We've updated the prompt library to make it easier for teams to collaborate using the Organizations feature. Prompts can already be owned by an organization - now, they're easier to find, filter, and manage.

As of Sourcegraph 6.4, customers using self-hosted models through the openaicompatible provider can now configure:

• Custom headers: Add authentication keys or other custom HTTP headers to LLM requests
• Non-legacy completions: Use /chat/completions instead of the older /completions endpoint for Cody's autocomplete queries

We've added a variety of new LLM options from OpenAI and Google for Cody users:

Cody Free:

Smart Apply is a Cody feature that applies high-confidence code edits from chat responses directly into your codebase, streamlining your development workflow. Cody uses a targeted model for Smart Apply that is well-suited for low latency, and the previous model used (Claude 3.5 Sonnet) has been replaced by a new model: Qwen 2.5 Coder.

This update improves the responsiveness of Smart Apply in both VS Code and JetBrains by ~5x while preserving edit quality.

JetBrains users can now try auto-edit, now available as an experimental opt-in in the Cody plugin.

Auto-edit analyzes your recent changes and suggests context-aware edits—like cleaning up code, adding missing pieces, or improving structure. Instead of writing every change yourself, you can apply Cody's suggestions directly in your IDE.

Batch Changes now supports using GitHub fine-grained access tokens as credentials for creating and managing changesets. This support is experimental and is especially useful for customers who prefer not to use GitHub Apps due to their broad repo access, and who also disallow personal access tokens (PATs) because of their wide permissions and lack of expiration controls. Fine-grained access tokens strike a better balance: they’re more secure than PATs and more flexible than GitHub Apps.

They can be used for both user-level and site-admin credentials in Batch Changes. However, note that fine-grained tokens can be more complex to set up and may require admin approval in your GitHub organization.

Site admins can now fully customize the examples shown in the batch spec library - visible when defining a batch spec for a new batch change - using three new GraphQL APIs:

• createBatchSpecLibraryRecord
• updateBatchSpecLibraryRecord
• deleteBatchSpecLibraryRecord

Batch Changes now supports a new bulk action to help teams working in fast-moving codebases: rebase changesets.

This makes it significantly easier for teams to keep changesets up to date. Instead of rebasing each changeset manually, users can now do it all at once with a single action—streamlining workflows and reducing friction when managing large-scale changes.

Developers using Cody chat now have access to two variations of Claude 3.7 Sonnet: the standard model useful for faster, more responsive interactions, and another optimized for reasoning ("extended thinking").

With this update, Claude 3.7 Sonnet can now be used in different contexts depending on whether long-form reasoning is required or for tasks where speed and performance is a priority.

You can now sign commits with SSH keys in Batch Changes - giving enterprise teams a more secure, user-level alternative to GitHub Apps for commit verification. This feature is available in experimental form and currently supports GitHub and GitLab.

To get started, users add a personal access token (PAT) and check a box to enable commit signing. When they do, Sourcegraph generates an SSH key pair, surfaces the public key, and guides users to add it to their code host as a signing key. Site admins can also add PATs, and they function as a global credential to all users who don't set their own.

We’ve improved how Sourcegraph ranks results in the main search bar to deliver more relevant results tailored to each user. When you search for something like data router, Sourcegraph now applies best-in-class ranking strategies that better understand your full query - not just keywords in isolation. In addition, we boost results from repositories you’ve recently contributed to, making it easier to find the code you care about faster.

Flexible code search queries - where you are looking for something, but don’t 100% remember the name - has been improved. Below is a before and after for the query contributors job that highlights this improvement and our use of BM25 ranking.

The Batch Changes list page now supports searching by title, letting you filter down results by typing keywords that match the batch change’s name. Previously, the list view only showed the 15 most recent batch changes by default, with the option to load 15 more at a time. For customers with long histories of batch changes - sometimes hundreds deep - this made it time-consuming to locate a specific one.

Now you can simply search by title to quickly narrow the list and jump straight to the change you care about, significantly improving the experience for teams managing large volumes of batch changes.

Announced in January, auto-edit goes beyond traditional autocomplete by analyzing recent edits and suggesting context-aware changes that offers a seamless, non-linear coding experience.

Enterprise customers on Google Cloud Platform (GCP) can now use the "extended thinking" variant of Claude 3.7 Sonnet - optimized for extended reasoning and deeper understanding - when using Cody.

This update allows customers that rely on GCP infrastructure access to Anthropic's latest and greatest model, resulting in richer, more thoughtful responses in chat-based interactions within Cody.

Sourcegraph Analytics now has an Overview page that highlights and explains key value metrics including usage, time saved with Sourcegraph, and Percentage of Code Written (PCW) by Cody.

Our guiding philosophy is to provide users access to the latest and greatest models, and we review model availability based off usage and feedback as older models are replaced by newer ones. With the latest update of Sourcegraph and IDE plugins, we are making the following changes to model availability for Cody Free, Cody Pro, Sourcegraph Enterprise Starter and Enterprise customers who use Cody Gateway.

We are deprecating the following models [...]

OpenAI's latest cost-efficient reasoning model o3-mini was announced last month, and in Sourcegraph 6.1 we are making o3-mini-high available to all Enterprise Starter and Enterprise customers.

o3-mini is purported to be OpenAI's "highest performing released model on SWEbench-verified" for software engineering tasks, and we're excited to provide access to this model to customers.

A few weeks ago we added a major upgrade to the Prompt Library, with the ability to add specific files, repositories, and other context in saved prompts. With this update we've streamlined the UI in the editor by moving all of the 'current' context buttons like Current File and Current Selection into the @-mentions menu, creating a more natural-feeling spot for all of your context options to live in one place.

This change does not break existing prompts that use cody:// syntax and they will function as normal.

We recently announced the experimental version of Cody for Visual Studio, starting with chat functionality to help you understand the code you're working with, and today we're excited to add autocomplete to the latest version of the plugin.

Visual Studio users can now leverage the same autocomplete experience as they would in Cody for VS Code and JetBrains, with Cody providing accurate single and multi-line autocomplete suggestions while writing code.

We're making Sourcegraph more accessible to growing teams! Enterprise Starter is a new plan designed for teams of up to 50 developers, giving them access to powerful code search, AI chat, multi-repo context, and more—all for just $19 per user/month.

What's included: