins on Cody Enterprise instances can now configure prompt pre-instructions. These are text instructions that Cody uses for every chat query, allowing teams to shape how Cody responds to users. For example, if you don't want Cody to answer questions relating to sensitive non-code matters, you can pre-instruct Cody against them.

Cody is built to support the latest and greatest LLMs interchangeably so that developers always have access to the most powerful code AI solution. For Cody Enterprise customers, we're expanding Cody to be even more flexible and allow admins to select multiple models from multiple providers, which end users can then choose from on-demand.

We're excited to announce general availability for enterprise model election. Cody Enterprise users can now select and hot-swap between multiple model options. Cody Enterprise admins can select which models to provide for users, including models from different providers, including Amazon Bedrock, Azure OpenAI, and Google Cloud Vertex AI.

Currently, Sourcegraph's minimum required version of Postgres, the database management system used for all Sourcegraph instances, is Postgres 12. Postgres 12 is reaching end-of-life and will no longer be supported by Postgres. Because of this, Sourcegraph will be updating our minimum supported version to Postgres 16.

If you are using Sourcegraph's released Postgres images, these images will be updated to Postgres 16 as part of the Sourcegraph 5.10 release and all near-term subsequent releases. With this update, Sourcegraph will experience a longer-than-average downtime at the time of the upgrade to version 5.10 or beyond. This downtime is proportional to the amount of code indexed in your instance and can range from approximately 15 minutes to a couple of hours. The downtime will only occur at the first upgrade to version 5.10 or beyond, and not during any subsequent upgrades.

While Cody's autocomplete and chat functions speed up the inner dev loop, we've consistently heard from engineering leaders that they want more customizable ways to promote code AI best practices across their organization. Organizations that widely adopt code AI tools report better unit test and documentation coverage, not to mention faster issue-to-PR times. One Sourcegraph customer, 1Password, reports that unit tests that used to take a full day to write now take 10 minutes. However, AI coding tools leave much to be desired:

• AI tools today require writing long and cumbersome prompts over and over again, which could have taken longer than writing the code itself
• AI tools require users to go back and forth with the language model and clarify what they want, taking up valuable developer time
• AI tools don't use proper context, so if a developer doesn't use your enterprise's code context or reference best practices, they could end up writing poor quality code

Hey everyone! 👋

We're making our release updates even better! You'll now find more detailed info about what's new between versions in our technical changelog on GitHub.

Cody now supports the updated Claude 3.5 Sonnet and Claude 3.5 Haiku models across all plans.

Anthropic notes that the upgraded version of Claude 3.5 Sonnet has significant gains over its predecessor in coding. Claude 3.5 Haiku matches the performance of Claude 3 Opus on many evaluations at a similar speed to the previous generation of Haiku, meaning that users now get significant reasoning power with snappier responses.

The Prompt Library is a great way for users within an organization to share, discover, and use prompts while working with Cody chat. We've introduced a new concept to Prompts called Promoted Prompts which allows admins to highlight Prompts to users that appear at the top of a Prompt list, directing users to use specific Prompts that encourage best practices within the organization.

Admins can promote a Prompt by checking the Promoted box in the Prompt edit screen.

Perforce allows gating access to individual parts of a depot based on criteria besides username, including by IP address. Previously, Sourcegraph only supported enforcing username-based restrictions to individual files and folders based on the Perforce protections table. In this release, admins can configure their network infrastructure to securely communicate user IP addresses to Sourcegraph, enforcing allow/deny access to individual files and folders based on the user's IP address as well.

Please read our docs for more information.

Announced as part of the 5.6.0 release in August, the new search experience saw significant improvements in speed and simplicity, helping users search, navigate, and find answers about their codebase faster than ever.

Originally available as an opt-in for users, this new experience is now the default in 5.9.0, with the option to opt out back to the old experience.

Hot on the heels of the updates we rolled out to VS Code, the improvements we've made to the Cody sidebar are now available for JetBrains and Cody Enterprise users. Prompt and command use and discovery has been simplified, and we've tidied up the display of draft Prompts so that only drafts you own will appear in the UI.

We are excited to roll out an experimental version of Cody for Visual Studio! This is the first step in the journey to general availability and we'd love to hear your feedback.

This experimental version currently supports chat, and does not support autocomplete or inline editing capabilities.