Set up code context for your site
Code context is currently in open beta for GitHub users in Rovo Chat and Teamwork Graph (TWG) CLI, and rolling out to Bitbucket shortly.
The current experience may change before general availability.
Who can do this? Role: Organization admin Atlassian Cloud: Standard, Premium, Enterprise Atlassian Government Cloud: Not available |
Code context enables intelligent search across your connected source code repositories, directly within the Atlassian tools your team already uses. Whether you're navigating an unfamiliar codebase, investigating a bug, or asking an Rovo agent to help with a task, code context helps surface the right code faster.
Understand how code context works
Before you begin
There are a few things worth checking before enabling code context:
Scan for secrets in your repositories. Code context indexes all content in opted-in repositories. If your repositories contain hardcoded API keys, passwords, tokens, or other sensitive data, that content will be indexed and discoverable by anyone with repository access. We recommend running a scan for secrets and changing any findings before enabling the feature.
Check your data residency requirements. Data residency configuration isn't currently supported for code context. Indexed code and embeddings are stored and processed in the United States. If your organization has data residency or data sovereignty requirements outside the US, confirm that enabling code context is appropriate for your situation. Understand data residency
Confirm indexing rights. Make sure your organization has the rights and approvals needed to allow Atlassian to mirror, index, and store your source code.
Check the Github for Atlassian connector is added and configure for your preferred site. Read about how to set up the connector
Set up code context
To enable code context for your site:
Go to Atlassian Administration. Select your organization if you have more than one.
Select Rovo, then Code context.
Select Enable code context.
Select the site you’d like to set up with code context.
Carefully review the terms to enable code context.
Once enabled, your connected code will immediately start indexing. This can take up to 24 hours. At this stage, there’s no indicator available to show which repos are indexed.
You can disable code context at any time, and indexing will stop immediately. All stored embeddings, indices, and code chunks are deleted.
If you encounter any problems while installing code context, refresh and try again.
Permissions and access
Code context is built to enforce permissions as a core principle, not an afterthought, and is especially designed to respect your Source Code Management (SCM) permissions. Code context doesn't grant users access beyond what their SCM permissions allow.
Users will see results only for repositories and branches they already have access to in the source SCM. Atlassian validates permissions at query time against the repository's permission endpoint.
If an organization admin enables code context for a repository, individual contributors cannot exclude their code from indexing. This is consistent with how existing Bitbucket lexical search already works.
The Teamwork Graph CLI augments Atlassian coding agents (via the Rovo CLI) or third-party products (like Claude Code or Codex).
If you use code context via the Teamwork Graph CLI with a third-party agent, your source code will be sent to those products and governed by their terms, which may expose proprietary code and IP.
You’re responsible for assessing the third-party providers security and suitability, for managing all their associated costs, API capacity, and agent actions.
We want to hear how code context is working for your team. Share feedback and report issues directly through the Rovo Chat, or this form if you’re using the TWG CLI
Was this helpful?