Fixed arguments passed to InvalidTool.run(). (#1340)

[InvalidTool.run()](72ef69d1ba/langchain/agents/tools.py (L43))
returns "{arg}is not a valid tool, try another one.".
However, no function name is actually given in the argument.
This causes LLM to be stuck in a loop, unable to find the right tool.

This may resolve these Issues.
https://github.com/hwchase17/langchain/issues/998
https://github.com/hwchase17/langchain/issues/702

langchain/agents/agent.py

@@ -426,7 +426,7 @@ class AgentExecutor(Chain, BaseModel):
             )
         else:
             observation = InvalidTool().run(
-                output.tool_input,
+                output.tool,
                 verbose=self.verbose,
                 color=None,
                 llm_prefix="",
@@ -473,7 +473,7 @@ class AgentExecutor(Chain, BaseModel):
             )
         else:
             observation = await InvalidTool().arun(
-                output.tool_input,
+                output.tool,
                 verbose=self.verbose,
                 color=None,
                 llm_prefix="",