| @mastra/core@1.38.0 | ## Highlights ### OAuth ToolProviders runtime for stored agents (connections + toolkit-scoped tool resolution) Mastra now includes the v1 ToolProvider runtime plus server routes, editor wiring, and client SDK methods to manage OAuth-backed connections and let stored agents pin specific connections per toolkit at execution time (including per-author vs shared vs caller-supplied scopes). ### New MySQL storage adapter `@mastra/mysql` adds a first-party MySQL storage backend with broad domai | High | 6/3/2026 |
| @mastra/core@1.37.0 | ## Highlights ### Google Cloud Spanner Storage Adapter (`@mastra/spanner@1.0.0`) New first-party storage backend for Google Cloud Spanner (GoogleSQL) covering most Mastra storage domains (memory, workflows, schedules, observability, etc.), including persisting tracing spans for Studio and supporting the local Spanner emulator. ### Agent Channels Streaming UX + Tool Rendering Controls (Core + Slack) Major upgrades to channel adapters: opt-in streaming text deltas, adaptive typing indicato | High | 5/27/2026 |
| @mastra/core@1.35.0 | ## Highlights ### FGA Route Policy Coverage + Resolver Hooks (Core/Server/WorkOS) New FGA route policy coverage controls add guardrails for protected routes, with built-in resource route metadata resolution and resolver hooks so you can centrally map route → `{resourceType, resourceId, permission}` while still overriding per-route config. ### Favorites Storage Domain for Agents/Skills (Core + Storage Adapters) A new `favorites` storage domain lets users favorite/unfavorite stored agents | High | 5/18/2026 |
| @mastra/core@1.33.0 | ## Highlights ### Push-capable PubSub + HTTP workflow event ingestion Mastra now supports push delivery for workflow events: PubSubs declare `supportedModes`, `Mastra.handleWorkflowEvent(event)` is the unified entry point, and servers expose `POST /api/workflows/events` so brokers like GCP Pub/Sub push/SNS/EventBridge can deliver events over HTTP (no pull worker required). ### Response caching for identical LLM steps (`ResponseCache`) A new opt-in `ResponseCache` input processor can skip | High | 5/13/2026 |
| @mastra/core@1.32.0 | ## Highlights ### Fine-Grained Authorization (FGA) across Mastra (core + server adapters + MCP) Mastra now supports relationship-based, resource-level authorization with centralized enforcement before agent runs (`generate()`/`stream()`), tool/workflow execution, and memory thread access via new `IFGAProvider`/`IFGAManager` + `checkFGA()`/`FGADeniedError`. FGA is also enforced consistently in `@mastra/server` handlers, all built-in server adapters (Express/Fastify/Hono/Koa), and MCP tool exe | High | 5/6/2026 |
| @mastra/core@1.31.0 | ## Highlights ### Platform Channels Framework (Core + Server + Client) A new channels architecture adds `ChannelProvider`, a dedicated `ChannelsStorage` domain, and `ChannelConnectResult` connection flows (OAuth, deep link, immediate), with Mastra-level `connect/disconnect/list` APIs and matching `MastraClient.channels` methods. ### Slack Channel Integration (`@mastra/slack`) New Slack provider connects agents to Slack workspaces with OAuth-based app provisioning, manifest drift detectio | High | 5/4/2026 |
| @mastra/core@1.29.0 | ## Highlights ### Azure Blob Storage workspace + blob store (`@mastra/azure`) New `@mastra/azure` adds an Azure Blob Storage `WorkspaceFilesystem` provider (`@mastra/azure/blob`) and an `AzureBlobStore` content-addressable store for skill versioning, with support for connection string, account key, SAS token, `DefaultAzureCredential`, anonymous auth, prefix namespacing, and read-only mode. ### Stream “until idle” to include background task results in the same turn `agent.streamUntilIdle( | High | 4/30/2026 |
| @mastra/core@1.27.0 | ## Highlights ### CLI-Driven Browser Automation + Screencasts `@mastra/core` and the new `@mastra/browser-viewer` package add end-to-end browser automation for CLI-based agent workflows. `BrowserViewer` launches Chrome via Playwright with remote debugging, and a new `BrowserCliHandler` automatically detects browser CLIs (`agent-browser`, `browser-use`, `browse`) and injects the CDP URL into commands — no manual wiring needed. Browser sessions are thread-isolated with automatic lifecycle ma | High | 4/24/2026 |
| @mastra/core@1.24.0 | ## Highlights ### End-to-end RAG Tracing + New RAG/Graph Span Types RAG ingestion and query operations are now visible in Mastra tracing with new span types (e.g., `RAG_INGESTION`, `RAG_EMBEDDING`, `RAG_VECTOR_OPERATION`, `RAG_ACTION`, `GRAPH_ACTION`) plus helpers like `startRagIngestion()` / `withRagIngestion()`. Instrumentation is opt-in via an `observabilityContext`, and `@mastra/rag` automatically threads context from agent `TOOL_CALL` spans into vector and graph tools. ### CloudExpor | High | 4/8/2026 |
| @mastra/core@1.16.0 | ## Highlights ### Smarter Model Selection for Observational Memory `@mastra/memory` now lets you route observer and reflector calls to different models based on input size using `ModelByInputTokens`. Short inputs can go to a fast, cheap model while longer ones get sent to a more capable one -- all configured declaratively with token thresholds. Tracing shows which model was selected and why. ### MongoDB Support for Datasets and Experiments `@mastra/mongodb` now stores versioned datas | Medium | 3/26/2026 |
| @mastra/core@1.14.0 | ## Highlights ### AI Gateway Tool Support in the Agentic Loop `@mastra/core` now supports AI Gateway tools (e.g. `gateway.tools.perplexitySearch()`) as provider-executed tools: it infers `providerExecuted`, merges streamed provider results back into the originating tool calls, and skips local execution when the provider already returned a result. ### More Reliable Observational Memory (Cache Stability + “As Of” Retrieval) Observational memory persistence is more stable via dated message | Low | 3/19/2026 |
| @mastra/core@1.13.0 | ## Highlights ### Observability Storage Domain (schemas + in-memory implementations) Mastra now ships zod-based storage schemas and in-memory implementations for all observability signals (scores, logs, feedback, metrics, discovery), with full type inference and a base `ObservabilityStorage` that includes default method implementations. ### New persistent Workspace filesystem: `@mastra/agentfs` The new `AgentFSFilesystem` workspace provider adds Turso/SQLite-backed, database-persistent f | Low | 3/17/2026 |
| @mastra/core@1.12.0 | ## Highlights ### Cloudflare Durable Objects Storage Adapter `@mastra/cloudflare` adds a new Durable Objects–backed storage implementation (in addition to KV), with SQLite persistence, batch operations, and table/column validation—enabling more robust stateful storage on Cloudflare. ### Workspace Filesystem Path Resolution Now Matches Real Filesystem Semantics `LocalFilesystem` no longer treats absolute paths like `/file.txt` as workspace-relative; absolute paths now resolve to real file | Low | 3/16/2026 |
| @mastra/core@1.11.0 | ## Highlights ### Dynamic Model Fallback Arrays (Runtime Routing) Agents can now use `model` functions that return full fallback arrays (`ModelWithRetries[]`), enabling context-driven model routing (tier/region/etc.) with nested/async selection and proper `maxRetries` inheritance. ### Standard Schema + Zod v4 Compatibility Layer Mastra adds Standard Schema normalization (`toStandardSchema`, `standardSchemaToJSONSchema`) across Zod v3/v4, AI SDK Schema, and JSON Schema via `@mastra/schema | Low | 3/16/2026 |
| @mastra/core@1.10.0 | ## Highlights ### Tool `inputExamples` to improve model tool-call accuracy Tool definitions can now include `inputExamples`, which are passed through to models that support them (e.g., Anthropic’s `input_examples`) to demonstrate valid inputs and reduce malformed tool calls. ### MCP client fetch hooks now receive `RequestContext` (auth/cookie forwarding) `@mastra/mcp` adds requestContext support to custom `fetch` functions for MCP HTTP server definitions, enabling request-scoped forw | Low | 3/9/2026 |
| @mastra/core@1.9.0 | ## Highlights ### Major Workspace & Sandbox upgrades (token-aware output, mounts, process control, LSP resolution) Workspaces get significant capabilities: workspace tool output is now token-limited, ANSI-stripped for model context, and `.gitignore`-aware to reduce token usage. Sandbox commands support `abortSignal` for cancellation, plus background process streaming callbacks (`onStdout`/`onStderr`/`onExit`), and local symlink mounts in `LocalSandbox`. Tools can be exposed under custom na | Low | 3/4/2026 |
| @mastra/core@1.8.0 | ## Highlights ### Supervisor Pattern for Multi-Agent Coordination A new supervisor pattern enables orchestrating multiple agents via `stream()` and `generate()`, with delegation hooks, iteration monitoring, completion scoring, memory isolation, tool approval propagation, context filtering, and a bail mechanism. ### Metadata-Only Vector Queries (Optional `queryVector`) Vector querying now supports metadata-only retrieval by making `queryVector` optional (with at least one of `queryVector` | Low | 3/2/2026 |
| @mastra/core@1.7.0 | ## Highlights ### Background Process Management in Workspaces & Sandboxes Workspaces now support spawning and managing long-running background processes (via `SandboxProcessManager` / `ProcessHandle`), with new tools like `execute_command` (`background: true`), `get_process_output`, and `kill_process` plus improved streaming terminal-style UI. ### Runtime Tool Configuration Updates via `Workspace.setToolsConfig()` You can dynamically enable/disable tools at runtime on an existing workspa | Low | 2/25/2026 |
| @mastra/core@1.6.0 | ## Highlights ### AST-Based Workspace Edit Tool (`mastra_workspace_ast_edit`) A new AST edit tool enables intelligent code transformations (rename identifiers, add/remove/merge imports, pattern-based replacements with metavariables) and is automatically available when `@ast-grep/napi` is installed, enabling robust refactors beyond string-based edits. ### Harness UX + Built-ins: Streaming Tool Argument Previews and Task Tools Tool renderers now stream argument previews in real time (i | Low | 2/24/2026 |
| @mastra/core@1.5.0 | ## Highlights ### Core Harness: A Reusable Orchestration Layer for Agent Apps A new generic `Harness` in `@mastra/core` provides a foundation for building agent-powered applications with modes, state management, built-in tools (`ask_user`, `submit_plan`), subagent support, Observational Memory integration, model discovery, permission-aware tool approval, and event-driven/thread/heartbeat management. ### Workspace Capability Upgrades (Security, Discovery, and Search) Workspaces gain * | Low | 2/20/2026 |
| @mastra/core@1.4.0 | ## Highlights ### Datasets & Experiments (core + server + Studio UI) Mastra now has first-class evaluation primitives: versioned Datasets (with JSON Schema validation and SCD-2 item versioning) and Experiments that run agents against datasets with configurable scorers and result tracking. This ships end-to-end across `@mastra/core` APIs, new `/datasets` REST endpoints in `@mastra/server`, and a full Studio UI for managing datasets, triggering experiments, and comparing results. ### Work | Low | 2/16/2026 |
| @mastra/core@1.3.0 | ## Highlights ### Observational Memory Async Buffering (default-on) + New Streaming Events Observational memory now buffers background observations/reflections by default to avoid blocking as conversations grow, and introduces structured streaming status/events (`data-om-status` plus buffering start/end/failed markers) for better UI/telemetry. ### Workspace Mounts (CompositeFilesystem) Workspaces can now mount multiple filesystem providers (S3/GCS/local/etc.) into a single unified di | Low | 2/11/2026 |
| mastra@1.2.0 | ## Highlights ### Observational Memory for long-running agents Observational Memory is a new Mastra Memory feature which makes small context windows behave like large ones, while retaining long-term memory. It compresses conversations into dense observations logs (5–40x smaller than raw messages). When observations grow too long, they're condensed into reflections. Supports thread and resource scopes. It requires the latest versions of `@mastra/core`, `@mastra/memory`, `mastra`, and `@mast | Low | 2/4/2026 |
| mastra@1.1.0 | ## Highlights ### Unified Workspace API (Filesystem + Sandbox Execution + Search + Skills) A new `Workspace` capability unifies agent-accessible filesystem operations, sandboxed command/code execution, keyword/semantic/hybrid search, and SKILL.md discovery with safety controls (read-only, approval flows, read-before-write guards). The Workspace is exposed end-to-end: core Workspace class (`@mastra/core/workspace`), server API endpoints (`/workspaces/...`), and new `@mastra/client-js` works | Low | 1/30/2026 |
| @mastra/core@1.0.0-beta.21 | # Changelog ## [@mastra/ai-sdk@1.0.0-beta.14](https://github.com/mastra-ai/mastra/blob/8edb59796838fbece6868afc558af4c3581c0e9b/client-sdks/ai-sdk/CHANGELOG.md) ### Patch Changes - Add structured output support to agent.network() method. Users can now pass a `structuredOutput` option with a Zod schema to get typed results from network execution. ([#11701](https://github.com/mastra-ai/mastra/pull/11701)) The stream exposes `.object` (Promise) and `.objectStream` (ReadableStream) get | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.20 | # Changelog ## [@mastra/ai-sdk@1.0.0-beta.13](https://github.com/mastra-ai/mastra/blob/b3e7a74b36001336085d9b02be9bfafca8762f3f/client-sdks/ai-sdk/CHANGELOG.md) ### Patch Changes - Add embedded documentation support for Mastra packages ([#11472](https://github.com/mastra-ai/mastra/pull/11472)) Mastra packages now include embedded documentation in the published npm package under `dist/docs/`. This enables coding agents and AI assistants to understand and use the framework by reading | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.19 | # Changelog ## [@mastra/ai-sdk@1.0.0-beta.12](https://github.com/mastra-ai/mastra/blob/483764477e6a596e7809552d59ef380bf04152e7/client-sdks/ai-sdk/CHANGELOG.md) ### Patch Changes - Fix data chunk property filtering to only include type, data, and id properties ([#11477](https://github.com/mastra-ai/mastra/pull/11477)) Previously, when `isDataChunkType` checks were performed, the entire chunk object was returned, potentially letting extra properties like `from`, `runId`, `metadata`, | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.18 | # Changelog ## [@mastra/core@1.0.0-beta.18](https://github.com/mastra-ai/mastra/blob/3d9c9fb3cda8825b2d61a17e78d15f29470d2a28/packages/core/CHANGELOG.md) ### Patch Changes - Fixed semantic recall fetching all thread messages instead of only matched ones. ([#11435](https://github.com/mastra-ai/mastra/pull/11435)) When using `semanticRecall` with `scope: 'thread'`, the processor was incorrectly fetching all messages from the thread instead of just the semantically matched messages wi | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.17 | # Changelog ## [@mastra/core@1.0.0-beta.17](https://github.com/mastra-ai/mastra/blob/4cbe85007721a517939d67e5967d59ea7a62bc16/packages/core/CHANGELOG.md) ### Patch Changes - Fix Zod 4 compatibility for storage schema detection ([#11431](https://github.com/mastra-ai/mastra/pull/11431)) If you're using Zod 4, `buildStorageSchema` was failing to detect nullable and optional fields correctly. This caused `NOT NULL constraint failed` errors when storing observability spans and other dat | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.16 | # Changelog ## [@mastra/agent-builder@1.0.0-beta.8](https://github.com/mastra-ai/mastra/blob/a82c2753261d52d3ff2205bda99aa79ea000bc1b/packages/agent-builder/CHANGELOG.md) ### Patch Changes - Fixed inline type narrowing for `tool.execute()` return type when using `outputSchema`. ([#11420](https://github.com/mastra-ai/mastra/pull/11420)) **Problem:** When calling `tool.execute()`, TypeScript couldn't narrow the `ValidationError | OutputType` union after checking `'error' in result && | Low | 1/10/2026 |
| @mastra/core@0.24.10-alpha.0 | # Changelog ## [@mastra/core@0.24.10-alpha.0](https://github.com/mastra-ai/mastra/blob/fd37787c80842aa7dc0ab458dad4d4665a6804f7/packages/core/CHANGELOG.md) ### Patch Changes - Fix model-level and runtime header support for LLM calls ([#11303](https://github.com/mastra-ai/mastra/pull/11303)) This fixes a bug where custom headers configured on models (like `anthropic-beta`) were not being passed through to the underlying AI SDK calls. The fix properly handles headers from multiple so | Low | 1/10/2026 |
| 2025-12-18 | # Changelog ## [@mastra/deployer@0.24.9-alpha.1](https://github.com/mastra-ai/mastra/blob/aab8fd14310b23da8ed5ab0e24517a341ff54e1f/packages/deployer/CHANGELOG.md) ### Patch Changes - Update prompt handler to use new scoring system instead of deprecated evals. ([#11274](https://github.com/mastra-ai/mastra/pull/11274)) --- ## [@mastra/server@0.24.9-alpha.1](https://github.com/mastra-ai/mastra/blob/aab8fd14310b23da8ed5ab0e24517a341ff54e1f/packages/server/CHANGELOG.md) ### Patch Ch | Low | 1/10/2026 |
| @mastra/core@0.24.9-alpha.0 | # Changelog ## Summary - **Total packages with changes**: 14 - **Packages with major changes**: 0 - **Packages with minor changes**: 0 - **Packages with patch changes**: 1 --- ## @mastra/client-js@0.17.2-alpha.0 ### Dependency Updates - @mastra/core@0.24.9-alpha.0 --- ## @mastra/core@0.24.9-alpha.0 ### Patch Changes - Fix memory leak in telemetry decorators when processing large payloads. The `@withSpan` decorator now uses bounded serialization utilities to prevent unbounded memory gro | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.14 | # Changelog ## [@mastra/agent-builder@1.0.0-beta.6](https://github.com/mastra-ai/mastra/blob/f6c82ec3e48315735dfd80b9571623abe2677174/packages/agent-builder/CHANGELOG.md) ### Patch Changes - Add support for AI SDK v6 (LanguageModelV3) ([#11191](https://github.com/mastra-ai/mastra/pull/11191)) Agents can now use `LanguageModelV3` models from AI SDK v6 beta providers like `@ai-sdk/openai@^3.0.0-beta`. **New features:** - Usage normalization: V3's nested usage format is normal | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.13 | # Changelog ## [@mastra/core@1.0.0-beta.13](https://github.com/mastra-ai/mastra/blob/79c7a8782284f324db8df7897289783680c74732/packages/core/CHANGELOG.md) ### Patch Changes - Add `onFinish` and `onError` lifecycle callbacks to workflow options ([#11200](https://github.com/mastra-ai/mastra/pull/11200)) Workflows now support lifecycle callbacks for server-side handling of workflow completion and errors: - `onFinish`: Called when workflow completes with any status (success, failed, | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.12 | # Changelog ## Summary - **Total packages with changes**: 39 - **Packages with major changes**: 0 - **Packages with minor changes**: 0 - **Packages with patch changes**: 26 --- ## @mastra/agent-builder@1.0.0-beta.5 ### Patch Changes - Embed AI types to fix peerdeps mismatches ([`9650cce`](https://github.com/mastra-ai/mastra/commit/9650cce52a1d917ff9114653398e2a0f5c3ba808)) ### Dependency Updates - @mastra/core@1.0.0-beta.12 - @mastra/memory@1.0.0-beta.5 --- ## @mastra/ai-sdk@1.0.0-beta | Low | 1/10/2026 |
| 2025-12-10 | # Changelog ## Summary - **Total packages with changes**: 13 - **Packages with major changes**: 0 - **Packages with minor changes**: 0 - **Packages with patch changes**: 1 --- ## @mastra/client-js@0.17.1-alpha.0 ### Dependency Updates - @mastra/core@0.24.8-alpha.0 --- ## @mastra/dane@0.1.25-alpha.0 ### Dependency Updates - @mastra/core@0.24.8-alpha.0 --- ## @mastra/deployer@0.24.8-alpha.0 ### Patch Changes - Add simple virtual check for tsconfigpaths plugin, misbehaves on CI ([#110 | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.11 | # Changelog ## Summary - **Total packages with changes**: 16 - **Packages with major changes**: 0 - **Packages with minor changes**: 1 - **Packages with patch changes**: 10 --- ## @mastra/ai-sdk@1.0.0-beta.8 ### Patch Changes - Support new Workflow tripwire run status. Tripwires that are thrown from within a workflow will now bubble up and return a graceful state with information about tripwires. ([#10947](https://github.com/mastra-ai/mastra/pull/10947)) When a workflow contains an agen | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.10 | # Changelog ## Summary - **Total packages with changes**: 35 - **Packages with major changes**: 0 - **Packages with minor changes**: 4 - **Packages with patch changes**: 29 --- ## @mastra/arize@1.0.0-beta.5 ### Patch Changes - Fixed CachedToken tracking in all Observability Exporters. Also fixed TimeToFirstToken in Langfuse, Braintrust, PostHog exporters. Fixed trace formatting in Posthog Exporter. ([#11029](https://github.com/mastra-ai/mastra/pull/11029)) ### Dependency Updates - @mastr | Low | 1/10/2026 |
| @mastra/core@unknown | # Changelog ## Summary - **Total packages with changes**: 12 - **Packages with major changes**: 0 - **Packages with minor changes**: 0 - **Packages with patch changes**: 4 --- ## @mastra/agent-builder@0.2.6-alpha.1 ### Patch Changes - Fix install step validation error by making targetPath optional in InstallInputSchema. This resolves the "expected string, received undefined" error when running the agent builder template workflow without explicitly providing a targetPath parameter. ([#10923 | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.9 | # Changelog ## Summary - **Total packages with changes**: 22 - **Packages with major changes**: 0 - **Packages with minor changes**: 4 - **Packages with patch changes**: 12 --- ## @mastra/ai-sdk@1.0.0-beta.7 ### Patch Changes - Return NetworkDataPart on each agent-execution-event and workflow-execution-event in network streams ([#10982](https://github.com/mastra-ai/mastra/pull/10982)) - Fixed tool-call-suspended chunks being dropped in workflow-step-output when using AI SDK. Previously, w | Low | 1/10/2026 |
| @mastra/core@0.24.7-alpha.2 | # Changelog ## Summary - **Total packages with changes**: 11 - **Packages with major changes**: 0 - **Packages with minor changes**: 0 - **Packages with patch changes**: 3 --- ## @mastra/client-js@0.17.0-alpha.2 ### Patch Changes - The client-js package had its own simpler zodToJsonSchema implementation that was missing critical features from schema-compat. This could cause issues when users pass Zod schemas with `z.record()` or `z.date()` through the MastraClient. ([#10925](https://github | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.8 | # Changelog ## Summary - **Total packages with changes**: 29 - **Packages with major changes**: 0 - **Packages with minor changes**: 1 - **Packages with patch changes**: 18 --- ## @mastra/agent-builder@1.0.0-beta.4 ### Patch Changes - Fix install step validation error by making targetPath optional in InstallInputSchema. This resolves the "expected string, received undefined" error when running the agent builder template workflow without explicitly providing a targetPath parameter. ([#10922 | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.7 | # Changelog ## Summary - **Total packages with changes**: 46 - **Packages with major changes**: 0 - **Packages with minor changes**: 14 - **Packages with patch changes**: 40 --- ## @mastra/arize@1.0.0-beta.3 ### Patch Changes - Updated OtelExporters, Bridge, and Arize packages to better implement GenAI v1.38.0 Otel Semantic Conventions. See: ([#10591](https://github.com/mastra-ai/mastra/pull/10591)) https://github.com/open-telemetry/semantic-conventions/blob/v1.38.0/docs/gen-ai/README.md | Low | 1/10/2026 |
| @mastra/core@0.24.7-alpha.1 | # Changelog ## Summary - **Total packages with changes**: 28 - **Packages with major changes**: 0 - **Packages with minor changes**: 1 - **Packages with patch changes**: 22 --- ## @mastra/agent-builder@0.2.6-alpha.0 ### Dependency Updates - @mastra/core@0.24.7-alpha.1 - @mastra/memory@0.15.13-alpha.0 --- ## @mastra/braintrust@0.2.4-alpha.0 ### Patch Changes - Adds `braintrustLogger` as a parameter to `BraintrustExporter` allowing developers to pass in their own braintrust logger. ([#10 | Low | 1/10/2026 |
| @mastra/core@0.24.7-alpha.0 | # Changelog ## Summary - **Total packages with changes**: 14 - **Packages with major changes**: 0 - **Packages with minor changes**: 0 - **Packages with patch changes**: 2 --- ## @mastra/client-js@0.16.16-alpha.0 ### Dependency Updates - @mastra/core@0.24.7-alpha.0 --- ## @mastra/core@0.24.7-alpha.0 ### Patch Changes - Fix corrupted provider-registry.json file ([#10605](https://github.com/mastra-ai/mastra/pull/10605)) --- ## @mastra/dane@0.1.24-alpha.0 ### Dependency Updates - @mas | Low | 1/10/2026 |
| @mastra/core@1.0.0-beta.6 | # Changelog ## Summary - **Total packages with changes**: 47 - **Packages with major changes**: 1 - **Packages with minor changes**: 18 - **Packages with patch changes**: 31 --- ## @mastra/agent-builder@1.0.0-beta.3 ### Dependency Updates - @mastra/core@1.0.0-beta.6 - @mastra/memory@1.0.0-beta.3 --- ## @mastra/ai-sdk@1.0.0-beta.5 ### Minor Changes - Add framework-agnostic stream handlers for use outside of Hono/Mastra server ([#10628](https://github.com/mastra-ai/mastra/pull/10628)) | Low | 1/10/2026 |
| @mastra/core@0.24.6 | # Highlights ## Stream nested execution context from Workflows and Networks to your UI Agent responses now stream live through workflows and networks, with complete execution metadata flowing to your UI. **In workflows**, pipe agent streams directly through steps: ```typescript const planActivities = createStep({ execute: async ({ mastra, writer }) => { const agent = mastra?.getAgent('weatherAgent'); const response = await agent.stream('Plan activities'); await res | Low | 11/27/2025 |
| @mastra/core@0.24.3 | # Highlights ## Generate Endpoint Fix for OpenAI Streaming We've switched to using proper generate endpoints for model calls, fixing a critical permission issue with OpenAI streaming. No more 403 errors when your users don't have full model permissions - the generate endpoint respects granular API key scopes properly. ## AI SDK v5: Fine-Grained Stream Control Building custom UIs? You now have complete control over what gets sent in your AI SDK streams. Configure exactly which message | Low | 11/20/2025 |
| @mastra/core@0.24.1 | # Highlights ## 1.0 Beta is ready! We've worked hard on a 1.0 beta version to signal that Mastra is ready for prime time and there will not be any breaking changes in the near future. Please visit the [migration guide](https://mastra.ai/guides/v1/migrations/upgrade-to-v1/overview) to get started. ## Improved support for files in models We added the ability not to download images or any supported files by the model, and instead send the raw URL so it can handle it on its own. This impro | Low | 11/14/2025 |
| @mastra/core@0.24.0 | # Highlights This release focuses primarily on bug fixes and stability improvements. ## AI-SDK We've resolved several issues related to message deduplication and preserving lastMessageIds. More importantly, this release adds support for suspend/resume operations and custom data writes, with network data now properly surfacing as data-parts. ## Bundling We've fully resolved bundling issues with the reflect-metadata package by ensuring it's not removed during the bundling step. This | Low | 11/5/2025 |
| @mastra/core@0.23.3 | # Highlights ### Tool Schema Validation Fixed a critical bug in `@mastra/core` where tool input validation used the original Zod schema while LLMs received a transformed version. This caused validation failures with models like OpenAI o3 and Claude 3.5 Haiku that send valid responses matching the transformed schema (e.g., converting .optional() to .nullable()). # Changelog ## @mastra/ai-sdk - Fix usage tracking with agent network ([#9226](https://github.com/mastra-ai/mastra/pull/922 | Low | 11/3/2025 |
| @mastra/core@0.23.1 | # Changelog ## @mastra/agent-builder - Update peerdeps to 0.23.0-0 ([#9043](https://github.com/mastra-ai/mastra/pull/9043)) ## @mastra/ai-sdk - Pass original messages in chatRoute to fix uiMessages duplication #8830 ([#8904](https://github.com/mastra-ai/mastra/pull/8904)) - network routing agent text delta ai-sdk streaming ([#8979](https://github.com/mastra-ai/mastra/pull/8979)) - Support writing custom top level stream chunks ([#8922](https://github.com/mastra-ai/mastra/pull/8922)) - R | Low | 10/28/2025 |
| @mastra/core@0.21.1 | # Highlights ## Model Routing everywhere Model configuration has been unified across `@mastra/core`, `@mastra/evals`, and related packages, with all components now accepting the same flexible Model Configuration. This enables consistent model specification using magic strings ("openai/gpt-4o"), config objects with custom URLs, or dynamic resolution functions across scorers, processors, and relevance scoring components. ```typescript // All of these now work everywhere models are accept | Low | 10/16/2025 |
| @mastra/core@0.20.1 | ## Highlights ### Workflows Workflows now support global state, you can now read `state` in each of your defined steps and set it with`setState`. This makes it easier to manage state over multiple steps nstead of passing it through input/output variables. ```typescript const firstStep = createStep({ id: "first-step", execute({ setState }) { setState({ myValue: "a value", }); }, }); const secondStep = createStep({ id: "second-step", execute({ state }) { | Low | 10/8/2025 |
| @mastra/core@0.20.0 | # Mastra Release - 2025-10-03 This release includes improvements to documentation, playground functionality, API naming conventions, and various bug fixes across the platform. ## Agents - Reorganizes the agent memory documentation by explaining async memory configuration, introducing runtime context, and moving detailed content to the appropriate Memory section. [#8410](https://github.com/mastra-ai/mastra/pull/8410) ## CLI / Playground - Fixes a bug where the shell option was brea | Low | 10/3/2025 |
| @mastra/core@0.19.1 | # Mastra Release - 2025-10-01 We are excited to announce the release of our new **model router** and model fallbacks! You can now choose any model provider and model without the need to install or import it. If one model is not functioning properly, you will automatically be able to fallback to another model. ## Agents - Updates step identification by including description and component key when steps are created from agents or tools, and updates related tests. [#8151](https://github.co | Low | 10/1/2025 |
| @mastra/core@0.18.0 | # Mastra Release - 2025-09-23 ## Agents - Bugs related to agent type handling. [#8072](https://github.com/mastra-ai/mastra/pull/8072) - An error related to the tripwire controller being closed prematurely. [#8099](https://github.com/mastra-ai/mastra/pull/8099) - The type system for agent output options by introducing a single OUTPUT generic, ensuring mutual exclusivity between 'output' and 'structuredOutput', improving type inference and safety, and laying the groundwork for future struc | Low | 9/23/2025 |
