Results
When you call theRunner.run methods, you either get a:
RunResultif you callrunorrun_syncRunResultStreamingif you callrun_streamed
Both of these inherit fromRunResultBase, which is where most useful information is present.
Final output
Thefinal_output property contains the final output of the last agent that ran. This is either:
- a
str, if the last agent didn't have anoutput_typedefined - an object of type
last_agent.output_type, if the agent had an output type defined.
Note
final_output is of typeAny. We can't statically type this, because of handoffs. If handoffs occur, that means any Agent might be the last agent, so we don't statically know the set of possible output types.
Inputs for the next turn
You can useresult.to_input_list() to turn the result into an input list that concatenates the original input you provided, to the items generated during the agent run. This makes it convenient to take the outputs of one agent run and pass them into another run, or to run it in a loop and append new user inputs each time.
Last agent
Thelast_agent property contains the last agent that ran. Depending on your application, this is often useful for the next time the user inputs something. For example, if you have a frontline triage agent that hands off to a language-specific agent, you can store the last agent, and re-use it the next time the user messages the agent.
New items
Thenew_items property contains the new items generated during the run. The items areRunItems. A run item wraps the raw item generated by the LLM.
MessageOutputItemindicates a message from the LLM. The raw item is the message generated.HandoffCallItemindicates that the LLM called the handoff tool. The raw item is the tool call item from the LLM.HandoffOutputItemindicates that a handoff occurred. The raw item is the tool response to the handoff tool call. You can also access the source/target agents from the item.ToolCallItemindicates that the LLM invoked a tool.ToolCallOutputItemindicates that a tool was called. The raw item is the tool response. You can also access the tool output from the item.ReasoningItemindicates a reasoning item from the LLM. The raw item is the reasoning generated.
Other information
Guardrail results
Theinput_guardrail_results andoutput_guardrail_results properties contain the results of the guardrails, if any. Guardrail results can sometimes contain useful information you want to log or store, so we make these available to you.
Raw responses
Theraw_responses property contains theModelResponses generated by the LLM.
Original input
Theinput property contains the original input you provided to therun method. In most cases you won't need this, but it's available in case you do.