@hSSKrSSKJr SSKJr SSKJrJrJr SSK J r S\ S\ S\4S jr S \\ \\ 4S\\4S jrg) N)Sequence) AgentAction) AIMessage BaseMessage ToolMessage)ToolAgentAction agent_action observationreturnc[U[5(d[R"USS9nOUn[ UR USUR0S9$![a [U5nN8f=f)aKConvert agent action and observation into a tool message. Args: agent_action: the tool invocation request from the agent. observation: the result of the tool invocation. Returns: ToolMessage that corresponds to the original tool invocation. Raises: ValueError: if the observation cannot be converted to a string. F) ensure_asciiname) tool_call_idcontentadditional_kwargs) isinstancestrjsondumps Exceptionrrtool)r r rs `/var/www/html/shao/venv/lib/python3.13/site-packages/langchain/agents/format_scratchpad/tools.py_create_tool_messagerso k3 ' ' 'jj5AG !..!<#4#45   '+&G 'sAA('A(intermediate_stepsc0/nUHup#[U[5(aL/[UR5Q[ X#5PnUR UVs/sH oUU;dM UPM sn5 MfUR [URS95 M U$s snf)zConvert (AgentAction, tool output) tuples into ToolMessages. Args: intermediate_steps: Steps the LLM has taken to date, along with observations. Returns: list of messages to send to the LLM for the next prediction. )r) rrlist message_logrextendappendrlog)rmessagesr r new_messagesnews rformat_to_tool_messagesr$+sH%7! lO 4 4l../$\?L OOLPLSx.>? @&8 OQs B B )rcollections.abcrlangchain_core.agentsrlangchain_core.messagesrrr%langchain.agents.output_parsers.toolsrrrtuplerr$rr,sf $- B!: {C'7!89 +r+