feat: improve error handling of Agent component, solves Empty ExceptionWithMessageError (#6097)

* Gracefully handle Errors

* updates to Error handling

* update in Error handling

* update lint error similar to main

* [autofix.ci] apply automated fixes

* [autofix.ci] apply automated fixes (attempt 2/3)

* feat: add max retry and request timeout to open ai component, fixes remote protocol error caused by OpenAI LLM in Agents (#6118)

* update to __str__ and fix lint errors

* [autofix.ci] apply automated fixes

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>

Author: edwinjosechittilappilly

src/backend/base/langflow/base/agents/agent.py

@@ -14,6 +14,7 @@
 from langflow.field_typing import Tool
 from langflow.inputs.inputs import InputTypes, MultilineInput
 from langflow.io import BoolInput, HandleInput, IntInput, MessageTextInput
+from langflow.logging import logger
 from langflow.memory import delete_message
 from langflow.schema import Data
 from langflow.schema.content_block import ContentBlock
@@ -171,8 +172,11 @@ async def run_agent(
             msg_id = e.agent_message.id
             await delete_message(id_=msg_id)
             await self._send_message_event(e.agent_message, category="remove_message")
+            logger.error(f"ExceptionWithMessageError: {e}")
             raise
-        except Exception:
+        except Exception as e:
+            # Log or handle any other exceptions
+            logger.error(f"Error: {e}")
             raise
 
         self.status = result

src/backend/base/langflow/base/agents/errors.py

@@ -0,0 +1,15 @@
+from anthropic import BadRequestError as AnthropicBadRequestError
+from cohere import BadRequestError as CohereBadRequestError
+from httpx import HTTPStatusError
+
+from langflow.schema.message import Message
+
+
+class CustomBadRequestError(AnthropicBadRequestError, CohereBadRequestError, HTTPStatusError):
+    def __init__(self, agent_message: Message | None, message: str):
+        super().__init__(message)
+        self.message = message
+        self.agent_message = agent_message
+
+    def __str__(self):
+        return f"{self.message}"

src/backend/base/langflow/base/agents/events.py

@@ -14,9 +14,17 @@
 
 
 class ExceptionWithMessageError(Exception):
-    def __init__(self, agent_message: Message):
+    def __init__(self, agent_message: Message, message: str):
         self.agent_message = agent_message
-        super().__init__()
+        super().__init__(message)
+        self.message = message
+
+    def __str__(self):
+        return (
+            f"Agent message: {self.agent_message.text} \nError: {self.message}."
+            if self.agent_message.error or self.agent_message.text
+            else f"{self.message}."
+        )
 
 
 class InputDict(TypedDict):
@@ -273,6 +281,5 @@ async def process_agent_events(
                 agent_message, start_time = await chain_handler(event, agent_message, send_message_method, start_time)
         agent_message.properties.state = "complete"
     except Exception as e:
-        raise ExceptionWithMessageError(agent_message) from e
-
+        raise ExceptionWithMessageError(agent_message, str(e)) from e
     return await Message.create(**agent_message.model_dump())

src/backend/base/langflow/components/agents/agent.py

@@ -1,6 +1,7 @@
 from langchain_core.tools import StructuredTool
 
 from langflow.base.agents.agent import LCToolsAgentComponent
+from langflow.base.agents.events import ExceptionWithMessageError
 from langflow.base.models.model_input_constants import (
     ALL_PROVIDER_FIELDS,
     MODEL_DYNAMIC_UPDATE_FIELDS,
@@ -65,43 +66,32 @@ class AgentComponent(ToolCallingAgentComponent):
 
     async def message_response(self) -> Message:
         try:
+            # Get LLM model and validate
             llm_model, display_name = self.get_llm()
             if llm_model is None:
-                msg = "No language model selected"
+                msg = "No language model selected. Please choose a model to proceed."
                 raise ValueError(msg)
             self.model_name = get_model_name(llm_model, display_name=display_name)
-        except Exception as e:
-            # Log the error for debugging purposes
-            logger.error(f"Error retrieving language model: {e}")
-            raise
 
-        try:
+            # Get memory data
             self.chat_history = await self.get_memory_data()
-        except Exception as e:
-            logger.error(f"Error retrieving chat history: {e}")
-            raise
 
-        if self.add_current_date_tool:
-            try:
+            # Add current date tool if enabled
+            if self.add_current_date_tool:
                 if not isinstance(self.tools, list):  # type: ignore[has-type]
                     self.tools = []
-                # Convert CurrentDateComponent to a StructuredTool
                 current_date_tool = (await CurrentDateComponent(**self.get_base_args()).to_toolkit()).pop(0)
-                if isinstance(current_date_tool, StructuredTool):
-                    self.tools.append(current_date_tool)
-                else:
+                if not isinstance(current_date_tool, StructuredTool):
                     msg = "CurrentDateComponent must be converted to a StructuredTool"
                     raise TypeError(msg)
-            except Exception as e:
-                logger.error(f"Error adding current date tool: {e}")
-                raise
+                self.tools.append(current_date_tool)
 
-        if not self.tools:
-            msg = "Tools are required to run the agent."
-            logger.error(msg)
-            raise ValueError(msg)
+            # Validate tools
+            if not self.tools:
+                msg = "Tools are required to run the agent. Please add at least one tool."
+                raise ValueError(msg)
 
-        try:
+            # Set up and run agent
             self.set(
                 llm=llm_model,
                 tools=self.tools,
@@ -110,12 +100,18 @@ async def message_response(self) -> Message:
                 system_prompt=self.system_prompt,
             )
             agent = self.create_agent_runnable()
+            return await self.run_agent(agent)
+
+        except (ValueError, TypeError, KeyError) as e:
+            logger.error(f"{type(e).__name__}: {e!s}")
+            raise
+        except ExceptionWithMessageError as e:
+            logger.error(f"ExceptionWithMessageError occurred: {e}")
+            raise
         except Exception as e:
-            logger.error(f"Error setting up the agent: {e}")
+            logger.error(f"Unexpected error: {e!s}")
             raise
 
-        return await self.run_agent(agent)
-
     async def get_memory_data(self):
         memory_kwargs = {
             component_input.name: getattr(self, f"{component_input.name}") for component_input in self.memory_inputs
@@ -126,22 +122,26 @@ async def get_memory_data(self):
         return await MemoryComponent(**self.get_base_args()).set(**memory_kwargs).retrieve_messages()
 
     def get_llm(self):
-        if isinstance(self.agent_llm, str):
-            try:
-                provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)
-                if provider_info:
-                    component_class = provider_info.get("component_class")
-                    display_name = component_class.display_name
-                    inputs = provider_info.get("inputs")
-                    prefix = provider_info.get("prefix", "")
-                    return (
-                        self._build_llm_model(component_class, inputs, prefix),
-                        display_name,
-                    )
-            except Exception as e:
-                msg = f"Error building {self.agent_llm} language model"
-                raise ValueError(msg) from e
-        return self.agent_llm, None
+        if not isinstance(self.agent_llm, str):
+            return self.agent_llm, None
+
+        try:
+            provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)
+            if not provider_info:
+                msg = f"Invalid model provider: {self.agent_llm}"
+                raise ValueError(msg)
+
+            component_class = provider_info.get("component_class")
+            display_name = component_class.display_name
+            inputs = provider_info.get("inputs")
+            prefix = provider_info.get("prefix", "")
+
+            return self._build_llm_model(component_class, inputs, prefix), display_name
+
+        except Exception as e:
+            logger.error(f"Error building {self.agent_llm} language model: {e!s}")
+            msg = f"Failed to initialize language model: {e!s}"
+            raise ValueError(msg) from e
 
     def _build_llm_model(self, component, inputs, prefix=""):
         model_kwargs = {input_.name: getattr(self, f"{prefix}{input_.name}") for input_ in inputs}

src/backend/base/langflow/components/models/openai.py

@@ -68,6 +68,20 @@ class OpenAIModelComponent(LCModelComponent):
             advanced=True,
             value=1,
         ),
+        IntInput(
+            name="max_retries",
+            display_name="Max Retries",
+            info="The maximum number of retries to make when generating.",
+            advanced=True,
+            value=5,
+        ),
+        IntInput(
+            name="timeout",
+            display_name="Timeout",
+            info="The timeout for requests to OpenAI completion API.",
+            advanced=True,
+            value=700,
+        ),
     ]
 
     def build_model(self) -> LanguageModel:  # type: ignore[type-var]
@@ -79,6 +93,8 @@ def build_model(self) -> LanguageModel:  # type: ignore[type-var]
         openai_api_base = self.openai_api_base or "https://api.openai.com/v1"
         json_mode = self.json_mode
         seed = self.seed
+        max_retries = self.max_retries
+        timeout = self.timeout
 
         api_key = SecretStr(openai_api_key).get_secret_value() if openai_api_key else None
         output = ChatOpenAI(
@@ -89,6 +105,8 @@ def build_model(self) -> LanguageModel:  # type: ignore[type-var]
             api_key=api_key,
             temperature=temperature if temperature is not None else 0.1,
             seed=seed,
+            max_retries=max_retries,
+            request_timeout=timeout,
         )
         if json_mode:
             output = output.bind(response_format={"type": "json_object"})