adding index + 1 so its in order

.gitignore

@@ -14,4 +14,5 @@ test.py
 rc-tests/*
 *.pkl
 temp/*
-.vscode/*
+.vscode/*
+crew_tasks_output.json

docs/core-concepts/Crews.md

@@ -155,4 +155,23 @@ for async_result in async_results:
     print(async_result)
 ```
 
+### Replaying from specific task:
+You can now replay from a specific task using our cli command replay.
+
+The replay_from_tasks feature in CrewAI allows you to replay from a specific task using the command-line interface (CLI). By running the command `crewai replay -t <task_id>`, you can specify the task name for the replay process.
+
+Kickoffs will now create a `crew_tasks_ouput.json` file with the output of the tasks which you use to retrieve the task id to replay.
+
+
+### Replaying from specific task Using the CLI
+To use the replay feature, follow these steps:
+
+1. Open your terminal or command prompt.
+2. Navigate to the directory where your CrewAI project is located.
+3. Run the following command:
+
+```shell
+crewai replay -t <task_id>
+```
+
 These methods provide flexibility in how you manage and execute tasks within your crew, allowing for both synchronous and asynchronous workflows tailored to your needs

docs/how-to/LLM-Connections.md

@@ -127,7 +127,7 @@ llm = HuggingFaceHub(
 ```
 
 ## OpenAI Compatible API Endpoints
-Switch between APIs and models seamlessly using environment variables, supporting platforms like FastChat, LM Studio, Groq, and Mistral AI.
+Switch between APIs and models seamlessly using environment variables, supporting platforms like FastChat, LM Studio, and Mistral AI.
 
 ### Configuration Examples
 #### FastChat
@@ -144,13 +144,6 @@ OPENAI_API_BASE="http://localhost:1234/v1"
 OPENAI_API_KEY="lm-studio"
 ```
 
-#### Groq API
-```sh
-OPENAI_API_KEY=your-groq-api-key
-OPENAI_MODEL_NAME='llama3-8b-8192'
-OPENAI_API_BASE=https://api.groq.com/openai/v1
-```
-
 #### Mistral API
 ```sh
 OPENAI_API_KEY=your-mistral-api-key
@@ -218,4 +211,4 @@ azure_agent = Agent(
 ```
 
 ## Conclusion
-Integrating CrewAI with different LLMs expands the framework's versatility, allowing for customized, efficient AI solutions across various domains and platforms.
+Integrating CrewAI with different LLMs expands the framework's versatility, allowing for customized, efficient AI solutions across various domains and platforms.

poetry.lock

@@ -2282,17 +2282,6 @@ files = [
     {file = "jmespath-1.0.1.tar.gz", hash = "sha256:90261b206d6defd58fdd5e85f478bf633a2901798906be2ad389150c5c60edbe"},
 ]
 
-[[package]]
-name = "json-repair"
-version = "0.25.2"
-description = "A package to repair broken json strings"
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "json_repair-0.25.2-py3-none-any.whl", hash = "sha256:51d67295c3184b6c41a3572689661c6128cef6cfc9fb04db63130709adfc5bf0"},
-    {file = "json_repair-0.25.2.tar.gz", hash = "sha256:161a56d7e6bbfd4cad3a614087e3e0dbd0e10d402dd20dc7db418432428cb32b"},
-]
-
 [[package]]
 name = "jsonpatch"
 version = "1.33"
@@ -2406,8 +2395,8 @@ langchain-core = ">=0.2.10,<0.3.0"
 langchain-text-splitters = ">=0.2.0,<0.3.0"
 langsmith = ">=0.1.17,<0.2.0"
 numpy = [
-    {version = ">=1,<2", markers = "python_version < \"3.12\""},
     {version = ">=1.26.0,<2.0.0", markers = "python_version >= \"3.12\""},
+    {version = ">=1,<2", markers = "python_version < \"3.12\""},
 ]
 pydantic = ">=1,<3"
 PyYAML = ">=5.3"
@@ -2448,8 +2437,8 @@ langchain = ">=0.2.6,<0.3.0"
 langchain-core = ">=0.2.10,<0.3.0"
 langsmith = ">=0.1.0,<0.2.0"
 numpy = [
-    {version = ">=1,<2", markers = "python_version < \"3.12\""},
     {version = ">=1.26.0,<2.0.0", markers = "python_version >= \"3.12\""},
+    {version = ">=1,<2", markers = "python_version < \"3.12\""},
 ]
 PyYAML = ">=5.3"
 requests = ">=2,<3"
@@ -2472,8 +2461,8 @@ jsonpatch = ">=1.33,<2.0"
 langsmith = ">=0.1.75,<0.2.0"
 packaging = ">=23.2,<25"
 pydantic = [
-    {version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
     {version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
+    {version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
 ]
 PyYAML = ">=5.3"
 tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
@@ -2522,8 +2511,8 @@ files = [
 [package.dependencies]
 orjson = ">=3.9.14,<4.0.0"
 pydantic = [
-    {version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
     {version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
+    {version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
 ]
 requests = ">=2,<3"
 
@@ -4000,8 +3989,8 @@ files = [
 annotated-types = ">=0.4.0"
 pydantic-core = "2.20.1"
 typing-extensions = [
-    {version = ">=4.6.1", markers = "python_version < \"3.13\""},
     {version = ">=4.12.2", markers = "python_version >= \"3.13\""},
+    {version = ">=4.6.1", markers = "python_version < \"3.13\""},
 ]
 
 [package.extras]
@@ -6101,4 +6090,4 @@ tools = ["crewai-tools"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<=3.13"
-content-hash = "2cf5a3904e7cbcfebb85e198b6035252d47213a9b0dd3dd51837516e03b38d3e"
+content-hash = "0dbf6f6e2e841fb3eec4ff87ea5d6b430f29702118fee91307983c6b2581e59e"

pyproject.toml

@@ -28,7 +28,6 @@ appdirs = "^1.4.4"
 jsonref = "^1.1.0"
 agentops = { version = "^0.1.9", optional = true }
 embedchain = "^0.1.114"
-json-repair = "^0.25.2"
 
 [tool.poetry.extras]
 tools = ["crewai-tools"]

src/crewai/agent.py

@@ -1,14 +1,13 @@
 import os
-from inspect import signature
 from typing import Any, List, Optional, Tuple
 
 from langchain.agents.agent import RunnableAgent
-from langchain.agents.tools import BaseTool
 from langchain.agents.tools import tool as LangChainTool
+from langchain.tools.render import render_text_description
 from langchain_core.agents import AgentAction
 from langchain_core.callbacks import BaseCallbackHandler
 from langchain_openai import ChatOpenAI
-from pydantic import Field, InstanceOf, PrivateAttr, model_validator
+from pydantic import Field, InstanceOf, model_validator
 
 from crewai.agents import CacheHandler, CrewAgentExecutor, CrewAgentParser
 from crewai.agents.agent_builder.base_agent import BaseAgent
@@ -55,11 +54,8 @@ class Agent(BaseAgent):
             tools: Tools at agents disposal
             step_callback: Callback to be executed after each step of the agent execution.
             callbacks: A list of callback functions from the langchain library that are triggered during the agent's execution process
-            allow_code_execution: Enable code execution for the agent.
-            max_retry_limit: Maximum number of retries for an agent to execute a task when an error occurs.
     """
 
-    _times_executed: int = PrivateAttr(default=0)
     max_execution_time: Optional[int] = Field(
         default=None,
         description="Maximum execution time for an agent to execute a task",
@@ -100,10 +96,6 @@ class Agent(BaseAgent):
     allow_code_execution: Optional[bool] = Field(
         default=False, description="Enable code execution for the agent."
     )
-    max_retry_limit: int = Field(
-        default=2,
-        description="Maximum number of retries for an agent to execute a task when an error occurs.",
-    )
 
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
@@ -175,15 +167,14 @@ class Agent(BaseAgent):
             if memory.strip() != "":
                 task_prompt += self.i18n.slice("memory").format(memory=memory)
 
-        tools = tools or self.tools or []
-        parsed_tools = self._parse_tools(tools)
+        tools = tools or self.tools
+
+        parsed_tools = self._parse_tools(tools or [])  # type: ignore # Argument 1 to "_parse_tools" of "Agent" has incompatible type "list[Any] | None"; expected "list[Any]"
         self.create_agent_executor(tools=tools)
         self.agent_executor.tools = parsed_tools
         self.agent_executor.task = task
 
-        self.agent_executor.tools_description = self._render_text_description_and_args(
-            parsed_tools
-        )
+        self.agent_executor.tools_description = render_text_description(parsed_tools)
         self.agent_executor.tools_names = self.__tools_names(parsed_tools)
 
         if self.crew and self.crew._train:
@@ -191,20 +182,13 @@ class Agent(BaseAgent):
         else:
             task_prompt = self._use_trained_data(task_prompt=task_prompt)
 
-        try:
-            result = self.agent_executor.invoke(
-                {
-                    "input": task_prompt,
-                    "tool_names": self.agent_executor.tools_names,
-                    "tools": self.agent_executor.tools_description,
-                }
-            )["output"]
-        except Exception as e:
-            self._times_executed += 1
-            if self._times_executed > self.max_retry_limit:
-                raise e
-            result = self.execute_task(task, context, tools)
-
+        result = self.agent_executor.invoke(
+            {
+                "input": task_prompt,
+                "tool_names": self.agent_executor.tools_names,
+                "tools": self.agent_executor.tools_description,
+            }
+        )["output"]
         if self.max_rpm:
             self._rpm_controller.stop_rpm_counter()
 
@@ -236,7 +220,7 @@ class Agent(BaseAgent):
         Returns:
             An instance of the CrewAgentExecutor class.
         """
-        tools = tools or self.tools or []
+        tools = tools or self.tools
 
         agent_args = {
             "input": lambda x: x["input"],
@@ -331,7 +315,6 @@ class Agent(BaseAgent):
             tools_list = []
             for tool in tools:
                 tools_list.append(tool)
-
         return tools_list
 
     def _training_handler(self, task_prompt: str) -> str:
@@ -358,52 +341,6 @@ class Agent(BaseAgent):
                 )
         return task_prompt
 
-    def _render_text_description(self, tools: List[BaseTool]) -> str:
-        """Render the tool name and description in plain text.
-
-        Output will be in the format of:
-
-        .. code-block:: markdown
-
-            search: This tool is used for search
-            calculator: This tool is used for math
-        """
-        description = "\n".join(
-            [
-                f"Tool name: {tool.name}\nTool description:\n{tool.description}"
-                for tool in tools
-            ]
-        )
-
-        return description
-
-    def _render_text_description_and_args(self, tools: List[BaseTool]) -> str:
-        """Render the tool name, description, and args in plain text.
-
-        Output will be in the format of:
-
-        .. code-block:: markdown
-
-            search: This tool is used for search, args: {"query": {"type": "string"}}
-            calculator: This tool is used for math, \
-    args: {"expression": {"type": "string"}}
-        """
-        tool_strings = []
-        for tool in tools:
-            args_schema = str(tool.args)
-            if hasattr(tool, "func") and tool.func:
-                sig = signature(tool.func)
-                description = (
-                    f"Tool Name: {tool.name}{sig}\nTool Description: {tool.description}"
-                )
-            else:
-                description = (
-                    f"Tool Name: {tool.name}\nTool Description: {tool.description}"
-                )
-            tool_strings.append(f"{description}\nTool Arguments: {args_schema}")
-
-        return "\n".join(tool_strings)
-
     @staticmethod
     def __tools_names(tools) -> str:
         return ", ".join([t.name for t in tools])

src/crewai/agents/agent_builder/utilities/base_agent_tool.py

@@ -24,7 +24,6 @@ class BaseAgentTools(BaseModel, ABC):
             is_list = coworker.startswith("[") and coworker.endswith("]")
             if is_list:
                 coworker = coworker[1:-1].split(",")[0]
-
         return coworker
 
     def delegate_work(
@@ -41,13 +40,11 @@ class BaseAgentTools(BaseModel, ABC):
         coworker = self._get_coworker(coworker, **kwargs)
         return self._execute(coworker, question, context)
 
-    def _execute(
-        self, agent_name: Union[str, None], task: str, context: Union[str, None]
-    ):
+    def _execute(self, agent: Union[str, None], task: str, context: Union[str, None]):
         """Execute the command."""
         try:
-            if agent_name is None:
-                agent_name = ""
+            if agent is None:
+                agent = ""
 
             # It is important to remove the quotes from the agent name.
             # The reason we have to do this is because less-powerful LLM's
@@ -56,7 +53,7 @@ class BaseAgentTools(BaseModel, ABC):
             # {"task": "....", "coworker": "....
             # when it should look like this:
             # {"task": "....", "coworker": "...."}
-            agent_name = agent_name.casefold().replace('"', "").replace("\n", "")
+            agent_name = agent.casefold().replace('"', "").replace("\n", "")
 
             agent = [  # type: ignore # Incompatible types in assignment (expression has type "list[BaseAgent]", variable has type "str | None")
                 available_agent
@@ -78,9 +75,9 @@ class BaseAgentTools(BaseModel, ABC):
             )
 
         agent = agent[0]
-        task_with_assigned_agent = Task(  # type: ignore # Incompatible types in assignment (expression has type "Task", variable has type "str")
+        task = Task(  # type: ignore # Incompatible types in assignment (expression has type "Task", variable has type "str")
             description=task,
             agent=agent,
             expected_output="Your best answer to your coworker asking you this, accounting for the context shared.",
         )
-        return agent.execute_task(task_with_assigned_agent, context)
+        return agent.execute_task(task, context)  # type: ignore # "str" has no attribute "execute_task"

src/crewai/agents/agent_builder/utilities/base_output_converter_base.py

@@ -1,7 +1,7 @@
 from abc import ABC, abstractmethod
 from typing import Any, Optional
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, PrivateAttr
 
 
 class OutputConverter(BaseModel, ABC):
@@ -21,6 +21,7 @@ class OutputConverter(BaseModel, ABC):
         max_attempts (int): Maximum number of conversion attempts (default: 3).
     """
 
+    _is_gpt: bool = PrivateAttr(default=True)
     text: str = Field(description="Text to be converted.")
     llm: Any = Field(description="The language model to be used to convert the text.")
     model: Any = Field(description="The model to be used to convert the text.")
@@ -40,8 +41,7 @@ class OutputConverter(BaseModel, ABC):
         """Convert text to json."""
         pass
 
-    @property
-    @abstractmethod
-    def is_gpt(self) -> bool:
+    @abstractmethod  # type: ignore #  Name "_is_gpt" already defined on line 25
+    def _is_gpt(self, llm):  # type: ignore #  Name "_is_gpt" already defined on line 25
         """Return if llm provided is of gpt from openai."""
         pass

src/crewai/agents/executor.py

@@ -1,6 +1,14 @@
 import threading
 import time
-from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
+from typing import (
+    Any,
+    Dict,
+    Iterator,
+    List,
+    Optional,
+    Tuple,
+    Union,
+)
 
 from langchain.agents import AgentExecutor
 from langchain.agents.agent import ExceptionTool
@@ -11,7 +19,9 @@ from langchain_core.tools import BaseTool
 from langchain_core.utils.input import get_color_mapping
 from pydantic import InstanceOf
 
-from crewai.agents.agent_builder.base_agent_executor_mixin import CrewAgentExecutorMixin
+from crewai.agents.agent_builder.base_agent_executor_mixin import (
+    CrewAgentExecutorMixin,
+)
 from crewai.agents.tools_handler import ToolsHandler
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
 from crewai.utilities import I18N

src/crewai/agents/parser.py

@@ -1,7 +1,6 @@
 import re
 from typing import Any, Union
 
-from json_repair import repair_json
 from langchain.agents.output_parsers import ReActSingleInputOutputParser
 from langchain_core.agents import AgentAction, AgentFinish
 from langchain_core.exceptions import OutputParserException
@@ -49,15 +48,11 @@ class CrewAgentParser(ReActSingleInputOutputParser):
                 raise OutputParserException(
                     f"{FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE}: {text}"
                 )
-            action = action_match.group(1)
-            clean_action = self._clean_action(action)
-
-            action_input = action_match.group(2).strip()
-
-            tool_input = action_input.strip(" ").strip('"')
-            safe_tool_input = self._safe_repair_json(tool_input)
-
-            return AgentAction(clean_action, safe_tool_input, text)
+            action = action_match.group(1).strip()
+            action_input = action_match.group(2)
+            tool_input = action_input.strip(" ")
+            tool_input = tool_input.strip('"')
+            return AgentAction(action, tool_input, text)
 
         elif includes_answer:
             return AgentFinish(
@@ -92,30 +87,3 @@ class CrewAgentParser(ReActSingleInputOutputParser):
                 llm_output=text,
                 send_to_llm=True,
             )
-
-    def _clean_action(self, text: str) -> str:
-        """Clean action string by removing non-essential formatting characters."""
-        return re.sub(r"^\s*\*+\s*|\s*\*+\s*$", "", text).strip()
-
-    def _safe_repair_json(self, tool_input: str) -> str:
-        UNABLE_TO_REPAIR_JSON_RESULTS = ['""', "{}"]
-
-        # Skip repair if the input starts and ends with square brackets
-        # Explanation: The JSON parser has issues handling inputs that are enclosed in square brackets ('[]').
-        # These are typically valid JSON arrays or strings that do not require repair. Attempting to repair such inputs
-        # might lead to unintended alterations, such as wrapping the entire input in additional layers or modifying
-        # the structure in a way that changes its meaning. By skipping the repair for inputs that start and end with
-        # square brackets, we preserve the integrity of these valid JSON structures and avoid unnecessary modifications.
-        if tool_input.startswith("[") and tool_input.endswith("]"):
-            return tool_input
-
-        # Before repair, handle common LLM issues:
-        # 1. Replace """ with " to avoid JSON parser errors
-
-        tool_input = tool_input.replace('"""', '"')
-
-        result = repair_json(tool_input)
-        if result in UNABLE_TO_REPAIR_JSON_RESULTS:
-            return tool_input
-
-        return str(result)

src/crewai/cli/cli.py

@@ -1,8 +1,11 @@
 import click
 import pkg_resources
 
+
 from .create_crew import create_crew
 from .train_crew import train_crew
+from .replay_from_task import replay_task_command
+from .list_task_outputs import show_task_outputs
 
 
 @click.group()
@@ -48,5 +51,32 @@ def train(n_iterations: int):
     train_crew(n_iterations)
 
 
+@crewai.command()
+@click.option(
+    "-t",
+    "--task_id",
+    type=str,
+    help="Replay the crew from this task ID, including all subsequent tasks.",
+)
+def replay(task_id: str) -> None:
+    """
+    Replay the crew execution from a specific task.
+
+    Args:
+        task_id (str): The ID of the task to replay from.
+    """
+    try:
+        click.echo(f"Replaying the crew from task {task_id}")
+        replay_task_command(task_id)
+    except Exception as e:
+        click.echo(f"An error occurred while replaying: {e}", err=True)
+
+
+@crewai.command()
+def list_completed_tasks_ids():
+    """List all task outputs saved from crew_tasks_output.json."""
+    show_task_outputs()
+
+
 if __name__ == "__main__":
     crewai()

src/crewai/cli/list_task_outputs.py

@@ -0,0 +1,34 @@
+import subprocess
+import click
+from pathlib import Path
+import json
+
+
+def show_task_outputs() -> None:
+    """
+    Replay the crew execution from a specific task.
+
+    Args:
+      task_id (str): The ID of the task to replay from.
+    """
+
+    try:
+        file_path = Path("crew_tasks_output.json")
+        if not file_path.exists():
+            click.echo("crew_tasks_output.json not found.")
+            return
+
+        with open(file_path, "r") as f:
+            tasks = json.load(f)
+
+        for index, task in enumerate(tasks):
+            click.echo(f"Task {index + 1}: {task['task_id']}")
+            click.echo(f"Description: {task['output']['description']}")
+            click.echo("---")
+
+    except subprocess.CalledProcessError as e:
+        click.echo(f"An error occurred while replaying the task: {e}", err=True)
+        click.echo(e.output, err=True)
+
+    except Exception as e:
+        click.echo(f"An unexpected error occurred: {e}", err=True)

src/crewai/cli/replay_from_task.py

@@ -0,0 +1,24 @@
+import subprocess
+import click
+
+
+def replay_task_command(task_id: str) -> None:
+    """
+    Replay the crew execution from a specific task.
+
+    Args:
+      task_id (str): The ID of the task to replay from.
+    """
+    command = ["poetry", "run", "replay_from_task", task_id]
+
+    try:
+        result = subprocess.run(command, capture_output=False, text=True, check=True)
+        if result.stderr:
+            click.echo(result.stderr, err=True)
+
+    except subprocess.CalledProcessError as e:
+        click.echo(f"An error occurred while replaying the task: {e}", err=True)
+        click.echo(e.output, err=True)
+
+    except Exception as e:
+        click.echo(f"An unexpected error occurred: {e}", err=True)

src/crewai/cli/templates/main.py

@@ -21,3 +21,13 @@ def train():
 
     except Exception as e:
         raise Exception(f"An error occurred while training the crew: {e}")
+
+def replay_from_task():
+    """
+    Replay the crew execution from a specific task.
+    """
+    try:
+        {{crew_name}}Crew().crew().replay_from_task(task_id=sys.argv[1])
+
+    except Exception as e:
+        raise Exception(f"An error occurred while replaying the crew: {e}")

src/crewai/cli/templates/pyproject.toml

@@ -11,6 +11,7 @@ crewai = { extras = ["tools"], version = "^0.35.8" }
 [tool.poetry.scripts]
 {{folder_name}} = "{{folder_name}}.main:run"
 train = "{{folder_name}}.main:train"
+replay = "{{folder_name}}.main:replay_from_task"
 
 [build-system]
 requires = ["poetry-core"]

src/crewai/crew.py

@@ -6,15 +6,15 @@ from typing import Any, Dict, List, Optional, Tuple, Union
 
 from langchain_core.callbacks import BaseCallbackHandler
 from pydantic import (
-  UUID4,
-  BaseModel,
-  ConfigDict,
-  Field,
-  InstanceOf,
-  Json,
-  PrivateAttr,
-  field_validator,
-  model_validator,
+    UUID4,
+    BaseModel,
+    ConfigDict,
+    Field,
+    InstanceOf,
+    Json,
+    PrivateAttr,
+    field_validator,
+    model_validator,
 )
 from pydantic_core import PydanticCustomError
 
@@ -31,8 +31,16 @@ from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry import Telemetry
 from crewai.tools.agent_tools import AgentTools
 from crewai.utilities import I18N, FileHandler, Logger, RPMController
-from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
+from crewai.utilities.constants import (
+    CREW_TASKS_OUTPUT_FILE,
+    TRAINED_AGENTS_DATA_FILE,
+    TRAINING_DATA_FILE,
+)
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
+from crewai.utilities.task_output_handler import (
+    ExecutionLog,
+    TaskOutputJsonHandler,
+)
 from crewai.utilities.formatter import (
     aggregate_raw_outputs_from_task_outputs,
     aggregate_raw_outputs_from_tasks,
@@ -80,6 +88,10 @@ class Crew(BaseModel):
     _entity_memory: Optional[InstanceOf[EntityMemory]] = PrivateAttr()
     _train: Optional[bool] = PrivateAttr(default=False)
     _train_iteration: Optional[int] = PrivateAttr()
+    _inputs: Optional[Dict[str, Any]] = PrivateAttr(default=None)
+    _logging_color: str = PrivateAttr(
+        default="bold_purple",
+    )
 
     cache: bool = Field(default=True)
     model_config = ConfigDict(arbitrary_types_allowed=True)
@@ -135,6 +147,14 @@ class Crew(BaseModel):
         default=False,
         description="output_log_file",
     )
+    task_execution_output_json_files: Optional[List[str]] = Field(
+        default=None,
+        description="List of file paths for task execution JSON files.",
+    )
+    execution_logs: List[ExecutionLog] = Field(
+        default=[],
+        description="List of execution logs for tasks",
+    )
 
     @field_validator("id", mode="before")
     @classmethod
@@ -170,6 +190,7 @@ class Crew(BaseModel):
         self._rpm_controller = RPMController(max_rpm=self.max_rpm, logger=self._logger)
         self._telemetry = Telemetry()
         self._telemetry.set_tracer()
+        self._telemetry.crew_creation(self)
         return self
 
     @model_validator(mode="after")
@@ -376,7 +397,12 @@ class Crew(BaseModel):
     ) -> CrewOutput:
         """Starts the crew to work on its assigned tasks."""
         self._execution_span = self._telemetry.crew_execution_span(self, inputs)
+        TaskOutputJsonHandler(CREW_TASKS_OUTPUT_FILE).initialize_file()
+        TaskOutputJsonHandler(CREW_TASKS_OUTPUT_FILE).reset()
+        self._logging_color = "bold_purple"
+
         if inputs is not None:
+            self._inputs = inputs
             self._interpolate_inputs(inputs)
         self._set_tasks_callbacks()
 
@@ -403,7 +429,7 @@ class Crew(BaseModel):
         if self.process == Process.sequential:
             result = self._run_sequential_process()
         elif self.process == Process.hierarchical:
-            result = self._run_hierarchical_process()  # type: ignore # Incompatible types in assignment (expression has type "str | dict[str, Any]", variable has type "str")
+            result = self._run_hierarchical_process()
         else:
             raise NotImplementedError(
                 f"The process '{self.process}' is not implemented yet."
@@ -491,126 +517,51 @@ class Crew(BaseModel):
 
         return results
 
+    def _store_execution_log(
+        self,
+        task: Task,
+        output: TaskOutput,
+        task_index: int,
+        was_replayed: bool = False,
+    ):
+        if self._inputs:
+            inputs = self._inputs
+        else:
+            inputs = {}
+
+        log = ExecutionLog(
+            task_id=str(task.id),
+            expected_output=task.expected_output,
+            output={
+                "description": output.description,
+                "summary": output.summary,
+                "raw": output.raw,
+                "pydantic": output.pydantic,
+                "json_dict": output.json_dict,
+                "output_format": output.output_format,
+                "agent": output.agent,
+            },
+            task_index=task_index,
+            inputs=inputs,
+            was_replayed=was_replayed,
+        )
+        if task_index < len(self.execution_logs):
+            self.execution_logs[task_index] = log
+        else:
+            self.execution_logs.append(log)
+
+        TaskOutputJsonHandler(CREW_TASKS_OUTPUT_FILE).update(task_index, log)
+
     def _run_sequential_process(self) -> CrewOutput:
         """Executes tasks sequentially and returns the final output."""
-        task_outputs: List[TaskOutput] = []
-        futures: List[Tuple[Task, Future[TaskOutput]]] = []
+        return self._execute_tasks(self.tasks)
 
-        for task in self.tasks:
-            if task.agent and task.agent.allow_delegation:
-                agents_for_delegation = [
-                    agent for agent in self.agents if agent != task.agent
-                ]
-                if len(self.agents) > 1 and len(agents_for_delegation) > 0:
-                    delegation_tools = task.agent.get_delegation_tools(
-                        agents_for_delegation
-                    )
-
-                    # Add tools if they are not already in task.tools
-                    for new_tool in delegation_tools:
-                        # Find the index of the tool with the same name
-                        existing_tool_index = next(
-                            (
-                                index
-                                for index, tool in enumerate(task.tools or [])
-                                if tool.name == new_tool.name
-                            ),
-                            None,
-                        )
-                        if not task.tools:
-                            task.tools = []
-
-                        if existing_tool_index is not None:
-                            # Replace the existing tool
-                            task.tools[existing_tool_index] = new_tool 
-                        else:
-                            # Add the new tool
-                            task.tools.append(new_tool)
-
-            role = task.agent.role if task.agent is not None else "None"
-            self._logger.log("debug", f"== Working Agent: {role}", color="bold_purple")
-            self._logger.log(
-                "info", f"== Starting Task: {task.description}", color="bold_purple"
-            )
-
-            if self.output_log_file:
-                self._file_handler.log(
-                    agent=role, task=task.description, status="started"
-                )
-
-            if task.async_execution:
-                context = (
-                    aggregate_raw_outputs_from_tasks(task.context)
-                    if task.context
-                    else aggregate_raw_outputs_from_task_outputs(task_outputs)
-                )
-                future = task.execute_async(
-                    agent=task.agent, context=context, tools=task.tools
-                )
-                futures.append((task, future))
-            else:
-                # Before executing a synchronous task, wait for all async tasks to complete
-                if futures:
-                    # Clear task_outputs before processing async tasks
-                    task_outputs = []
-                    for future_task, future in futures:
-                        task_output = future.result()
-                        task_outputs.append(task_output)
-                        self._process_task_result(future_task, task_output)
-
-                    # Clear the futures list after processing all async results
-                    futures.clear()
-
-                context = (
-                    aggregate_raw_outputs_from_tasks(task.context)
-                    if task.context
-                    else aggregate_raw_outputs_from_task_outputs(task_outputs)
-                )
-                task_output = task.execute_sync(
-                    agent=task.agent, context=context, tools=task.tools
-                )
-                task_outputs = [task_output]
-                self._process_task_result(task, task_output)
-
-        if futures:
-            # Clear task_outputs before processing async tasks
-            task_outputs = []
-            for future_task, future in futures:
-                task_output = future.result()
-                task_outputs.append(task_output)
-                self._process_task_result(future_task, task_output)
-
-        # Important: There should only be one task output in the list
-        #            If there are more or 0, something went wrong.
-        if len(task_outputs) != 1:
-            raise ValueError(
-                "Something went wrong. Kickoff should return only one task output."
-            )
-
-        final_task_output = task_outputs[0]
-
-        final_string_output = final_task_output.raw
-        self._finish_execution(final_string_output)
-
-        token_usage = self.calculate_usage_metrics()
-
-        return CrewOutput(
-            raw=final_task_output.raw,
-            pydantic=final_task_output.pydantic,
-            json_dict=final_task_output.json_dict,
-            tasks_output=[task.output for task in self.tasks if task.output],
-            token_usage=token_usage,
-        )
-
-    def _process_task_result(self, task: Task, output: TaskOutput) -> None:
-        role = task.agent.role if task.agent is not None else "None"
-        self._logger.log("debug", f"== [{role}] Task output: {output}\n\n")
-        if self.output_log_file:
-            self._file_handler.log(agent=role, task=output, status="completed")
-
-    # TODO: @joao, Breaking change. Changed return type. Usage metrics is included in crewoutput
     def _run_hierarchical_process(self) -> CrewOutput:
         """Creates and assigns a manager agent to make sure the crew completes the tasks."""
+        self._create_manager_agent()
+        return self._execute_tasks(self.tasks, self.manager_agent)
+
+    def _create_manager_agent(self):
         i18n = I18N(prompt_file=self.prompt_file)
         if self.manager_agent is not None:
             self.manager_agent.allow_delegation = True
@@ -629,74 +580,127 @@ class Crew(BaseModel):
             )
             self.manager_agent = manager
 
+    def _execute_tasks(
+        self,
+        tasks: List[Task],
+        manager: Optional[BaseAgent] = None,
+        start_index: Optional[int] = 0,
+        was_replayed: bool = False,
+    ) -> CrewOutput:
+        """Executes tasks sequentially and returns the final output.
+
+        Args:
+            tasks (List[Task]): List of tasks to execute
+            manager (Optional[BaseAgent], optional): Manager agent to use for delegation. Defaults to None.
+
+        Returns:
+            CrewOutput: Final output of the crew
+        """
+
         task_outputs: List[TaskOutput] = []
-        futures: List[Tuple[Task, Future[TaskOutput]]] = []
+        futures: List[Tuple[Task, Future[TaskOutput], int]] = []
+        last_sync_output: Optional[TaskOutput] = None
 
-        # TODO: IF USER OVERRIDE THE CONTEXT, PASS THAT
-        for task in self.tasks:
-            self._logger.log("debug", f"Working Agent: {manager.role}")
-            self._logger.log("info", f"Starting Task: {task.description}")
+        for task_index, task in enumerate(tasks):
+            if start_index is not None and task_index < start_index:
+                if task.output:
+                    if task.async_execution:
+                        task_outputs.append(task.output)
+                    else:
+                        task_outputs = [task.output]
+                        last_sync_output = task.output
+                continue
 
-            if self.output_log_file:
-                self._file_handler.log(
-                    agent=manager.role, task=task.description, status="started"
+            self._prepare_task(task, manager)
+            if self.process == Process.hierarchical:
+                agent_to_use = manager
+            else:
+                agent_to_use = task.agent
+            if agent_to_use is None:
+                raise ValueError(
+                    f"No agent available for task: {task.description}. Ensure that either the task has an assigned agent or a manager agent is provided."
                 )
+            self._log_task_start(task, agent_to_use)
 
             if task.async_execution:
-                context = (
-                    aggregate_raw_outputs_from_tasks(task.context)
-                    if task.context
-                    else aggregate_raw_outputs_from_task_outputs(task_outputs)
+                context = self._get_context(
+                    task, [last_sync_output] if last_sync_output else []
                 )
                 future = task.execute_async(
-                    agent=manager, context=context, tools=manager.tools
+                    agent=agent_to_use,
+                    context=context,
+                    tools=agent_to_use.tools,
                 )
-                futures.append((task, future))
+                futures.append((task, future, task_index))
             else:
-                # Before executing a synchronous task, wait for all async tasks to complete
                 if futures:
-                    # Clear task_outputs before processing async tasks
-                    task_outputs = []
-                    for future_task, future in futures:
-                        task_output = future.result()
-                        task_outputs.append(task_output)
-                        self._process_task_result(future_task, task_output)
-
-                    # Clear the futures list after processing all async results
+                    task_outputs.extend(
+                        self._process_async_tasks(futures, was_replayed)
+                    )
                     futures.clear()
 
-                context = (
-                    aggregate_raw_outputs_from_tasks(task.context)
-                    if task.context
-                    else aggregate_raw_outputs_from_task_outputs(task_outputs)
-                )
+                context = self._get_context(task, task_outputs)
                 task_output = task.execute_sync(
-                    agent=manager, context=context, tools=manager.tools
+                    agent=agent_to_use,
+                    context=context,
+                    tools=agent_to_use.tools,
                 )
                 task_outputs = [task_output]
                 self._process_task_result(task, task_output)
+                self._store_execution_log(task, task_output, task_index, was_replayed)
 
-        # Process any remaining async results
         if futures:
-            # Clear task_outputs before processing async tasks
-            task_outputs = []
-            for future_task, future in futures:
-                task_output = future.result()
-                task_outputs.append(task_output)
-                self._process_task_result(future_task, task_output)
+            task_outputs = self._process_async_tasks(futures, was_replayed)
 
-        # Important: There should only be one task output in the list
-        #            If there are more or 0, something went wrong.
+        return self._create_crew_output(task_outputs)
+
+    def _prepare_task(self, task: Task, manager: Optional[BaseAgent]):
+        if self.process == Process.hierarchical:
+            self._update_manager_tools(task, manager)
+        elif task.agent and task.agent.allow_delegation:
+            self._add_delegation_tools(task)
+
+    def _add_delegation_tools(self, task: Task):
+        agents_for_delegation = [agent for agent in self.agents if agent != task.agent]
+        if len(self.agents) > 1 and agents_for_delegation:
+            task.tools += task.agent.get_delegation_tools(agents_for_delegation)  # type: ignore
+
+    def _log_task_start(self, task: Task, agent: Optional[BaseAgent]):
+        color = self._logging_color
+        role = agent.role if agent else "None"
+        self._logger.log("debug", f"== Working Agent: {role}", color=color)
+        self._logger.log("info", f"== Starting Task: {task.description}", color=color)
+        if self.output_log_file:
+            self._file_handler.log(agent=role, task=task.description, status="started")
+
+    def _update_manager_tools(self, task: Task, manager: Optional[BaseAgent]):
+        if task.agent and manager:
+            manager.tools = task.agent.get_delegation_tools([task.agent])
+        if manager:
+            manager.tools = manager.get_delegation_tools(self.agents)
+
+    def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
+        context = (
+            aggregate_raw_outputs_from_tasks(task.context)
+            if task.context
+            else aggregate_raw_outputs_from_task_outputs(task_outputs)
+        )
+        return context
+
+    def _process_task_result(self, task: Task, output: TaskOutput) -> None:
+        role = task.agent.role if task.agent is not None else "None"
+        self._logger.log("debug", f"== [{role}] Task output: {output}\n\n")
+        if self.output_log_file:
+            self._file_handler.log(agent=role, task=output, status="completed")
+
+    def _create_crew_output(self, task_outputs: List[TaskOutput]) -> CrewOutput:
         if len(task_outputs) != 1:
             raise ValueError(
                 "Something went wrong. Kickoff should return only one task output."
             )
-
         final_task_output = task_outputs[0]
-
         final_string_output = final_task_output.raw
         self._finish_execution(final_string_output)
-
         token_usage = self.calculate_usage_metrics()
 
         return CrewOutput(
@@ -707,6 +711,69 @@ class Crew(BaseModel):
             token_usage=token_usage,
         )
 
+    def _process_async_tasks(
+        self,
+        futures: List[Tuple[Task, Future[TaskOutput], int]],
+        was_replayed: bool = False,
+    ) -> List[TaskOutput]:
+        task_outputs = []
+        for future_task, future, task_index in futures:
+            task_output = future.result()
+            task_outputs.append(task_output)
+            self._process_task_result(future_task, task_output)
+            self._store_execution_log(
+                future_task, task_output, task_index, was_replayed
+            )
+        return task_outputs
+
+    def _find_task_index(
+        self, task_id: str, stored_outputs: List[Any]
+    ) -> Optional[int]:
+        return next(
+            (
+                index
+                for (index, d) in enumerate(stored_outputs)
+                if d["task_id"] == str(task_id)
+            ),
+            None,
+        )
+
+    def replay_from_task(
+        self, task_id: str, inputs: Optional[Dict[str, Any]] = None
+    ) -> CrewOutput:
+        stored_outputs = TaskOutputJsonHandler(CREW_TASKS_OUTPUT_FILE).load()
+        start_index = self._find_task_index(task_id, stored_outputs)
+
+        if start_index is None:
+            raise ValueError(f"Task with id {task_id} not found in the crew's tasks.")
+
+        replay_inputs = (
+            inputs if inputs is not None else stored_outputs[start_index]["inputs"]
+        )
+        self._inputs = replay_inputs
+
+        if replay_inputs:
+            self._interpolate_inputs(replay_inputs)
+
+        if self.process == Process.hierarchical:
+            self._create_manager_agent()
+
+        for i in range(start_index):
+            stored_output = stored_outputs[i]["output"]
+            task_output = TaskOutput(
+                description=stored_output["description"],
+                agent=stored_output["agent"],
+                raw=stored_output["raw"],
+                pydantic=stored_output["pydantic"],
+                json_dict=stored_output["json_dict"],
+                output_format=stored_output["output_format"],
+            )
+            self.tasks[i].output = task_output
+
+        self._logging_color = "bold_blue"
+        result = self._execute_tasks(self.tasks, self.manager_agent, start_index, True)
+        return result
+
     def copy(self):
         """Create a deep copy of the Crew."""
 

src/crewai/crews/crew_output.py

@@ -24,8 +24,6 @@ class CrewOutput(BaseModel):
         description="Processed token summary", default={}
     )
 
-    # TODO: Joao - Adding this safety check breakes when people want to see
-    #                   The full output of a CrewOutput.
     # @property
     # def pydantic(self) -> Optional[BaseModel]:
     #     # Check if the final task output included a pydantic model

src/crewai/task.py

@@ -204,6 +204,7 @@ class Task(BaseModel):
         tools: Optional[List[Any]],
     ) -> TaskOutput:
         """Run the core execution logic of the task."""
+        self.agent = agent
         agent = agent or self.agent
         if not agent:
             raise Exception(
@@ -244,7 +245,9 @@ class Task(BaseModel):
             content = (
                 json_output
                 if json_output
-                else pydantic_output.model_dump_json() if pydantic_output else result
+                else pydantic_output.model_dump_json()
+                if pydantic_output
+                else result
             )
             self._save_file(content)
 
@@ -378,7 +381,7 @@ class Task(BaseModel):
     def _convert_with_instructions(
         self, result: str, model: Type[BaseModel]
     ) -> Union[dict, BaseModel, str]:
-        llm = self.agent.function_calling_llm or self.agent.llm
+        llm = self.agent.function_calling_llm or self.agent.llm  # type: ignore # Item "None" of "BaseAgent | None" has no attribute "function_calling_llm"
         instructions = self._get_conversion_instructions(model, llm)
 
         converter = self._create_converter(

src/crewai/tasks/task_output.py

@@ -11,9 +11,7 @@ class TaskOutput(BaseModel):
 
     description: str = Field(description="Description of the task")
     summary: Optional[str] = Field(description="Summary of the task", default=None)
-    raw: str = Field(
-        description="Raw output of the task", default=""
-    )  # TODO: @joao: breaking change, by renaming raw_output to raw, but now consistent with CrewOutput
+    raw: str = Field(description="Raw output of the task", default="")
     pydantic: Optional[BaseModel] = Field(
         description="Pydantic output of task", default=None
     )
@@ -32,8 +30,6 @@ class TaskOutput(BaseModel):
         self.summary = f"{excerpt}..."
         return self
 
-    # TODO: Joao - Adding this safety check breakes when people want to see
-    #                   The full output of a TaskOutput or CrewOutput.
     # @property
     # def pydantic(self) -> Optional[BaseModel]:
     #     # Check if the final task output included a pydantic model

src/crewai/telemetry/telemetry.py

@@ -80,7 +80,7 @@ class Telemetry:
                 self.ready = False
                 self.trace_set = False
 
-    def crew_creation(self, crew: Crew, inputs: dict[str, Any] | None):
+    def crew_creation(self, crew):
         """Records the creation of a crew."""
         if self.ready:
             try:
@@ -93,12 +93,6 @@ class Telemetry:
                 )
                 self._add_attribute(span, "python_version", platform.python_version())
                 self._add_attribute(span, "crew_id", str(crew.id))
-
-                if crew.share_crew:
-                    self._add_attribute(
-                        span, "crew_inputs", json.dumps(inputs) if inputs else None
-                    )
-
                 self._add_attribute(span, "crew_process", crew.process)
                 self._add_attribute(span, "crew_memory", crew.memory)
                 self._add_attribute(span, "crew_number_of_tasks", len(crew.tasks))
@@ -120,7 +114,7 @@ class Telemetry:
                                 "llm": json.dumps(self._safe_llm_attributes(agent.llm)),
                                 "delegation_enabled?": agent.allow_delegation,
                                 "tools_names": [
-                                    tool.name.casefold() for tool in agent.tools or []
+                                    tool.name.casefold() for tool in agent.tools
                                 ],
                             }
                             for agent in crew.agents
@@ -145,7 +139,7 @@ class Telemetry:
                                     else None
                                 ),
                                 "tools_names": [
-                                    tool.name.casefold() for tool in task.tools or []
+                                    tool.name.casefold() for tool in task.tools
                                 ],
                             }
                             for task in crew.tasks
@@ -167,11 +161,10 @@ class Telemetry:
         if self.ready:
             try:
                 tracer = trace.get_tracer("crewai.telemetry")
+                span = tracer.start_span("Task Execution")
 
                 created_span = tracer.start_span("Task Created")
 
-                self._add_attribute(created_span, "crew_id", str(crew.id))
-                self._add_attribute(created_span, "task_index", crew.tasks.index(task))
                 self._add_attribute(created_span, "task_id", str(task.id))
 
                 if crew.share_crew:
@@ -185,10 +178,6 @@ class Telemetry:
                 created_span.set_status(Status(StatusCode.OK))
                 created_span.end()
 
-                span = tracer.start_span("Task Execution")
-
-                self._add_attribute(span, "crew_id", str(crew.id))
-                self._add_attribute(span, "task_index", crew.tasks.index(task))
                 self._add_attribute(span, "task_id", str(task.id))
 
                 if crew.share_crew:
@@ -286,8 +275,6 @@ class Telemetry:
         """
         if (self.ready) and (crew.share_crew):
             try:
-                self.crew_creation(crew, inputs)
-
                 tracer = trace.get_tracer("crewai.telemetry")
                 span = tracer.start_span("Crew Execution")
                 self._add_attribute(
@@ -296,9 +283,7 @@ class Telemetry:
                     pkg_resources.get_distribution("crewai").version,
                 )
                 self._add_attribute(span, "crew_id", str(crew.id))
-                self._add_attribute(
-                    span, "crew_inputs", json.dumps(inputs) if inputs else None
-                )
+                self._add_attribute(span, "inputs", json.dumps(inputs))
                 self._add_attribute(
                     span,
                     "crew_agents",

src/crewai/tools/agent_tools.py

@@ -7,7 +7,7 @@ class AgentTools(BaseAgentTools):
     """Default tools around agent delegation"""
 
     def tools(self):
-        coworkers = ", ".join([f"{agent.role}" for agent in self.agents])
+        coworkers = f"[{', '.join([f'{agent.role}' for agent in self.agents])}]"
         tools = [
             StructuredTool.from_function(
                 func=self.delegate_work,

src/crewai/utilities/constants.py

@@ -1,2 +1,3 @@
 TRAINING_DATA_FILE = "training_data.pkl"
 TRAINED_AGENTS_DATA_FILE = "trained_agents_data.pkl"
+CREW_TASKS_OUTPUT_FILE = "crew_tasks_output.json"

src/crewai/utilities/converter.py

@@ -2,8 +2,10 @@ import json
 
 from langchain.schema import HumanMessage, SystemMessage
 from langchain_openai import ChatOpenAI
-
-from crewai.agents.agent_builder.utilities.base_output_converter import OutputConverter
+from pydantic import model_validator
+from crewai.agents.agent_builder.utilities.base_output_converter_base import (
+    OutputConverter,
+)
 
 
 class ConverterError(Exception):
@@ -17,10 +19,15 @@ class ConverterError(Exception):
 class Converter(OutputConverter):
     """Class that converts text into either pydantic or json."""
 
+    @model_validator(mode="after")
+    def check_llm_provider(self):
+        if not self._is_gpt(self.llm):
+            self._is_gpt = False
+
     def to_pydantic(self, current_attempt=1):
         """Convert text to pydantic."""
         try:
-            if self.is_gpt:
+            if self._is_gpt:
                 return self._create_instructor().to_pydantic()
             else:
                 return self._create_chain().invoke({})
@@ -34,7 +41,7 @@ class Converter(OutputConverter):
     def to_json(self, current_attempt=1):
         """Convert text to json."""
         try:
-            if self.is_gpt:
+            if self._is_gpt:
                 return self._create_instructor().to_json()
             else:
                 return json.dumps(self._create_chain().invoke({}).model_dump())
@@ -68,7 +75,5 @@ class Converter(OutputConverter):
         )
         return new_prompt | self.llm | parser
 
-    @property
-    def is_gpt(self) -> bool:
-        """Return if llm provided is of gpt from openai."""
-        return isinstance(self.llm, ChatOpenAI) and self.llm.openai_api_base is None
+    def _is_gpt(self, llm) -> bool:  # type: ignore # BUG? Name "_is_gpt" defined on line 20 hides name from outer scope
+        return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None

src/crewai/utilities/crew_json_encoder.py

@@ -0,0 +1,31 @@
+from datetime import datetime
+import json
+from uuid import UUID
+from pydantic import BaseModel
+
+
+class CrewJSONEncoder(json.JSONEncoder):
+    def default(self, obj):
+        if isinstance(obj, BaseModel):
+            return self._handle_pydantic_model(obj)
+        elif isinstance(obj, UUID):
+            return str(obj)
+
+        elif isinstance(obj, datetime):
+            return obj.isoformat()
+        return super().default(obj)
+
+    def _handle_pydantic_model(self, obj):
+        try:
+            data = obj.model_dump()
+            # Remove circular references
+            for key, value in data.items():
+                if isinstance(value, BaseModel):
+                    data[key] = str(
+                        value
+                    )  # Convert nested models to string representation
+            return data
+        except RecursionError:
+            return str(
+                obj
+            )  # Fall back to string representation if circular reference is detected

src/crewai/utilities/file_handler.py

@@ -1,5 +1,7 @@
 import os
 import pickle
+
+
 from datetime import datetime
 
 

src/crewai/utilities/printer.py

@@ -8,6 +8,8 @@ class Printer:
             self._print_bold_green(content)
         elif color == "bold_purple":
             self._print_bold_purple(content)
+        elif color == "bold_blue":
+            self._print_bold_blue(content)
         else:
             print(content)
 
@@ -22,3 +24,6 @@ class Printer:
 
     def _print_red(self, content):
         print("\033[91m {}\033[00m".format(content))
+
+    def _print_bold_blue(self, content):
+        print("\033[1m\033[94m {}\033[00m".format(content))

src/crewai/utilities/task_output_handler.py

@@ -0,0 +1,69 @@
+import json
+import os
+
+from pydantic import BaseModel, Field
+from datetime import datetime
+from typing import Dict, Any, Optional, List
+from crewai.utilities.crew_json_encoder import CrewJSONEncoder
+
+
+class ExecutionLog(BaseModel):
+    task_id: str
+    expected_output: Optional[str] = None
+    output: Dict[str, Any]
+    timestamp: datetime = Field(default_factory=datetime.now)
+    task_index: int
+    inputs: Dict[str, Any] = Field(default_factory=dict)
+    was_replayed: bool = False
+
+    def __getitem__(self, key: str) -> Any:
+        return getattr(self, key)
+
+
+class TaskOutputJsonHandler:
+    def __init__(self, file_name: str) -> None:
+        self.file_path = os.path.join(os.getcwd(), file_name)
+
+    def initialize_file(self) -> None:
+        if not os.path.exists(self.file_path) or os.path.getsize(self.file_path) == 0:
+            with open(self.file_path, "w") as file:
+                json.dump([], file)
+
+    def update(self, task_index: int, log: ExecutionLog):
+        logs = self.load()
+        if task_index < len(logs):
+            logs[task_index] = log
+        else:
+            logs.append(log)
+        self.save(logs)
+
+    def save(self, logs: List[ExecutionLog]):
+        with open(self.file_path, "w") as file:
+            json.dump(logs, file, indent=2, cls=CrewJSONEncoder)
+
+    def reset(self):
+        """Reset the JSON file by creating an empty file."""
+        with open(self.file_path, "w") as f:
+            json.dump([], f)
+
+    def load(self) -> List[ExecutionLog]:
+        try:
+            if (
+                not os.path.exists(self.file_path)
+                or os.path.getsize(self.file_path) == 0
+            ):
+                return []
+
+            with open(self.file_path, "r") as file:
+                return json.load(file)
+        except FileNotFoundError:
+            print(f"File {self.file_path} not found. Returning empty list.")
+            return []
+        except json.JSONDecodeError:
+            print(
+                f"Error decoding JSON from file {self.file_path}. Returning empty list."
+            )
+            return []
+        except Exception as e:
+            print(f"An unexpected error occurred: {e}")
+            return []

tests/agent_test.py

@@ -963,54 +963,3 @@ def test_agent_use_trained_data(crew_training_handler):
     crew_training_handler.assert_has_calls(
         [mock.call(), mock.call("trained_agents_data.pkl"), mock.call().load()]
     )
-
-
-def test_agent_max_retry_limit():
-    agent = Agent(
-        role="test role",
-        goal="test goal",
-        backstory="test backstory",
-        max_retry_limit=1,
-    )
-
-    task = Task(
-        agent=agent,
-        description="Say the word: Hi",
-        expected_output="The word: Hi",
-        human_input=True,
-    )
-
-    error_message = "Error happening while sending prompt to model."
-    with patch.object(
-        CrewAgentExecutor, "invoke", wraps=agent.agent_executor.invoke
-    ) as invoke_mock:
-        invoke_mock.side_effect = Exception(error_message)
-
-        assert agent._times_executed == 0
-        assert agent.max_retry_limit == 1
-
-        with pytest.raises(Exception) as e:
-            agent.execute_task(
-                task=task,
-            )
-        assert e.value.args[0] == error_message
-        assert agent._times_executed == 2
-
-        invoke_mock.assert_has_calls(
-            [
-                mock.call(
-                    {
-                        "input": "Say the word: Hi\n\nThis is the expect criteria for your final answer: The word: Hi \n you MUST return the actual complete content as the final answer, not a summary.",
-                        "tool_names": "",
-                        "tools": "",
-                    }
-                ),
-                mock.call(
-                    {
-                        "input": "Say the word: Hi\n\nThis is the expect criteria for your final answer: The word: Hi \n you MUST return the actual complete content as the final answer, not a summary.",
-                        "tool_names": "",
-                        "tools": "",
-                    }
-                ),
-            ]
-        )

tests/agents/test_crew_agent_parser.py

@@ -1,378 +0,0 @@
-import pytest
-from crewai.agents.parser import CrewAgentParser
-from langchain_core.agents import AgentAction, AgentFinish
-from langchain_core.exceptions import OutputParserException
-
-
-@pytest.fixture
-def parser():
-    p = CrewAgentParser()
-    p.agent = MockAgent()
-    return p
-
-
-def test_valid_action_parsing_special_characters(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: what's the temperature in SF?"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what's the temperature in SF?"
-
-
-def test_valid_action_parsing_with_json_tool_input(parser):
-    text = """
-    Thought: Let's find the information
-    Action: query
-    Action Input: ** {"task": "What are some common challenges or barriers that you have observed or experienced when implementing AI-powered solutions in healthcare settings?", "context": "As we've discussed recent advancements in AI applications in healthcare, it's crucial to acknowledge the potential hurdles. Some possible obstacles include...", "coworker": "Senior Researcher"}
-    """
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    expected_tool_input = '{"task": "What are some common challenges or barriers that you have observed or experienced when implementing AI-powered solutions in healthcare settings?", "context": "As we\'ve discussed recent advancements in AI applications in healthcare, it\'s crucial to acknowledge the potential hurdles. Some possible obstacles include...", "coworker": "Senior Researcher"}'
-    assert result.tool == "query"
-    assert result.tool_input == expected_tool_input
-
-
-def test_valid_action_parsing_with_quotes(parser):
-    text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: "temperature in SF"'
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "temperature in SF"
-
-
-def test_valid_action_parsing_with_curly_braces(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: {temperature in SF}"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "{temperature in SF}"
-
-
-def test_valid_action_parsing_with_angle_brackets(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: <temperature in SF>"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "<temperature in SF>"
-
-
-def test_valid_action_parsing_with_parentheses(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: (temperature in SF)"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "(temperature in SF)"
-
-
-def test_valid_action_parsing_with_mixed_brackets(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: [temperature in {SF}]"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "[temperature in {SF}]"
-
-
-def test_valid_action_parsing_with_nested_quotes(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: \"what's the temperature in 'SF'?\""
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what's the temperature in 'SF'?"
-
-
-def test_valid_action_parsing_with_incomplete_json(parser):
-    text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: {"query": "temperature in SF"'
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == '{"query": "temperature in SF"}'
-
-
-def test_valid_action_parsing_with_special_characters(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: what is the temperature in SF? @$%^&*"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what is the temperature in SF? @$%^&*"
-
-
-def test_valid_action_parsing_with_combination(parser):
-    text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: "[what is the temperature in SF?]"'
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "[what is the temperature in SF?]"
-
-
-def test_valid_action_parsing_with_mixed_quotes(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: \"what's the temperature in SF?\""
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what's the temperature in SF?"
-
-
-def test_valid_action_parsing_with_newlines(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: what is\nthe temperature in SF?"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what is\nthe temperature in SF?"
-
-
-def test_valid_action_parsing_with_escaped_characters(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: what is the temperature in SF? \\n"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what is the temperature in SF? \\n"
-
-
-def test_valid_action_parsing_with_json_string(parser):
-    text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: {"query": "temperature in SF"}'
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == '{"query": "temperature in SF"}'
-
-
-def test_valid_action_parsing_with_unbalanced_quotes(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: \"what is the temperature in SF?"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what is the temperature in SF?"
-
-
-def test_clean_action_no_formatting(parser):
-    action = "Ask question to senior researcher"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_leading_asterisks(parser):
-    action = "** Ask question to senior researcher"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_trailing_asterisks(parser):
-    action = "Ask question to senior researcher **"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_leading_and_trailing_asterisks(parser):
-    action = "** Ask question to senior researcher **"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_multiple_leading_asterisks(parser):
-    action = "**** Ask question to senior researcher"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_multiple_trailing_asterisks(parser):
-    action = "Ask question to senior researcher ****"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_spaces_and_asterisks(parser):
-    action = "  **  Ask question to senior researcher  **  "
-    cleaned_action = parser._clean_action(action)
-    print(f"Original action: '{action}'")
-    print(f"Cleaned action: '{cleaned_action}'")
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_only_asterisks(parser):
-    action = "****"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == ""
-
-
-def test_clean_action_with_empty_string(parser):
-    action = ""
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == ""
-
-
-def test_valid_final_answer_parsing(parser):
-    text = (
-        "Thought: I found the information\nFinal Answer: The temperature is 100 degrees"
-    )
-    result = parser.parse(text)
-    assert isinstance(result, AgentFinish)
-    assert result.return_values["output"] == "The temperature is 100 degrees"
-
-
-def test_missing_action_error(parser):
-    text = "Thought: Let's find the temperature\nAction Input: what is the temperature in SF?"
-    with pytest.raises(OutputParserException) as exc_info:
-        parser.parse(text)
-    assert "Could not parse LLM output" in str(exc_info.value)
-
-
-def test_missing_action_input_error(parser):
-    text = "Thought: Let's find the temperature\nAction: search"
-    with pytest.raises(OutputParserException) as exc_info:
-        parser.parse(text)
-    assert "Could not parse LLM output" in str(exc_info.value)
-
-
-def test_action_and_final_answer_error(parser):
-    text = "Thought: I found the information\nAction: search\nAction Input: what is the temperature in SF?\nFinal Answer: The temperature is 100 degrees"
-    with pytest.raises(OutputParserException) as exc_info:
-        parser.parse(text)
-    assert "both perform Action and give a Final Answer" in str(exc_info.value)
-
-
-def test_safe_repair_json(parser):
-    invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": Senior Researcher'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_unrepairable(parser):
-    invalid_json = "{invalid_json"
-    result = parser._safe_repair_json(invalid_json)
-    print("result:", invalid_json)
-    assert result == invalid_json  # Should return the original if unrepairable
-
-
-def test_safe_repair_json_missing_quotes(parser):
-    invalid_json = (
-        '{task: "Research XAI", context: "Explainable AI", coworker: Senior Researcher}'
-    )
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_unclosed_brackets(parser):
-    invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_extra_commas(parser):
-    invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher",}'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_trailing_commas(parser):
-    invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher",}'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_single_quotes(parser):
-    invalid_json = "{'task': 'Research XAI', 'context': 'Explainable AI', 'coworker': 'Senior Researcher'}"
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_mixed_quotes(parser):
-    invalid_json = "{'task': \"Research XAI\", 'context': \"Explainable AI\", 'coworker': 'Senior Researcher'}"
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_unescaped_characters(parser):
-    invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher\n"}'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    print("result:", result)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_missing_colon(parser):
-    invalid_json = '{"task" "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_missing_comma(parser):
-    invalid_json = '{"task": "Research XAI" "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_unexpected_trailing_characters(parser):
-    invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"} random text'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_special_characters_key(parser):
-    invalid_json = '{"task!@#": "Research XAI", "context$%^": "Explainable AI", "coworker&*()": "Senior Researcher"}'
-    expected_repaired_json = '{"task!@#": "Research XAI", "context$%^": "Explainable AI", "coworker&*()": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_parsing_with_whitespace(parser):
-    text = " Thought: Let's find the temperature \n Action: search \n Action Input: what is the temperature in SF? "
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what is the temperature in SF?"
-
-
-def test_parsing_with_special_characters(parser):
-    text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: "what is the temperature in SF?"'
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what is the temperature in SF?"
-
-
-def test_integration_valid_and_invalid(parser):
-    text = """
-    Thought: Let's find the temperature
-    Action: search
-    Action Input: what is the temperature in SF?
-
-    Thought: I found the information
-    Final Answer: The temperature is 100 degrees
-
-    Thought: Missing action
-    Action Input: invalid
-
-    Thought: Missing action input
-    Action: invalid
-    """
-    parts = text.strip().split("\n\n")
-    results = []
-    for part in parts:
-        try:
-            result = parser.parse(part.strip())
-            results.append(result)
-        except OutputParserException as e:
-            results.append(e)
-
-    assert isinstance(results[0], AgentAction)
-    assert isinstance(results[1], AgentFinish)
-    assert isinstance(results[2], OutputParserException)
-    assert isinstance(results[3], OutputParserException)
-
-
-class MockAgent:
-    def increment_formatting_errors(self):
-        pass
-
-
-# TODO: ADD TEST TO MAKE SURE ** REMOVAL DOESN'T MESS UP ANYTHING

tests/cassettes/test_replay_feature.yaml

@@ -0,0 +1,697 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are Researcher. You''re an expert researcher,
+      specialized in technology, software engineering, AI and startups. You work as
+      a freelancer and is now working on doing research and analysis for a new customer.\nYour
+      personal goal is: Make the best research and analysis on content about AI and
+      AI agentsTo give my best complete final answer to the task use the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: my best complete
+      final answer to the task.\nYour final answer must be the great and the most
+      complete as possible, it must be outcome described.\n\nI MUST use these formats,
+      my job depends on it!\nCurrent Task: Generate a list of 5 interesting ideas
+      to explore for an article, where each bulletpoint is under 15 words.\n\nThis
+      is the expect criteria for your final answer: Bullet point list of 5 important
+      events. No additional commentary. \n you MUST return the actual complete content
+      as the final answer, not a summary.\n\nBegin! This is VERY important to you,
+      use the tools available and give your best Final Answer, your job depends on
+      it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
+      "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '1237'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.3
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.3
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        \n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Ethical"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        implications"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        of"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        decision"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-making"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        healthcare"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        agents"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        revolution"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"izing"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        customer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        service"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        e"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-commerce"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Advances"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-driven"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        predictive"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        maintenance"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        for"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        industries"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        The"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        role"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        of"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        autonomous"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        vehicle"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        safety"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        personalized"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        education"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Adaptive"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        learning"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        technologies"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a097b99ad909e50-SJC
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Tue, 09 Jul 2024 15:52:44 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=3B5vxI0ieroGmK5h7cD7a8bCSrrPh4hLjrbw87J9XRE-1720540364-1.0.1.1-BXhaEwefXZ7Ez0Fg7.8O4AAnOoPc5b7O.4CdzhLnbo9WIF30RlsTzH58YBRxoQipeSCQMxhePm2HaNR6nNfWEQ;
+        path=/; expires=Tue, 09-Jul-24 16:22:44 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=D7VkuRYil_ytD3F4vcJzvO0gmVHyb3ZlnhCIjCrlyWE-1720540364005-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - user-soijsnuwuk3xvbf91w0jc33c
+      openai-processing-ms:
+      - '114'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '5000'
+      x-ratelimit-limit-tokens:
+      - '450000'
+      x-ratelimit-remaining-requests:
+      - '4999'
+      x-ratelimit-remaining-tokens:
+      - '449712'
+      x-ratelimit-reset-requests:
+      - 12ms
+      x-ratelimit-reset-tokens:
+      - 38ms
+      x-request-id:
+      - req_94f0907cc8b2065f1e223070d2be2a85
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"content": "You are Researcher. You''re an expert researcher,
+      specialized in technology, software engineering, AI and startups. You work as
+      a freelancer and is now working on doing research and analysis for a new customer.\nYour
+      personal goal is: Make the best research and analysis on content about AI and
+      AI agentsTo give my best complete final answer to the task use the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: my best complete
+      final answer to the task.\nYour final answer must be the great and the most
+      complete as possible, it must be outcome described.\n\nI MUST use these formats,
+      my job depends on it!\nCurrent Task: Generate a list of 5 interesting ideas
+      to explore for an article, where each bulletpoint is under 15 words.\n\nThis
+      is the expect criteria for your final answer: Bullet point list of 5 important
+      events. No additional commentary. \n you MUST return the actual complete content
+      as the final answer, not a summary.\n\nBegin! This is VERY important to you,
+      use the tools available and give your best Final Answer, your job depends on
+      it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
+      "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '1237'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=3B5vxI0ieroGmK5h7cD7a8bCSrrPh4hLjrbw87J9XRE-1720540364-1.0.1.1-BXhaEwefXZ7Ez0Fg7.8O4AAnOoPc5b7O.4CdzhLnbo9WIF30RlsTzH58YBRxoQipeSCQMxhePm2HaNR6nNfWEQ;
+        _cfuvid=D7VkuRYil_ytD3F4vcJzvO0gmVHyb3ZlnhCIjCrlyWE-1720540364005-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.3
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.3
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        \n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Evolution"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        of"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Agents"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Customer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Service"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Healthcare"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Transform"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ing"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Diagnostics"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Treatment"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Ethical"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Imp"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"lications"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        of"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Autonomous"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Systems"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Driven"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Start"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ups"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Dis"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ruption"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Innovation"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Cyber"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"security"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Def"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ending"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Against"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Modern"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Threat"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"s"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a097ba2bc449e50-SJC
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Tue, 09 Jul 2024 15:52:45 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - user-soijsnuwuk3xvbf91w0jc33c
+      openai-processing-ms:
+      - '117'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '5000'
+      x-ratelimit-limit-tokens:
+      - '450000'
+      x-ratelimit-remaining-requests:
+      - '4999'
+      x-ratelimit-remaining-tokens:
+      - '449712'
+      x-ratelimit-reset-requests:
+      - 12ms
+      x-ratelimit-reset-tokens:
+      - 38ms
+      x-request-id:
+      - req_a28d912698f7b75be87900d3a64bc91f
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_replay_from_task_setup_context.yaml

@@ -0,0 +1,161 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
+      goal is: Test GoalTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      my best complete final answer to the task.\nYour final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!\nCurrent Task: Test Task\n\nThis is the
+      expect criteria for your final answer: Say Hi to John \n you MUST return the
+      actual complete content as the final answer, not a summary.\n\nThis is the context
+      you''re working with:\ncontext raw output\n\nBegin! This is VERY important to
+      you, use the tools available and give your best Final Answer, your job depends
+      on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop":
+      ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '918'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.3
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.3
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        Hi"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        John"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a2327f1190467c1-SJC
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Fri, 12 Jul 2024 18:39:27 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=df.hIcEr2QTS045wWa7HSF0ATx6AeLAoPPW0FoIx7W4-1720809567-1.0.1.1-1Y2nQ4DHdc5HUHFO08LdQOoWZykmQ0xe67vzmv2dS4OnnKEHYd9GMzcq.vWODTXoI.BoSxQiRrylKYuuO2t8Tw;
+        path=/; expires=Fri, 12-Jul-24 19:09:27 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=Zmb0XRHa49q2R664FqlS3F.aojtATJKKGnkUiQoH92I-1720809567257-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '83'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '22000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '21999792'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_4fd8c7c8d47e20be017fb8de1ccb07c9
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_replay_interpolates_inputs_properly.yaml

@@ -0,0 +1,472 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
+      goal is: Test GoalTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      my best complete final answer to the task.\nYour final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!\nCurrent Task: Context Task\n\nThis is
+      the expect criteria for your final answer: Say John \n you MUST return the actual
+      complete content as the final answer, not a summary.\n\nBegin! This is VERY
+      important to you, use the tools available and give your best Final Answer, your
+      job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n":
+      1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '851'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.3
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.3
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        Say"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        John"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4hrEQNmcSJd7kCqA2oxUWQ4qOr","object":"chat.completion.chunk","created":1720808063,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a23033dc9abce48-SJC
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Fri, 12 Jul 2024 18:14:23 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=iykqFZ5ecR102MDyK48cHc9Ge3aXJBNKkesB4w9tCz4-1720808063-1.0.1.1-Eg_rjCINHV9hw7HzDFtJgxfwBfr9SahyJnbyo.JfBNFYax9M.ZcSVwmQwySE6AzVg.5AaLC05iljPfXmN26FrA;
+        path=/; expires=Fri, 12-Jul-24 18:44:23 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=KWM5AhkXkvM2JvJ6J7QHiC9iposfEkI9eZRl8w6aVTY-1720808063923-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '84'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '22000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '21999807'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_e6b4b9610f2f254a228ad44dda349115
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
+      goal is: Test GoalTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      my best complete final answer to the task.\nYour final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!\nCurrent Task: Test Task\n\nThis is the
+      expect criteria for your final answer: Say Hi to John \n you MUST return the
+      actual complete content as the final answer, not a summary.\n\nThis is the context
+      you''re working with:\nSay John\n\nBegin! This is VERY important to you, use
+      the tools available and give your best Final Answer, your job depends on it!\n\nThought:\n",
+      "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"], "stream":
+      true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '908'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=iykqFZ5ecR102MDyK48cHc9Ge3aXJBNKkesB4w9tCz4-1720808063-1.0.1.1-Eg_rjCINHV9hw7HzDFtJgxfwBfr9SahyJnbyo.JfBNFYax9M.ZcSVwmQwySE6AzVg.5AaLC05iljPfXmN26FrA;
+        _cfuvid=KWM5AhkXkvM2JvJ6J7QHiC9iposfEkI9eZRl8w6aVTY-1720808063923-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.3
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.3
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        Hi"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        John"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iocDiUNkL6NucVvumIQYikY61","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a230340ec4cce48-SJC
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Fri, 12 Jul 2024 18:14:24 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '69'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '22000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '21999795'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_f3233314439a85e7a197be3d067c6d1c
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
+      goal is: Test GoalTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      my best complete final answer to the task.\nYour final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!\nCurrent Task: Test Task\n\nThis is the
+      expect criteria for your final answer: Say Hi to John \n you MUST return the
+      actual complete content as the final answer, not a summary.\n\nThis is the context
+      you''re working with:\ncontext raw output\n\nBegin! This is VERY important to
+      you, use the tools available and give your best Final Answer, your job depends
+      on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop":
+      ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '918'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=iykqFZ5ecR102MDyK48cHc9Ge3aXJBNKkesB4w9tCz4-1720808063-1.0.1.1-Eg_rjCINHV9hw7HzDFtJgxfwBfr9SahyJnbyo.JfBNFYax9M.ZcSVwmQwySE6AzVg.5AaLC05iljPfXmN26FrA;
+        _cfuvid=KWM5AhkXkvM2JvJ6J7QHiC9iposfEkI9eZRl8w6aVTY-1720808063923-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.3
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.3
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        Hi"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        John"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kF4iAwQ2K0M2fy86qpF660mrclmY","object":"chat.completion.chunk","created":1720808064,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a2303443f0cce48-SJC
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Fri, 12 Jul 2024 18:14:24 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '86'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '22000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '21999791'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_649687e24793d5b5782ecf58bc76386a
+    status:
+      code: 200
+      message: OK
+version: 1

tests/crew_test.py

@@ -1,5 +1,6 @@
 """Test Agent creation and execution basic functionality."""
 
+import os
 import json
 from concurrent.futures import Future
 from unittest import mock
@@ -15,8 +16,10 @@ from crewai.crews.crew_output import CrewOutput
 from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.process import Process
 from crewai.task import Task
+from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
 from crewai.utilities import Logger, RPMController
+from crewai.utilities.constants import CREW_TASKS_OUTPUT_FILE
 
 ceo = Agent(
     role="CEO",
@@ -136,7 +139,6 @@ def test_async_task_cannot_include_sequential_async_tasks_in_context():
 
 
 def test_context_no_future_tasks():
-
     task2 = Task(
         description="Task 2",
         expected_output="output",
@@ -584,7 +586,6 @@ def test_sequential_async_task_execution_completion():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_single_task_with_async_execution():
-
     researcher_agent = Agent(
         role="Researcher",
         goal="Make the best research and analysis on content about AI and AI agents",
@@ -740,7 +741,6 @@ def test_async_task_execution_call_count():
     ) as mock_execute_sync, patch.object(
         Task, "execute_async", return_value=mock_future
     ) as mock_execute_async:
-
         crew.kickoff()
 
         assert mock_execute_async.call_count == 2
@@ -1148,7 +1148,6 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_delegation_is_not_enabled_if_there_are_only_one_agent():
-
     researcher = Agent(
         role="Researcher",
         goal="Make the best research and analysis on content about AI and AI agents",
@@ -1238,10 +1237,10 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
     print(crew.usage_metrics)
 
     assert crew.usage_metrics == {
-        "total_tokens": 2217,
-        "prompt_tokens": 1847,
-        "completion_tokens": 370,
-        "successful_requests": 4,
+        "total_tokens": 311,
+        "prompt_tokens": 224,
+        "completion_tokens": 87,
+        "successful_requests": 1,
     }
 
 
@@ -1271,7 +1270,7 @@ def test_hierarchical_crew_creation_tasks_with_agents():
     assert crew.manager_agent.tools is not None
     print("TOOL DESCRIPTION", crew.manager_agent.tools[0].description)
     assert crew.manager_agent.tools[0].description.startswith(
-        "Delegate a specific task to one of the following coworkers: Senior Writer"
+        "Delegate a specific task to one of the following coworkers: [Senior Writer, Researcher]"
     )
 
 
@@ -1380,7 +1379,6 @@ def test_crew_does_not_interpolate_without_inputs():
             interpolate_task_inputs.assert_not_called()
 
 
-# TODO: Ask @joao if we want to start throwing errors if inputs are not provided
 # def test_crew_partial_inputs():
 #     agent = Agent(
 #         role="{topic} Researcher",
@@ -1404,7 +1402,6 @@ def test_crew_does_not_interpolate_without_inputs():
 #     assert crew.agents[0].backstory == "You have a lot of experience with AI."
 
 
-# TODO: If we do want ot throw errors if we are missing inputs. Add in this test.
 # def test_crew_invalid_inputs():
 #     agent = Agent(
 #         role="{topic} Researcher",
@@ -1806,3 +1803,472 @@ def test__setup_for_training():
 
     for agent in agents:
         assert agent.allow_delegation is False
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_replay_feature():
+    list_ideas = Task(
+        description="Generate a list of 5 interesting ideas to explore for an article, where each bulletpoint is under 15 words.",
+        expected_output="Bullet point list of 5 important events. No additional commentary.",
+        agent=researcher,
+    )
+    write = Task(
+        description="Write a sentence about the events",
+        expected_output="A sentence about the events",
+        agent=writer,
+        context=[list_ideas],
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[list_ideas, write],
+        process=Process.sequential,
+    )
+
+    with patch.object(Task, "execute_sync") as mock_execute_task:
+        mock_execute_task.return_value = TaskOutput(
+            description="Mock description",
+            raw="Mocked output for list of ideas",
+            agent="Researcher",
+            json_dict=None,
+            output_format=OutputFormat.RAW,
+            pydantic=None,
+            summary="Mocked output for list of ideas",
+        )
+
+        crew.kickoff()
+        crew.replay_from_task(str(write.id))
+        # Ensure context was passed correctly
+        assert mock_execute_task.call_count == 3
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_replay_from_task_error():
+    task = Task(
+        description="Come up with a list of 5 interesting ideas to explore for an article",
+        expected_output="5 bullet points with a paragraph for each idea.",
+        agent=researcher,
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[task],
+    )
+
+    with pytest.raises(TypeError) as e:
+        crew.replay_from_task()  # type: ignore purposefully throwing err
+        assert "task_id is required" in str(e)
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_task_output_file_creation():
+    agent = Agent(
+        role="Content Writer",
+        goal="Write engaging content on various topics.",
+        backstory="You have a background in journalism and creative writing.",
+    )
+
+    task = Task(
+        description="Write a detailed article about AI in healthcare.",
+        expected_output="A 1 paragraph article about AI.",
+        agent=agent,
+    )
+
+    crew = Crew(agents=[agent], tasks=[task])
+
+    with patch.object(Task, "execute_sync") as mock_execute_task:
+        mock_execute_task.return_value = TaskOutput(
+            description="Write about AI in healthcare.",
+            raw="Artificial Intelligence (AI) is revolutionizing healthcare by enhancing diagnostic accuracy, personalizing treatment plans, and streamlining administrative tasks.",
+            agent="Content Writer",
+            json_dict=None,
+            output_format=OutputFormat.RAW,
+            pydantic=None,
+            summary="Write about AI in healthcare...",
+        )
+
+        crew.kickoff()
+
+        # Check if the crew_tasks_output.json file is created
+        assert os.path.exists(CREW_TASKS_OUTPUT_FILE)
+
+        # Clean up the file after test
+        if os.path.exists(CREW_TASKS_OUTPUT_FILE):
+            os.remove(CREW_TASKS_OUTPUT_FILE)
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_replay_without_output_tasks_json():
+    agent = Agent(
+        role="Technical Writer",
+        goal="Write detailed technical documentation.",
+        backstory="You have a background in software engineering and technical writing.",
+    )
+
+    task = Task(
+        description="Document the process of setting up a Python project.",
+        expected_output="A step-by-step guide on setting up a Python project.",
+        agent=agent,
+    )
+
+    crew = Crew(agents=[agent], tasks=[task])
+
+    with patch.object(Task, "execute_sync") as mock_execute_task:
+        mock_execute_task.return_value = TaskOutput(
+            description="Document the process of setting up a Python project.",
+            raw="To set up a Python project, first create a virtual environment...",
+            agent="Technical Writer",
+            json_dict=None,
+            output_format=OutputFormat.RAW,
+            pydantic=None,
+            summary="Document the process of setting up a Python project...",
+        )
+
+        if os.path.exists(CREW_TASKS_OUTPUT_FILE):
+            os.remove(CREW_TASKS_OUTPUT_FILE)
+
+        with pytest.raises(ValueError):
+            crew.replay_from_task(str(task.id))
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_replay_task_with_context():
+    agent1 = Agent(
+        role="Researcher",
+        goal="Research AI advancements.",
+        backstory="You are an expert in AI research.",
+    )
+    agent2 = Agent(
+        role="Writer",
+        goal="Write detailed articles on AI.",
+        backstory="You have a background in journalism and AI.",
+    )
+
+    task1 = Task(
+        description="Research the latest advancements in AI.",
+        expected_output="A detailed report on AI advancements.",
+        agent=agent1,
+    )
+    task2 = Task(
+        description="Summarize the AI advancements report.",
+        expected_output="A summary of the AI advancements report.",
+        agent=agent2,
+    )
+    task3 = Task(
+        description="Write an article based on the AI advancements summary.",
+        expected_output="An article on AI advancements.",
+        agent=agent2,
+    )
+    task4 = Task(
+        description="Create a presentation based on the AI advancements article.",
+        expected_output="A presentation on AI advancements.",
+        agent=agent2,
+        context=[task1],
+    )
+
+    crew = Crew(
+        agents=[agent1, agent2],
+        tasks=[task1, task2, task3, task4],
+        process=Process.sequential,
+    )
+
+    mock_task_output1 = TaskOutput(
+        description="Research the latest advancements in AI.",
+        raw="Detailed report on AI advancements...",
+        agent="Researcher",
+        json_dict=None,
+        output_format=OutputFormat.RAW,
+        pydantic=None,
+        summary="Detailed report on AI advancements...",
+    )
+    mock_task_output2 = TaskOutput(
+        description="Summarize the AI advancements report.",
+        raw="Summary of the AI advancements report...",
+        agent="Writer",
+        json_dict=None,
+        output_format=OutputFormat.RAW,
+        pydantic=None,
+        summary="Summary of the AI advancements report...",
+    )
+    mock_task_output3 = TaskOutput(
+        description="Write an article based on the AI advancements summary.",
+        raw="Article on AI advancements...",
+        agent="Writer",
+        json_dict=None,
+        output_format=OutputFormat.RAW,
+        pydantic=None,
+        summary="Article on AI advancements...",
+    )
+    mock_task_output4 = TaskOutput(
+        description="Create a presentation based on the AI advancements article.",
+        raw="Presentation on AI advancements...",
+        agent="Writer",
+        json_dict=None,
+        output_format=OutputFormat.RAW,
+        pydantic=None,
+        summary="Presentation on AI advancements...",
+    )
+
+    with patch.object(Task, "execute_sync") as mock_execute_task:
+        mock_execute_task.side_effect = [
+            mock_task_output1,
+            mock_task_output2,
+            mock_task_output3,
+            mock_task_output4,
+        ]
+
+        crew.kickoff()
+
+        # Check if the crew_tasks_output.json file is created
+        assert os.path.exists(CREW_TASKS_OUTPUT_FILE)
+
+        # Replay task4 and ensure it uses task1's context properly
+        with patch.object(Task, "execute_sync") as mock_replay_task:
+            mock_replay_task.return_value = mock_task_output4
+
+            replayed_output = crew.replay_from_task(str(task4.id))
+            assert replayed_output.raw == "Presentation on AI advancements..."
+
+        # Clean up the file after test
+        if os.path.exists(CREW_TASKS_OUTPUT_FILE):
+            os.remove(CREW_TASKS_OUTPUT_FILE)
+
+
+def test_replay_from_task_with_context():
+    agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
+    task1 = Task(
+        description="Context Task", expected_output="Say Task Output", agent=agent
+    )
+    task2 = Task(
+        description="Test Task", expected_output="Say Hi", agent=agent, context=[task1]
+    )
+
+    context_output = TaskOutput(
+        description="Context Task Output",
+        agent="test_agent",
+        raw="context raw output",
+        pydantic=None,
+        json_dict={},
+        output_format=OutputFormat.RAW,
+    )
+    task1.output = context_output
+
+    crew = Crew(agents=[agent], tasks=[task1, task2], process=Process.sequential)
+
+    with patch(
+        "crewai.utilities.task_output_handler.TaskOutputJsonHandler.load",
+        return_value=[
+            {
+                "task_id": str(task1.id),
+                "output": {
+                    "description": context_output.description,
+                    "summary": context_output.summary,
+                    "raw": context_output.raw,
+                    "pydantic": context_output.pydantic,
+                    "json_dict": context_output.json_dict,
+                    "output_format": context_output.output_format,
+                    "agent": context_output.agent,
+                },
+                "inputs": {},
+            },
+            {
+                "task_id": str(task2.id),
+                "output": {
+                    "description": "Test Task Output",
+                    "summary": None,
+                    "raw": "test raw output",
+                    "pydantic": None,
+                    "json_dict": {},
+                    "output_format": "json",
+                    "agent": "test_agent",
+                },
+                "inputs": {},
+            },
+        ],
+    ):
+        crew.replay_from_task(str(task2.id))
+
+        assert crew.tasks[1].context[0].output.raw == "context raw output"
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_replay_with_invalid_task_id():
+    agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
+    task1 = Task(
+        description="Context Task", expected_output="Say Task Output", agent=agent
+    )
+    task2 = Task(
+        description="Test Task", expected_output="Say Hi", agent=agent, context=[task1]
+    )
+
+    context_output = TaskOutput(
+        description="Context Task Output",
+        agent="test_agent",
+        raw="context raw output",
+        pydantic=None,
+        json_dict={},
+        output_format=OutputFormat.RAW,
+    )
+    task1.output = context_output
+
+    crew = Crew(agents=[agent], tasks=[task1, task2], process=Process.sequential)
+
+    with patch(
+        "crewai.utilities.task_output_handler.TaskOutputJsonHandler.load",
+        return_value=[
+            {
+                "task_id": str(task1.id),
+                "output": {
+                    "description": context_output.description,
+                    "summary": context_output.summary,
+                    "raw": context_output.raw,
+                    "pydantic": context_output.pydantic,
+                    "json_dict": context_output.json_dict,
+                    "output_format": context_output.output_format,
+                    "agent": context_output.agent,
+                },
+                "inputs": {},
+            },
+            {
+                "task_id": str(task2.id),
+                "output": {
+                    "description": "Test Task Output",
+                    "summary": None,
+                    "raw": "test raw output",
+                    "pydantic": None,
+                    "json_dict": {},
+                    "output_format": "json",
+                    "agent": "test_agent",
+                },
+                "inputs": {},
+            },
+        ],
+    ):
+        with pytest.raises(
+            ValueError,
+            match="Task with id bf5b09c9-69bd-4eb8-be12-f9e5bae31c2d not found in the crew's tasks.",
+        ):
+            crew.replay_from_task("bf5b09c9-69bd-4eb8-be12-f9e5bae31c2d")
+
+
+@patch.object(Crew, "_interpolate_inputs")
+def test_replay_interpolates_inputs_properly(mock_interpolate_inputs):
+    agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
+    task1 = Task(description="Context Task", expected_output="Say {name}", agent=agent)
+    task2 = Task(
+        description="Test Task",
+        expected_output="Say Hi to {name}",
+        agent=agent,
+        context=[task1],
+    )
+
+    context_output = TaskOutput(
+        description="Context Task Output",
+        agent="test_agent",
+        raw="context raw output",
+        pydantic=None,
+        json_dict={},
+        output_format=OutputFormat.RAW,
+    )
+    task1.output = context_output
+
+    crew = Crew(agents=[agent], tasks=[task1, task2], process=Process.sequential)
+    crew.kickoff(inputs={"name": "John"})
+
+    with patch(
+        "crewai.utilities.task_output_handler.TaskOutputJsonHandler.load",
+        return_value=[
+            {
+                "task_id": str(task1.id),
+                "output": {
+                    "description": context_output.description,
+                    "summary": context_output.summary,
+                    "raw": context_output.raw,
+                    "pydantic": context_output.pydantic,
+                    "json_dict": context_output.json_dict,
+                    "output_format": context_output.output_format,
+                    "agent": context_output.agent,
+                },
+                "inputs": {"name": "John"},
+            },
+            {
+                "task_id": str(task2.id),
+                "output": {
+                    "description": "Test Task Output",
+                    "summary": None,
+                    "raw": "test raw output",
+                    "pydantic": None,
+                    "json_dict": {},
+                    "output_format": "json",
+                    "agent": "test_agent",
+                },
+                "inputs": {"name": "John"},
+            },
+        ],
+    ):
+        crew.replay_from_task(str(task2.id))
+        assert crew._inputs == {"name": "John"}
+        assert mock_interpolate_inputs.call_count == 2
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_replay_from_task_setup_context():
+    agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
+    task1 = Task(description="Context Task", expected_output="Say {name}", agent=agent)
+    task2 = Task(
+        description="Test Task",
+        expected_output="Say Hi to {name}",
+        agent=agent,
+    )
+    context_output = TaskOutput(
+        description="Context Task Output",
+        agent="test_agent",
+        raw="context raw output",
+        pydantic=None,
+        json_dict={},
+        output_format=OutputFormat.RAW,
+    )
+    task1.output = context_output
+    crew = Crew(agents=[agent], tasks=[task1, task2], process=Process.sequential)
+    with patch(
+        "crewai.utilities.task_output_handler.TaskOutputJsonHandler.load",
+        return_value=[
+            {
+                "task_id": str(task1.id),
+                "output": {
+                    "description": context_output.description,
+                    "summary": context_output.summary,
+                    "raw": context_output.raw,
+                    "pydantic": context_output.pydantic,
+                    "json_dict": context_output.json_dict,
+                    "output_format": context_output.output_format,
+                    "agent": context_output.agent,
+                },
+                "inputs": {"name": "John"},
+            },
+            {
+                "task_id": str(task2.id),
+                "output": {
+                    "description": "Test Task Output",
+                    "summary": None,
+                    "raw": "test raw output",
+                    "pydantic": None,
+                    "json_dict": {},
+                    "output_format": "json",
+                    "agent": "test_agent",
+                },
+                "inputs": {"name": "John"},
+            },
+        ],
+    ):
+        crew.replay_from_task(str(task2.id))
+
+        # Check if the first task's output was set correctly
+        assert crew.tasks[0].output is not None
+        assert isinstance(crew.tasks[0].output, TaskOutput)
+        assert crew.tasks[0].output.description == "Context Task Output"
+        assert crew.tasks[0].output.agent == "test_agent"
+        assert crew.tasks[0].output.raw == "context raw output"
+        assert crew.tasks[0].output.output_format == OutputFormat.RAW
+
+        assert crew.tasks[1].prompt_context == "context raw output"

tests/task_test.py

@@ -81,7 +81,7 @@ def test_task_prompt_includes_expected_output():
 
     with patch.object(Agent, "execute_task") as execute:
         execute.return_value = "ok"
-        task.execute_sync()
+        task.execute_sync(agent=researcher)
         execute.assert_called_once_with(task=task, context=None, tools=[])
 
 
@@ -104,7 +104,7 @@ def test_task_callback():
 
     with patch.object(Agent, "execute_task") as execute:
         execute.return_value = "ok"
-        task.execute_sync()
+        task.execute_sync(agent=researcher)
         task_completed.assert_called_once_with(task.output)
 
 
@@ -129,7 +129,7 @@ def test_task_callback_returns_task_ouput():
 
     with patch.object(Agent, "execute_task") as execute:
         execute.return_value = "exported_ok"
-        task.execute_sync()
+        task.execute_sync(agent=researcher)
         # Ensure the callback is called with a TaskOutput object serialized to JSON
         task_completed.assert_called_once()
         callback_data = task_completed.call_args[0][0]
@@ -521,9 +521,7 @@ def test_save_task_json_output():
     with patch.object(Task, "_save_file") as save_file:
         save_file.return_value = None
         crew.kickoff()
-        save_file.assert_called_once_with(
-            {"score": 4}
-        )  # TODO: @Joao, should this be a dict or a json string?
+        save_file.assert_called_once_with({"score": 4})
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])