langchain 0.3.27__py3-none-any.whl → 0.4.0.dev0__py3-none-any.whl

langchain/agents/agent.py

@@ -64,6 +64,7 @@ class BaseSingleActionAgent(BaseModel):
         return ["output"]
 
     def get_allowed_tools(self) -> Optional[list[str]]:
+        """Get allowed tools."""
         return None
 
     @abstractmethod
@@ -115,8 +116,8 @@ class BaseSingleActionAgent(BaseModel):
     def return_stopped_response(
         self,
         early_stopping_method: str,
-        intermediate_steps: list[tuple[AgentAction, str]],
-        **kwargs: Any,
+        intermediate_steps: list[tuple[AgentAction, str]],  # noqa: ARG002
+        **_: Any,
     ) -> AgentFinish:
         """Return response when agent has been stopped due to max iterations.
 
@@ -124,7 +125,6 @@ class BaseSingleActionAgent(BaseModel):
             early_stopping_method: Method to use for early stopping.
             intermediate_steps: Steps the LLM has taken to date,
                 along with observations.
-            **kwargs: User inputs.
 
         Returns:
             AgentFinish: Agent finish object.
@@ -167,6 +167,7 @@ class BaseSingleActionAgent(BaseModel):
         """Return Identifier of an agent type."""
         raise NotImplementedError
 
+    @override
     def dict(self, **kwargs: Any) -> builtins.dict:
         """Return dictionary representation of agent.
 
@@ -195,6 +196,7 @@ class BaseSingleActionAgent(BaseModel):
 
             # If working with agent executor
             agent.agent.save(file_path="path/agent.yaml")
+
         """
         # Convert file to Path object.
         save_path = Path(file_path) if isinstance(file_path, str) else file_path
@@ -288,8 +290,8 @@ class BaseMultiActionAgent(BaseModel):
     def return_stopped_response(
         self,
         early_stopping_method: str,
-        intermediate_steps: list[tuple[AgentAction, str]],
-        **kwargs: Any,
+        intermediate_steps: list[tuple[AgentAction, str]],  # noqa: ARG002
+        **_: Any,
     ) -> AgentFinish:
         """Return response when agent has been stopped due to max iterations.
 
@@ -297,7 +299,6 @@ class BaseMultiActionAgent(BaseModel):
             early_stopping_method: Method to use for early stopping.
             intermediate_steps: Steps the LLM has taken to date,
                 along with observations.
-            **kwargs: User inputs.
 
         Returns:
             AgentFinish: Agent finish object.
@@ -316,6 +317,7 @@ class BaseMultiActionAgent(BaseModel):
         """Return Identifier of an agent type."""
         raise NotImplementedError
 
+    @override
     def dict(self, **kwargs: Any) -> builtins.dict:
         """Return dictionary representation of agent."""
         _dict = super().model_dump()
@@ -338,6 +340,7 @@ class BaseMultiActionAgent(BaseModel):
 
             # If working with agent executor
             agent.agent.save(file_path="path/agent.yaml")
+
         """
         # Convert file to Path object.
         save_path = Path(file_path) if isinstance(file_path, str) else file_path
@@ -650,6 +653,7 @@ class LLMSingleActionAgent(BaseSingleActionAgent):
         """
         return list(set(self.llm_chain.input_keys) - {"intermediate_steps"})
 
+    @override
     def dict(self, **kwargs: Any) -> builtins.dict:
         """Return dictionary representation of agent."""
         _dict = super().dict()
@@ -734,6 +738,7 @@ class Agent(BaseSingleActionAgent):
     allowed_tools: Optional[list[str]] = None
     """Allowed tools for the agent. If None, all tools are allowed."""
 
+    @override
     def dict(self, **kwargs: Any) -> builtins.dict:
         """Return dictionary representation of agent."""
         _dict = super().dict()
@@ -749,18 +754,6 @@ class Agent(BaseSingleActionAgent):
         """Return values of the agent."""
         return ["output"]
 
-    def _fix_text(self, text: str) -> str:
-        """Fix the text.
-
-        Args:
-            text: Text to fix.
-
-        Returns:
-            str: Fixed text.
-        """
-        msg = "fix_text not implemented for this agent."
-        raise ValueError(msg)
-
     @property
     def _stop(self) -> list[str]:
         return [
@@ -1020,6 +1013,7 @@ class ExceptionTool(BaseTool):
     description: str = "Exception tool"
     """Description of the tool."""
 
+    @override
     def _run(
         self,
         query: str,
@@ -1027,6 +1021,7 @@ class ExceptionTool(BaseTool):
     ) -> str:
         return query
 
+    @override
     async def _arun(
         self,
         query: str,
@@ -1184,9 +1179,10 @@ class AgentExecutor(Chain):
         to reflect the changes made in the root_validator.
         """
         if isinstance(self.agent, Runnable):
-            return cast(RunnableAgentType, self.agent)
+            return cast("RunnableAgentType", self.agent)
         return self.agent
 
+    @override
     def save(self, file_path: Union[Path, str]) -> None:
         """Raise error - saving not supported for Agent Executors.
 
@@ -1217,7 +1213,7 @@ class AgentExecutor(Chain):
         callbacks: Callbacks = None,
         *,
         include_run_info: bool = False,
-        async_: bool = False,  # arg kept for backwards compat, but ignored
+        async_: bool = False,  # noqa: ARG002 arg kept for backwards compat, but ignored
     ) -> AgentExecutorIterator:
         """Enables iteration over steps taken to reach final output.
 

langchain/agents/agent_iterator.py

@@ -157,6 +157,12 @@ class AgentExecutorIterator:
         outputs: dict[str, Any],
         run_manager: Union[CallbackManagerForChainRun, AsyncCallbackManagerForChainRun],
     ) -> AddableDict:
+        """Make final outputs for the iterator.
+
+        Args:
+            outputs: The outputs from the agent executor.
+            run_manager: The run manager to use for callbacks.
+        """
         # have access to intermediate steps by design in iterator,
         # so return only outputs may as well always be true.
 
@@ -172,6 +178,7 @@ class AgentExecutorIterator:
         return prepared_outputs
 
     def __iter__(self: AgentExecutorIterator) -> Iterator[AddableDict]:
+        """Create an async iterator for the AgentExecutor."""
         logger.debug("Initialising AgentExecutorIterator")
         self.reset()
         callback_manager = CallbackManager.configure(
@@ -190,14 +197,14 @@ class AgentExecutorIterator:
             name=self.run_name,
         )
         try:
-            while self.agent_executor._should_continue(
+            while self.agent_executor._should_continue(  # noqa: SLF001
                 self.iterations,
                 self.time_elapsed,
             ):
                 # take the next step: this plans next action, executes it,
                 # yielding action and observation as they are generated
                 next_step_seq: NextStepOutput = []
-                for chunk in self.agent_executor._iter_next_step(
+                for chunk in self.agent_executor._iter_next_step(  # noqa: SLF001
                     self.name_to_tool_map,
                     self.color_mapping,
                     self.inputs,
@@ -214,7 +221,7 @@ class AgentExecutorIterator:
                             yield AddableDict(steps=[chunk], messages=chunk.messages)
 
                 # convert iterator output to format handled by _process_next_step_output
-                next_step = self.agent_executor._consume_next_step(next_step_seq)
+                next_step = self.agent_executor._consume_next_step(next_step_seq)  # noqa: SLF001
                 # update iterations and time elapsed
                 self.update_iterations()
                 # decide if this is the final output
@@ -258,14 +265,14 @@ class AgentExecutorIterator:
         )
         try:
             async with asyncio_timeout(self.agent_executor.max_execution_time):
-                while self.agent_executor._should_continue(
+                while self.agent_executor._should_continue(  # noqa: SLF001
                     self.iterations,
                     self.time_elapsed,
                 ):
                     # take the next step: this plans next action, executes it,
                     # yielding action and observation as they are generated
                     next_step_seq: NextStepOutput = []
-                    async for chunk in self.agent_executor._aiter_next_step(
+                    async for chunk in self.agent_executor._aiter_next_step(  # noqa: SLF001
                         self.name_to_tool_map,
                         self.color_mapping,
                         self.inputs,
@@ -288,7 +295,7 @@ class AgentExecutorIterator:
                                 )
 
                     # convert iterator output to format handled by _process_next_step
-                    next_step = self.agent_executor._consume_next_step(next_step_seq)
+                    next_step = self.agent_executor._consume_next_step(next_step_seq)  # noqa: SLF001
                     # update iterations and time elapsed
                     self.update_iterations()
                     # decide if this is the final output
@@ -336,7 +343,7 @@ class AgentExecutorIterator:
         # Check for tool return
         if len(next_step_output) == 1:
             next_step_action = next_step_output[0]
-            tool_return = self.agent_executor._get_tool_return(next_step_action)
+            tool_return = self.agent_executor._get_tool_return(next_step_action)  # noqa: SLF001
             if tool_return is not None:
                 return self._return(tool_return, run_manager=run_manager)
 
@@ -364,7 +371,7 @@ class AgentExecutorIterator:
         # Check for tool return
         if len(next_step_output) == 1:
             next_step_action = next_step_output[0]
-            tool_return = self.agent_executor._get_tool_return(next_step_action)
+            tool_return = self.agent_executor._get_tool_return(next_step_action)  # noqa: SLF001
             if tool_return is not None:
                 return await self._areturn(tool_return, run_manager=run_manager)
 
@@ -376,7 +383,7 @@ class AgentExecutorIterator:
         """
         logger.warning("Stopping agent prematurely due to triggering stop condition")
         # this manually constructs agent finish with output key
-        output = self.agent_executor._action_agent.return_stopped_response(
+        output = self.agent_executor._action_agent.return_stopped_response(  # noqa: SLF001
             self.agent_executor.early_stopping_method,
             self.intermediate_steps,
             **self.inputs,
@@ -389,7 +396,7 @@ class AgentExecutorIterator:
         the stopped response.
         """
         logger.warning("Stopping agent prematurely due to triggering stop condition")
-        output = self.agent_executor._action_agent.return_stopped_response(
+        output = self.agent_executor._action_agent.return_stopped_response(  # noqa: SLF001
             self.agent_executor.early_stopping_method,
             self.intermediate_steps,
             **self.inputs,
@@ -404,7 +411,7 @@ class AgentExecutorIterator:
         """
         Return the final output of the iterator.
         """
-        returned_output = self.agent_executor._return(
+        returned_output = self.agent_executor._return(  # noqa: SLF001
             output,
             self.intermediate_steps,
             run_manager=run_manager,
@@ -421,7 +428,7 @@ class AgentExecutorIterator:
         """
         Return the final output of the async iterator.
         """
-        returned_output = await self.agent_executor._areturn(
+        returned_output = await self.agent_executor._areturn(  # noqa: SLF001
             output,
             self.intermediate_steps,
             run_manager=run_manager,

langchain/agents/agent_toolkits/vectorstore/base.py

@@ -90,6 +90,7 @@ def create_vectorstore_agent(
 
     Returns:
         AgentExecutor: Returns a callable AgentExecutor object. Either you can call it or use run method with the query to get the response
+
     """  # noqa: E501
     tools = toolkit.get_tools()
     prompt = ZeroShotAgent.create_prompt(tools, prefix=prefix)
@@ -198,6 +199,7 @@ def create_vectorstore_router_agent(
 
     Returns:
         AgentExecutor: Returns a callable AgentExecutor object. Either you can call it or use run method with the query to get the response.
+
     """  # noqa: E501
     tools = toolkit.get_tools()
     prompt = ZeroShotAgent.create_prompt(tools, prefix=prefix)

langchain/agents/chat/base.py

@@ -13,6 +13,7 @@ from langchain_core.prompts.chat import (
 )
 from langchain_core.tools import BaseTool
 from pydantic import Field
+from typing_extensions import override
 
 from langchain._api.deprecation import AGENT_DEPRECATION_WARNING
 from langchain.agents.agent import Agent, AgentOutputParser
@@ -65,6 +66,7 @@ class ChatAgent(Agent):
         return agent_scratchpad
 
     @classmethod
+    @override
     def _get_default_output_parser(cls, **kwargs: Any) -> AgentOutputParser:
         return ChatOutputParser()
 

langchain/agents/conversational/base.py

@@ -11,6 +11,7 @@ from langchain_core.language_models import BaseLanguageModel
 from langchain_core.prompts import PromptTemplate
 from langchain_core.tools import BaseTool
 from pydantic import Field
+from typing_extensions import override
 
 from langchain._api.deprecation import AGENT_DEPRECATION_WARNING
 from langchain.agents.agent import Agent, AgentOutputParser
@@ -35,6 +36,7 @@ class ConversationalAgent(Agent):
     """Output parser for the agent."""
 
     @classmethod
+    @override
     def _get_default_output_parser(
         cls,
         ai_prefix: str = "AI",

langchain/agents/conversational_chat/base.py

@@ -20,6 +20,7 @@ from langchain_core.prompts.chat import (
 )
 from langchain_core.tools import BaseTool
 from pydantic import Field
+from typing_extensions import override
 
 from langchain.agents.agent import Agent, AgentOutputParser
 from langchain.agents.conversational_chat.output_parser import ConvoOutputParser
@@ -42,6 +43,7 @@ class ConversationalChatAgent(Agent):
     """Template for the tool response."""
 
     @classmethod
+    @override
     def _get_default_output_parser(cls, **kwargs: Any) -> AgentOutputParser:
         return ConvoOutputParser()
 

langchain/agents/initialize.py

@@ -90,7 +90,7 @@ def initialize_agent(
         )
         with contextlib.suppress(NotImplementedError):
             # TODO: Add tags from the serialized object directly.
-            tags_.append(agent_obj._agent_type)
+            tags_.append(agent_obj._agent_type)  # noqa: SLF001
     else:
         msg = (
             "Somehow both `agent` and `agent_path` are None, this should never happen."

langchain/agents/json_chat/base.py

@@ -160,6 +160,7 @@ def create_json_chat_agent(
                     MessagesPlaceholder("agent_scratchpad"),
                 ]
             )
+
     """  # noqa: E501
     missing_vars = {"tools", "tool_names", "agent_scratchpad"}.difference(
         prompt.input_variables + list(prompt.partial_variables),

langchain/agents/mrkl/base.py

@@ -12,6 +12,7 @@ from langchain_core.prompts import PromptTemplate
 from langchain_core.tools import BaseTool, Tool
 from langchain_core.tools.render import render_text_description
 from pydantic import Field
+from typing_extensions import override
 
 from langchain._api.deprecation import AGENT_DEPRECATION_WARNING
 from langchain.agents.agent import Agent, AgentExecutor, AgentOutputParser
@@ -51,6 +52,7 @@ class ZeroShotAgent(Agent):
     output_parser: AgentOutputParser = Field(default_factory=MRKLOutputParser)
 
     @classmethod
+    @override
     def _get_default_output_parser(cls, **kwargs: Any) -> AgentOutputParser:
         return MRKLOutputParser()
 

langchain/agents/openai_assistant/base.py

@@ -229,7 +229,7 @@ class OpenAIAssistantRunnable(RunnableSerializable[dict, OutputType]):
     """Use as a LangChain agent, compatible with the AgentExecutor."""
 
     @model_validator(mode="after")
-    def validate_async_client(self) -> Self:
+    def _validate_async_client(self) -> Self:
         if self.async_client is None:
             import openai
 

langchain/agents/openai_functions_agent/agent_token_buffer_memory.py

@@ -4,6 +4,7 @@ from typing import Any
 
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.messages import BaseMessage, get_buffer_string
+from typing_extensions import override
 
 from langchain.agents.format_scratchpad import (
     format_to_openai_function_messages,
@@ -55,6 +56,7 @@ class AgentTokenBufferMemory(BaseChatMemory):
         """
         return [self.memory_key]
 
+    @override
     def load_memory_variables(self, inputs: dict[str, Any]) -> dict[str, Any]:
         """Return history buffer.
 

langchain/agents/openai_functions_agent/base.py

@@ -134,7 +134,7 @@ class OpenAIFunctionsAgent(BaseSingleActionAgent):
                 messages,
                 callbacks=callbacks,
             )
-        return self.output_parser._parse_ai_message(predicted_message)
+        return self.output_parser.parse_ai_message(predicted_message)
 
     async def aplan(
         self,
@@ -167,7 +167,7 @@ class OpenAIFunctionsAgent(BaseSingleActionAgent):
             functions=self.functions,
             callbacks=callbacks,
         )
-        return self.output_parser._parse_ai_message(predicted_message)
+        return self.output_parser.parse_ai_message(predicted_message)
 
     def return_stopped_response(
         self,
@@ -359,6 +359,7 @@ def create_openai_functions_agent(
                     MessagesPlaceholder("agent_scratchpad"),
                 ]
             )
+
     """
     if "agent_scratchpad" not in (
         prompt.input_variables + list(prompt.partial_variables)

langchain/agents/openai_functions_multi_agent/base.py

@@ -125,7 +125,7 @@ class OpenAIMultiFunctionsAgent(BaseMultiActionAgent):
         return [t.name for t in self.tools]
 
     @model_validator(mode="after")
-    def validate_prompt(self) -> Self:
+    def _validate_prompt(self) -> Self:
         prompt: BasePromptTemplate = self.prompt
         if "agent_scratchpad" not in prompt.input_variables:
             msg = (

langchain/agents/openai_tools/base.py

@@ -84,6 +84,7 @@ def create_openai_tools_agent(
                     MessagesPlaceholder("agent_scratchpad"),
                 ]
             )
+
     """
     missing_vars = {"agent_scratchpad"}.difference(
         prompt.input_variables + list(prompt.partial_variables),

langchain/agents/output_parsers/json.py

@@ -6,6 +6,7 @@ from typing import Union
 from langchain_core.agents import AgentAction, AgentFinish
 from langchain_core.exceptions import OutputParserException
 from langchain_core.utils.json import parse_json_markdown
+from typing_extensions import override
 
 from langchain.agents.agent import AgentOutputParser
 
@@ -40,6 +41,7 @@ class JSONAgentOutputParser(AgentOutputParser):
     ```
     """
 
+    @override
     def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
         try:
             response = parse_json_markdown(text)

langchain/agents/output_parsers/openai_functions.py

@@ -8,7 +8,10 @@ from langchain_core.messages import (
     AIMessage,
     BaseMessage,
 )
+from langchain_core.messages.utils import convert_from_v1_message
 from langchain_core.outputs import ChatGeneration, Generation
+from langchain_core.v1.messages import AIMessage as AIMessageV1
+from typing_extensions import override
 
 from langchain.agents.agent import AgentOutputParser
 
@@ -30,7 +33,7 @@ class OpenAIFunctionsAgentOutputParser(AgentOutputParser):
         return "openai-functions-agent"
 
     @staticmethod
-    def _parse_ai_message(message: BaseMessage) -> Union[AgentAction, AgentFinish]:
+    def parse_ai_message(message: BaseMessage) -> Union[AgentAction, AgentFinish]:
         """Parse an AI message."""
         if not isinstance(message, AIMessage):
             msg = f"Expected an AI message got {type(message)}"
@@ -79,18 +82,22 @@ class OpenAIFunctionsAgentOutputParser(AgentOutputParser):
             log=str(message.content),
         )
 
+    @override
     def parse_result(
         self,
-        result: list[Generation],
+        result: Union[list[Generation], AIMessageV1],
         *,
         partial: bool = False,
     ) -> Union[AgentAction, AgentFinish]:
+        if isinstance(result, AIMessageV1):
+            result = [ChatGeneration(message=convert_from_v1_message(result))]
         if not isinstance(result[0], ChatGeneration):
             msg = "This output parser only works on ChatGeneration output"
             raise ValueError(msg)  # noqa: TRY004
         message = result[0].message
-        return self._parse_ai_message(message)
+        return self.parse_ai_message(message)
 
+    @override
     def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
         msg = "Can only parse messages"
         raise ValueError(msg)

langchain/agents/output_parsers/openai_tools.py

@@ -2,7 +2,10 @@ from typing import Union
 
 from langchain_core.agents import AgentAction, AgentFinish
 from langchain_core.messages import BaseMessage
+from langchain_core.messages.utils import convert_from_v1_message
 from langchain_core.outputs import ChatGeneration, Generation
+from langchain_core.v1.messages import AIMessage as AIMessageV1
+from typing_extensions import override
 
 from langchain.agents.agent import MultiActionAgentOutputParser
 from langchain.agents.output_parsers.tools import (
@@ -53,18 +56,22 @@ class OpenAIToolsAgentOutputParser(MultiActionAgentOutputParser):
     def _type(self) -> str:
         return "openai-tools-agent-output-parser"
 
+    @override
     def parse_result(
         self,
-        result: list[Generation],
+        result: Union[list[Generation], AIMessageV1],
         *,
         partial: bool = False,
     ) -> Union[list[AgentAction], AgentFinish]:
+        if isinstance(result, AIMessageV1):
+            result = [ChatGeneration(message=convert_from_v1_message(result))]
         if not isinstance(result[0], ChatGeneration):
             msg = "This output parser only works on ChatGeneration output"
             raise ValueError(msg)  # noqa: TRY004
         message = result[0].message
         return parse_ai_message_to_openai_tool_action(message)
 
+    @override
     def parse(self, text: str) -> Union[list[AgentAction], AgentFinish]:
         msg = "Can only parse messages"
         raise ValueError(msg)

langchain/agents/output_parsers/react_json_single_input.py

@@ -5,6 +5,7 @@ from typing import Union
 
 from langchain_core.agents import AgentAction, AgentFinish
 from langchain_core.exceptions import OutputParserException
+from typing_extensions import override
 
 from langchain.agents.agent import AgentOutputParser
 from langchain.agents.chat.prompt import FORMAT_INSTRUCTIONS
@@ -46,9 +47,11 @@ class ReActJsonSingleInputOutputParser(AgentOutputParser):
     pattern: Pattern = re.compile(r"^.*?`{3}(?:json)?\n?(.*?)`{3}.*?$", re.DOTALL)
     """Regex pattern to parse the output."""
 
+    @override
     def get_format_instructions(self) -> str:
         return FORMAT_INSTRUCTIONS
 
+    @override
     def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
         includes_answer = FINAL_ANSWER_ACTION in text
         try:

langchain/agents/output_parsers/react_single_input.py

@@ -3,6 +3,7 @@ from typing import Union
 
 from langchain_core.agents import AgentAction, AgentFinish
 from langchain_core.exceptions import OutputParserException
+from typing_extensions import override
 
 from langchain.agents.agent import AgentOutputParser
 from langchain.agents.mrkl.prompt import FORMAT_INSTRUCTIONS
@@ -45,9 +46,11 @@ class ReActSingleInputOutputParser(AgentOutputParser):
 
     """
 
+    @override
     def get_format_instructions(self) -> str:
         return FORMAT_INSTRUCTIONS
 
+    @override
     def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
         includes_answer = FINAL_ANSWER_ACTION in text
         regex = (

langchain/agents/output_parsers/self_ask.py

@@ -3,6 +3,7 @@ from typing import Union
 
 from langchain_core.agents import AgentAction, AgentFinish
 from langchain_core.exceptions import OutputParserException
+from typing_extensions import override
 
 from langchain.agents.agent import AgentOutputParser
 
@@ -35,6 +36,7 @@ class SelfAskOutputParser(AgentOutputParser):
     followups: Sequence[str] = ("Follow up:", "Followup:")
     finish_string: str = "So the final answer is: "
 
+    @override
     def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
         last_line = text.split("\n")[-1]
         if not any(follow in last_line for follow in self.followups):

langchain/agents/output_parsers/tools.py

@@ -9,12 +9,17 @@ from langchain_core.messages import (
     BaseMessage,
     ToolCall,
 )
+from langchain_core.messages.utils import convert_from_v1_message
 from langchain_core.outputs import ChatGeneration, Generation
+from langchain_core.v1.messages import AIMessage as AIMessageV1
+from typing_extensions import override
 
 from langchain.agents.agent import MultiActionAgentOutputParser
 
 
 class ToolAgentAction(AgentActionMessageLog):
+    """ "Tool agent action."""
+
     tool_call_id: str
     """Tool call that this message is responding to."""
 
@@ -44,7 +49,12 @@ def parse_ai_message_to_tool_action(
             try:
                 args = json.loads(function["arguments"] or "{}")
                 tool_calls.append(
-                    ToolCall(name=function_name, args=args, id=tool_call["id"]),
+                    ToolCall(
+                        name=function_name,
+                        args=args,
+                        id=tool_call["id"],
+                        type="tool_call",
+                    )
                 )
             except JSONDecodeError as e:
                 msg = (
@@ -90,18 +100,22 @@ class ToolsAgentOutputParser(MultiActionAgentOutputParser):
     def _type(self) -> str:
         return "tools-agent-output-parser"
 
+    @override
     def parse_result(
         self,
-        result: list[Generation],
+        result: Union[list[Generation], AIMessageV1],
         *,
         partial: bool = False,
     ) -> Union[list[AgentAction], AgentFinish]:
+        if isinstance(result, AIMessageV1):
+            result = [ChatGeneration(message=convert_from_v1_message(result))]
         if not isinstance(result[0], ChatGeneration):
             msg = "This output parser only works on ChatGeneration output"
             raise ValueError(msg)  # noqa: TRY004
         message = result[0].message
         return parse_ai_message_to_tool_action(message)
 
+    @override
     def parse(self, text: str) -> Union[list[AgentAction], AgentFinish]:
         msg = "Can only parse messages"
         raise ValueError(msg)