@-mention suggestions in Deep Search conversations are now scoped to the active search context. Repositories outside the selected search context might still be part of the suggestions if they have been recently selected.
Exclude repositories matching specified patterns from Deep Search results using context filters.
Added a toggle in the Deep Search scope picker to control the deepSearch.useDefaultSearchContext setting, allowing users to configure whether to use the default search context without manually editing settings JSON.
The home page now greets first-time users with a prompt box and a "How it works" overview instead of an empty list.
Batch spec executions now emit structured audit events containing the raw spec, commands, coding-agent inputs, and normalized container image metadata.
Code Finder now uses GPT 5.6 Luna as its underlying model.
Sourcegraph OAuth clients can now have a maximum session duration, after which the user will have to reauthenticate completely to get a new access and refresh token pair.
Added support for GPT 5.6 model family to Cody.
Moved files are now indicated with a special icon and badge in the diff viewer and are auto-collapsed by default.
Normal user accounts (as opposed to service accounts) can now also be given unrestricted access to repositories via the GraphQL API.
Added cloud_instance_gcp_project_id column to Enterprise Portal subscriptions table to track GCP project IDs for Sourcegraph Cloud instances.
Enterprise Portal displays an environment badge ("Dev" or "Local") in the header when running in non-production environments to help distinguish them from production.
License issuers must now explicitly select user cap enforcement (hard-capped or soft-capped) when creating limited-user licenses.
Fixed excessive spacing between the Deep Search prompt editor and suggested searches.
Fixed repository and revision rows in search context detail pages rendering outside their table in Safari.
Fixed an issue related to batch changes where a merged PR would show up as failed.
Changeset sync jobs for changesets missing credentials are now deprioritized and backed off to prevent them from starving healthy sync work.
Agent conversations now remain pinned to the bottom while responses stream, even when Markdown rendering or tool steps cause layout changes.
Fixed timeline markers being unresponsive to hover when adjacent to open previews
Fixed timeline rail overlay blocking header controls in agent conversations
Access token curl examples now use double-quoted arguments with escaped quotes on Windows while preserving single-quote syntax on other platforms.
Fixed Cody Web chat failures when browsers advertise zstd compression support.
Fixed runtime database user provisioning to grant access to the active schema instead of only public, ensuring non-superuser deployments work correctly with custom PostgreSQL schemas.
batch-exec helper binary from published artifacts, ensuring version compatibilitybatch-exec binary and provides installation instructionsSupport sending GitHub and GitLab auth tokens via HTTP headers instead of query parameters
The worker service waits up to 5 seconds for the Redis instance to become available before continuing without it. This minimizes occurrences where worker jobs are processed without enforcing the correct rate limits.
Upgraded @grpc/grpc-js to 1.14.4 to fix two high-severity remote denial-of-service vulnerabilities (CVE-2026-48068 and CVE-2026-48069) that could crash the docs server.
Added grant-scope picker to tool-approval UI, allowing users to grant agent access to a secret once (default), for the duration of the session, or permanently.
See what's happening in your repository at a glance.
AI agents are changing everything.
Code is written in "factories", partially by humans, partially automated. The pace of change is relentless, and we've got to keep up with it.
We're releasing a new repository overview: our first iteration into making Sourcegraph a platform that empowers you to stay plugged in to the changes across your codebase.
Give it a whirl, and let us know what you think.
Deep Search can now cross-reference and aggregate larger result sets, and write its findings to downloadable CSV, JSON, and SVG files.
Ask Deep Search for codebase wide inventories, audits, or migration reports that would be too large to present cleanly in an answer. Deep Search summarizes the key findings in chat and attaches the full structured output for further analysis or tracking.
Deep Search can also read generated CSV and JSON files in follow-up investigations. This allows it to filter, join, or enrich previously collected results without repeating the original codebase searches.
Generated files appear directly in the Deep Search answer, where you can preview or download them.
Try prompts like:
profile-service through getProfileFeatures. Create a CSV with the consuming service, repository, source URL, field mask, feature group, and request type.old/package but does not yet import new/package.Learn more in the Deep Search documentation.
Give Deep Search durable instructions and task-specific skills tailored to your organization.
Deep Search can now follow your organization’s conventions on every run. Add durable AGENTS.md-style guidance for standards and preferences, plus task-specific skills that help the agent handle specialized workflows with the right instructions.
Configure customization globally, for an organization, or in your personal settings. Guidance and skills can be entered directly or loaded from an explicitly configured Sourcegraph repository location, with an optional path and branch or revision. Repository sources can contain AGENTS.md and skills at skills/<name>/SKILL.md or .agents/skills/<name>/SKILL.md; they are not automatically discovered from every repository involved in a search.
Guidance is included in agent runs, while skills are advertised by name and description and loaded only when relevant, preserving context for the task. Settings are applied from global to organization to personal scope, and later skills override earlier skills with the same name, case-insensitively.
Agentic Batch Changes supports the same customization model for its coordinating agent. Guidance and skills do not flow into delegated coding agents such as Claude Code or Codex.
Deep Search can cross-reference and aggregate large result sets for codebase-wide inventories, audits, migration planning, and other structured investigations
Migrated Deep Search guidance setting from experimental features to stable configuration path.
Recent Deep Search contexts are now reconciled against live data when the picker opens, preventing stale or deleted contexts from appearing in the recents list.
The coordinator agent in Agentic Batch Changes can now cancel workspace execution.
The Agentic Batch Changes coordinator agent can now read files in repositories directly, cutting down on planning time.
Bundled coding-agent CLIs (Codex and Claude Code) with checksum-pinned versions at build time, eliminating runtime downloads from public installers. Supported across v1 and v2 executor runtimes with executor version gating.
Migrated Agentic Batch Change guidance setting from experimental features to stable configuration path.
The Duration column in the batch-change-agents workspace list now updates live for in-flight workspaces (queued/processing/canceling), showing elapsed time that ticks up in real time.
Agentic Batch Changes' coordinator agent now uses Claude Opus 5.
Agent guidance sources are now clickable links that open their configured repository paths.
Added a labeled "Viewed" chip for marking files as viewed in the compare/diff view, replacing the previous unlabeled circle control.
MCP server now supports protocol version 2026-07-28 while maintaining backward compatibility with older clients.
Microsoft Teams is now supported as a notification channel for observability alerts.
Data tables now show an edge shadow on the sticky row-number/checkbox column while horizontally scrolled.
Fixed spacing between Deep Search prompt editor and error/quota banners
Fixed layout shift in the search context picker
Fixed filtering references by location in the code navigation Explore panel.
Fixed a panic in precise code navigation that could occur when a repository had multiple SCIP uploads indexing the same file path.
Fixed a deadlock between executor heartbeats and the unknown-commit janitor that could cause code intelligence indexing jobs to stall.
Fixed go-to-definition (cmd/ctrl+click) in the file view not scrolling to the definition when it was off-screen.
Fixed phantom next page appearing in batch spec library pagination when the number of records is an exact multiple of the page size.
Fixed a swallowed marshalling error in batch changes that could lead to downstream inconsistencies
Fixed an issue where the Batch Changes reconciler would silently mark a changeset as undrafted even when the operation failed to reach the code host due to remote repository resolution errors. The reconciler now properly surfaces these errors and schedules retries, preventing changesets from being incorrectly left in draft state.
Changesets whose reconciler hit a transient error (e.g. a code-host timeout) are no longer reported to the agent as a terminal failure while they are still being retried automatically.
Changesets created by Agentic Batch Changes no longer include forced line breaks in their descriptions.
Executor jobs, including Kubernetes-backed jobs, now have a default maximum runtime of 60 minutes.
Clarified that changing the gitMaxConcurrentClones site configuration setting requires restarting the worker service or pod to take effect.
Fixed page layout title alignment issue
Run exhaustive, codebase-wide searches from your own integrations with Search Jobs in the Sourcegraph API.
Search Jobs have landed in the Sourcegraph API. A Search Job runs your query across every repository, branch, and revision in your codebase. Use it for audits, security reviews, and large scale migrations.
Search Jobs are served from the versioned /api/ endpoints and authenticated with access tokens scoped to externalapi:read and externalapi:write. Jobs run asynchronously, and results are available as JSONL once a job completes. Each token only sees and manages its own jobs.
You can explore the available operations and download the OpenAPI schema from the searchjobs service section of the interactive API reference at /api-reference (e.g. https://sourcegraph.example.com/api-reference).
The Search Jobs operations in the Sourcegraph GraphQL API, now the debug API, remain available and unchanged. For long-term support and a stable integration experience, we recommend building on the new Sourcegraph API instead.
If you have any feedback, please reach out to support@sourcegraph.com.
Added a Grafana dashboard for monitoring Batch Changes server-side background workers, queue stores, and stalled-job resetters.
Added indicator highlighting suggested Batch Changes code host credential method
Agentic batch change agents now wake automatically when a changeset's CI passes, even when no onCIFailure hook fired. The resume is labelled "Resumed automatically: changeset CI passed" in the thread timeline.
Read files generated from Deep Search in Agentic Batch Changes
The managed coding-agent base image now includes Python 3, ripgrep, and jq by default, avoiding the need to install these tools at execution time.
Agentic Batch Changes links that you can't access now show a placeholder indicating how to request access
Polished the batch change agent detail page UI: improved table layout consistency, redesigned workspace column display, updated status badges, added missing empty states, and unified toolbar patterns across plan and resolve views.
Batch Changes secrets pages now cross-link between per-user and global secrets. When Agentic Batch Changes is enabled, both pages explain how secret descriptions guide Agentic Batch Changes.
Added a "Generating a ConnectRPC client" section to the API reference intro docs, showing how to download the proto schema (.binpb) — all services by default, or a comma-separated subset via ?service= — and generate typed stubs with buf. This renders as an always-visible section in the API reference page (built on the proto download added in #14309), so customers can self-serve ConnectRPC/protobuf client generation. The OpenAPI golden snapshot is regenerated to match.
Added proto schema download to the API reference page. The Download button now offers both OpenAPI schema (.yaml) and proto schema (.binpb) options, enabling ConnectRPC/protobuf consumers to generate typed clients directly from the external API definition (e.g. via buf generate sourcegraph-api.binpb).
Service account access token creation page now displays an informational alert recommending M2M OAuth credentials as an alternative that eliminates manual token rotation.
Added support for Claude Opus 5
Hide Ownership tabs for repositories without a CODEOWNERS file.
MCP search tools are now correctly attributed to MCP rather than Deep Search in backend telemetry.
Fixed an issue where code navigation request cancellations would incorrectly be counted as errors in SLO statistics.
Fixed pagination of code intelligence data
Janitor sub-jobs for cleaning up deleted commits (e.g. on force-pushes) have been tuned to reduce unnecessary DB pressure.
Clarified when SSH push key needs to be configured for Batch Changes
Surface OAuth errors when connecting code hosts for Batch Changes
Batch Changes now correctly shows UNKNOWN CI status instead of transient pending/passed states when required check classification is supported but the initial sync has not yet completed.
Fixed review state for merged and closed changesets that could incorrectly show as pending approval
Fixed an issue where workspaces would disappear from the UI when switching between batch specs until the page was refreshed.
Fixed thread panel on the /new page to always start expanded instead of using the previous session's collapsed state.
Batch Change Agent messages now stop after 24 hours if they do not finish, surfacing a recoverable failure instead of remaining active indefinitely.
Agentic Batch Changes can now present multiple-choice questions, each allowing free-form input.
Fixed Code Insights charts failing to load when data points render at nearly identical positions, preserving access to insight edit and delete controls.
The markChangedFilesAsViewed mutation now rejects requests that contain files with both srcOID and dstOID set to nil.
batch-exec helper binary from published artifacts, ensuring version compatibility.batch-exec binary and provides installation instructions.Fixed smart hover summary bugs that could result in additional codeintel resource consumption.
Hybrid search now has a separately configurable changed-path length limit via SEARCHER_HYBRID_MAX_TOTAL_PATHS_LENGTH, with a default of 300 KB.
Our new MCP tool finds relevant code faster with lower token usage.
Code Finder, a fast and efficient agent optimized specifically for code search, is now available in Beta through the Sourcegraph MCP server.
Code Finder is a tool that helps coding agents quickly locate relevant implementations, configuration, tests, or documentation within a single repository. It returns a concise summary with links and line ranges, giving your agent focused results it can immediately use.
To show the strengths of using an optimized search agent, we assembled a benchmark suite with a variety of search tasks across several repositories, from small to large. The results show clear improvements in speed and cost. In particular, Code Finder is more than twice as fast compared to a coding agent searching with local tools and up to 40% cheaper than a coding agent using our MCP toolset, achieving comparable result quality.
| Variant | Duration | Cost |
|---|---|---|
| Code Finder | 1.00× | 1.00× |
| MCP tools | 1.14× | 1.63× |
| Local search | 2.19× | 1.32× |
Code Finder already powers file discovery within Deep Search, letting Deep Search spend less of its token budget locating files and more on reasoning about the code and producing a thorough final response.
Code Finder is free while in Beta. The feature will become billable with credits once it becomes generally available. For more information on our MCP server and Code Finder usage, see the documentation.
See exactly what changed, at any scale.
Following its Beta period, the redesigned compare page is now generally available. It's a ground-up rebuild of how you view changes between two revisions — fast, complete, and built to stay useful even on very large diffs.
What you get:
There are two ways in: open any repository and click Compare, or go to a repository's Branches tab and compare branches directly.
This is the diff view we're adopting across Sourcegraph: it already powers the commit page and Agentic Batch Changes, and it'll soon roll out to more places where you review code.
Added source.read_file module to the evaluator, enabling file search, reading exact repo/path/revision matches, and source context inspection within a single evaluator execution.
Added an alert for SCIP uploads that exceed the configured processing time limit.
Batch Changes now uses required GitHub checks when computing changeset CI status, preventing optional check failures from incorrectly marking changesets as failed.
Site admins can now audit Agentic Batch Changes activity: tool approval decisions, agent deletion, and read token rotation are recorded in the audit log.
Batch change workspaces now display their last-known results (diff, steps, changeset specs, and timing) after re-preparing a spec but before re-executing, with a stale banner indicating the workspace needs to be re-run.
Improved Finder prompt to provide more complete answers with better file references.
The new compare page is now generally available.
Improved Perforce compatibility for the compare page.
Added a commit/history panel to the compare page diff viewer, allowing users to view changes for individual commits within the selected range.
Introduced a dedicated site config setting for blocking specific MCP tools. The setting is "mcp.tools.disabled": ["tool_name"] - you supply an array of tool names that should be disabled across all MCP endpoints.
Enabled Code Finder MCP tool by default for customers who have signed AI terms.
Added the mcp.deepSearchTool.enabled site configuration option for controlling the Deep Search tool on general-purpose MCP endpoints. The environment variable SRC_MCP_DISABLE_DEEPSEARCH_TOOL is deprecated and will be removed in a future release.
Audit logs now show whether the user is a service account or not.
Fixed ambiguous file mentions by using ':' delimiter between repository name and file path instead of '/', preventing the model from misinterpreting multi-segment repository names as a single repository.
Redacted secret values in executor logs are now annotated as {{ REDACTED secrets.NAME }} instead of ${{ secrets.NAME }} to make clear the value was removed.
Fail validation with a clear error when a hook step's files target path contains invalid characters.
The publish_workspaces tool now distinguishes between workspaces that completed with no changes and workspaces that are not ready for publishing. Workspaces that finished execution (COMPLETED/SKIPPED) but produced an empty diff are reported separately as workspace_ids_no_outcome. The tool now errors immediately when a selected workspace has not successfully finished (still queued/processing, or failed/canceled), preventing silent failures and allowing the agent to wait or retry appropriately.
Avoided redundant SSE streams while BCA agents run, reducing browser connection usage
Transcript step timestamps now adapt to available space: wider layouts show timestamps beside timeline dots on hover, while narrower layouts display them in tooltips.
Fixed an issue where paused agent streams could exhaust browser connection limits and stall unrelated requests.
Validate buildImage.baseImage against container registry allow/denylist to prevent unauthorized base images in Agentic Batch Changes.
Message stream retries now use exponential backoff (2/4/8/16/32 seconds) instead of retrying every 2ms, reducing unnecessary reconnect bursts.
Fixed Code Insights dashboards failing to load when an errored insight contains chart data that cannot be rendered, allowing the affected insight to be edited or deleted.
GitLab API error messages are now logged during permissions sync to aid troubleshooting.
Added upper limit to number of log events that can be sent per batch
Fixed an edge case where entitlement release could fail if the context was cancelled during the operation.
Fixed notification badge spacing for double-digit counts in the sidebar.
Fixed an issue where users who signed in through an external provider could not create a password.