Releasesby GlyphFilter Repositories by Provider ID in the API
The v3 repositories endpoint accepts a provider_repository_id filter.
Also shipped Nov 2, 2026Cognition in November 2026 →
Managed warehouse for MLflow (Beta)
Managed warehouse for MLflow is available in Beta, enabling users to view Unity Catalog traces in the MLflow UI without manually choosing a SQL warehouse.
Check out GitHub code without long-lived credentials on self-hosted agents
Self-hosted agents can now use temporary, read-only GitHub App tokens for repository checkout. This eliminates the need to distribute and rotate long-lived SSH keys or personal access tokens across your agent fleet.
Serving tuned Gemini 3.x models on global endpoints
Serving tuned Gemini 3.x models on global endpoints is available in General Availability (GA) . You can copy fine-tuned Gemini 3.x models to the global region using the Model Registry models:copy API, deploy them to global serving endpoints, and send inference requests directly to aiplatform.googleapis.com .
[Launched] Generally Available: Change from virtual network integration to a private endpoint capable network configuration in Azure Database for PostgreSQL flexible server
You now have greater flexibility in network design for Azure Database for PostgreSQL Flexible Server workloads. Now you can change existing VNet-integrated servers from delegated-subnet networking to a private endpoint-capable configuration, enabling secu
[Launched] Generally Available: Restart databases in Azure SQL DB via the Azure portal
You can now restart or fail over databases directly from the Azure portal, including single databases, Hyperscale databases, and databases in elastic pools, without writing scripts against the Rest API or contacting support. Learn more.
Lakehouse caching for cross-cloud data access is generally available (GA)
Lakehouse caching for cross-cloud data access is generally available (GA). Cross-cloud caching is disabled by default. You can opt in to caching on a Lakehouse federated catalog or a BigQuery cross-cloud connection to cache remote files in your Google Cloud region. This helps reduce cross-cloud egress costs and accelerate subsequent queries.
More from DevinEvery Devin release →
Clearer Read-only Access in the Composer
Viewers who can read but not write to a session now see that they lack write access in the composer, and "Continue in a new session" is offered only when the new session will be able to read this one.
"Fix with Devin" Links to the Session
On a blueprint build page, the "Fix with Devin" toast links straight to the session handling the fix when the batch lands in one session, and points at the rows otherwise.
Multi-repo Scans up to 1,000 Repositories
The per-scan repository cap for code scans is raised from 500 to 1,000 in the UI and the API.
Auto-scan Controls and Schedules
Auto-scan can be turned on or off from a session's Findings tab, a scan's auto-scan schedule is shown in the scan detail and the Devin MCP get_scan tool, and the threat-model lead offers weekly or monthly incremental scans when it finishes.
Findings Improvements
The Findings tab's quick-wins card shows a carousel of recommended findings' summaries, and the organization Findings page opens as a session tab with a "Chat with Findings" entry point.
"Not in" Slack Channel Conditions
Slack channel conditions in Automations accept "not in", so a trigger can exclude a list of channels.
Automations Settings Refresh
The Automations settings page gets an Automations icon, empty states, a default-policy setup flow and consistent row actions; the intro dialog adds a Preflight checks step; and network-policy edits now apply to the automation's already-running sessions.
Multiple Files in One Slack Post
Devin's Slack tool can attach several files to a single post_message .