ta
TanStack
OSS
ta
Pipelines
Nx runs
Insights
Compare tasks
Analytics
Sign in
Toggle Sidebar
ai
ai
Pipelines
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/**
⌘K
fix(ai-harness): return done from the subagent start binding
Succeeded
in
2m 40s
Started
Linux
4 CPU cores
read-write
access token used
Copy command
nx run-many --targets=build --exclude=examples/**,testing/**
1768
fa900e9
GitHub
Open on GitHub
Tasks
Resource Usage
ta
TanStack
OSS