langchain-ai/deepagents · error · RuntimeError

task tool not configured for this eval

Error message

task tool not configured for this eval

What it means

The task bridge raises this RuntimeError when the active ToolRuntime exists but contains no subagent task tool (`find_subagent_task_tool` returns None). `task()` cannot dispatch a subagent unless the task tool was configured in the runtime's toolset. This indicates the eval environment lacks subagent wiring despite subagents being enabled in the REPL.

Source

Thrown at libs/partners/quickjs/langchain_quickjs/_repl.py:593

    ) -> Any:
        """Validate JS `task()` input and invoke the runner on the right loop.

        The QuickJS host call runs on the REPL worker loop, but subagent runnables
        should execute on the parent LangGraph loop when one exists so callbacks,
        context, and async loop affinity match normal tool execution.
        """
        validated = self._validate_task_payload(payload)
        description, subagent_type, label, response_schema = validated

        async def _call() -> Any:
            runtime = state.outer_runtime
            if runtime is None:
                msg = "task() requires an active ToolRuntime"
                raise RuntimeError(msg)
            task_tool = find_subagent_task_tool(getattr(runtime, "tools", ()) or ())
            if task_tool is None:
                msg = "task tool not configured for this eval"
                raise RuntimeError(msg)
            return await call_subagent_task_tool(
                task_tool,
                description=description,
                subagent_type=subagent_type,
                response_schema=response_schema,
                runtime=runtime,
                label=label,
            )

        outer_loop = state.outer_loop
        if outer_loop is None:
            return await _call()
        current_loop = asyncio.get_running_loop()
        if current_loop is outer_loop:
            return await _call()
        future = asyncio.run_coroutine_threadsafe(_call(), outer_loop)
        try:
            return await asyncio.wrap_future(future)

View on GitHub (pinned to a1af029e6e)

Solutions

1. Configure subagents so the task tool is present in the runtime's tools
2. Disable subagents (`subagents_enabled=False`) if task() is not expected to work
3. Log/inspect `runtime.tools` at eval start to confirm the task tool is registered

# Python side, before enabling task() for JS
tools = list(getattr(runtime, 'tools', ()) or ())
assert any(t.name and 'task' in t.name.lower() for t in tools), 'task tool missing'

def has_task_tool(runtime) -> bool:
    from langchain_quickjs._repl import find_subagent_task_tool
    return find_subagent_task_tool(getattr(runtime, 'tools', ()) or ()) is not None

try:
    result = await task(payload)
except (RuntimeError,) as e:
    if 'not configured' in str(e):
        log.warning('subagent task tool missing from runtime tools')
        return None
    raise

When it happens

Trigger: JS calls `task()` while `runtime.tools` contains no task tool — subagents enabled in the REPL config but the agent was built without subagent tools, or the tool list is empty/filtered.

Common situations: Config mismatch: REPL created with `subagents_enabled=True` but the agent's tool list omits the subagent task tool; tools filtered out by middleware; or using an eval harness that builds the runtime without subagents.

Related errors

• task() requires non-empty string field `description`
• task() requires non-empty string field `subagentType`
• task() field `label` must be a string when provided
• task() field `responseSchema` must be an object when provide
• task() requires an active ToolRuntime

AI-assisted analysis of langchain-ai/deepagents@a1af029e6e (2026-08-29). Data as JSON: /api/errors/a16d44f9fd75e305. Report an issue: GitHub.