Databricks Release Notes

Unity Gateway now supports Anthropic Claude Fable 5.1 as a Databricks-hosted model. You can access this model using Foundation Model APIs.

Customers are responsible for ensuring their compliance with applicable terms.

Automatic change data feed (Auto CDF) computes row-level changes at query time using row tracking, without requiring you to manually enable change data feed on each Delta Lake or Apache Iceberg v3 table. Auto CDF removes write-time overhead and makes MERGE and UPDATE operations about 15% faster on tables that you query for changes. It works with batch queries, Structured Streaming, and Delta Sharing, and requires Databricks Runtime 19 or above with row tracking enabled. See Automatic change data feed.

The pipeline_events system table is in Beta. This table records Lakeflow pipelines event log entries for pipelines in your account, capturing lifecycle transitions, flow progress, data quality metrics, errors, and other operational data across all pipelines and workspaces in a region. Use it to query historical pipeline activity, build alerts on pipeline failures, and correlate pipeline behavior with other Lakeflow system tables.

See Pipeline events system table reference.

ABAC GRANT policies for models, model services, model provider services, and model context protocol (MCP) services are now generally available. These policies dynamically grant Unity Catalog privileges to securable objects whose governed tags match a condition, instead of granting privileges on each object individually. See ABAC GRANT policies.

You can now use TIMESTAMP(9) and TIMESTAMP_NTZ(9) for nanosecond-precision timestamps in Databricks SQL and Databricks Runtime 19 and above.

See TIMESTAMP type and TIMESTAMP_NTZ type.

Model Serving now supports GLM 5.3 as a Databricks-hosted model in supported US and Americas regions. This text-only mixture of experts (MoE) model supports a context window of up to 1,048,576 tokens, up to 65,536 output tokens, function calling, structured output, coding, agentic tool use, and always-on reasoning. You can access this model using Foundation Model APIs.

Customers are responsible for ensuring their compliance with applicable terms.

You can now restrict a service principal's OAuth secret to specific API scopes, such as sql or jobs, instead of all APIs. A token minted from a scoped secret can't exceed those scopes, which limits the impact of a leaked secret. See Authorize service principal access to Databricks with OAuth.

The ai_transcribe() SQL function transcribes an audio file into text. It returns the transcript as time-stamped segments, and labels each segment with a speaker when speaker diarization is enabled for your workspace. The output is a VARIANT value, so you can chain it into other AI Functions. This feature is in Beta.

See ai_transcribe function.

Unity Gateway can now track and cap spend on external model providers, such as Amazon Bedrock and Azure AI Foundry, not just Databricks-provided models. If your organization already has capacity commitments directly with a provider, Unity Gateway becomes the single point to track that usage and enforce spend limits across teams and use cases. To turn it on, enable External Model Spend in Budgets (Beta) on the account console Previews page, then select Include external model usage when you create a budget scoped to the Unity Gateway resource type.

See Include external model usage.

You can now publish, govern, and share agent skills with Unity Catalog. A skill is a first-class Unity Catalog securable (catalog.schema.skill) that follows the SKILL.md specification, so you register it once and control who can discover, use, and update it with the same permissions, tags, and audit that protect your tables. Coding agents download published skills or load them live over MCP. See Skills support in Unity Gateway.

You can now run prompts with Genie Code as a task in a Lakeflow Job. Genie Code runs your prompt autonomously. It can read upstream task outputs and call tools as needed. The task returns a link to the resulting Genie Code conversation with its response. See Genie Code task for jobs.

Use Genie Code to develop and troubleshoot deep learning workloads in notebooks connected to AI Runtime. Now in Public Preview, it generates distributed training code, resolves environment and dependency issues, and debugs GPU and distributed workload failures. See Use Genie Code with AI Runtime.

You can now use OpenSharing to share foreign Delta tables, which are Delta-format tables registered in a foreign catalog such as OneLake, a Hive metastore, or AWS Glue. Providers add foreign Delta tables to a share, and recipients access the shared data in read-only format. See Add foreign Delta tables to a share and Read data in a shared foreign Delta table.

The Atlassian Audit Logs connector is now available in Lakeflow Connect in Beta. Workspace admins can control access to this feature from the Previews page.

The connector ingests organization audit log events, such as user, security, and configuration changes, from Atlassian into Databricks. Authentication uses an Atlassian organization API key.

See Atlassian Audit Logs connector.

You can now call ai_parse_document, ai_extract, and ai_classify through the AI Functions REST API. See intelligent document processing for more details.

Zhipu AI GLM 5.3 Flash is now available on Unity Gateway for multimodal reasoning, coding, and agentic workloads. Access it through the same governed API as other models, with centralized permissions, guardrails, spend controls, and observability, and switch models without changing application code.

Customers are responsible for ensuring their compliance with applicable terms.

To query the model and see supported regions, see Use foundation models.

xAI Grok 4.6 is now available on Unity Gateway for reasoning-heavy coding and agentic workflows. Access it through the same governed API as other models, with centralized permissions, guardrails, spend controls, and observability, and switch models without changing application code.

Customers are responsible for ensuring their compliance with applicable terms.

To query the model and see supported regions, see Use foundation models.

Ingesting into streaming tables with Zerobus Ingest in Lakeflow Connect is now generally available. Writing to a streaming table works the same way as writing to a managed Delta table, with the same limits and quotas. See Create or identify the target table.