build(deps): bump @mastra/memory from 1.6.1 to 1.17.4

[dependabot]

Bumps @mastra/memory from 1.6.1 to 1.17.4.

Release notes

Sourced from @​mastra/memory's releases.

Mar 25, 2026

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 datasets with full item history and time-travel queries, plus experiment results and CRUD. If you're already using MongoDBStore, this works automatically with no extra setup.

Okta Auth and RBAC

New @mastra/auth-okta package brings SSO authentication and role-based access control via Okta. Map Okta groups to Mastra permissions, verify JWTs against Okta's JWKS endpoint, and manage sessions -- or pair Okta RBAC with a different auth provider like Auth0 or Clerk.

Breaking Changes

• None called out in this changelog.

Changelog

@​mastra/core@​1.16.0

Minor Changes

• Added dataset-agent association and experiment status tracking for the Evaluate workflow. (#14470)

  • Dataset targeting: Added targetType and targetIds fields to datasets, enabling association with agents, scorers, or workflows. Datasets can now be linked to multiple entities.
  • Experiment status: Added status field to experiment results ('needs-review', 'reviewed', 'complete') for review queue workflow.
  • Dataset experiment routes: Added API endpoints for triggering experiments from a dataset with configurable target type and target ID.
  • LLM data generation: Added endpoint for generating dataset items using an LLM with configurable count and prompt.
  • Failure analysis: Added endpoint for clustering experiment failures and proposing tags using LLM analysis.

• Added agent version support for experiments. When triggering an experiment, you can now pass an agentVersion parameter to pin which agent version to use. The agent version is stored with the experiment and returned in experiment responses. (#14562)

  const client = new MastraClient();
  await client.triggerDatasetExperiment({
  datasetId: "my-dataset",
  targetType: "agent",
  targetId: "my-agent",
  version: 3, // pin to dataset version 3
  agentVersion: "ver_abc123" // pin to a specific agent version
  });

• Added tool suspension handling to the Harness. (#14611)

  When a tool calls suspend() during execution, the harness now emits a tool_suspended event, reports agent_end with reason 'suspended', and exposes respondToToolSuspension() to resume execution with user-provided data.

... (truncated)

Changelog

Sourced from @​mastra/memory's changelog.

1.17.4

Patch Changes

• Fixed idle timeout and provider-change observation activations blocking on in-progress reflection buffering. These triggers now return immediately, letting the background reflection complete asynchronously. (#15937)

• Updated dependencies [920c757, d587199, 1fe2533, f8694b6]:

  • @​mastra/core@​1.30.0

1.17.4-alpha.0

Patch Changes

• Fixed idle timeout and provider-change observation activations blocking on in-progress reflection buffering. These triggers now return immediately, letting the background reflection complete asynchronously. (#15937)

• Updated dependencies [d587199]:

  • @​mastra/core@​1.29.2-alpha.0

1.17.3

Patch Changes

• Fixed memory package startup with older core versions. (#15772)

• Updated dependencies [6db978c, 512a013, e9becde, 703a443, 808df1b]:

  • @​mastra/core@​1.29.1

1.17.3-alpha.0

Patch Changes

• Fixed memory package startup with older core versions. (#15772)

1.17.2

Patch Changes

• Fixed the recall tool so message browsing uses the current thread by default and explains when it does. (#15807)

• Updated dependencies [28caa5b, c1ae974, b510d36, 13b4d7c, 7a7b313, c04417b, cf25a03, 8a71261, 9e973b0, dd934a0, ba6b0c5, a6dac0a, 5a4b1ee, 5a4b1ee, 5a4b1ee, 6c8c6c7, 5a4b1ee, 7d056b6, 9cef83b, d30e215, 021a60f, 73f2809, aedeea4, 26f1f94, 8126d86, 73b45fa, ae97520, 7a7b313, 441670a]:

  • @​mastra/core@​1.29.0

1.17.2-alpha.0

Patch Changes

• Fixed Observational Memory duplicate assistant messages when a thread is rerun or an agent continues a long-running loop. (#15774)

• Fixed the recall tool so message browsing uses the current thread by default and explains when it does. (#15807)

... (truncated)

Commits

• 9119f5c chore: version - exit prerelease mode
• f8694b6 feat(core,inngest): durable agent architecture with resumable streams (#12557)
• d064cd8 chore: version packages
• 4b2e4f3 fix(memory): don't block on reflection buffering for idle timeout activations...
• f90c8ab chore: version - exit prerelease mode
• e9becde fix(core): avoid duplicate agent loop response items (#15897)
• 8a70f90 chore: upgrade TypeScript from 5.9.3 to 6.0.3 (#15884)
• 45ea358 fix tests (#15918)
• 30fe03e chore(deps): update ai sdk (#15770)
• 3b85ecc chore: version packages
• Additional commits viewable in compare view