Feature: AgentExecutor execution time limit (#2399)

`AgentExecutor` already has support for limiting the number of
iterations. But the amount of time taken for each iteration can vary
quite a bit, so it is difficult to place limits on the execution time.
This PR adds a new field `max_execution_time` to the `AgentExecutor`
model. When called asynchronously, the agent loop is wrapped in an
`asyncio.timeout()` context which triggers the early stopping response
if the time limit is reached. When called synchronously, the agent loop
checks for both the max_iteration limit and the time limit after each
iteration.

When used asynchronously `max_execution_time` gives really tight control
over the max time for an execution chain. When used synchronously, the
chain can unfortunately exceed max_execution_time, but it still gives
more control than trying to estimate the number of max_iterations needed
to cap the execution time.

---------

Co-authored-by: Zachary Jones <zjones@zetaglobal.com>

tests/unit_tests/agents/test_agent.py

@@ -70,10 +70,16 @@ def test_agent_bad_action() -> None:
 
 
 def test_agent_stopped_early() -> None:
-    """Test react chain when bad action given."""
+    """Test react chain when max iterations or max execution time is exceeded."""
+    # iteration limit
     agent = _get_agent(max_iterations=0)
     output = agent.run("when was langchain made")
-    assert output == "Agent stopped due to max iterations."
+    assert output == "Agent stopped due to iteration limit or time limit."
+
+    # execution time limit
+    agent = _get_agent(max_execution_time=0.0)
+    output = agent.run("when was langchain made")
+    assert output == "Agent stopped due to iteration limit or time limit."
 
 
 def test_agent_with_callbacks_global() -> None: