npx @buildinternet/releases get mastraNew core/server/client support lets you query individual completed spans (with filters, cursors, previews, and model cost) via storage.querySpans() / client.querySpans() / `POST…
Mastra({ channels }) now accepts a resolver function (via channels() in @mastra/connect) so channel connections added/removed on Mastra Platform appear on a running server without redeploy; use…
Classifiers are now registerable on Mastra with a management API and usable as typed workflow steps, while the new ClassifierProcessor enforces classifier policies on agent input, output, and streaming and fails closed by default (opt in to prior fail-open with errorStrategy: 'warn'). Tools can adopt long-running native background operations via context.background.adopt(), @mastra/connect 0.3.0 adds ten generated SaaS tool providers, and Inngest workflows accept a retries option for durable runs.
@mastra/mcp@2.0.0@mastra/mcp is now rebuilt on the MCP 2026-07-28 revision: no initialize handshake/session headers, and tools that need input use first-class suspend/resume (context.suspend() +…
A new Studio Workflow Builder backend can be enabled via the workflowBuilder editor option, adding an editor-owned agent that authors persisted workflow definitions plus new server endpoints (`GET…
Trace querying gains rich predicates for same-span properties (model/provider, duration, outcome, identity, lineage), portable top-level metadata.* filters, and richer feedback/scores filters across Postgres, ClickHouse, and DuckDB. Observability storage adds idempotent batch deleteFeedback() and deleteScores() with matching DELETE /api/observability routes and client methods, plus a deploy-scoped Cloud worker provisioning manifest and first-chunk streaming timeout.
Mastra now has a strict, portable “advanced trace query” contract (bounded time ranges, recursive predicates, thread grouping, deterministic cursor pagination) plus an…
New reusable template APIs in @mastra/platform-workspace plus @mastra/e2b repo templates let sandboxes start from a pre-cloned, pre-built repository image (with background rebuilds and…
AdaptableLogger contract standardizes trace correlation by injecting trace_id/span_id into native log records during traced operations, with loggerOptions controlling correlation and export. PinoLogger implements the adapter. Deployment worker runtime now exposes a /health endpoint (503 during startup, 200 once ready). Also fixed worker schedule discovery, resume robustness with falsy payloads, and broken click-through from Studio. Removed several @mastra/playground-ui DataList API options.
@mastra/elasticsearch adds an ElasticSearchStore that can power memory, workflow snapshots, scores, and semantic recall from a single Elasticsearch cluster, while new @mastra/valkey and…
New dataset experiment APIs let external orchestrators own the experiment loop while Mastra stays the system of record, with server-side run, external result submission, and idempotent finalization. Concurrent workflow resume() calls are now atomic — losers get WORKFLOW_RESUME_ALREADY_CLAIMED and HTTP 409. Also added graceful shutdown controls for generated servers, automatic while-active message delivery in sessions, and a multi-turn LLM judge scorer.
Stored agents created via the Agents API can now run with durable: true, enabling durable execution (with configurable loop settings) without shipping new code, and inheriting cache/pubsub from your…
CostGuardProcessor is renamed to TokenCostControl with new budgeting options (warnAtPercent, per-request maxCost, user/organization/session scopes, per-model breakdowns). Automatic agent runs are now opt-in per Factory on upgrade, and external-parent traces now appear as trace roots in Studio. Also adds Agent.listActiveThreadRuns() and indexed redaction tokens.
File-based agents can now declare recurring tasks via a schedules/ directory (TS or Markdown) that syncs to schedule storage at startup, eliminating runtime registration code and making schedule IDs stable across builds.
###…
processToolResult lets processors scan, transform, or abort tool output before the LLM sees it, and transient: true signals deliver per-turn context without persisting to stored memory. Also added tool definitions to MODEL_GENERATION spans and the @mastra/deepeval exporter; fixed a suspended-runs memory leak and a session resumption bug.
Workflows can now be authored as data and round-trip through JSON via new declarative step entry types (agent, tool, mapping, plus composite entries), with toStorableGraph() and…