adding index + 1 so its in order

* Cleaned up task execution to now have separate paths for async and sync execution. Updating all kickoff functions to return CrewOutput. WIP. Waiting for Joao feedback on async task execution with task_output

* Consistently storing async and sync output for context

* outline tests I need to create going forward

* Major rehaul of TaskOutput and CrewOutput. Updated all tests to work with new change. Need to add in a few final tricky async tests and add a few more to verify output types on TaskOutput and CrewOutput.

* Encountering issues with callback. Need to test on main. WIP

* working on tests. WIP

* WIP. Figuring out disconnect issue.

* Cleaned up logs now that I've isolated the issue to the LLM

* more wip.

* WIP. It looks like usage metrics has always been broken for async

* Update parent crew who is managing for_each loop

* Merge in main to bugfix/kickoff-for-each-usage-metrics

* Clean up code for review

* Add new tests

* Final cleanup. Ready for review.

* Moving copy functionality from Agent to BaseAgent

* Fix renaming issue

* Fix linting errors

* use BaseAgent instead of Agent where applicable

* Fixing missing function. Working on tests.

* WIP. Needing team to review change

* Fixing issues brought about by merge

* WIP

* Implement major fixes from yesterdays group conversation. Now working on tests.

* The majority of tasks are working now. Need to fix converter class

* Fix final failing test

* Fix linting and type-checker issues

* Add more tests to fully test CrewOutput and TaskOutput changes

* Add in validation for async cannot depend on other async tasks.

* Update validators and tests

.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

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

@@ -1,7 +1,6 @@
 import asyncio
 import json
 import uuid
-from datetime import datetime
 from concurrent.futures import Future
 from typing import Any, Dict, List, Optional, Tuple, Union
 
@@ -32,11 +31,20 @@ 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.crew_json_encoder import CrewJSONEncoder
+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.file_handler import TaskOutputJsonHandler
-from crewai.utilities.formatter import aggregate_raw_outputs_from_task_outputs
+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,
+)
 from crewai.utilities.training_handler import CrewTrainingHandler
 
 try:
@@ -74,13 +82,16 @@ class Crew(BaseModel):
     _rpm_controller: RPMController = PrivateAttr()
     _logger: Logger = PrivateAttr()
     _file_handler: FileHandler = PrivateAttr()
-    _task_output_handler: TaskOutputJsonHandler = PrivateAttr()
     _cache_handler: InstanceOf[CacheHandler] = PrivateAttr(default=CacheHandler())
     _short_term_memory: Optional[InstanceOf[ShortTermMemory]] = PrivateAttr()
     _long_term_memory: Optional[InstanceOf[LongTermMemory]] = PrivateAttr()
     _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)
@@ -140,13 +151,11 @@ class Crew(BaseModel):
         default=None,
         description="List of file paths for task execution JSON files.",
     )
-    execution_logs: List[Dict[str, Any]] = Field(
+    execution_logs: List[ExecutionLog] = Field(
         default=[],
         description="List of execution logs for tasks",
     )
 
-    _log_file: str = PrivateAttr(default="crew_tasks_output.json")
-
     @field_validator("id", mode="before")
     @classmethod
     def _deny_user_set_id(cls, v: Optional[UUID4]) -> None:
@@ -178,7 +187,6 @@ class Crew(BaseModel):
         self._logger = Logger(self.verbose)
         if self.output_log_file:
             self._file_handler = FileHandler(self.output_log_file)
-        self._task_output_handler = TaskOutputJsonHandler(self._log_file)
         self._rpm_controller = RPMController(max_rpm=self.max_rpm, logger=self._logger)
         self._telemetry = Telemetry()
         self._telemetry.set_tracer()
@@ -266,6 +274,63 @@ class Crew(BaseModel):
 
         return self
 
+    @model_validator(mode="after")
+    def validate_end_with_at_most_one_async_task(self):
+        """Validates that the crew ends with at most one asynchronous task."""
+        final_async_task_count = 0
+
+        # Traverse tasks backward
+        for task in reversed(self.tasks):
+            if task.async_execution:
+                final_async_task_count += 1
+            else:
+                break  # Stop traversing as soon as a non-async task is encountered
+
+        if final_async_task_count > 1:
+            raise PydanticCustomError(
+                "async_task_count",
+                "The crew must end with at most one asynchronous task.",
+                {},
+            )
+
+        return self
+
+    @model_validator(mode="after")
+    def validate_async_task_cannot_include_sequential_async_tasks_in_context(self):
+        """
+        Validates that if a task is set to be executed asynchronously,
+        it cannot include other asynchronous tasks in its context unless
+        separated by a synchronous task.
+        """
+        for i, task in enumerate(self.tasks):
+            if task.async_execution and task.context:
+                for context_task in task.context:
+                    if context_task.async_execution:
+                        for j in range(i - 1, -1, -1):
+                            if self.tasks[j] == context_task:
+                                raise ValueError(
+                                    f"Task '{task.description}' is asynchronous and cannot include other sequential asynchronous tasks in its context."
+                                )
+                            if not self.tasks[j].async_execution:
+                                break
+        return self
+
+    @model_validator(mode="after")
+    def validate_context_no_future_tasks(self):
+        """Validates that a task's context does not include future tasks."""
+        task_indices = {id(task): i for i, task in enumerate(self.tasks)}
+
+        for task in self.tasks:
+            if task.context:
+                for context_task in task.context:
+                    if id(context_task) not in task_indices:
+                        continue  # Skip context tasks not in the main tasks list
+                    if task_indices[id(context_task)] > task_indices[id(task)]:
+                        raise ValueError(
+                            f"Task '{task.description}' has a context dependency on a future task '{context_task.description}', which is not allowed."
+                        )
+        return self
+
     def _setup_from_config(self):
         assert self.config is not None, "Config should not be None."
 
@@ -332,10 +397,13 @@ class Crew(BaseModel):
     ) -> CrewOutput:
         """Starts the crew to work on its assigned tasks."""
         self._execution_span = self._telemetry.crew_execution_span(self, inputs)
-        self.execution_logs = []
+        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._interpolate_inputs(inputs)
         self._set_tasks_callbacks()
 
         i18n = I18N(prompt_file=self.prompt_file)
@@ -359,10 +427,9 @@ class Crew(BaseModel):
         metrics = []
 
         if self.process == Process.sequential:
-            result = self._run_sequential_process(inputs)
+            result = self._run_sequential_process()
         elif self.process == Process.hierarchical:
-            result, manager_metrics = self._run_hierarchical_process()  # type: ignore # Incompatible types in assignment (expression has type "str | dict[str, Any]", variable has type "str")
-            metrics.append(manager_metrics)
+            result = self._run_hierarchical_process()
         else:
             raise NotImplementedError(
                 f"The process '{self.process}' is not implemented yet."
@@ -401,9 +468,7 @@ class Crew(BaseModel):
         self.usage_metrics = total_usage_metrics
         return results
 
-    async def kickoff_async(
-        self, inputs: Optional[CrewOutput] = {}
-    ) -> Union[str, Dict]:
+    async def kickoff_async(self, inputs: Optional[Dict[str, Any]] = {}) -> CrewOutput:
         """Asynchronous kickoff method to start the crew execution."""
         return await asyncio.to_thread(self.kickoff, inputs)
 
@@ -452,267 +517,51 @@ class Crew(BaseModel):
 
         return results
 
-    def _store_execution_log(self, task, output, task_index, inputs=None):
-        log = {
-            "task_id": str(task.id),
-            "description": task.description,
-            "expected_output": task.expected_output,
-            "agent_role": task.agent.role if task.agent else "None",
-            "output": {
-                "description": task.description,
-                "summary": task.description,
-                "raw_output": output.raw_output,
-                "pydantic_output": output.pydantic_output,
-                "json_output": output.json_output,
-                "agent": task.agent.role if task.agent else "None",
-            },
-            "timestamp": datetime.now().isoformat(),
-            "task_index": task_index,
-            # "output_py": output.pydantic_output,
-            "inputs": inputs,
-            # "task": task.model_dump(),
-        }
-        self.execution_logs.append(log)
-        self._task_output_handler.append(log)
-
-    def _run_sequential_process(
-        self, inputs: Dict[str, Any] | None = None
-    ) -> CrewOutput:
-        """Executes tasks sequentially and returns the final output."""
-        self.execution_logs = []
-        task_outputs = self._execute_tasks(self.tasks, inputs=inputs)
-        final_string_output = aggregate_raw_outputs_from_task_outputs(task_outputs)
-        self._finish_execution(final_string_output)
-        self.save_execution_logs()
-        token_usage = self.calculate_usage_metrics()
-
-        return self._format_output(task_outputs, token_usage)
-
-    def _execute_tasks(
+    def _store_execution_log(
         self,
-        tasks,
-        start_index=0,
-        is_replay=False,
-        inputs: Dict[str, Any] | None = None,
-    ):
-        task_outputs: List[TaskOutput] = []
-        futures: List[Tuple[Task, Future[TaskOutput]]] = []
-        for task_index, task in enumerate(tasks[start_index:], start=start_index):
-            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:
-                    task.tools += task.agent.get_delegation_tools(agents_for_delegation)
-
-            role = task.agent.role if task.agent is not None else "None"
-            log_prefix = "== Replaying from" if is_replay else "=="
-            log_color = "bold_blue" if is_replay else "bold_purple"
-            self._logger.log(
-                "debug", f"{log_prefix} Working Agent: {role}", color=log_color
-            )
-            self._logger.log(
-                "info",
-                f"{log_prefix} {'Replaying' if is_replay else 'Starting'} Task: {task.description}",
-                color=log_color,
-            )
-
-            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_task_outputs(task_outputs)
-                future = task.execute_async(
-                    agent=task.agent, context=context, tools=task.tools
-                )
-                futures.append((task, future))
-            else:
-                if futures:
-                    task_outputs = self._process_async_tasks(
-                        futures, task_index, inputs
-                    )
-                    futures.clear()
-
-                context = 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)
-                self._store_execution_log(task, task_output, task_index, inputs)
-
-        if futures:
-            task_outputs = self._process_async_tasks(futures, len(tasks), inputs)
-
-        return task_outputs
-
-    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 _process_async_tasks(
-        self,
-        futures: List[Tuple[Task, Future[TaskOutput]]],
+        task: Task,
+        output: TaskOutput,
         task_index: int,
-        inputs: Dict[str, Any] | None = None,
-    ) -> List[TaskOutput]:
-        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)
-            self._store_execution_log(future_task, task_output, task_index, inputs)
+        was_replayed: bool = False,
+    ):
+        if self._inputs:
+            inputs = self._inputs
+        else:
+            inputs = {}
 
-        return task_outputs
-
-    def replay_from_task(self, task_id: str):
-        stored_outputs = self._load_stored_outputs()
-        start_index = next(
-            (
-                index
-                for (index, d) in enumerate(stored_outputs)
-                if d["task_id"] == str(task_id)
-            ),
-            None,
+        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 start_index is None:
-            raise ValueError(f"Task with id {task_id} not found in the crew's tasks.")
-        # Create a map of task ID to stored output
-        stored_output_map: Dict[str, dict] = {
-            log["task_id"]: log["output"] for log in stored_outputs
-        }
+        if task_index < len(self.execution_logs):
+            self.execution_logs[task_index] = log
+        else:
+            self.execution_logs.append(log)
 
-        task_outputs: List[
-            TaskOutput
-        ] = []  # will propogate the old outputs first to add context then fill the content with the new task outputs relative to the replay start
-        futures: List[Tuple[Task, Future[TaskOutput]]] = []
-        context = ""
+        TaskOutputJsonHandler(CREW_TASKS_OUTPUT_FILE).update(task_index, log)
 
-        inputs = stored_outputs[start_index].get("inputs", {})
-        if inputs is not None:
-            self._interpolate_inputs(inputs)
-        for task_index, task in enumerate(self.tasks):
-            if task_index < start_index:
-                # Use stored output for tasks before the replay point
-                if task.id in stored_output_map:
-                    stored_output = stored_output_map[task.id]
-                    task_output = TaskOutput(
-                        description=stored_output["description"],
-                        raw_output=stored_output["raw_output"],
-                        pydantic_output=stored_output["pydantic_output"],
-                        json_output=stored_output["json_output"],
-                        agent=stored_output["agent"],
-                    )
-                    task_outputs.append(task_output)
-                    context += (
-                        f"\nTask {task_index + 1} Output:\n{task_output.raw_output}"
-                    )
-            else:
-                role = task.agent.role if task.agent is not None else "None"
-                log_color = "bold_blue"
-                self._logger.log(
-                    "debug", f"Replaying Working Agent: {role}", color=log_color
-                )
-                self._logger.log(
-                    "info",
-                    f"Replaying Task: {task.description}",
-                    color=log_color,
-                )
+    def _run_sequential_process(self) -> CrewOutput:
+        """Executes tasks sequentially and returns the final output."""
+        return self._execute_tasks(self.tasks)
 
-                if self.output_log_file:
-                    self._file_handler.log(
-                        agent=role, task=task.description, status="started"
-                    )
-                # Execute task for replay and subsequent tasks
-                if task.async_execution:
-                    future = task.execute_async(
-                        agent=task.agent, context=context, tools=task.tools
-                    )
-                    futures.append((task, future))
-                else:
-                    if futures:
-                        async_outputs = self._process_async_tasks(
-                            futures, task_index, inputs
-                        )
-                        task_outputs.extend(async_outputs)
-                        for output in async_outputs:
-                            context += (
-                                f"\nTask {task_index + 1} Output:\n{output.raw_output}"
-                            )
-                        futures.clear()
-                    task_output = task.execute_sync(
-                        agent=task.agent, context=context, tools=task.tools
-                    )
-                    task_outputs.append(task_output)
-                    self._process_task_result(task, task_output)
-                    self._store_execution_log(task, task_output, task_index, inputs)
-                    context += (
-                        f"\nTask {task_index + 1} Output:\n{task_output.raw_output}"
-                    )
-
-        # Process any remaining async tasks
-        if futures:
-            async_outputs = self._process_async_tasks(futures, len(self.tasks), inputs)
-            task_outputs.extend(async_outputs)
-        # Calculate usage metrics
-        token_usage = self.calculate_usage_metrics()
-
-        # Format and return the final output
-        return self._format_output(task_outputs, token_usage)
-
-    def _load_stored_outputs(self) -> List[Dict]:
-        try:
-            with open(self._log_file, "r") as f:
-                return json.load(f)
-        except FileNotFoundError:
-            self._logger.log(
-                "warning",
-                f"Log file {self._log_file} not found. Starting with empty logs.",
-            )
-            return []
-        except json.JSONDecodeError:
-            self._logger.log(
-                "error",
-                f"Failed to parse log file {self._log_file}. Starting with empty logs.",
-            )
-            return []
-
-    def save_execution_logs(self, filename: str | None = None):
-        """Save execution logs to a file."""
-        if filename:
-            self._log_file = filename
-        try:
-            with open(self._log_file, "w") as f:
-                json.dump(self.execution_logs, f, indent=2, cls=CrewJSONEncoder)
-        except Exception as e:
-            self._logger.log("error", f"Failed to save execution logs: {str(e)}")
-
-    def load_execution_logs(self, filename: str | None = None):
-        """Load execution logs from a file."""
-        if filename:
-            self._log_file = filename
-        try:
-            with open(self._log_file, "r") as f:
-                self.execution_logs = json.load(f)
-        except FileNotFoundError:
-            self._logger.log(
-                "warning",
-                f"Log file {self._log_file} not found. Starting with empty logs.",
-            )
-            self.execution_logs = []
-        except json.JSONDecodeError:
-            self._logger.log(
-                "error",
-                f"Failed to parse log file {self._log_file}. Starting with empty logs.",
-            )
-            self.execution_logs = []
-
-    def _run_hierarchical_process(self) -> Tuple[CrewOutput, Dict[str, Any]]:
+    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
@@ -731,63 +580,200 @@ 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
 
-        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_task_outputs(task_outputs)
-                future = task.execute_async(
-                    agent=manager, context=context, tools=manager.tools
+                context = self._get_context(
+                    task, [last_sync_output] if last_sync_output else []
                 )
-                futures.append((task, future))
+                future = task.execute_async(
+                    agent=agent_to_use,
+                    context=context,
+                    tools=agent_to_use.tools,
+                )
+                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_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)
 
-        final_string_output = aggregate_raw_outputs_from_task_outputs(task_outputs)
+        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 (
-            self._format_output(task_outputs, token_usage),
-            token_usage,
+        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_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."""
 
@@ -838,18 +824,6 @@ class Crew(BaseModel):
         for agent in self.agents:
             agent.interpolate_inputs(inputs)
 
-    def _format_output(
-        self, output: List[TaskOutput], token_usage: Optional[Dict[str, Any]]
-    ) -> CrewOutput:
-        """
-        Formats the output of the crew execution.
-        """
-        return CrewOutput(
-            output=output,
-            tasks_output=[task.output for task in self.tasks if task and task.output],
-            token_usage=token_usage,
-        )
-
     def _finish_execution(self, final_string_output: str) -> None:
         if self.max_rpm:
             self._rpm_controller.stop_rpm_counter()

src/crewai/crews/crew_output.py

@@ -1,13 +1,22 @@
-from typing import Any, Dict, List
+import json
+from typing import Any, Dict, Optional
 
 from pydantic import BaseModel, Field
 
+from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
-from crewai.utilities.formatter import aggregate_raw_outputs_from_task_outputs
 
 
 class CrewOutput(BaseModel):
-    output: List[TaskOutput] = Field(description="Result of the final task")
+    """Class that represents the result of a crew."""
+
+    raw: str = Field(description="Raw output of crew", default="")
+    pydantic: Optional[BaseModel] = Field(
+        description="Pydantic output of Crew", default=None
+    )
+    json_dict: Optional[Dict[str, Any]] = Field(
+        description="JSON dict output of Crew", default=None
+    )
     tasks_output: list[TaskOutput] = Field(
         description="Output of each task", default=[]
     )
@@ -15,30 +24,35 @@ class CrewOutput(BaseModel):
         description="Processed token summary", default={}
     )
 
-    # TODO: Ask @joao what is the desired behavior here
-    def result(
-        self,
-    ) -> List[str | BaseModel | Dict[str, Any]]:
-        """Return the result of the task based on the available output."""
-        results = [output.result() for output in self.output]
-        return results
+    # @property
+    # def pydantic(self) -> Optional[BaseModel]:
+    #     # Check if the final task output included a pydantic model
+    #     if self.tasks_output[-1].output_format != OutputFormat.PYDANTIC:
+    #         raise ValueError(
+    #             "No pydantic model found in the final task. Please make sure to set the output_pydantic property in the final task in your crew."
+    #         )
 
-    def raw_output(self) -> str:
-        """Return the raw output of the task."""
-        return aggregate_raw_outputs_from_task_outputs(self.output)
+    #     return self._pydantic
 
-    def to_output_dict(self) -> List[Dict[str, Any]]:
-        output_dict = [output.to_output_dict() for output in self.output]
-        return output_dict
+    @property
+    def json(self) -> Optional[str]:
+        if self.tasks_output[-1].output_format != OutputFormat.JSON:
+            raise ValueError(
+                "No JSON output found in the final task. Please make sure to set the output_json property in the final task in your crew."
+            )
 
-    def __getitem__(self, key: str) -> Any:
-        if len(self.output) == 0:
-            return None
-        elif len(self.output) == 1:
-            return self.output[0][key]
-        else:
-            return [output[key] for output in self.output]
+        return json.dumps(self.json_dict)
+
+    def to_dict(self) -> Dict[str, Any]:
+        if self.json_dict:
+            return self.json_dict
+        if self.pydantic:
+            return self.pydantic.model_dump()
+        raise ValueError("No output to convert to dictionary")
 
-    # TODO: Confirm with Joao that we want to print the raw output and not the object
     def __str__(self):
-        return str(self.raw_output())
+        if self.pydantic:
+            return str(self.pydantic)
+        if self.json_dict:
+            return str(self.json_dict)
+        return self.raw

src/crewai/task.py

@@ -1,10 +1,11 @@
+import json
 import os
 import re
 import threading
 import uuid
 from concurrent.futures import Future
 from copy import copy
-from typing import Any, Dict, List, Optional, Type, Union
+from typing import Any, Dict, List, Optional, Tuple, Type, Union
 
 from langchain_openai import ChatOpenAI
 from opentelemetry.trace import Span
@@ -12,10 +13,10 @@ from pydantic import UUID4, BaseModel, Field, field_validator, model_validator
 from pydantic_core import PydanticCustomError
 
 from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry.telemetry import Telemetry
 from crewai.utilities.converter import Converter, ConverterError
-from crewai.utilities.formatter import aggregate_raw_outputs_from_task_outputs
 from crewai.utilities.i18n import I18N
 from crewai.utilities.printer import Printer
 from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
@@ -99,6 +100,10 @@ class Task(BaseModel):
         description="Whether the task should have a human review the final answer of the agent",
         default=False,
     )
+    converter_cls: Optional[Type[Converter]] = Field(
+        description="A converter class used to export structured output",
+        default=None,
+    )
 
     _telemetry: Telemetry
     _execution_span: Span | None = None
@@ -159,18 +164,6 @@ class Task(BaseModel):
             )
         return self
 
-    def wait_for_completion(self) -> str | BaseModel:
-        """Wait for asynchronous task completion and return the output."""
-        assert self.async_execution, "Task is not set to be executed asynchronously."
-
-        if self._future:
-            self._future.result()  # Wait for the future to complete
-            self._future = None
-
-        assert self.output, "Task output is not set."
-
-        return self.output.exported_output
-
     def execute_sync(
         self,
         agent: Optional[BaseAgent] = None,
@@ -187,7 +180,7 @@ class Task(BaseModel):
         tools: Optional[List[Any]] = None,
     ) -> Future[TaskOutput]:
         """Execute the task asynchronously."""
-        future = Future()
+        future: Future[TaskOutput] = Future()
         threading.Thread(
             target=self._execute_task_async, args=(agent, context, tools, future)
         ).start()
@@ -211,6 +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(
@@ -219,31 +213,24 @@ class Task(BaseModel):
 
         self._execution_span = self._telemetry.task_started(crew=agent.crew, task=self)
 
-        if self.context:
-            task_outputs: List[TaskOutput] = []
-            for task in self.context:
-                # if task.async_execution:
-                #     task.wait_for_completion()
-                if task.output:
-                    task_outputs.append(task.output)
-            context = aggregate_raw_outputs_from_task_outputs(task_outputs)
-
         self.prompt_context = context
-        tools = tools or self.tools
+        tools = tools or self.tools or []
 
         result = agent.execute_task(
             task=self,
             context=context,
             tools=tools,
         )
-        exported_output = self._export_output(result)
+
+        pydantic_output, json_output = self._export_output(result)
 
         task_output = TaskOutput(
             description=self.description,
-            raw_output=result,
-            pydantic_output=exported_output["pydantic"],
-            json_output=exported_output["json"],
+            raw=result,
+            pydantic=pydantic_output,
+            json_dict=json_output,
             agent=agent.role,
+            output_format=self._get_output_format(),
         )
         self.output = task_output
 
@@ -254,6 +241,16 @@ class Task(BaseModel):
             self._telemetry.task_ended(self._execution_span, self)
             self._execution_span = None
 
+        if self.output_file:
+            content = (
+                json_output
+                if json_output
+                else pydantic_output.model_dump_json()
+                if pydantic_output
+                else result
+            )
+            self._save_file(content)
+
         return task_output
 
     def prompt(self) -> str:
@@ -289,7 +286,7 @@ class Task(BaseModel):
         """Increment the delegations counter."""
         self.delegations += 1
 
-    def copy(self, agents: Optional[List["BaseAgent"]] = None) -> "Task":
+    def copy(self, agents: List["BaseAgent"]) -> "Task":
         """Create a deep copy of the Task."""
         exclude = {
             "id",
@@ -320,28 +317,39 @@ class Task(BaseModel):
 
         return copied_task
 
+    def _create_converter(self, *args, **kwargs) -> Converter:
+        """Create a converter instance."""
+        converter = self.agent.get_output_converter(*args, **kwargs)
+        if self.converter_cls:
+            converter = self.converter_cls(*args, **kwargs)
+        return converter
+
     def _export_output(
         self, result: str
-    ) -> Dict[str, Union[BaseModel, Dict[str, Any]]]:
-        output = {
-            "pydantic": None,
-            "json": None,
-        }
+    ) -> Tuple[Optional[BaseModel], Optional[Dict[str, Any]]]:
+        pydantic_output: Optional[BaseModel] = None
+        json_output: Optional[Dict[str, Any]] = None
 
         if self.output_pydantic or self.output_json:
             model_output = self._convert_to_model(result)
-            output["pydantic"] = (
+            pydantic_output = (
                 model_output if isinstance(model_output, BaseModel) else None
             )
-            output["json"] = model_output if isinstance(model_output, dict) else None
+            if isinstance(model_output, str):
+                try:
+                    json_output = json.loads(model_output)
+                except json.JSONDecodeError:
+                    json_output = None
+            else:
+                json_output = model_output if isinstance(model_output, dict) else None
 
-        if self.output_file:
-            self._save_output(output["raw"])
-
-        return output
+        return pydantic_output, json_output
 
     def _convert_to_model(self, result: str) -> Union[dict, BaseModel, str]:
         model = self.output_pydantic or self.output_json
+        if model is None:
+            return result
+
         try:
             return self._validate_model(result, model)
         except Exception:
@@ -373,10 +381,10 @@ 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 = Converter(
+        converter = self._create_converter(
             llm=llm, text=result, model=model, instructions=instructions
         )
         exported_result = (
@@ -392,6 +400,13 @@ class Task(BaseModel):
 
         return exported_result
 
+    def _get_output_format(self) -> OutputFormat:
+        if self.output_json:
+            return OutputFormat.JSON
+        if self.output_pydantic:
+            return OutputFormat.PYDANTIC
+        return OutputFormat.RAW
+
     def _get_conversion_instructions(self, model: Type[BaseModel], llm: Any) -> str:
         instructions = "I'm gonna convert this raw text into valid JSON."
         if not self._is_gpt(llm):
@@ -400,6 +415,9 @@ class Task(BaseModel):
         return instructions
 
     def _save_output(self, content: str) -> None:
+        if not self.output_file:
+            raise Exception("Output file path is not set.")
+
         directory = os.path.dirname(self.output_file)
         if directory and not os.path.exists(directory):
             os.makedirs(directory)

src/crewai/tasks/__init__.py

@@ -0,0 +1,4 @@
+from crewai.tasks.output_format import OutputFormat
+from crewai.tasks.task_output import TaskOutput
+
+__all__ = ["OutputFormat", "TaskOutput"]

src/crewai/tasks/output_format.py

@@ -0,0 +1,9 @@
+from enum import Enum
+
+
+class OutputFormat(str, Enum):
+    """Enum that represents the output format of a task."""
+
+    JSON = "json"
+    PYDANTIC = "pydantic"
+    RAW = "raw"

src/crewai/tasks/task_output.py

@@ -1,22 +1,27 @@
-from typing import Any, Dict, Optional, Union
+import json
+from typing import Any, Dict, Optional
 
 from pydantic import BaseModel, Field, model_validator
 
+from crewai.tasks.output_format import OutputFormat
+
 
-# TODO: This is a breaking change. Confirm with @joao
 class TaskOutput(BaseModel):
     """Class that represents the result of a task."""
 
     description: str = Field(description="Description of the task")
     summary: Optional[str] = Field(description="Summary of the task", default=None)
-    raw_output: str = Field(description="Result of the task")
-    pydantic_output: Optional[BaseModel] = Field(
-        description="Pydantic model output", default=None
+    raw: str = Field(description="Raw output of the task", default="")
+    pydantic: Optional[BaseModel] = Field(
+        description="Pydantic output of task", default=None
     )
-    json_output: Optional[Dict[str, Any]] = Field(
-        description="JSON output", default=None
+    json_dict: Optional[Dict[str, Any]] = Field(
+        description="JSON dictionary of task", default=None
     )
     agent: str = Field(description="Agent that executed the task")
+    output_format: OutputFormat = Field(
+        description="Output format of the task", default=OutputFormat.RAW
+    )
 
     @model_validator(mode="after")
     def set_summary(self):
@@ -25,32 +30,45 @@ class TaskOutput(BaseModel):
         self.summary = f"{excerpt}..."
         return self
 
-    # TODO: Ask @joao what is the desired behavior here
-    def result(self) -> Union[str, BaseModel, Dict[str, Any]]:
-        """Return the result of the task based on the available output."""
-        if self.pydantic_output:
-            return self.pydantic_output
-        elif self.json_output:
-            return self.json_output
-        else:
-            return self.raw_output
+    # @property
+    # def pydantic(self) -> Optional[BaseModel]:
+    #     # Check if the final task output included a pydantic model
+    #     if self.output_format != OutputFormat.PYDANTIC:
+    #         raise ValueError(
+    #             """
+    #             Invalid output format requested.
+    #             If you would like to access the pydantic model,
+    #             please make sure to set the output_pydantic property for the task.
+    #             """
+    #         )
 
-    def __getitem__(self, key: str) -> Any:
-        """Retrieve a value from the pydantic_output or json_output based on the key."""
-        if self.pydantic_output and hasattr(self.pydantic_output, key):
-            return getattr(self.pydantic_output, key)
-        if self.json_output and key in self.json_output:
-            return self.json_output[key]
-        raise KeyError(f"Key '{key}' not found in pydantic_output or json_output")
+    #     return self._pydantic
 
-    def to_output_dict(self) -> Dict[str, Any]:
+    @property
+    def json(self) -> Optional[str]:
+        if self.output_format != OutputFormat.JSON:
+            raise ValueError(
+                """
+                Invalid output format requested.
+                If you would like to access the JSON output,
+                please make sure to set the output_json property for the task
+                """
+            )
+
+        return json.dumps(self.json_dict)
+
+    def to_dict(self) -> Dict[str, Any]:
         """Convert json_output and pydantic_output to a dictionary."""
         output_dict = {}
-        if self.json_output:
-            output_dict.update(self.json_output)
-        if self.pydantic_output:
-            output_dict.update(self.pydantic_output.model_dump())
+        if self.json_dict:
+            output_dict.update(self.json_dict)
+        if self.pydantic:
+            output_dict.update(self.pydantic.model_dump())
         return output_dict
 
     def __str__(self) -> str:
-        return self.raw_output
+        if self.pydantic:
+            return str(self.pydantic)
+        if self.json_dict:
+            return str(self.json_dict)
+        return self.raw

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/crew_json_encoder.py

@@ -6,12 +6,26 @@ from pydantic import BaseModel
 
 class CrewJSONEncoder(json.JSONEncoder):
     def default(self, obj):
-        if isinstance(obj, datetime):
-            return obj.isoformat()
-        if isinstance(obj, UUID):
-            return str(obj)
         if isinstance(obj, BaseModel):
-            return obj.model_dump()
-        if hasattr(obj, "__dict__"):
-            return obj.__dict__
-        return str(obj)
+            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

@@ -1,9 +1,8 @@
 import os
 import pickle
-from datetime import datetime
-import json
 
-from crewai.utilities.crew_json_encoder import CrewJSONEncoder
+
+from datetime import datetime
 
 
 class FileHandler:
@@ -69,37 +68,3 @@ class PickleHandler:
                 return {}  # Return an empty dictionary if the file is empty or corrupted
             except Exception:
                 raise  # Raise any other exceptions that occur during loading
-
-
-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 append(self, log) -> None:
-        if not os.path.exists(self.file_path) or os.path.getsize(self.file_path) == 0:
-            # Initialize the file with an empty list if it doesn't exist or is empty
-            with open(self.file_path, "w") as file:
-                json.dump([], file)
-        with open(self.file_path, "r+") as file:
-            try:
-                file_data = json.load(file)
-            except json.JSONDecodeError:
-                # If the file contains invalid JSON, initialize it with an empty list
-                file_data = []
-
-            file_data.append(log)
-            file.seek(0)
-            json.dump(file_data, file, indent=2, cls=CrewJSONEncoder)
-            file.truncate()
-
-    def load(self) -> list:
-        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)

src/crewai/utilities/formatter.py

@@ -1,5 +1,6 @@
 from typing import List
 
+from crewai.task import Task
 from crewai.tasks.task_output import TaskOutput
 
 
@@ -8,5 +9,12 @@ def aggregate_raw_outputs_from_task_outputs(task_outputs: List[TaskOutput]) -> s
     dividers = "\n\n----------\n\n"
 
     # Join task outputs with dividers
-    context = dividers.join(output.raw_output for output in task_outputs)
+    context = dividers.join(output.raw for output in task_outputs)
     return context
+
+
+def aggregate_raw_outputs_from_tasks(tasks: List[Task]) -> str:
+    """Generate string context from the tasks."""
+    task_outputs = [task.output for task in tasks if task.output is not None]
+
+    return aggregate_raw_outputs_from_task_outputs(task_outputs)

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

@@ -4,6 +4,10 @@ from unittest import mock
 from unittest.mock import patch
 
 import pytest
+from langchain.tools import tool
+from langchain_core.exceptions import OutputParserException
+from langchain_openai import ChatOpenAI
+
 from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
 from crewai.agents.executor import CrewAgentExecutor
@@ -11,9 +15,6 @@ from crewai.agents.parser import CrewAgentParser
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
 from crewai.utilities import RPMController
-from langchain.tools import tool
-from langchain_core.exceptions import OutputParserException
-from langchain_openai import ChatOpenAI
 
 
 def test_agent_creation():
@@ -630,8 +631,9 @@ def test_agent_use_specific_tasks_output_as_context(capsys):
 
     crew = Crew(agents=[agent1, agent2], tasks=tasks)
     result = crew.kickoff()
-    assert "bye" not in result.raw_output().lower()
-    assert "hi" in result.raw_output().lower() or "hello" in result.raw_output().lower()
+    print("LOWER RESULT", result.raw)
+    assert "bye" not in result.raw.lower()
+    assert "hi" in result.raw.lower() or "hello" in result.raw.lower()
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -643,7 +645,7 @@ def test_agent_step_callback():
     with patch.object(StepCallback, "callback") as callback:
 
         @tool
-        def learn_about_AI(topic) -> float:
+        def learn_about_AI(topic) -> str:
             """Useful for when you need to learn about AI to write an paragraph about it."""
             return "AI is a very broad field."
 
@@ -677,7 +679,7 @@ def test_agent_function_calling_llm():
     with patch.object(llm.client, "create", wraps=llm.client.create) as private_mock:
 
         @tool
-        def learn_about_AI(topic) -> float:
+        def learn_about_AI(topic) -> str:
             """Useful for when you need to learn about AI to write an paragraph about it."""
             return "AI is a very broad field."
 
@@ -749,8 +751,8 @@ def test_tool_result_as_answer_is_the_final_answer_for_the_agent():
     crew = Crew(agents=[agent1], tasks=tasks)
 
     result = crew.kickoff()
-    print("RESULT: ", result.raw_output())
-    assert result.raw_output() == "Howdy!"
+    print("RESULT: ", result.raw)
+    assert result.raw == "Howdy!"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])

tests/cassettes/test_kickoff_for_each_single_input.yaml

@@ -0,0 +1,192 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are dog Researcher. You have a lot of experience
+      with dog.\nYour personal goal is: Express hot takes on dog.To 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: Give me an analysis around dog.\n\nThis is the expect criteria for your
+      final answer: 1 bullet point about dog that''s under 15 words. \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
+      connection:
+      - keep-alive
+      content-length:
+      - '951'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.10
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.10
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        Dogs"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        are"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        unparalleled"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        loyalty"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        companionship"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        to"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        humans"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a0959de6b916783-ATL
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Tue, 09 Jul 2024 15:29:42 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=LA.xC.jE_aMjiSgGgU6kDsBPhb_akgqn_4Rx.jXYfnQ-1720538982-1.0.1.1-l5Q1BHprIz5Jxb4HWyYsMfbg6mEnP2H95Vxt89ez24pKOb__90s8LJBBqK52zmPNcPYSSUcaR0wRAaSVFoa4Fw;
+        path=/; expires=Tue, 09-Jul-24 15:59:42 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=zzJ51X.VwRkIq7VLCg9xPQGbXoUmAH6b.2g6sf6Y58Y-1720538982657-0.0.1.1-604800000;
+        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:
+      - '240'
+      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:
+      - '21999783'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_abdec68aded596628dfd5b999919447d
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_output_json_dict_sequential.yaml

@@ -0,0 +1,453 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
+      in scoring titles.\nYour personal goal is: Score the titleTo 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: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expect criteria for your final
+      answer: The score of the title. \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
+      connection:
+      - keep-alive
+      content-length:
+      - '997'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.10
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.10
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a0b45f368ab6734-ATL
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Tue, 09 Jul 2024 21:05:38 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=43lNOCqE3W6gMhKEVIvu20BhU4nI7wyQYcgn28hcb3o-1720559138-1.0.1.1-2pdG6KFn0J2AHC_tnhcxXCqmZ_RyZfwthLi5ET6Aq4v1L9z3EcYxV1D1CeKjOgEBJPLD9GUDdMmIR3h86QYx7w;
+        path=/; expires=Tue, 09-Jul-24 21:35:38 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=T4YvZnF6fWjq7JTPVyPFDIHaXBpT8E23GcG55Q0Ky6A-1720559138248-0.0.1.1-604800000;
+        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:
+      - '159'
+      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:
+      - '21999771'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_a58604fe17d3de5d4491ec972e98312b
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
+      "I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
+      {"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
+      "function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
+      `ScoreOutput` with all the required parameters with correct types", "parameters":
+      {"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
+      ["score"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '519'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=43lNOCqE3W6gMhKEVIvu20BhU4nI7wyQYcgn28hcb3o-1720559138-1.0.1.1-2pdG6KFn0J2AHC_tnhcxXCqmZ_RyZfwthLi5ET6Aq4v1L9z3EcYxV1D1CeKjOgEBJPLD9GUDdMmIR3h86QYx7w;
+        _cfuvid=T4YvZnF6fWjq7JTPVyPFDIHaXBpT8E23GcG55Q0Ky6A-1720559138248-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.10
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.10
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA2xSTW/bMAy9+1cIPMeDncRL7Gt2GNJhOWzdDmthKIriqJFETaK7FkH++yDHjd2g
+        PggEH98HSJ8SxkDtoGIgDpyEcTotn1Zr8/1lvViV9+rY6ru/zhW/8i+HpvA/YRIZuH2Sgt5YnwQa
+        pyUptBdYeMlJRtV8Mc2Kosxnyw4wuJM60hpH6RzTaTadp1mR5rOeeEAlZICK/UkYY+zUvTGi3ckX
+        qFg2eesYGQJvJFTXIcbAo44d4CGoQNwSTAZQoCVpY2rbaj0CCFHXgms9GF++06ge9sS1rk3Y/Cvv
+        Nq75upx+Pj7/vsfnb2ta6ZHfRfrVdYH2rRXX/Yzwa7+6MWMMLDcd94dALzctuZZu6IwB901rpKUY
+        HU4PEOLwA1TzM7wbPScf1Y99db6uVWPjPG7DzZZgr6wKh9pLHrq0EAjdxSLKPXbna99dBJxH46gm
+        PEobBZf99WD4Xwaw6DFC4nrEKZI+HoTXQNLUe2Ub6Z1X3Slh7+p5li3lbLvIS0jOyX8AAAD//wMA
+        s5wGAdMCAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a0b45f828146734-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 09 Jul 2024 21:05:38 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '215'
+      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:
+      - '21999969'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_34b28faf23b6422bb0855e6a45c65e92
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"input": ["examples(Examples): Specific scenarios used to explain counting,
+      addition, and subtraction through the zoo theme, such as counting animals, adding
+      new ones, and subtracting adopted ones."], "model": "text-embedding-ada-002",
+      "encoding_format": "base64"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '265'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.10
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.10
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.3
+    method: POST
+    uri: https://api.openai.com/v1/embeddings
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA1SaWw+ySrel779fsbJu6R0RkJp8d5xEzoWAp06nI4gIHpBDFVA7+7938F3Z3X1j
+        IqJgMWvMMZ6q//zXX3/93WR1kQ9///uvv19VP/z9P5Zjt+tw/fvff/3Pf/31119//efv9f87s3hn
+        xe1Wfcrf6b8Pq8+tmP7+91/8fx/5vyf9+6+/VYHbhcL5EyZzUN8aML+TT5g+ChmrzjYPH2qdqV16
+        NJs25BtD8dhUNEg1pR4Cch2RP6wE0kRo302x9m3Q7szJ2L+nvTG/n+crsl3BDVfRZtMRg/Yc+C+L
+        Yeu6vhutK+VXANs9U0fdoK6b73YK3Hq6UfxJPWOyZuEIlmGq+PguPh6zelMAe/0s6GV7S7O+7KIG
+        ykDwcDhfOI+W77UKHRdeCXev3Hq0nSEFzVUm6l73WrceGt6HQ+cOWOVQ5TFV7wU4HXFDt63uGIMT
+        PZ9Qa8YzXPUfL+PHQn6iyTZHjIdcTGj1Snj0WrMXmfzLyOj1Is2Q8NsbNdHNYEL+KACJWeOH6101
+        dGzFgw7aLUiJ2IgVm070WCD3LFZEMK4zm3lfrUDdWmIoK5PYjbO4OkOaoYSGZG4yOpbfEsSQAxwE
+        5ith2cZ2kTvLQC13XGejkY25YlnnEW+V2yGZBe3hgiWoN5ybpPe+cGlLeAzzPeSJa6BRTZMCRcpO
+        wrosZAYrKfLh+0pkqgnsk8zHtpNlr7v0VNsaJOu82W7AxMNMQ8/NsqlrD2e4yDGlu/dDZqM1Njka
+        PXND8nNVdTNv6EflNO51nB2dNxtxFnNK9LVC6ho7u2aOChLacs8NmeIjyZb3MioMoQjl6/5R06Fy
+        e5jl6EN3JlfVM9ud7E1l7SPs9onjMecWtUqBIo0mrKuT+cOf1N/9hxtL2BhL/bUQfqsA42izqWmG
+        L2e4bC1KHZrE3hhYFcB6iv1wIpve6/OrkqP5dHSJGO/1WjBfwRMa0Rewtn/o2VTZDxeqGErsdjQy
+        xmMw+eDfy3v4+n45NpshXFHP1doynsgYss3HQtv+dAzncXOrl/GUQN7v7FBM0LWm35NsotXr4mJd
+        tT71yMeyitBaXoeSEBy7uX86LUqMUcDqYH6zLoJ9pHAgX4jUf+tkIPL4hPrOHbHn3R6IdXUtK438
+        eGNsr4rs0R1FHm3K+YHDZu0i8RXdLGjCfou3icHVQ3bUJRhb8sZO3588BqWvgutePTJ+zgWbIkMX
+        Vk/jQ8JeKF7e6MkbC+7WtcF+P8ts1OGhorXsYLqr6eRNj1UrgRNDg/2vt/XmWTznMEihTfhEbVHb
+        zooAe3zKiHLy99nkSbIL/OtUYWwFfMdC8SOBZVjqn+fNzDJREc3uPrYUc5ew7niW4SNIGO93rZOR
+        Tf10ZXm/tel2Vw31/HBXKqJDT/HZYys2rlhggRKXF3xEnZ7N7aviFaabBb3GJysZQZZ4eKjXI/Zj
+        zTfaJ7gj2nBuiwM+aQy2PuVPZGUrI5T2o1KzbW210O9tiazN0fS+oRgB3L6Tid0iH43R+yQVrF6Z
+        S6rI22e9NJY+mPR0p8ZFxll7UhUXdaWwp76SKcn0WeUu2pXzFEKEb8Zyf4LyVrCNfSnTmfjTE8k6
+        l4SdH209evy7gqlyXRxcuMybHjV2QeTeX6xd+ohNduZxaChcQjWOOyAm2c0ZsFyTUHj2kjc2pjXC
+        5B4TrN8jNREOZ1oikXcVIrGsR2xbhy0I78Kn+Pqq2cjHs76RPGBklE/fZMzFfajcHMul7k+fzG5l
+        oa3Bv7F5eWjZ4FnbEGrExKU+jWQdXte+sq3zhO4ORp/NpW1cYW9uKIGjL9fMDrGE9iaidJtTxxBi
+        4VmAa7sN1qZujYbWmnwF02yHLc3XjenL8zNc11TBWHpY9cRpkgvm6fGl3rh16rHzuhlN5ecRNvGg
+        duOjnCJE3olP0FeVkzF7qKq8C/gE/+lX3PxJIUo/NtWy7bobz8ZFgETihHCEdOfxfXg/o7aILGoV
+        zw7N8rosf3pMSlc9GKNS3Cx0DLcuVZsyqmnuhAJSWJAQcV4R9md+zlC5dNcUUkepez5C7B9ibH2j
+        kU3qS7bAi8sv3ZbbrpvTYrZguX8yiU2SsPUpfQOVxCPFz2H05u9GvSo61+9JVb11Nh9FQZIFx9Jx
+        OD1nj0G80QHNzy1VyY14Sz8o0KbWzZAzz3s0QzhcEWrnEHuNR5L5a2U5BLYRhUJsiYz0wZgrN/nG
+        YXsDRiLM4rmAbH9Uw7WbiskgT6mM3DsU/3y/eKsp3M+Nh4+n8Jv86kHWdl+NBvSp1u3TufHQhGRL
+        3T75GtQVbgUseoJNSWgY23ipCtNdelO3VhvEPnkoAzqXXTgx81ozQag59NLtkNoW22b0N/+W64cg
+        f1lHxc39CWouDyHbSR80a8fSBs8lM+F29aseeeHoo/dGPtPtMYzr8XN6piiMPELkm9ElM3SOK28o
+        FonUJlnCppUkw2SOKk77M486vp1doAOh2KroNZnWRWihfN9+sA1kMHo1TXLo6P7zxz/M/PtdAhsQ
+        F8rne9xNlX58w3i+GXhbyqea3LMG0IV5LJTl7GCM61V+hnXOttjGld/NR5GT0XHoRew/P37Sc0qf
+        o3vfrQmf0dl4fT/fGeqgZ1Rjply3p9tZhql8PULQoMpYaI0E8X1RhKOaa6yjA1/BvohC6pgmrunO
+        SyO40oJSD2UdGnqn59EYSyO2tY6xLxiXI/Iv4FM3s4J6GBOlAPn9zbC7eTvGog8N4u4VJqKprTr6
+        yS1ZttBzJKg7Vl6v3S4NxCV/oUt/QEu9SPKvP666+6abH3vnKXvru4Ut25EzKnzPIN8Lv6D7m84y
+        ZtllAxm2cqIM89TNZhe5cE/FFXngp1nzdNW5kDmVQ7fu8Ojoos9wXFcE48gc6lYZ+FFmulVQjXO+
+        jOyZxCuX7gCEIe2FaIb3//R/977PvW/RzrKyyiuLoJ5+jGn5v6ih1xXdWk6DxmSj2QrMck8S1hnJ
+        HKWPXDESKab7qTugIbqkKmh+ecWWcY3ZvHddC1Q5FnEwH9tk5IUiRIczcgnHU8vgm7IqlaEedKo/
+        +QTxxir9U89UT6lr9Ja16SG0TyJRnINUs6HSCaw+7YC32ms05n7KWwApX1Gt2VVLPfdHGT7zlvp7
+        X/Wms3aVZencGtT5+R9+x8vwdElLd8oOGdNlWMco/g45xtuz3c195uXwXMlt2C56zjbnjwp1+d2T
+        9vExPdE0xBhQJmakDJ8BYnzacH/0xTqszW50hB0B45u/8K/fiOdn5IKWpnt6/+4bNEWGK4DRswN1
+        hu0jGfOgyoF3Kg3v5lWIJhT1R1Tf4Rj+9Lmr90IM1fwOqBbM627xU2d0XpUZtpb+1Xg8KeUjSzxq
+        vvlHws47/grkvNFDbrjU9bxabVy4c5vzMj8Doze+RgE5IirWHm/fYLu1p4N94Ca8i/dVN6+lVoak
+        QDkp/ZljBD/44ucXqWHnJRtxnI8oPMUtdb7ykExVHxyBvz067HoCZfNmo6RIf51mImxPYz0+0CkC
+        lqYaPoXVGs2GVNuw3z9X1BeTyWgvq0QCfrc608A5nOvRPdxteV8LFd2lYZnNyNvM6Ms1F7IK6pMx
+        zfdPDGLW+j9/4C3+SIYROIeG4aYxJv+VvjfPoduF4vtxZUwWhTOg/YViSzwDmlLzECEH3c9U3ytl
+        NvsC8yGn+ki3+hWMwXrVR+B25EKQrH+88VsXNnpmlyfWymCXre+ufgSp7wasfg9Qz4fPGEHmlA6+
+        ZWPrzfvTzYT6MwbUIPWElv7HI3v9LsgLmm9CZjEqlJVJIqL+/OTih2Fci0EozOcqG7StVipLv8M7
+        DR8YwVwUol8+Wt1OQd1/nmIKsbh7412Crh2pW+sMtnouyOa2Nup+6edQ+vsqnL3cYbTIjPDndzB+
+        oHfW7Ivwidbf4kCG2FyhITB7HQTRs2g4XIxOtOyyRUt+xQbStox9ckuC+/6BsX8dk4Qh9ngD17ZC
+        KJqc3o3bTxujJR+GXIloN9bHvbx56W5IvfgqG/S0VWc5cU4OduPTO5lf2TUEtmumUOLghkZPniyk
+        9znBuG2Hbnx3mqRsAt7AJ/f0SabjZRuhvtikVJ/iHRqK9NHD97FyCUsuEhtmMFTw4uqLHbOxE3pr
+        ihD0ytDDEtKP0Zuz1ipL3qSn/EIQ6Z9OA8/G4rG5/7w9NnibEtQoKOiWrt71mO3FGB0b90n95Doy
+        usw/tOWdgO7K5y1h1SsT0KMQe2yo1atjt6bwUcg3PJF1UiRTkT6I4l84H//8Fzu+plRJ6mtNABX3
+        ej7dIklJW8EiPNyK+htdUh1c6Y7pUp9s7B7AIZu7PwhHQtwt9T9Ck0YXqnY7r+uaV2BBLDWYFsOl
+        7qZcfx3ltW96OOO/ejbNdxojJbvk1ORwUPfh/TPC9WUYVC8j5LEvKiJIv/sbDZ2yzpb+XMG4Xgfk
+        OJ+rZL7Mqgxzd+CpRkzVI/1TaxRnf1lRVwrMRAz2kaUsfo2G/BGh+arv3qh8H4GakmAj5gqHHJb8
+        To3kIv3jX7wcDjiknzRh18s4Qyc1uz9+elCkjSQv/TwEJVMy4qRSCGbRvjCuxjiblYFf+jth2Ajy
+        LGMHXNowqOOLbqP92iPtrPDoI/sr6vqc1s3H9Eog4WoHb4dz1xHl1L0h3d8/Cy+wk97ZRhXksncK
+        5V/e1tNvCL/rK9pK8PpiParKz384h4ozaDW/BTRVtov1S1Kxhn73nLLWmjs55nOOxvQcPeF8ZjOZ
+        0En1GD6ujmhjDTsiba9lNzpxXaLH+1tjez/e6qmxr2ewz2EaKsO8r/sVC0x4cLcLWc1qZLAoriql
+        PlQt2ROzNJpn31noaHwLshK8oh7PfqSDswnW1OAaVLPYNlzIpzgNJW43McrZlxZmKF2adnyGxrp+
+        SrCyDTUcL1GMpp0pj9D0JqYu52pI/J5mE6r5GdCtcltnk3U+p3DjYpeMMYVsNDvRhLk78RRP3tMY
+        m2/TQ/KmCXUfH9OY8O7UIkWNhVDBsWAM2tYp4YPzDoeX1+D1XnFLIcx5hVqP46Ebvp6lonbyn9Rs
+        AivrP8/VEXZDoWJVb+du8QsmuvX6B1vZXHn0x7PMSHbwtssC9EmVjsB7nvLwsoK0Zvus6ZFGczHk
+        5OSSjaX2ldA3/ahEUd9TRh6uqMq/6wfVXu3mfkpbOB6Q9uNv/+i7mfob3N2suzfVa69E1T4TsZee
+        Tmh04q6Ex/p9XPqj3s07VQ3/8DQf4yqbLBzb8Fg/j9SZv3zd2pdAl8NcUOjumu+90R/3BITLDHRr
+        cTzrl/wFDTAnRGYcevM53lRwcTsdO2iyjNE9nFzonYOG/SUPDqfKyJGBLx4N4fvIZkRvnHyI1B01
+        rLvhiRm+XNHi/0J58aPLfHzC51tucd6qk0eb19b8k3dZrKYGU756iI5cNi3jqxtD1W+P4D9GA+cX
+        tEvE8w6ukG2EkchsO9ekShQf7b/XdcjvQ8TI9TDYiBYMQuG11ZO5fbU8WvI5kYRAqKfH90JgJz0/
+        WJc16jWCfW3lZxRzZLwH0cLnVBsKFGsEkOgwslPtELzGBKpuuLu38CodPpH3pta7+BhzapcyIGJy
+        eJepX8ayvL/CfXKBoGjUvTHAX/eXt6i20aRsmf89nMvXd+GLQcfehm7CBm121PDut25G9MABlh+E
+        4qRMa6bM9hmc+X0IF96WMOEbcfD5VluqvlzizZjucqW27RL7k+wnbF5fSkj2nkpEh7t5M3mvI9gx
+        NaVqdTYzatlNi8IpNan5EotkUKqGwDVmJQ7U9z6bd6rt/8l/6ou82cTIqCLZ2e+pUWYvRHnNO//8
+        U6gEm33Snhx0hOt6UKiaiQGbs8+jVMaXm1B74QnTzesqOBze15ArnBeazp3WgpdzB2rifWHMxzQm
+        cIolibQL35mEyyb66WM4h2HSTStyrcB7zv7CT5DHrkoOv/HBW/N0QWPn1bNy9zhEvUIiBlv0BT1D
+        7Up1X61Q/6tXXvHOZJ0YXDf9/D+/U850121Zx/RWvgJmUkhDnlre5FHEwdUvY+psXM+Ta9xcNws/
+        I1xp1V0v2HH748NU69xVMmvR4Q2SygfUK9cdG44RNqHth9vCw/SOn9MsRPhdmVQN6IMN/PPcQmUl
+        UbhZ83YtWKIDUBh8geMV53csbFMJPRuTx0G3Zqi/VA8f1lPkY1XbB4wRKZEQ7s0Tva5FyMiejQJS
+        c2lYeFpQv9dbhYP6MwcY319FNu3Io0L2zuBCODtS0ueT1YB+lDO8ZQfHm7fEm2FuDJO0931uDMLo
+        5kCe2peajx6j+VHk7x8/JFTXLY8v1qMOcp121D8756TnrnaMIq590O1bXBt9q7/ecCuaG1n8Vz1N
+        VlUo+/17FYpj8EqoUq1adC9znZqZd8kmr2oALsxhNIyxu/SbrYliR6+ovnLK+sdHAesqh7WC1xMh
+        7QMTbb/qm4bBbrPki3cF5aHV6Y83iWNgcL88FK5b3fHma1GncPJ2Ghm1/YBodF+XKJyOJpEurcTm
+        B/+af3yWumaXe+yXNy0pUnEUPgdGo7tSwaZWTXx9zXP38wtoqW/sr4I+6XmH8Sg2cowTtXrVJLUb
+        CX48BrNLysTf+ou8fobYiD40GZTkxMlNGl9CaeT3jBW7ofkzH4KUK7tesqYciXoyhGKp7Or1zy95
+        8NZJaRri8vmmQMrWxWTUrQ3il/4ny+fQJPLifyaeE1p4XcAk4i+flN3nCepKdKnph1qyduTkCKcg
+        fdLdog/jvYpzFHN+hR0tfiHCXU8hLL8fZv4tr0lw1BvgCdHw8rwz4j45HuiKi6n9PN7Qn37xelkd
+        WeWMZ/TAzBQMQaAhe/Ft3ZMymwE5Hyl89fyM5vkK/e//UL9d37xZcc9PiJSthHfPpPXmn37Pcvwh
+        YjA4bLo9eAJKXF2w8eLbf/SASusjtlXhgwatGQgwECYayn1d0x8PtQ0aEv4lcskcrmP9x5ewufAY
+        tjlTFf14kbXfd2zw8uKKvMYCrFvSZEyPA7iyyjwU3r4fw1t7kmzDku+wgUM3m/I+tcBbSXO4+R7T
+        bj54eQlIJWuqGSivx+srF8DVtJ6qpnGqmbhqXbir/OGXR7MlT5nyst5Cd1sW1vPCO2BZv8OuvArY
+        6GzPJXpvpHNYlu9Dxvr3qYRnlj3D9Qqbmfjrj7xTajQINvts0uK0gsMMz4WvvuuZf5MKKJd9yaf4
+        rLpp7zsqoG/wCpF305DQxUGElvmCA+EhsUHMe/kPL+Qur8Cbx1dqKfNKkLG61Bd7X5IIdoGQULzw
+        oMlVQkDISmxy8kbfmFD0TGGLYge7axESqt7tJzxcXsfRLvSSZX5zcIzfe7rku2R8nJiFwtV0DVcO
+        aMma2F4Lx4GIIRfsNsYvf2wU7rQh/LIeN0kIYrT40d/6hMHfZFP4h7dE1w+L71nJKVb/VajndDFj
+        U31wodiHDXbmLULUuZ0bdE1TB9uhs2N/+NlMXZXaW+2YzBMaYvjxvTV9QzIARf3P74WKt/vU4/SR
+        RvmXT+1lPaHXyyCGV7y2ybS+6h07NT38+CdWkX/I1sLoFnCVP0dS773GG25clAOuBgk7jv/wRrN4
+        WsAdnTGcRsFB7FE1PvDiZ4uxT7pffeqQOAcHq0yzmHDgtAJyq1Lp8rzQoGVxD/qtRkRY9K7vW+ai
+        rXPdUP/oX7u+1B4yHLNbuuQBnY3HYBNCHm25JU9axthRDCjUyCmciFl6Q1JOOlr0NxSWfLfk0Qb4
+        Pi9oVE9fY9jF21H55TnjQEvUkIHMP71b+P/Xm8ihaODef9fYvl1eHbnq+A3b644Reck7bKhcAj+9
+        9LTymbRTg3vg9cv2x3Pq0REwgYWnhPIl5bqmKdsKLfyJIOXsdHNw1FuAz7jFP94/65dslslwtbE9
+        67YxPz7xqDQXoQ83jc1lrSVq8NObhb9HBtuvfAmC4FPjYAesm+LXVgCejw74sKwHjWQgIyrClUmU
+        +ehmbMlTctdxIjVqvWTMOKUCMk5YDzn64ZMxM58xRFcnw4ffetxPb68vzaA7aafWE+43b1juj6q0
+        ey58VyLglOlMf7x//o0Pp9vWwu9OHW2vL/KHh8HTYDUp4mqG1ldrMmvjqiOKe35D7psJNYTb4P1Z
+        f22mtl74kJoxvxMs5e/froD/+tdff/2v3w6Dd3MrXsvGgKGYhv/4760C/3G9Xf+D54U/2xBIfy2L
+        v//9zw6Ev79d8/4O/3tonsWn//vff4mbP3sN/h6a4fr6f4//a7nUf/3r/wAAAP//AwCfQckA4CAA
+        AA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a0b45f9bc6c4589-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 09 Jul 2024 21:05:39 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=IuvCm3DYH_Yj2KCjQfa873zjAj_2TgaF47eD6tQ4Mhs-1720559139-1.0.1.1-fWDjNt6ARNNwSwU4ZoyX.VoMhynDVIi97V54zsXBMuMg_KjRGid.vTsH.YWP4cEbPWj_vdlZjnfl3ef4S90Eog;
+        path=/; expires=Tue, 09-Jul-24 21:35:39 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=uolQOZ2C52Hd5W7TXNWyFaYk4FEIIwP0B2MH49GGYtA-1720559139009-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - text-embedding-ada-002
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '18'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '10000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '9999953'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_5f80532d772393d55159f71cbd4e8211
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_output_json_sequential.yaml

@@ -0,0 +1,258 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
+      in scoring titles.\nYour personal goal is: Score the titleTo 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: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expect criteria for your final
+      answer: The score of the title. \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
+      connection:
+      - keep-alive
+      content-length:
+      - '997'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.10
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.10
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a0b45eb19a3c00b-ATL
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Tue, 09 Jul 2024 21:05:36 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=pA7SjF9QjLel4TzQ_lNj63W_TlcZBVsYreOxByhCguY-1720559136-1.0.1.1-HZhSIVb4ZIrgcL3DwhR7q53vNdieKNmEv_0ZAHDbmBBkD891hDrzxqLpBZSw7j_mFtCPQEjxpAMjD5JI3o8NEw;
+        path=/; expires=Tue, 09-Jul-24 21:35:36 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=OblnrTSQSq8R858tQhKPz9cFRCWv.MPPI1wxnvjeHJI-1720559136855-0.0.1.1-604800000;
+        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:
+      - '96'
+      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:
+      - '21999771'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_ee2fc8fd37b03ee0bcf92ff34f91a51c
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
+      "I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
+      {"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
+      "function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
+      `ScoreOutput` with all the required parameters with correct types", "parameters":
+      {"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
+      ["score"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '519'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=pA7SjF9QjLel4TzQ_lNj63W_TlcZBVsYreOxByhCguY-1720559136-1.0.1.1-HZhSIVb4ZIrgcL3DwhR7q53vNdieKNmEv_0ZAHDbmBBkD891hDrzxqLpBZSw7j_mFtCPQEjxpAMjD5JI3o8NEw;
+        _cfuvid=OblnrTSQSq8R858tQhKPz9cFRCWv.MPPI1wxnvjeHJI-1720559136855-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.10
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.10
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA2xS22rjMBB991eIeY4X5+K68WsoXbplt6WUQjfFKIp8SWSNkMabpiH/XuS4sRvW
+        D2KYM+fCjA8BY1CtIWUgSk6iNiqcbxZ3anfPy6sPnu92k23iVvttUl7/XPz+BSPPwNVGCvpi/RBY
+        GyWpQn2ChZWcpFcdJ5MojufjadICNa6l8rTCUDjDcBJNZmEUh+NpRyyxEtJByv4GjDF2aF8fUa/l
+        O6QsGn11aukcLySk5yHGwKLyHeDOVY64Jhj1oEBNUvvUulFqABCiygRXqjc+fYdB3e+JK5Wtdrc3
+        L83Y7h8Xm4/7l3/b13nx8Hz3MPA7Se9NGyhvtDjvZ4Cf++mFGWOged1ynwRa+ach09AFnTHgtmhq
+        qclHh8MSnB9eQjo7wrfRY/C/+q2rjue1KiyMxZW72BLkla5cmVnJXZsWHKE5WXi5t/Z8zbeLgLFY
+        G8oIt1J7wevuetD/Lz0YdxghcTXgxEEXD9zekayzvNKFtMZW7SkhN9k6Tq6mUZLPIwiOwScAAAD/
+        /wMAE8hqg9MCAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a0b45ef8871c00b-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 09 Jul 2024 21:05:37 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '298'
+      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:
+      - '21999969'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_cea16690999d7a4128fd55687dc31397
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_output_pydantic_sequential.yaml

@@ -0,0 +1,258 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
+      in scoring titles.\nYour personal goal is: Score the titleTo 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: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expect criteria for your final
+      answer: The score of the title. \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
+      connection:
+      - keep-alive
+      content-length:
+      - '997'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.10
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.10
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"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-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"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:
+      - 8a0b45e24b19bd4d-ATL
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Tue, 09 Jul 2024 21:05:35 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=N7yNe.ilaHt2MJPusthFVyL5PrE._f_nyf4RfU.oIv0-1720559135-1.0.1.1-oCOj_tvpNYp16zBvNbxW.TwSHAFXRiB_i23X4XBw_o01D1_7OKj_HwRNZWdwg9DjDh_C_FSMKTonmzQmsUmtdg;
+        path=/; expires=Tue, 09-Jul-24 21:35:35 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=aiUOV0PnMjHles7YFoHcFY7PK2Ag6MdKr0GWZzZ_rZo-1720559135403-0.0.1.1-604800000;
+        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:
+      - '105'
+      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:
+      - '21999771'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_759b74b995b84a531eae7df3eddf1196
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
+      "I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
+      {"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
+      "function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
+      `ScoreOutput` with all the required parameters with correct types", "parameters":
+      {"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
+      ["score"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '519'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=N7yNe.ilaHt2MJPusthFVyL5PrE._f_nyf4RfU.oIv0-1720559135-1.0.1.1-oCOj_tvpNYp16zBvNbxW.TwSHAFXRiB_i23X4XBw_o01D1_7OKj_HwRNZWdwg9DjDh_C_FSMKTonmzQmsUmtdg;
+        _cfuvid=aiUOV0PnMjHles7YFoHcFY7PK2Ag6MdKr0GWZzZ_rZo-1720559135403-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.10
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.10
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA2xS22rcMBB991eIeV4XX9ZJ1m8lEGgKSZtSUnLBKPLYq40sCWmcdFn234u8ztpZ
+        6gcxzJlzYca7iDGQNZQMxJqT6KyKV5vL680mzX58Xd4l773D7O63vMjP7rfrKwuLwDAvGxT0wfoi
+        TGcVkjT6AAuHnDCopudZUhSrNC8GoDM1qkBrLcVLE2dJtoyTIk7zkbg2UqCHkj1GjDG2G94QUdf4
+        F0qWLD46HXrPW4TyOMQYOKNCB7j30hPXBIsJFEYT6pBa90rNADJGVYIrNRkfvt2snvbElareb27S
+        b28/v7/VRXtP13X75+GMF+hmfgfprR0CNb0Wx/3M8GO/PDFjDDTvBu4vYRze9mR7OqEzBty1fYea
+        QnTYPYEPw09QLvfwaXQf/a9+Hqv9ca3KtNaZF3+yJWikln5dOeR+SAuejD1YBLnn4Xz9p4uAdaaz
+        VJF5RR0EL8brwfS/TGAxYmSIqxmniMZ44LeesKsaqVt01snhlNDYSmByvsrzPGkg2kf/AAAA//8D
+        AKtPZkLTAgAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a0b45e5ffd7bd4d-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 09 Jul 2024 21:05:36 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '153'
+      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:
+      - '21999969'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_36cd16b74a2085c72139d09309d21e39
+    status:
+      code: 200
+      message: OK
+version: 1

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",
@@ -87,6 +90,86 @@ def test_crew_config_conditional_requirement():
     ]
 
 
+def test_async_task_cannot_include_sequential_async_tasks_in_context():
+    task1 = Task(
+        description="Task 1",
+        async_execution=True,
+        expected_output="output",
+        agent=researcher,
+    )
+    task2 = Task(
+        description="Task 2",
+        async_execution=True,
+        expected_output="output",
+        agent=researcher,
+        context=[task1],
+    )
+    task3 = Task(
+        description="Task 3",
+        async_execution=True,
+        expected_output="output",
+        agent=researcher,
+        context=[task2],
+    )
+    task4 = Task(
+        description="Task 4",
+        expected_output="output",
+        agent=writer,
+    )
+    task5 = Task(
+        description="Task 5",
+        async_execution=True,
+        expected_output="output",
+        agent=researcher,
+        context=[task4],
+    )
+
+    # This should raise an error because task2 is async and has task1 in its context without a sync task in between
+    with pytest.raises(
+        ValueError,
+        match="Task 'Task 2' is asynchronous and cannot include other sequential asynchronous tasks in its context.",
+    ):
+        Crew(tasks=[task1, task2, task3, task4, task5], agents=[researcher, writer])
+
+    # This should not raise an error because task5 has a sync task (task4) in its context
+    try:
+        Crew(tasks=[task1, task4, task5], agents=[researcher, writer])
+    except ValueError:
+        pytest.fail("Unexpected ValidationError raised")
+
+
+def test_context_no_future_tasks():
+    task2 = Task(
+        description="Task 2",
+        expected_output="output",
+        agent=researcher,
+    )
+    task3 = Task(
+        description="Task 3",
+        expected_output="output",
+        agent=researcher,
+        context=[task2],
+    )
+    task4 = Task(
+        description="Task 4",
+        expected_output="output",
+        agent=researcher,
+    )
+    task1 = Task(
+        description="Task 1",
+        expected_output="output",
+        agent=researcher,
+        context=[task4],
+    )
+
+    # This should raise an error because task1 has a context dependency on a future task (task4)
+    with pytest.raises(
+        ValueError,
+        match="Task 'Task 1' has a context dependency on a future task 'Task 4', which is not allowed.",
+    ):
+        Crew(tasks=[task1, task2, task3, task4], agents=[researcher, writer])
+
+
 def test_crew_config_with_wrong_keys():
     no_tasks_config = json.dumps(
         {
@@ -144,10 +227,10 @@ def test_crew_creation():
     expected_string_output = "1. **The Rise of AI in Healthcare**: The convergence of AI and healthcare is a promising frontier, offering unprecedented opportunities for disease diagnosis and patient outcome prediction. AI's potential to revolutionize healthcare lies in its capacity to synthesize vast amounts of data, generating precise and efficient results. This technological breakthrough, however, is not just about improving accuracy and efficiency; it's about saving lives. As we stand on the precipice of this transformative era, we must prepare for the complex challenges and ethical questions it poses, while embracing its ability to reshape healthcare as we know it.\n\n2. **Ethical Implications of AI**: As AI intertwines with our daily lives, it presents a complex web of ethical dilemmas. This fusion of technology, philosophy, and ethics is not merely academically intriguing but profoundly impacts the fabric of our society. The questions raised range from decision-making transparency to accountability, and from privacy to potential biases. As we navigate this ethical labyrinth, it is crucial to establish robust frameworks and regulations to ensure that AI serves humanity, and not the other way around.\n\n3. **AI and Data Privacy**: The rise of AI brings with it an insatiable appetite for data, spawning new debates around privacy rights. Balancing the potential benefits of AI with the right to privacy is a unique challenge that intersects technology, law, and human rights. In an increasingly digital world, where personal information forms the backbone of many services, we must grapple with these issues. It's time to redefine the concept of privacy and devise innovative solutions that ensure our digital footprints are not abused.\n\n4. **AI in Job Market**: The discourse around AI's impact on employment is a narrative of contrast, a tale of displacement and creation. On one hand, AI threatens to automate a multitude of jobs, on the other, it promises to create new roles that we cannot yet imagine. This intersection of technology, economics, and labor rights is a critical dialogue that will shape our future. As we stand at this crossroads, we must not only brace ourselves for the changes but also seize the opportunities that this technological wave brings.\n\n5. **Future of AI Agents**: The evolution of AI agents signifies a leap towards a future where AI is not just a tool, but a partner. These sophisticated AI agents, employed in customer service to personal assistants, are redefining our interactions with technology. As we gaze into the future of AI agents, we see a landscape of possibilities and challenges. This journey will be about harnessing the potential of AI agents while navigating the issues of trust, dependence, and ethical use."
 
     assert str(result) == expected_string_output
-    assert result.raw_output() == expected_string_output
+    assert result.raw == expected_string_output
     assert isinstance(result, CrewOutput)
     assert len(result.tasks_output) == len(tasks)
-    assert result.result() == [expected_string_output]
+    assert result.raw == expected_string_output
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -174,7 +257,7 @@ def test_sync_task_execution():
     )
 
     mock_task_output = TaskOutput(
-        description="Mock description", raw_output="mocked output", agent="mocked agent"
+        description="Mock description", raw="mocked output", agent="mocked agent"
     )
 
     # Because we are mocking execute_sync, we never hit the underlying _execute_core
@@ -210,7 +293,7 @@ def test_hierarchical_process():
     result = crew.kickoff()
 
     assert (
-        result.raw_output()
+        result.raw
         == "1. 'Demystifying AI: An in-depth exploration of Artificial Intelligence for the layperson' - In this piece, we will unravel the enigma of AI, simplifying its complexities into digestible information for the everyday individual. By using relatable examples and analogies, we will journey through the neural networks and machine learning algorithms that define AI, without the jargon and convoluted explanations that often accompany such topics.\n\n2. 'The Role of AI in Startups: A Game Changer?' - Startups today are harnessing the power of AI to revolutionize their businesses. This article will delve into how AI, as an innovative force, is shaping the startup ecosystem, transforming everything from customer service to product development. We'll explore real-life case studies of startups that have leveraged AI to accelerate their growth and disrupt their respective industries.\n\n3. 'AI and Ethics: Navigating the Complex Landscape' - AI brings with it not just technological advancements, but ethical dilemmas as well. This article will engage readers in a thought-provoking discussion on the ethical implications of AI, exploring issues like bias in algorithms, privacy concerns, job displacement, and the moral responsibility of AI developers. We will also discuss potential solutions and frameworks to address these challenges.\n\n4. 'Unveiling the AI Agents: The Future of Customer Service' - AI agents are poised to reshape the customer service landscape, offering businesses the ability to provide round-the-clock support and personalized experiences. In this article, we'll dive deep into the world of AI agents, examining how they work, their benefits and limitations, and how they're set to redefine customer interactions in the digital age.\n\n5. 'From Science Fiction to Reality: AI in Everyday Life' - AI, once a concept limited to the realm of sci-fi, has now permeated our daily lives. This article will highlight the ubiquitous presence of AI, from voice assistants and recommendation algorithms, to autonomous vehicles and smart homes. We'll explore how AI, in its various forms, is transforming our everyday experiences, making the future seem a lot closer than we imagined."
     )
 
@@ -248,7 +331,7 @@ def test_crew_with_delegating_agents():
     result = crew.kickoff()
 
     assert (
-        result.raw_output()
+        result.raw
         == "AI Agents, simply put, are intelligent systems that can perceive their environment and take actions to reach specific goals. Imagine them as digital assistants that can learn, adapt and make decisions. They operate in the realms of software or hardware, like a chatbot on a website or a self-driving car. The key to their intelligence is their ability to learn from their experiences, making them better at their tasks over time. In today's interconnected world, AI agents are transforming our lives. They enhance customer service experiences, streamline business processes, and even predict trends in data. Vehicles equipped with AI agents are making transportation safer. In healthcare, AI agents are helping to diagnose diseases, personalizing treatment plans, and monitoring patient health. As we embrace the digital era, these AI agents are not just important, they're becoming indispensable, shaping a future where technology works intuitively and intelligently to meet our needs."
     )
 
@@ -413,7 +496,7 @@ def test_api_calls_throttling(capsys):
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_kickoff_for_each_full_ouput():
+def test_crew_kickoff_usage_metrics():
     inputs = [
         {"topic": "dog"},
         {"topic": "cat"},
@@ -432,14 +515,11 @@ def test_crew_kickoff_for_each_full_ouput():
         agent=agent,
     )
 
-    crew = Crew(agents=[agent], tasks=[task], full_output=True)
+    crew = Crew(agents=[agent], tasks=[task])
     results = crew.kickoff_for_each(inputs=inputs)
 
     assert len(results) == len(inputs)
     for result in results:
-        assert "usage_metrics" in result
-        assert isinstance(result["usage_metrics"], dict)
-
         # Assert that all required keys are in usage_metrics and their values are not None
         for key in [
             "total_tokens",
@@ -447,8 +527,8 @@ def test_crew_kickoff_for_each_full_ouput():
             "completion_tokens",
             "successful_requests",
         ]:
-            assert key in result["usage_metrics"]
-            assert result["usage_metrics"][key] > 0
+            assert key in result.token_usage
+            assert result.token_usage[key] > 0
 
 
 def test_agents_rpm_is_never_set_if_crew_max_RPM_is_not_set():
@@ -471,22 +551,6 @@ def test_agents_rpm_is_never_set_if_crew_max_RPM_is_not_set():
     assert agent._rpm_controller is None
 
 
-"""
-Future tests:
-TODO: 1 async task, 1 sync task. Make sure sync task waits for async to finish before starting.[]
-TODO: 3 async tasks, 1 sync task. Make sure sync task waits for async to finish before starting.
-TODO: 1 sync task, 1 async task. Make sure we wait for result from async before finishing crew.
-
-TODO: 3 async tasks, 1 sync task. Make sure context from all 3 async tasks is passed to sync task.
-TODO: 3 async tasks, 1 sync task. Pass in context from only 1 async task to sync task.
-
-TODO: Test pydantic output of CrewOutput and test type in CrewOutput result
-TODO: Test json output of CrewOutput and test type in CrewOutput result
-
-TODO: TEST THE SAME THING BUT WITH HIERARCHICAL PROCESS
-"""
-
-
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_sequential_async_task_execution_completion():
     list_ideas = Task(
@@ -515,51 +579,13 @@ def test_sequential_async_task_execution_completion():
     )
 
     sequential_result = sequential_crew.kickoff()
-    assert sequential_result.raw_output().startswith(
+    assert sequential_result.raw.startswith(
         "**The Evolution of Artificial Intelligence: A Journey Through Milestones**"
     )
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_hierarchical_async_task_execution_completion():
-    from langchain_openai import ChatOpenAI
-
-    list_ideas = Task(
-        description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
-        expected_output="Bullet point list of 5 important events.",
-        agent=researcher,
-        async_execution=True,
-    )
-    list_important_history = Task(
-        description="Research the history of AI and give me the 5 most important events that shaped the technology.",
-        expected_output="Bullet point list of 5 important events.",
-        agent=researcher,
-        async_execution=True,
-    )
-    write_article = Task(
-        description="Write an article about the history of AI and its most important events.",
-        expected_output="A 4 paragraph article about AI.",
-        agent=writer,
-        context=[list_ideas, list_important_history],
-    )
-
-    hierarchical_crew = Crew(
-        agents=[researcher, writer],
-        process=Process.hierarchical,
-        tasks=[list_ideas, list_important_history, write_article],
-        manager_llm=ChatOpenAI(temperature=0, model="gpt-4"),
-    )
-
-    hierarchical_result = hierarchical_crew.kickoff()
-
-    assert hierarchical_result.raw_output().startswith(
-        "The history of artificial intelligence (AI) is a fascinating journey"
-    )
-
-
 @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",
@@ -581,8 +607,7 @@ def test_single_task_with_async_execution():
     )
 
     result = crew.kickoff()
-    print(result.raw_output())
-    assert result.raw_output().startswith(
+    assert result.raw.startswith(
         "- The impact of AI agents on remote work productivity."
     )
 
@@ -615,17 +640,21 @@ def test_three_task_with_async_execution():
         async_execution=True,
     )
 
-    crew = Crew(
-        agents=[researcher_agent],
-        process=Process.sequential,
-        tasks=[bullet_list, numbered_list, letter_list],
-    )
+    # Expected result is that we will get an error
+    # because a crew can end only end with one or less
+    # async tasks
+    with pytest.raises(pydantic_core._pydantic_core.ValidationError) as error:
+        Crew(
+            agents=[researcher_agent],
+            process=Process.sequential,
+            tasks=[bullet_list, numbered_list, letter_list],
+        )
 
-    # Expected result is that we are going to concatenate the output from each async task.
-    # Because we add a buffer between each task, we should see a "----------" string
-    # after the first and second task in the final output.
-    result = crew.kickoff()
-    assert result.raw_output().count("\n\n----------\n\n") == 2
+    assert error.value.errors()[0]["type"] == "async_task_count"
+    assert (
+        "The crew must end with at most one asynchronous task."
+        in error.value.errors()[0]["msg"]
+    )
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -649,7 +678,7 @@ async def test_crew_async_kickoff():
         agent=agent,
     )
 
-    crew = Crew(agents=[agent], tasks=[task], full_output=True)
+    crew = Crew(agents=[agent], tasks=[task])
     results = await crew.kickoff_for_each_async(inputs=inputs)
 
     assert len(results) == len(inputs)
@@ -662,8 +691,7 @@ async def test_crew_async_kickoff():
             "successful_requests",
         ]:
             assert key in result.token_usage
-            # TODO: FIX THIS WHEN USAGE METRICS ARE RE-DONE
-            # assert result.token_usage[key] > 0
+            assert result.token_usage[key] > 0
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -696,7 +724,7 @@ def test_async_task_execution_call_count():
 
     # Create a valid TaskOutput instance to mock the return value
     mock_task_output = TaskOutput(
-        description="Mock description", raw_output="mocked output", agent="mocked agent"
+        description="Mock description", raw="mocked output", agent="mocked agent"
     )
 
     # Create a MagicMock Future instance
@@ -713,7 +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
@@ -723,10 +750,8 @@ def test_async_task_execution_call_count():
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_kickoff_for_each_single_input():
     """Tests if kickoff_for_each works with a single input."""
-    from unittest.mock import patch
 
     inputs = [{"topic": "dog"}]
-    expected_outputs = ["Dogs are loyal companions and popular pets."]
 
     agent = Agent(
         role="{topic} Researcher",
@@ -740,32 +765,21 @@ def test_kickoff_for_each_single_input():
         agent=agent,
     )
 
-    with patch.object(Agent, "execute_task") as mock_execute_task:
-        mock_execute_task.side_effect = expected_outputs
-        crew = Crew(agents=[agent], tasks=[task])
-        results = crew.kickoff_for_each(inputs=inputs)
+    crew = Crew(agents=[agent], tasks=[task])
+    results = crew.kickoff_for_each(inputs=inputs)
 
     assert len(results) == 1
-    print("RESULT:", results)
-    for result in results:
-        assert result == expected_outputs[0]
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_kickoff_for_each_multiple_inputs():
     """Tests if kickoff_for_each works with multiple inputs."""
-    from unittest.mock import patch
 
     inputs = [
         {"topic": "dog"},
         {"topic": "cat"},
         {"topic": "apple"},
     ]
-    expected_outputs = [
-        "Dogs are loyal companions and popular pets.",
-        "Cats are independent and low-maintenance pets.",
-        "Apples are a rich source of dietary fiber and vitamin C.",
-    ]
 
     agent = Agent(
         role="{topic} Researcher",
@@ -779,14 +793,10 @@ def test_kickoff_for_each_multiple_inputs():
         agent=agent,
     )
 
-    with patch.object(Agent, "execute_task") as mock_execute_task:
-        mock_execute_task.side_effect = expected_outputs
-        crew = Crew(agents=[agent], tasks=[task])
-        results = crew.kickoff_for_each(inputs=inputs)
+    crew = Crew(agents=[agent], tasks=[task])
+    results = crew.kickoff_for_each(inputs=inputs)
 
     assert len(results) == len(inputs)
-    for i, res in enumerate(results):
-        assert res == expected_outputs[i]
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -1058,7 +1068,7 @@ def test_crew_function_calling_llm():
     with patch.object(llm.client, "create", wraps=llm.client.create) as private_mock:
 
         @tool
-        def learn_about_AI(topic) -> float:
+        def learn_about_AI(topic) -> str:
             """Useful for when you need to learn about AI to write an paragraph about it."""
             return "AI is a very broad field."
 
@@ -1107,7 +1117,7 @@ def test_task_with_no_arguments():
     crew = Crew(agents=[researcher], tasks=[task])
 
     result = crew.kickoff()
-    assert result.raw_output() == "75"
+    assert result.raw == "75"
 
 
 def test_code_execution_flag_adds_code_tool_upon_kickoff():
@@ -1138,8 +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():
-    from unittest.mock import patch
-
     researcher = Agent(
         role="Researcher",
         goal="Make the best research and analysis on content about AI and AI agents",
@@ -1174,39 +1182,12 @@ def test_agents_do_not_get_delegation_tools_with_there_is_only_one_agent():
 
     result = crew.kickoff()
     assert (
-        result.raw_output()
+        result.raw
         == "Howdy! I hope this message finds you well and brings a smile to your face. Have a fantastic day!"
     )
     assert len(agent.tools) == 0
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_agent_usage_metrics_are_captured_for_sequential_process():
-    agent = Agent(
-        role="Researcher",
-        goal="Be super empathetic.",
-        backstory="You're love to sey howdy.",
-        allow_delegation=False,
-    )
-
-    task = Task(description="say howdy", expected_output="Howdy!", agent=agent)
-
-    crew = Crew(agents=[agent], tasks=[task])
-
-    result = crew.kickoff()
-    assert result.raw_output() == "Howdy!"
-
-    required_keys = [
-        "total_tokens",
-        "prompt_tokens",
-        "completion_tokens",
-        "successful_requests",
-    ]
-    for key in required_keys:
-        assert key in crew.usage_metrics, f"Key '{key}' not found in usage_metrics"
-        assert crew.usage_metrics[key] > 0, f"Value for key '{key}' is zero"
-
-
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_sequential_crew_creation_tasks_without_agents():
     task = Task(
@@ -1251,13 +1232,15 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
     )
 
     result = crew.kickoff()
-    assert result.raw_output() == '"Howdy!"'
+    assert result.raw == '"Howdy!"'
+
+    print(crew.usage_metrics)
 
     assert crew.usage_metrics == {
-        "total_tokens": 1927,
-        "prompt_tokens": 1557,
-        "completion_tokens": 370,
-        "successful_requests": 4,
+        "total_tokens": 311,
+        "prompt_tokens": 224,
+        "completion_tokens": 87,
+        "successful_requests": 1,
     }
 
 
@@ -1282,15 +1265,17 @@ def test_hierarchical_crew_creation_tasks_with_agents():
         manager_llm=ChatOpenAI(model="gpt-4o"),
     )
     crew.kickoff()
+
     assert crew.manager_agent is not None
     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]"
     )
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_hierarchical_crew_creation_tasks_without_async_execution():
+def test_hierarchical_crew_creation_tasks_with_async_execution():
     from langchain_openai import ChatOpenAI
 
     task = Task(
@@ -1394,7 +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",
@@ -1418,7 +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",
@@ -1485,7 +1468,7 @@ def test_tools_with_custom_caching():
     from crewai_tools import tool
 
     @tool
-    def multiplcation_tool(first_number: int, second_number: int) -> str:
+    def multiplcation_tool(first_number: int, second_number: int) -> int:
         """Useful for when you need to multiply two numbers together."""
         return first_number * second_number
 
@@ -1547,7 +1530,7 @@ def test_tools_with_custom_caching():
                 input={"first_number": 2, "second_number": 6},
                 output=12,
             )
-            assert result.raw_output() == "3"
+            assert result.raw == "3"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -1646,7 +1629,7 @@ def test_manager_agent():
     )
 
     mock_task_output = TaskOutput(
-        description="Mock description", raw_output="mocked output", agent="mocked agent"
+        description="Mock description", raw="mocked output", agent="mocked agent"
     )
 
     # Because we are mocking execute_sync, we never hit the underlying _execute_core
@@ -1822,6 +1805,470 @@ def test__setup_for_training():
         assert agent.allow_delegation is False
 
 
-# TODO: TEST EXPORT OUTPUT TASK WITH PYDANTIC
-# TODO: TEST EXPORT OUTPUT TASK WITH JSON
-# TODO: TEST EXPORT OUTPUT TASK CALLBACK
+@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=[])
 
 
@@ -104,11 +104,13 @@ 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)
 
 
 def test_task_callback_returns_task_ouput():
+    from crewai.tasks.output_format import OutputFormat
+
     researcher = Agent(
         role="Researcher",
         goal="Make the best research and analysis on content about AI and AI agents",
@@ -127,7 +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]
@@ -140,10 +142,12 @@ def test_task_callback_returns_task_ouput():
         output_dict = json.loads(callback_data)
         expected_output = {
             "description": task.description,
-            "exported_output": "exported_ok",
-            "raw_output": "exported_ok",
+            "raw": "exported_ok",
+            "pydantic": None,
+            "json_dict": None,
             "agent": researcher.role,
             "summary": "Give me a list of 5 interesting ideas to explore...",
+            "output_format": OutputFormat.RAW,
         }
         assert output_dict == expected_output
 
@@ -200,7 +204,7 @@ def test_multiple_output_type_error():
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_output_pydantic():
+def test_output_pydantic_sequential():
     class ScoreOutput(BaseModel):
         score: int
 
@@ -218,13 +222,46 @@ def test_output_pydantic():
         agent=scorer,
     )
 
-    crew = Crew(agents=[scorer], tasks=[task])
+    crew = Crew(agents=[scorer], tasks=[task], process=Process.sequential)
     result = crew.kickoff()
-    assert isinstance(result, ScoreOutput)
+    assert isinstance(result.pydantic, ScoreOutput)
+    assert result.to_dict() == {"score": 4}
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_output_json():
+def test_output_pydantic_hierarchical():
+    from langchain_openai import ChatOpenAI
+
+    class ScoreOutput(BaseModel):
+        score: int
+
+    scorer = Agent(
+        role="Scorer",
+        goal="Score the title",
+        backstory="You're an expert scorer, specialized in scoring titles.",
+        allow_delegation=False,
+    )
+
+    task = Task(
+        description="Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work'",
+        expected_output="The score of the title.",
+        output_pydantic=ScoreOutput,
+        agent=scorer,
+    )
+
+    crew = Crew(
+        agents=[scorer],
+        tasks=[task],
+        process=Process.hierarchical,
+        manager_llm=ChatOpenAI(model="gpt-4o"),
+    )
+    result = crew.kickoff()
+    assert isinstance(result.pydantic, ScoreOutput)
+    assert result.to_dict() == {"score": 4}
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_output_json_sequential():
     class ScoreOutput(BaseModel):
         score: int
 
@@ -242,9 +279,126 @@ def test_output_json():
         agent=scorer,
     )
 
-    crew = Crew(agents=[scorer], tasks=[task])
+    crew = Crew(agents=[scorer], tasks=[task], process=Process.sequential)
     result = crew.kickoff()
-    assert '{\n  "score": 4\n}' == result
+    assert '{"score": 4}' == result.json
+    assert result.to_dict() == {"score": 4}
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_output_json_hierarchical():
+    from langchain_openai import ChatOpenAI
+
+    class ScoreOutput(BaseModel):
+        score: int
+
+    scorer = Agent(
+        role="Scorer",
+        goal="Score the title",
+        backstory="You're an expert scorer, specialized in scoring titles.",
+        allow_delegation=False,
+    )
+
+    task = Task(
+        description="Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work'",
+        expected_output="The score of the title.",
+        output_json=ScoreOutput,
+        agent=scorer,
+    )
+
+    crew = Crew(
+        agents=[scorer],
+        tasks=[task],
+        process=Process.hierarchical,
+        manager_llm=ChatOpenAI(model="gpt-4o"),
+    )
+    result = crew.kickoff()
+    assert '{"score": 4}' == result.json
+    assert result.to_dict() == {"score": 4}
+
+
+def test_json_property_without_output_json():
+    class ScoreOutput(BaseModel):
+        score: int
+
+    scorer = Agent(
+        role="Scorer",
+        goal="Score the title",
+        backstory="You're an expert scorer, specialized in scoring titles.",
+        allow_delegation=False,
+    )
+
+    task = Task(
+        description="Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work'",
+        expected_output="The score of the title.",
+        output_pydantic=ScoreOutput,  # Using output_pydantic instead of output_json
+        agent=scorer,
+    )
+
+    crew = Crew(agents=[scorer], tasks=[task], process=Process.sequential)
+    result = crew.kickoff()
+
+    with pytest.raises(ValueError) as excinfo:
+        _ = result.json  # Attempt to access the json property
+
+    assert "No JSON output found in the final task." in str(excinfo.value)
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_output_json_dict_sequential():
+    class ScoreOutput(BaseModel):
+        score: int
+
+    scorer = Agent(
+        role="Scorer",
+        goal="Score the title",
+        backstory="You're an expert scorer, specialized in scoring titles.",
+        allow_delegation=False,
+    )
+
+    task = Task(
+        description="Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work'",
+        expected_output="The score of the title.",
+        output_json=ScoreOutput,
+        agent=scorer,
+    )
+
+    crew = Crew(agents=[scorer], tasks=[task], process=Process.sequential)
+    result = crew.kickoff()
+    assert {"score": 4} == result.json_dict
+    assert result.to_dict() == {"score": 4}
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_output_json_dict_hierarchical():
+    from langchain_openai import ChatOpenAI
+
+    class ScoreOutput(BaseModel):
+        score: int
+
+    scorer = Agent(
+        role="Scorer",
+        goal="Score the title",
+        backstory="You're an expert scorer, specialized in scoring titles.",
+        allow_delegation=False,
+    )
+
+    task = Task(
+        description="Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work'",
+        expected_output="The score of the title.",
+        output_json=ScoreOutput,
+        agent=scorer,
+    )
+
+    crew = Crew(
+        agents=[scorer],
+        tasks=[task],
+        process=Process.hierarchical,
+        manager_llm=ChatOpenAI(model="gpt-4o"),
+    )
+    result = crew.kickoff()
+    assert {"score": 4} == result.json_dict
+    assert result.to_dict() == {"score": 4}
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -280,7 +434,11 @@ def test_output_pydantic_to_another_task():
 
     crew = Crew(agents=[scorer], tasks=[task1, task2], verbose=2)
     result = crew.kickoff()
-    assert 5 == result.score
+    pydantic_result = result.pydantic
+    assert isinstance(
+        pydantic_result, ScoreOutput
+    ), "Expected pydantic result to be of type ScoreOutput"
+    assert 5 == pydantic_result.score
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -311,7 +469,7 @@ def test_output_json_to_another_task():
 
     crew = Crew(agents=[scorer], tasks=[task1, task2])
     result = crew.kickoff()
-    assert '{\n  "score": 5\n}' == result
+    assert '{"score": 5}' == result.json
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -363,7 +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('{\n  "score": 4\n}')
+        save_file.assert_called_once_with({"score": 4})
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -558,12 +716,78 @@ def test_interpolate_inputs():
     assert task.expected_output == "Bullet point list of 5 interesting ideas about ML."
 
 
-"""
-TODO: TEST SYNC
-- Verify return type
-"""
+def test_task_output_str_with_pydantic():
+    from crewai.tasks.output_format import OutputFormat
 
-"""
-TODO: TEST ASYNC
-- Verify return type
-"""
+    class ScoreOutput(BaseModel):
+        score: int
+
+    score_output = ScoreOutput(score=4)
+    task_output = TaskOutput(
+        description="Test task",
+        agent="Test Agent",
+        pydantic=score_output,
+        output_format=OutputFormat.PYDANTIC,
+    )
+
+    assert str(task_output) == str(score_output)
+
+
+def test_task_output_str_with_json_dict():
+    from crewai.tasks.output_format import OutputFormat
+
+    json_dict = {"score": 4}
+    task_output = TaskOutput(
+        description="Test task",
+        agent="Test Agent",
+        json_dict=json_dict,
+        output_format=OutputFormat.JSON,
+    )
+
+    assert str(task_output) == str(json_dict)
+
+
+def test_task_output_str_with_raw():
+    from crewai.tasks.output_format import OutputFormat
+
+    raw_output = "Raw task output"
+    task_output = TaskOutput(
+        description="Test task",
+        agent="Test Agent",
+        raw=raw_output,
+        output_format=OutputFormat.RAW,
+    )
+
+    assert str(task_output) == raw_output
+
+
+def test_task_output_str_with_pydantic_and_json_dict():
+    from crewai.tasks.output_format import OutputFormat
+
+    class ScoreOutput(BaseModel):
+        score: int
+
+    score_output = ScoreOutput(score=4)
+    json_dict = {"score": 4}
+    task_output = TaskOutput(
+        description="Test task",
+        agent="Test Agent",
+        pydantic=score_output,
+        json_dict=json_dict,
+        output_format=OutputFormat.PYDANTIC,
+    )
+
+    # When both pydantic and json_dict are present, pydantic should take precedence
+    assert str(task_output) == str(score_output)
+
+
+def test_task_output_str_with_none():
+    from crewai.tasks.output_format import OutputFormat
+
+    task_output = TaskOutput(
+        description="Test task",
+        agent="Test Agent",
+        output_format=OutputFormat.RAW,
+    )
+
+    assert str(task_output) == ""