Mastra shipped @mastra/core@1.69.0 on 2026-09-24: register classifiers on new Mastra({ classifiers }) and use them as typed workflow steps; ClassifierProcessor fails closed by default on I/O/stream; tools can context.background.adopt() long work; @mastra/connect adds ten generated SaaS tool providers (Slack, GitHub, Gmail, …).

Key Takeaways

  • ✓@mastra/core@1.69.0 tagged 2026-09-24 06:58 UTC (npm also rolled 1.70.0 later that day)
  • ✓First-class classifiers with list/add/remove and typed workflow steps + token usage
  • ✓ClassifierProcessor fails closed by default; opt into errorStrategy: 'warn'
  • ✓context.background.adopt({ completion, cancel }) for ack-then-finish tools (in-memory handles)
  • ✓@mastra/connect@0.3.x ships 10 generated providers (Slack, GitHub, Gmail/Calendar, …)
Mastra @mastra/core 1.69.0: first-class classifiers, fail-closed ClassifierProcessor, background.adopt, 10 Connect providers
🖼️Official Media
Click to view high-res
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
No model benchmark in this story · see current rankings
Full Leaderboard→
💰 Cost & PlansCompare
API & Subscription
Compare Plans↗
🛠️ Ecosystem & IDERules
Mastra · TypeScript · classifiers
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
🔗

Project Links & Resources

Direct Access
Direct access to official project resources and documentation
🐙
Mastra @mastra/core@1.69.0 Release
github.com/mastra-ai/mastra/releases/tag/%40mastra/core%401.69.0
↗
📖
Mastra docs
mastra.ai/docs
↗
📝
Mastra homepage
mastra.ai/
↗
🌐
npm @mastra/core
www.npmjs.com/package/@mastra/core
↗
🌐
npm @mastra/connect
www.npmjs.com/package/@mastra/connect
↗
🔬

In-Depth Technical Analysis

Core Background & Industry Pain Points

TS agents need typed routing/safety gates and long-running SaaS tools. Ad-hoc classifiers often fail open; background tools block execute(). Mastra 1.69 makes classifiers, policy processors, and background adopt first-class.

Architecture Highlights & Internals

Register classifiers on new Mastra({ classifiers }) with management APIs and tracing. ClassifierProcessor covers input/output/stream and fails closed by default. Tools context.background.adopt({ completion, cancel }) to ack immediately (in-memory handles). @mastra/connect adds 10 Nango-generated SaaS providers; Inngest runs gain configurable retries and better resume.

Benchmarks & Measured Numbers

No SWE-bench figures. Verified: tag @mastra/core@1.69.0; 10 Connect providers; fail-closed default; Playground UI breakings noted in the release.

Developer Getting Started

Bump @mastra/core to 1.69.0+, read mastra.ai/docs, wire ClassifierProcessor / connect(), see the GitHub release.

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗
Up NextMastra @mastra/core 1.70.0: ModelSelectionProcessor routes cheap vs strong models; durable streams gain closeOnSuspend
Read Now→