agentic_fabric.runners.single_agent_runner

Single-agent runner base class.

Single-agent runners execute simple, sequential tasks without multi-agent collaboration overhead. They’re ideal for:

  • Quick file edits

  • Code generation

  • Local development

  • Sequential workflows

Unlike multi-agent fabric agents, single-agent runners:

  • Take a single task string as input

  • Execute in one pass without delegation

  • Return results directly

  • Have minimal configuration overhead

Module Contents

Classes

SingleAgentRunner

Base class for single-agent runners.

API

class agentic_fabric.runners.single_agent_runner.SingleAgentRunner

Bases: agentic_fabric.capabilities.AgentCapabilityProviderMixin, abc.ABC

Base class for single-agent runners.

Single-agent runners provide a simpler execution model than multi-agent fabric agents. They execute a single task and return the result, without the complexity of agent collaboration, delegation, or hierarchical processes.

runner_name: str = 'single_agent'
abstractmethod run(task: str, working_dir: str | None = None, **kwargs: Any) → str

Execute a single task and return the result.

Args: task: The task to execute (e.g., “Add error handling to auth.py”). working_dir: Optional working directory for execution. **kwargs: Additional runner-specific parameters.

Returns: Task output as a string.

Raises: RuntimeError: If execution fails.

abstractmethod is_available() → bool

Check if this runner is available (dependencies installed, etc.).

Returns: True if the runner can be used.

Raises: NotImplementedError: Subclasses must override this.

get_required_env_vars() → list[str]

Get list of required environment variables.

Returns: List of environment variable names required by this runner.

agent_capabilities: ClassVar[collections.abc.Mapping[str, agentic_fabric.capabilities.AgentCapabilitySpec]] = None
agent_capability_methods: ClassVar[collections.abc.Mapping[str, str]] = None
classmethod list_capabilities(*, kind: str | None = None) → tuple[agentic_fabric.capabilities.AgentCapabilitySpec, ...]
call_capability(name: str, *args: Any, **kwargs: Any) → Any
capability_map() → collections.abc.Mapping[str, agentic_fabric.capabilities.AgentCapabilitySpec]