Evaluate streaming responses incrementally with service policies (Beta)
Databricks introduced incremental streaming evaluation in Beta for model output service policies, alongside an option for full response evaluation buffering.
Also shipped Nov 18, 2026Databricks in November 2026 →
V3 progress control | CodeRabbit Cloud, V3 review settings preview
CodeRabbit updated progress controls in the V3 review settings preview, allowing progress_updates configuration to control review-progress reporting format.
Hyperdrive, Workers VPC - Custom CA and client certificates (mTLS) for Workers VPC
Cloudflare Workers VPC now supports custom certificate authority (CA) verification and mutual TLS (mTLS) authentication for private VPC Services.
Spark Monitoring UI (General availability)
Snowflake announced the general availability of the Spark Monitoring UI in Snowsight for tracking and troubleshooting Snowpark Connect for Spark jobs and sessions.
Amazon OpenSearch Memory is now generally available
Amazon OpenSearch Memory is now generally available as a serverless capability in Amazon OpenSearch Service to store, extract, and retrieve persistent memory for AI agents.
Introducing the Apache Spark Optimization Agent for AWS Glue ETL
AWS Glue ETL introduced the Apache Spark Optimization Agent, which analyzes completed Spark runs to deliver automated cost and performance recommendations.
Gemini 4 Neon (GA)
Google Cloud announced the general availability of Gemini 4 Neon in Gemini Enterprise Agent Platform, supporting a 1M-token context window and four thinking levels.
More from Agent Bricks and Mosaic AIEvery Agent Bricks and Mosaic AI release →
Smart Routing now supports external models for coding agents (Beta)
Databricks added support for routing coding-agent subagents to external model providers in the Unity Gateway Managed Configuration beta.
Service policies protect embedding inputs (Beta)
Databricks added a Beta capability allowing service policies to run against single or batch embedding inputs to mask sensitive data and block unsafe content.
Gemini 3.6 Flash will be retired on November 19, 2026
Databricks announced that Google Gemini 3.6 Flash will be retired on November 19, 2026, after which calls will automatically redirect to Gemini 3.8 Flash.
Gemini 3.6 Flash is retired
Google Gemini 3.6 Flash was retired on November 19, 2026, with API calls automatically redirecting to Gemini 3.8 Flash at the same price.
Analyze agent usage and find wasted tokens with Unity Gateway Insights (Beta)
Unity Gateway Insights is now in beta, providing reports on agent usage and token consumption. It helps identify wasted tokens by analyzing session samples from the unified trace table.
OpenAI GPT-6.2 Astra and Sol are now available on Unity Gateway
OpenAI GPT-6.2 Astra and GPT-6.2 Sol models are now available on Unity Gateway. These models support text and image inputs, function calling, and reasoning.
Share Unity Catalog agent skills with OpenSharing and Databricks Marketplace (Beta)
Databricks launched a beta allowing data providers to include Unity Catalog agent skills in OpenSharing shares and Databricks Marketplace listings. Recipients receive read-only access to shared skills, and updates made by the provider sync asynchronously.
Google Gemini 4 Hydrogen is now available on Unity Gateway
Databricks made Google Gemini 4 Hydrogen available on Unity Gateway via Foundation Model APIs.