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.
Also shipped Nov 19, 2026Databricks in November 2026 →
Wait for pull request events with GitHub CLI
GitHub CLI gh v2.105.0 added preview support for gh event listen, enabling users and agents to subscribe to pull request events without polling.
Gemini 4 Hydrogen in CodeMender (Preview)
Google Cloud added preview support for Gemini 4 Hydrogen in CodeMender, accessible by supplying the --model gemini-4-hydrogen flag to cm subcommands.
Data Engineering Agent observability is generally available in BigQuery
BigQuery added general availability for Data Engineering Agent observability, allowing users to track request volume, model latency, token usage, and tool traces in Cloud Monitoring and Cloud Trace.
BigQuery introduces AI indexes in Preview
Google Cloud released AI indexes in BigQuery in Preview, enabling natural language search across columns using the AI.SEARCH function without manual embedding generation.
BigQuery Migration Service adds table validation in Preview
BigQuery Migration Service launched a table validation feature in Preview to verify schemas, row counts, and aggregated metrics between source databases and BigQuery tables.
BigQuery generative AI functions now support gemini-4-neon
BigQuery generative AI functions now support the generally available gemini-4-neon model.
More from Agent Bricks and Mosaic AIEvery Agent Bricks and Mosaic AI release →
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.
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.
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.
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.
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.