Runtime abstractions and contracts for the UiPath Python SDK.
uipath-runtime provides the foundational interfaces and base contracts for building agent runtimes in the UiPath ecosystem. It defines the protocols that all runtime implementations must follow and provides utilities for execution context, event streaming, tracing, structured error handling, durable execution, and human-in-the-loop interactions.
This package is typically used as a dependency by higher-level SDKs such as:
| Package | Downloads | Version |
|---|---|---|
uipath |
||
uipath-langchain |
||
uipath-llamaindex |
||
uipath-google-adk |
||
uipath-openai-agents |
||
uipath-agent-framework |
||
uipath-mcp |
You would use this directly only if you're building custom runtime implementations.
uv add uipath-runtime
Check out uipath-dev - an interactive application for building, testing, and debugging UiPath Python runtimes, agents, and automation scripts.
All runtimes implement the UiPathRuntimeProtocol (or one of its sub-protocols):
get_schema()— defines input and output JSON schemas.execute(input, options)— executes the runtime logic and returns aUiPathRuntimeResult.stream(input, options)— optionally streams runtime events for real-time monitoring.dispose()— releases resources when the runtime is no longer needed.
Any class that structurally implements these methods satisfies the protocol.
from typing import Any, AsyncGenerator, Optional from uipath.runtime import ( UiPathRuntimeResult, UiPathRuntimeStatus, UiPathRuntimeSchema, UiPathRuntimeEvent, UiPathExecuteOptions, UiPathStreamOptions, ) from uipath.runtime.events import UiPathRuntimeStateEvent class MyRuntime: """Example runtime implementing the UiPath runtime protocols.""" async def get_schema(self) -> UiPathRuntimeSchema: return UiPathRuntimeSchema( input={ "type": "object", "properties": {"message": {"type": "string"}}, "required": ["message"], }, output={ "type": "object", "properties": {"result": {"type": "string"}}, "required": ["result"], }, ) async def execute( self, input: Optional[dict[str, Any]] = None, options: Optional[UiPathExecuteOptions] = None, ) -> UiPathRuntimeResult: message = (input or {}).get("message", "") return UiPathRuntimeResult( output={'message': 'Hello from MyRuntime'}, status=UiPathRuntimeStatus.SUCCESSFUL, ) async def stream( self, input: Optional[dict[str, Any]] = None, options: Optional[UiPathStreamOptions] = None, ) -> AsyncGenerator[UiPathRuntimeEvent, None]: yield UiPathRuntimeStateEvent(payload={"status": "starting"}) yield UiPathRuntimeResult( output={"completed": True}, status=UiPathRuntimeStatus.SUCCESSFUL, ) async def dispose(self) -> None: pass
Runtimes can optionally emit real-time events during execution:
from uipath.runtime.events import ( UiPathRuntimeStateEvent, UiPathRuntimeMessageEvent, ) from uipath.runtime.result import UiPathRuntimeResult async for event in runtime.stream({"query": "hello"}): if isinstance(event, UiPathRuntimeStateEvent): print(f"State update: {event.payload}") elif isinstance(event, UiPathRuntimeMessageEvent): print(f"Message received: {event.payload}") elif isinstance(event, UiPathRuntimeResult): print(f"Completed: {event.output}")
If a runtime doesn’t support streaming, it raises a UiPathStreamNotSupportedError.
Runtime errors use a consistent, structured model:
from uipath.runtime.errors import UiPathRuntimeError, UiPathErrorCode, UiPathErrorCategory raise UiPathRuntimeError( UiPathErrorCode.EXECUTION_ERROR, "Agent failed", "Failed to call external service", UiPathErrorCategory.USER, )
Resulting JSON contract:
{
"code": "Python.EXECUTION_ERROR",
"title": "Agent failed",
"detail": "Failed to call external service",
"category": "User"
}UiPathRuntimeFactoryProtocol provides a consistent contract for discovering and creating runtime instances.
Factories decouple runtime construction (configuration, dependencies) from runtime execution, allowing orchestration, discovery, reuse, and tracing across multiple types of runtimes.
from typing import Any, AsyncGenerator, Optional from uipath.runtime import ( UiPathRuntimeResult, UiPathRuntimeStatus, UiPathRuntimeSchema, UiPathExecuteOptions, UiPathStreamOptions, UiPathRuntimeProtocol, UiPathRuntimeFactoryProtocol ) class MyRuntimeFactory: async def new_runtime(self, entrypoint: str, runtime_id: str) -> UiPathRuntimeProtocol: return MyRuntime() def discover_entrypoints(self) -> list[str]: return [] factory = MyRuntimeFactory() runtime = await factory.new_runtime("example", "id") result = await runtime.execute() print(result.output) # {'message': 'Hello from MyRuntime'}
UiPathRuntimeContext manages configuration, file I/O, and logs across runtime execution.
It can read JSON input files, capture all stdout/stderr logs, and automatically write output and result files when execution completes.
from uipath.runtime import UiPathRuntimeContext, UiPathRuntimeResult, UiPathRuntimeStatus with UiPathRuntimeContext(input_file="input.json", result_file="result.json", logs_file="execution.log") as ctx: ctx.result = await runtime.execute(ctx.input) # On exit: the result and logs are written automatically to the configured files
When execution fails, the context:
- Writes a structured error contract to the result file.
- Re-raises the original exception.
UiPathExecutionRuntime wraps any runtime with tracing, telemetry, and log collection capabilities. When running multiple runtimes in the same process, this wrapper ensures each execution's spans and logs are properly isolated and captured.
graph TB
TM[TraceManager<br/>Shared across all runtimes]
FACTORY[Factory]
RT[Runtime]
EXE[ExecutionRuntime<br/>exec-id: exec-id]
%% Factory creates runtimes
FACTORY -->|new_runtime| RT
%% Runtimes wrapped by ExecutionRuntime
RT -->|wrapped by| EXE
%% TraceManager shared with all
TM -.->|shared| EXE
%% Execution captures spans to TraceManager
EXE -->|captures spans| TM
%% Styling
style TM fill:#e1f5ff,stroke:#0277bd,stroke-width:3px
style FACTORY fill:#f3e5f5
style RT fill:#fff3e0
style EXE fill:#e8f5e9
from uipath.core import UiPathTraceManager from uipath.runtime import UiPathExecutionRuntime trace_manager = UiPathTraceManager() runtime = MyRuntime() executor = UiPathExecutionRuntime( runtime, trace_manager, root_span="my-runtime", execution_id="exec-123", ) result = await executor.execute({"message": "hello"}) spans = trace_manager.get_execution_spans("exec-123") # captured spans logs = executor.log_handler.buffer # captured logs print(result.output) # {'message': 'Hello from MyRuntime'}
This example demonstrates an orchestrator runtime that receives a UiPathRuntimeFactoryProtocol, creates child runtimes through it, and executes each one via UiPathExecutionRuntime, all within a single shared UiPathTraceManager.
Orchestrator Runtime
from typing import Any, Optional, AsyncGenerator from uipath.core import UiPathTraceManager from uipath.runtime import ( UiPathExecutionRuntime, UiPathRuntimeResult, UiPathRuntimeStatus, UiPathExecuteOptions, UiPathStreamOptions, UiPathRuntimeProtocol, UiPathRuntimeFactoryProtocol ) class ChildRuntime: """A simple child runtime that echoes its name and input.""" def __init__(self, name: str): self.name = name async def get_schema(self): return None async def execute( self, input: Optional[dict[str, Any]] = None, options: Optional[UiPathExecuteOptions] = None, ) -> UiPathRuntimeResult: payload = input or {} return UiPathRuntimeResult( output={ "runtime": self.name, "input": payload, }, status=UiPathRuntimeStatus.SUCCESSFUL, ) async def stream( self, input: Optional[dict[str, Any]] = None, options: Optional[UiPathStreamOptions] = None, ) -> AsyncGenerator[UiPathRuntimeResult, None]: yield await self.execute(input, options) async def dispose(self) -> None: pass class ChildRuntimeFactory: """Factory that creates ChildRuntime instances.""" async def new_runtime(self, entrypoint: str) -> UiPathRuntimeProtocol: return ChildRuntime(name=entrypoint) def discover_entrypoints(self) -> list[str]: return [] class OrchestratorRuntime: """A runtime that orchestrates multiple child runtimes via a factory.""" def __init__( self, factory: UiPathRuntimeFactoryProtocol, trace_manager: UiPathTraceManager, ): self.factory = factory self.trace_manager = trace_manager async def get_schema(self): return None async def execute( self, input: Optional[dict[str, Any]] = None, options: Optional[UiPathExecuteOptions] = None, ) -> UiPathRuntimeResult: payload = input or {} child_inputs: list[dict[str, Any]] = payload.get("children", []) child_results: list[dict[str, Any]] = [] for i, child_input in enumerate(child_inputs): # Use the factory to create a new child runtime child_runtime = await self.factory.new_runtime(entrypoint=f"child-{i}", runtime_id=f"child-{i}") # Wrap child runtime with tracing + logs execution_id = f"child-{i}" executor = UiPathExecutionRuntime( delegate=child_runtime, trace_manager=self.trace_manager, root_span=f"child-span-{i}", execution_id=execution_id, ) # Execute child runtime result = await executor.execute(child_input, options=options) child_results.append(result.output or {}) child_spans = trace_manager.get_execution_spans(execution_id) # Captured spans # Dispose the child runtime when finished await child_runtime.dispose() return UiPathRuntimeResult( output={ "main": True, "children": child_results, }, status=UiPathRuntimeStatus.SUCCESSFUL, ) async def stream( self, input: Optional[dict[str, Any]] = None, options: Optional[UiPathStreamOptions] = None, ) -> AsyncGenerator[UiPathRuntimeResult, None]: yield await self.execute(input, options) async def dispose(self) -> None: pass # Example usage async def main() -> None: trace_manager = UiPathTraceManager() factory = ChildRuntimeFactory() options = UiPathExecuteOptions() with UiPathRuntimeContext(job_id="main-job-001") as ctx: runtime = OrchestratorRuntime(factory=factory, trace_manager=trace_manager) input_data = { "children": [ {"message": "hello from child 1"}, {"message": "hello from child 2"}, ] } ctx.result = await runtime.execute(input=input_data, options=options) print(ctx.result.output) # Output: # { # "main": True, # "children": [ # {"runtime": "child-0", "input": {"message": "hello from child 1"}}, # {"runtime": "child-1", "input": {"message": "hello from child 2"}} # ] # }
This repository includes a complete blueprint for building new framework integrations using Claude Code (or any AI coding assistant):
- INTEGRATION_GENOME.md — A structured, phase-by-phase specification that guides you through building a full UiPath runtime integration for any Python agentic framework. Covers project scaffolding, config/loader, schema inference, execute/stream, HITL, factory registration, LLM Gateway, and CLI middleware.
- CLAUDE.md — Project instructions and structure overview for AI-assisted development.