chore(deps): bump @mastra/observability from 1.3.1 to 1.7.2

[dependabot]

Bumps @mastra/observability from 1.3.1 to 1.7.2.

Release notes

Sourced from @​mastra/observability's releases.

February 24, 2026

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 workspace instance (including re-enabling all tools by passing undefined), enabling safer modes like plan/read-only without recreating the workspace.

Observational Memory Reliability & Introspection Improvements

Core adds Harness.getObservationalMemoryRecord() for public access to the full OM record for the current thread, while @mastra/memory fixes major OM stability issues (shared tokenizer to prevent OOM/memory leaks, plus PostgreSQL deadlock fixes and clearer errors when threadId is missing).

Changelog

@​mastra/core@​1.7.0

Minor Changes

• Added getObservationalMemoryRecord() method to the Harness class. Fixes #13392. (#13395)

  This provides public access to the full ObservationalMemoryRecord for the current thread, including activeObservations, generationCount, and observationTokenCount. Previously, accessing raw observation text required bypassing the Harness abstraction by reaching into private storage internals.

  const record = await harness.getObservationalMemoryRecord();
  if (record) {
    console.log(record.activeObservations);
  }

• Added Workspace.setToolsConfig() method for dynamically updating per-tool configuration at runtime without recreating the workspace instance. Passing undefined re-enables all tools. (#13439)

  const workspace = new Workspace({ filesystem, sandbox });
  // Disable write tools (e.g., in plan/read-only mode)
  workspace.setToolsConfig({
  mastra_workspace_write_file: { enabled: false },
  mastra_workspace_edit_file: { enabled: false },
  });
  // Re-enable all tools
  workspace.setToolsConfig(undefined);

• Added HarnessDisplayState so any UI can read a single state snapshot instead of handling 35+ individual events. (#13427)

  Why: Previously, every UI (TUI, web, desktop) had to subscribe to dozens of granular Harness events and independently reconstruct what to display. This led to duplicated state tracking and inconsistencies across UI implementations. Now the Harness maintains a single canonical display state that any UI can read.

  Before: UIs subscribed to raw events and built up display state locally:

... (truncated)

Changelog

Sourced from @​mastra/observability's changelog.

1.7.2

Patch Changes

• Fixed Anthropic cache tokens being double-counted in observability metrics (#13914)

  Anthropic cache token usage is now normalized correctly for AI SDK v6-style usage payloads, so input token metrics and tracing output no longer overcount cached tokens when the total already includes them.

• Updated dependencies [cb15509, 81e4259, 951b8a1, 80c5668, 3d478c1, 2b4ea10, a0544f0, 6039f17, 06b928d, 6a8d984, c8c86aa]:

  • @​mastra/core@​1.22.0

1.7.2-alpha.0

Patch Changes

• Fixed Anthropic cache tokens being double-counted in observability metrics (#13914)

  Anthropic cache token usage is now normalized correctly for AI SDK v6-style usage payloads, so input token metrics and tracing output no longer overcount cached tokens when the total already includes them.

• Updated dependencies [81e4259, 951b8a1]:

  • @​mastra/core@​1.22.0-alpha.1

1.7.1

Patch Changes

• Fixed score and feedback annotations being dropped before spans flush by emitting from live correlation context when available. Scores and feedback can now also be stored without a trace ID when only contextual metadata is available. (#14942)

• Fixed pricing model lookup to fall back to dot-to-dash normalization for model names (e.g. gpt-5.2 → gpt-5-2), resolving no_matching_model errors for Azure deployments (#14959)

• Added error name and stack trace to SpanErrorInfo, allowing exporters to access the original error class name and stack trace for richer error reporting. (#14944)

• Updated dependencies [9a43b47, ec5c319, 6517789, 13f4327, 9ad6aa6, 2862127, 3d16814, 7f498d0, 8cf8a67, d7827e3]:

  • @​mastra/core@​1.21.0

1.7.1-alpha.0

Patch Changes

• Fixed score and feedback annotations being dropped before spans flush by emitting from live correlation context when available. Scores and feedback can now also be stored without a trace ID when only contextual metadata is available. (#14942)

• Fixed pricing model lookup to fall back to dot-to-dash normalization for model names (e.g. gpt-5.2 → gpt-5-2), resolving no_matching_model errors for Azure deployments (#14959)

• Added error name and stack trace to SpanErrorInfo, allowing exporters to access the original error class name and stack trace for richer error reporting. (#14944)

• Updated dependencies [ec5c319, 6517789, 9ad6aa6, 2862127, 3d16814, 7f498d0, 8cf8a67, d7827e3]:

  • @​mastra/core@​1.21.0-alpha.2

1.7.0

... (truncated)

Commits

• dcb6eeb chore: version - exit prerelease mode
• 9a7ace2 chore: version packages
• 951b8a1 fix: Anthropic cache tokens missing from Langfuse traces in streaming mode (#...
• c8c86aa feat: Mastra Gateway model router provider + memory integration (#14952)
• 89dec59 chore: version - exit prerelease mode
• 121c67f chore: version packages (alpha) (#14929)
• 8cf8a67 fix(datadog): set native error tags to fix [object Object] in Datadog Error...
• 145090c fix(observability): fall back to dot-to-dash model name normalization in pric...
• 3d16814 fix(core): split observability utils to prevent AsyncLocalStorage in browser ...
• ec5c319 fixed race condition and traceId nullability in scoring (#14942)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[dependabot]

Superseded by #504.