docs(docs): fix incorrect return type in should_continue example (#6068)

Description:
The documentation for the should_continue function contained an
incorrect return type annotation.
It was shown as Literal["environment", END], but the actual logic
returns "Action" or END.

This PR updates the example to use Literal["Action", END] so that the
documentation matches the intended behavior of the function.

Issue:
N/A

Dependencies:
None
This commit is contained in:
Shelton Cui
2025-09-09 14:33:27 +00:00
committed by GitHub
parent e6a9e1d1c1
commit 62f7548532
+1 -1
View File
@@ -1948,7 +1948,7 @@ const llmWithTools = llm.bindTools(tools);
# Conditional edge function to route to the tool node or end based upon whether the LLM made a tool call
def should_continue(state: MessagesState) -> Literal["environment", END]:
def should_continue(state: MessagesState) -> Literal["Action", END]:
"""Decide if we should continue the loop or stop based upon whether the LLM made a tool call"""
messages = state["messages"]