Releasesby Glyphprefect 3.7.3 - Scheduler go brrrr
Automatic dependency installation for pulled-code deployments is now opt-in. In 3.7.2, the runner would automatically prepare project dependencies when a deployment pulled code containing a pyproject.toml. This behavior is now disabled by default.
Also shipped Jun 1, 2026Prefect in June 2026 →
Fivetran CLI enters beta, Connect Card gains all_fields parameter
The beta Fivetran CLI manages accounts, connections, schema settings and users and helps develop custom connectors from the terminal. Connect Card's all_fields option shows setup fields hidden by default.
Unlocking a New Way to Build Enterprise Data Apps with Microsoft Fabric
Replit and Microsoft have collaborated to allow developers to build AI-powered applications in Replit and deploy them directly into Microsoft Fabric with enterprise governance.
May Release Spotlight
OpenRouter has released new speech and transcription APIs, Model Fusion, private models, and enterprise workspace controls, alongside 20 new model launches.
Protect apps in the new app builder
Live on cloud • Enterprise Public beta Apps created with the new app builder can now be protected and checked into your chosen Source Control Manager (SCM). Source Control lets organizations manage changes using remote SCM providers GitHub, GitLab, AWS CodeCommit, Bitbucket, and Azure Repos.
Customize RPID values for Passkeys GA
Boost Passkey adoption by enabling shared enrollment across subdomains. You can now customize the RP ID to allow a single Passkey to authenticate users across multiple applications under the same root domain. Now GA!
Fivetran Connector SDK 2.9 logs peak memory and adds Copilot plugins
Version 2.9.2 makes fivetran debug log peak memory usage and adds validation in fivetran init, and 2.9.1 lets fivetran init use Copilot plugins for AI-assisted connector development.
More from PrefectEvery Prefect release →
Prefect 3.7.4 - From cradle to grave
New Features 🎉 Emit lifecycle events (created, updated, deleted) for all domain objects including variables, flows, block documents, block types, concurrency limits, artifact collections, and automations Enhancements ➕➕ Add Redis-backed cleanup queue backend with optimistic transactions and cross-process wakeups Add cleanup reconciler for worker channel...
Prefect 3.7.2 - Delete after running
Enhancements ➕➕ Add delete flow run automation action Add worker channel handshake and heartbeat Add work-pool snapshot delivery to worker channel Index triggers by expect pattern to avoid O(n) scan in find_interested_triggers Cache variable reads within a single resolve_variables() call Cache block document template resolution Validate PEP 508 dependencies...
Prefect 3.7.1
Enhancements ➕➕ - Add deployment_name logging variable - Infer logs page size from API response in CLI - Add default result storage CLI - Add Pydantic-aware tojson template filter - Add worker channel protocol contract - Add worker channel client with REST fallback - Add worker cleanup executor - Add worker work-pool snapshot handling - Add...
Prefect 3.7.5 - No run left CANCELLING
Enhancements ➕➕ Add cancelling timeout cleanup producer Add backend observability for worker channel and cleanup queue Bug Fixes 🐞 Fix pending task runs in flow run graph Add index on event_resources(occurred) for vacuum performance Fix FastAPI 0.137 compatibility , skip route deletion when router is referenced Degrade events WebSocket on transient...
Launch Week: dbt orchestration and infrastructure debugging in Cloud
Prefect Cloud's spring launch week brought first-class dbt orchestration, infrastructure debugging in the run page, managed automations, config plugins, and per-workspace rate limits.
Prefect 3.7.6 - You can only be `Late` once
Bug Fixes 🐞 Return PrefectFutureList from Task.map when deferred=True Fix race condition in UI static directory creation with multiple workers Raise clear error when FlowRun/TaskRun passed as task argument Prevent duplicate Late state transitions in MarkLateRuns Quote -q and -p args separately in work-queue create output Development & Tidiness 🧹 Widen...
Prefect 3.7: infrastructure decorators and plugins are GA
Two of our most-requested experimental surfaces graduate to general availability, flows can render their own dependency graphs, and prepared workspaces now run with uv.
Prefect 3.7.0 - Our little features are all grown up 🥲
Prefect 3.7.0 promotes infrastructure decorators and the plugin system to GA. Infrastructure decorators are now ready for defining reusable run infrastructure directly in Python, and plugins now live in first-class settings with backward-compatible support for existing experimental configuration. Turns out they were just going through a phase.