taTanStackOSS
ta
  • Pipelines
  • Nx runs
Insights
  • Compare tasks
  • Analytics
aiai
  1. Pipelines
  2. fix(ai-harness): return done from the subagent start binding SubagentBinding.start is typed to return { subagentRunId, done }, where done settles when the child ends, but the session binding returned only { subagentRunId }. That broke @tanstack/ai-harness build and test:types. Capture the runAgent operation and resolve it as done, the same awaitable the agent group already uses. Also update the todos session-plugins test: chat() now checks a tool's JSON Schema before it runs, so an invalid todo status is a tool error the model sees, not the plugin's own "Each todo needs text and a status." message. The test now expects the input-validation error. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
    nx run-many --targets=build --exclude=examples/**,testing/**
fix(ai-harness): return done from the subagent start binding
Succeeded in 2m 40sStarted
Linux4 CPU cores
read-write access token used

nx run-many --targets=build --exclude=examples/**,testing/**

1768fa900e9GitHubOpen on GitHub
TasksResource Usage
Resource usage reports are turned off for this workspace
Your organization has the Resource usage add-on, but this workspace does not collect metrics for non distributed runs. Turn it back on in workspace settings.

© 2026 Nx Cloud

  • Terms
  • Privacy
  • Changelog
  • Status
  • Docs
  • Contact
  • Pricing
  • Company
  • @NxDevTools
taTanStackOSS