Compare commits

...

2 Commits

Author SHA1 Message Date
Greyson LaLonde
f6fa04528a fix: add async HITL support and chained-router tests
Some checks are pending
CodeQL Advanced / Analyze (actions) (push) Waiting to run
CodeQL Advanced / Analyze (python) (push) Waiting to run
Notify Downstream / notify-downstream (push) Waiting to run
asynchronous human-in-the-loop handling and related fixes.

- Extend human_input provider with async support: AsyncExecutorContext, handle_feedback_async, async prompt helpers (_prompt_input_async, _async_readline), and async training/regular feedback loops in SyncHumanInputProvider.
- Add async handler methods in CrewAgentExecutor and AgentExecutor (_ahandle_human_feedback, _ainvoke_loop) to integrate async provider flows.
- Change PlusAPI.get_agent to an async httpx call and adapt caller in agent_utils to run it via asyncio.run.
- Simplify listener execution in flow.Flow to correctly pass HumanFeedbackResult to listeners and unify execution path for router outcomes.
- Remove deprecated types/hitl.py definitions.
- Add tests covering chained router feedback, rejected paths, and mixed router/non-router listeners to prevent regressions.
2026-02-06 16:29:27 -05:00
Greyson LaLonde
7d498b29be fix: event ordering; flow state locks, routing
* fix: add current task id context and flow updates

introduce a context var for the current task id in `crewai.context` to track task scope. update `Flow._execute_single_listener` to return `(result, event_id)` and adjust callers to unpack it and append `FlowMethodName(str(result))` to `router_results`. set/reset the current task id at the start/end of task execution (async + sync) with minor import and call-site tweaks.

* fix: await event futures and flush event bus

call `crewai_event_bus.flush()` after crew kickoff. in `Flow`, await event handler futures instead of just collecting them: await pending `_event_futures` before finishing, await emitted futures immediately with try/except to log failures, then clear `_event_futures`. ensures handlers complete and errors surface.

* fix: continue iteration on tool completion events

expand the loop bridge listener to also trigger on tool completion events (`tool_completed` and `native_tool_completed`) so agent iteration resumes after tools finish. add a `requests.post` mock and response fixture in the liteagent test to simulate platform tool execution. refresh and sanitize vcr cassettes (updated model responses, timestamps, and header placeholders) to reflect tool-call flows and new recordings.

* fix: thread-safe state proxies & native routing

add thread-safe state proxies and refactor native tool routing.

* introduce `LockedListProxy` and `LockedDictProxy` in `flow.py` and update `StateProxy` to return them for list/dict attrs so mutations are protected by the flow lock.
* update `AgentExecutor` to use `StateProxy` on flow init, guard the messages setter with the state lock, and return a `StateProxy` from the temp state accessor.
* convert `call_llm_native_tools` into a listener (no direct routing return) and add `route_native_tool_result` to route based on state (pending tool calls, final answer, or context error).
* minor cleanup in `continue_iteration` to drop orphan listeners on init.
* update test cassettes for new native tool call responses, timestamps, and ids.

improves concurrency safety for shared state and makes native tool routing explicit.

* chore: regen cassettes

* chore: regen cassettes, remove duplicate listener call path
2026-02-06 14:02:43 -05:00
21 changed files with 1218 additions and 587 deletions

View File

@@ -1009,7 +1009,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
raise
if self.ask_for_human_input:
formatted_answer = self._handle_human_feedback(formatted_answer)
formatted_answer = await self._ahandle_human_feedback(formatted_answer)
self._create_short_term_memory(formatted_answer)
self._create_long_term_memory(formatted_answer)
@@ -1508,6 +1508,20 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
provider = get_provider()
return provider.handle_feedback(formatted_answer, self)
async def _ahandle_human_feedback(
self, formatted_answer: AgentFinish
) -> AgentFinish:
"""Process human feedback asynchronously via the configured provider.
Args:
formatted_answer: Initial agent result.
Returns:
Final answer after feedback.
"""
provider = get_provider()
return await provider.handle_feedback_async(formatted_answer, self)
def _is_training_mode(self) -> bool:
"""Check if training mode is active.

View File

@@ -1,6 +1,8 @@
import os
from typing import Any
from urllib.parse import urljoin
import os
import httpx
import requests
from crewai.cli.config import Settings
@@ -33,7 +35,11 @@ class PlusAPI:
if settings.org_uuid:
self.headers["X-Crewai-Organization-Id"] = settings.org_uuid
self.base_url = os.getenv("CREWAI_PLUS_URL") or str(settings.enterprise_base_url) or DEFAULT_CREWAI_ENTERPRISE_URL
self.base_url = (
os.getenv("CREWAI_PLUS_URL")
or str(settings.enterprise_base_url)
or DEFAULT_CREWAI_ENTERPRISE_URL
)
def _make_request(
self, method: str, endpoint: str, **kwargs: Any
@@ -49,8 +55,10 @@ class PlusAPI:
def get_tool(self, handle: str) -> requests.Response:
return self._make_request("GET", f"{self.TOOLS_RESOURCE}/{handle}")
def get_agent(self, handle: str) -> requests.Response:
return self._make_request("GET", f"{self.AGENTS_RESOURCE}/{handle}")
async def get_agent(self, handle: str) -> httpx.Response:
url = urljoin(self.base_url, f"{self.AGENTS_RESOURCE}/{handle}")
async with httpx.AsyncClient() as client:
return await client.get(url, headers=self.headers)
def publish_tool(
self,

View File

@@ -43,3 +43,23 @@ def platform_context(integration_token: str) -> Generator[None, Any, None]:
yield
finally:
_platform_integration_token.reset(token)
_current_task_id: contextvars.ContextVar[str | None] = contextvars.ContextVar(
"current_task_id", default=None
)
def set_current_task_id(task_id: str | None) -> contextvars.Token[str | None]:
"""Set the current task ID in the context. Returns a token for reset."""
return _current_task_id.set(task_id)
def reset_current_task_id(token: contextvars.Token[str | None]) -> None:
"""Reset the current task ID to its previous value."""
_current_task_id.reset(token)
def get_current_task_id() -> str | None:
"""Get the current task ID from the context."""
return _current_task_id.get()

View File

@@ -2,7 +2,9 @@
from __future__ import annotations
import asyncio
from contextvars import ContextVar, Token
import sys
from typing import TYPE_CHECKING, Protocol, runtime_checkable
@@ -46,13 +48,21 @@ class ExecutorContext(Protocol):
...
class AsyncExecutorContext(ExecutorContext, Protocol):
"""Extended context for executors that support async invocation."""
async def _ainvoke_loop(self) -> AgentFinish:
"""Invoke the agent loop asynchronously and return the result."""
...
@runtime_checkable
class HumanInputProvider(Protocol):
"""Protocol for human input handling.
Implementations handle the full feedback flow:
- Sync: prompt user, loop until satisfied
- Async: raise exception for external handling
- Async: use non-blocking I/O and async invoke loop
"""
def setup_messages(self, context: ExecutorContext) -> bool:
@@ -86,7 +96,7 @@ class HumanInputProvider(Protocol):
formatted_answer: AgentFinish,
context: ExecutorContext,
) -> AgentFinish:
"""Handle the full human feedback flow.
"""Handle the full human feedback flow synchronously.
Args:
formatted_answer: The agent's current answer.
@@ -100,6 +110,25 @@ class HumanInputProvider(Protocol):
"""
...
async def handle_feedback_async(
self,
formatted_answer: AgentFinish,
context: AsyncExecutorContext,
) -> AgentFinish:
"""Handle the full human feedback flow asynchronously.
Uses non-blocking I/O for user prompts and async invoke loop
for agent re-execution.
Args:
formatted_answer: The agent's current answer.
context: Async executor context for callbacks.
Returns:
The final answer after feedback processing.
"""
...
@staticmethod
def _get_output_string(answer: AgentFinish) -> str:
"""Extract output string from answer.
@@ -116,7 +145,7 @@ class HumanInputProvider(Protocol):
class SyncHumanInputProvider(HumanInputProvider):
"""Default synchronous human input via terminal."""
"""Default human input provider with sync and async support."""
def setup_messages(self, context: ExecutorContext) -> bool:
"""Use standard message setup.
@@ -157,6 +186,33 @@ class SyncHumanInputProvider(HumanInputProvider):
return self._handle_regular_feedback(formatted_answer, feedback, context)
async def handle_feedback_async(
self,
formatted_answer: AgentFinish,
context: AsyncExecutorContext,
) -> AgentFinish:
"""Handle feedback asynchronously without blocking the event loop.
Args:
formatted_answer: The agent's current answer.
context: Async executor context for callbacks.
Returns:
The final answer after feedback processing.
"""
feedback = await self._prompt_input_async(context.crew)
if context._is_training_mode():
return await self._handle_training_feedback_async(
formatted_answer, feedback, context
)
return await self._handle_regular_feedback_async(
formatted_answer, feedback, context
)
# ── Sync helpers ──────────────────────────────────────────────────
@staticmethod
def _handle_training_feedback(
initial_answer: AgentFinish,
@@ -209,6 +265,62 @@ class SyncHumanInputProvider(HumanInputProvider):
return answer
# ── Async helpers ─────────────────────────────────────────────────
@staticmethod
async def _handle_training_feedback_async(
initial_answer: AgentFinish,
feedback: str,
context: AsyncExecutorContext,
) -> AgentFinish:
"""Process training feedback asynchronously (single iteration).
Args:
initial_answer: The agent's initial answer.
feedback: Human feedback string.
context: Async executor context for callbacks.
Returns:
Improved answer after processing feedback.
"""
context._handle_crew_training_output(initial_answer, feedback)
context.messages.append(context._format_feedback_message(feedback))
improved_answer = await context._ainvoke_loop()
context._handle_crew_training_output(improved_answer)
context.ask_for_human_input = False
return improved_answer
async def _handle_regular_feedback_async(
self,
current_answer: AgentFinish,
initial_feedback: str,
context: AsyncExecutorContext,
) -> AgentFinish:
"""Process regular feedback with async iteration loop.
Args:
current_answer: The agent's current answer.
initial_feedback: Initial human feedback string.
context: Async executor context for callbacks.
Returns:
Final answer after all feedback iterations.
"""
feedback = initial_feedback
answer = current_answer
while context.ask_for_human_input:
if feedback.strip() == "":
context.ask_for_human_input = False
else:
context.messages.append(context._format_feedback_message(feedback))
answer = await context._ainvoke_loop()
feedback = await self._prompt_input_async(context.crew)
return answer
# ── I/O ───────────────────────────────────────────────────────────
@staticmethod
def _prompt_input(crew: Crew | None) -> str:
"""Show rich panel and prompt for input.
@@ -262,6 +374,79 @@ class SyncHumanInputProvider(HumanInputProvider):
finally:
formatter.resume_live_updates()
@staticmethod
async def _prompt_input_async(crew: Crew | None) -> str:
"""Show rich panel and prompt for input without blocking the event loop.
Args:
crew: The crew instance for context.
Returns:
User input string from terminal.
"""
from rich.panel import Panel
from rich.text import Text
from crewai.events.event_listener import event_listener
formatter = event_listener.formatter
formatter.pause_live_updates()
try:
if crew and getattr(crew, "_train", False):
prompt_text = (
"TRAINING MODE: Provide feedback to improve the agent's performance.\n\n"
"This will be used to train better versions of the agent.\n"
"Please provide detailed feedback about the result quality and reasoning process."
)
title = "🎓 Training Feedback Required"
else:
prompt_text = (
"Provide feedback on the Final Result above.\n\n"
"• If you are happy with the result, simply hit Enter without typing anything.\n"
"• Otherwise, provide specific improvement requests.\n"
"• You can provide multiple rounds of feedback until satisfied."
)
title = "💬 Human Feedback Required"
content = Text()
content.append(prompt_text, style="yellow")
prompt_panel = Panel(
content,
title=title,
border_style="yellow",
padding=(1, 2),
)
formatter.console.print(prompt_panel)
response = await _async_readline()
if response.strip() != "":
formatter.console.print("\n[cyan]Processing your feedback...[/cyan]")
return response
finally:
formatter.resume_live_updates()
async def _async_readline() -> str:
"""Read a line from stdin using the event loop's native I/O.
Falls back to asyncio.to_thread on platforms where piping stdin
is unsupported.
Returns:
The line read from stdin, with trailing newline stripped.
"""
loop = asyncio.get_running_loop()
try:
reader = asyncio.StreamReader()
protocol = asyncio.StreamReaderProtocol(reader)
await loop.connect_read_pipe(lambda: protocol, sys.stdin)
raw = await reader.readline()
return raw.decode().rstrip("\n")
except (OSError, NotImplementedError, ValueError):
return await asyncio.to_thread(input)
_provider: ContextVar[HumanInputProvider | None] = ContextVar(
"human_input_provider",

View File

@@ -1517,6 +1517,7 @@ class Crew(FlowTrackable, BaseModel):
final_string_output = final_task_output.raw
self._finish_execution(final_string_output)
self.token_usage = self.calculate_usage_metrics()
crewai_event_bus.flush()
crewai_event_bus.emit(
self,
CrewKickoffCompletedEvent(

View File

@@ -32,7 +32,8 @@ from crewai.events.types.tool_usage_events import (
ToolUsageFinishedEvent,
ToolUsageStartedEvent,
)
from crewai.flow.flow import Flow, listen, or_, router, start
from crewai.flow.flow import Flow, StateProxy, listen, or_, router, start
from crewai.flow.types import FlowMethodName
from crewai.hooks.llm_hooks import (
get_after_llm_call_hooks,
get_before_llm_call_hooks,
@@ -225,7 +226,11 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
@messages.setter
def messages(self, value: list[LLMMessage]) -> None:
"""Delegate to state for ExecutorContext conformance."""
self._state.messages = value
if self._flow_initialized and hasattr(self, "_state_lock"):
with self._state_lock:
self._state.messages = value
else:
self._state.messages = value
@property
def ask_for_human_input(self) -> bool:
@@ -253,6 +258,22 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
raise RuntimeError("Agent loop did not produce a final answer")
return answer
async def _ainvoke_loop(self) -> AgentFinish:
"""Invoke the agent loop asynchronously and return the result.
Required by AsyncExecutorContext protocol.
"""
self._state.iterations = 0
self._state.is_finished = False
self._state.current_answer = None
await self.akickoff()
answer = self._state.current_answer
if not isinstance(answer, AgentFinish):
raise RuntimeError("Agent loop did not produce a final answer")
return answer
def _format_feedback_message(self, feedback: str) -> LLMMessage:
"""Format feedback as a message for the LLM.
@@ -353,6 +374,8 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
Flow initialization is deferred to prevent event emission during agent setup.
Returns the temporary state until invoke() is called.
"""
if self._flow_initialized and hasattr(self, "_state_lock"):
return StateProxy(self._state, self._state_lock) # type: ignore[return-value]
return self._state
@property
@@ -461,15 +484,14 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
raise
@listen("continue_reasoning_native")
def call_llm_native_tools(
self,
) -> Literal["native_tool_calls", "native_finished", "context_error"]:
def call_llm_native_tools(self) -> None:
"""Execute LLM call with native function calling.
Always calls the LLM so it can read reflection prompts and decide
whether to provide a final answer or request more tools.
Returns routing decision based on whether tool calls or final answer.
Note: This is a listener, not a router. The route_native_tool_result
router fires after this to determine the next step based on state.
"""
try:
# Clear pending tools - LLM will decide what to do next after reading
@@ -499,8 +521,7 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
if isinstance(answer, list) and answer and self._is_tool_call_list(answer):
# Store tool calls for sequential processing
self.state.pending_tool_calls = list(answer)
return "native_tool_calls"
return # Router will check pending_tool_calls
if isinstance(answer, BaseModel):
self.state.current_answer = AgentFinish(
@@ -510,7 +531,7 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
)
self._invoke_step_callback(self.state.current_answer)
self._append_message_to_state(answer.model_dump_json())
return "native_finished"
return # Router will check current_answer
# Text response - this is the final answer
if isinstance(answer, str):
@@ -521,8 +542,7 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
)
self._invoke_step_callback(self.state.current_answer)
self._append_message_to_state(answer)
return "native_finished"
return # Router will check current_answer
# Unexpected response type, treat as final answer
self.state.current_answer = AgentFinish(
@@ -532,13 +552,12 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
)
self._invoke_step_callback(self.state.current_answer)
self._append_message_to_state(str(answer))
return "native_finished"
# Router will check current_answer
except Exception as e:
if is_context_length_exceeded(e):
self._last_context_error = e
return "context_error"
return # Router will check _last_context_error
if e.__class__.__module__.startswith("litellm"):
raise e
handle_unknown_error(self._printer, e, verbose=self.agent.verbose)
@@ -551,6 +570,22 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
return "execute_tool"
return "agent_finished"
@router(call_llm_native_tools)
def route_native_tool_result(
self,
) -> Literal["native_tool_calls", "native_finished", "context_error"]:
"""Route based on LLM response for native tool calling.
Checks state set by call_llm_native_tools to determine next step.
This router is needed because only router return values trigger
downstream listeners.
"""
if self._last_context_error is not None:
return "context_error"
if self.state.pending_tool_calls:
return "native_tool_calls"
return "native_finished"
@listen("execute_tool")
def execute_tool_action(self) -> Literal["tool_completed", "tool_result_is_final"]:
"""Execute the tool action and handle the result."""
@@ -908,9 +943,11 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
self.state.iterations += 1
return "initialized"
@listen("initialized")
@listen(or_("initialized", "tool_completed", "native_tool_completed"))
def continue_iteration(self) -> Literal["check_iteration"]:
"""Bridge listener that connects iteration loop back to iteration check."""
if self._flow_initialized:
self._discard_or_listener(FlowMethodName("continue_iteration"))
return "check_iteration"
@router(or_(initialize_reasoning, continue_iteration))
@@ -1152,7 +1189,7 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
)
if self.state.ask_for_human_input:
formatted_answer = self._handle_human_feedback(formatted_answer)
formatted_answer = await self._ahandle_human_feedback(formatted_answer)
self._create_short_term_memory(formatted_answer)
self._create_long_term_memory(formatted_answer)
@@ -1369,6 +1406,20 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
provider = get_provider()
return provider.handle_feedback(formatted_answer, self)
async def _ahandle_human_feedback(
self, formatted_answer: AgentFinish
) -> AgentFinish:
"""Process human feedback asynchronously and refine answer.
Args:
formatted_answer: Initial agent result.
Returns:
Final answer after feedback.
"""
provider = get_provider()
return await provider.handle_feedback_async(formatted_answer, self)
def _is_training_mode(self) -> bool:
"""Check if training mode is active.

View File

@@ -7,7 +7,14 @@ for building event-driven workflows with conditional execution and routing.
from __future__ import annotations
import asyncio
from collections.abc import Callable, Sequence
from collections.abc import (
Callable,
ItemsView,
Iterator,
KeysView,
Sequence,
ValuesView,
)
from concurrent.futures import Future
import copy
import inspect
@@ -409,6 +416,132 @@ def and_(*conditions: str | FlowCondition | Callable[..., Any]) -> FlowCondition
return {"type": AND_CONDITION, "conditions": processed_conditions}
class LockedListProxy(Generic[T]):
"""Thread-safe proxy for list operations.
Wraps a list and uses a lock for all mutating operations.
"""
def __init__(self, lst: list[T], lock: threading.Lock) -> None:
self._list = lst
self._lock = lock
def append(self, item: T) -> None:
with self._lock:
self._list.append(item)
def extend(self, items: list[T]) -> None:
with self._lock:
self._list.extend(items)
def insert(self, index: int, item: T) -> None:
with self._lock:
self._list.insert(index, item)
def remove(self, item: T) -> None:
with self._lock:
self._list.remove(item)
def pop(self, index: int = -1) -> T:
with self._lock:
return self._list.pop(index)
def clear(self) -> None:
with self._lock:
self._list.clear()
def __setitem__(self, index: int, value: T) -> None:
with self._lock:
self._list[index] = value
def __delitem__(self, index: int) -> None:
with self._lock:
del self._list[index]
def __getitem__(self, index: int) -> T:
return self._list[index]
def __len__(self) -> int:
return len(self._list)
def __iter__(self) -> Iterator[T]:
return iter(self._list)
def __contains__(self, item: object) -> bool:
return item in self._list
def __repr__(self) -> str:
return repr(self._list)
def __bool__(self) -> bool:
return bool(self._list)
class LockedDictProxy(Generic[T]):
"""Thread-safe proxy for dict operations.
Wraps a dict and uses a lock for all mutating operations.
"""
def __init__(self, d: dict[str, T], lock: threading.Lock) -> None:
self._dict = d
self._lock = lock
def __setitem__(self, key: str, value: T) -> None:
with self._lock:
self._dict[key] = value
def __delitem__(self, key: str) -> None:
with self._lock:
del self._dict[key]
def pop(self, key: str, *default: T) -> T:
with self._lock:
return self._dict.pop(key, *default)
def update(self, other: dict[str, T]) -> None:
with self._lock:
self._dict.update(other)
def clear(self) -> None:
with self._lock:
self._dict.clear()
def setdefault(self, key: str, default: T) -> T:
with self._lock:
return self._dict.setdefault(key, default)
def __getitem__(self, key: str) -> T:
return self._dict[key]
def __len__(self) -> int:
return len(self._dict)
def __iter__(self) -> Iterator[str]:
return iter(self._dict)
def __contains__(self, key: object) -> bool:
return key in self._dict
def keys(self) -> KeysView[str]:
return self._dict.keys()
def values(self) -> ValuesView[T]:
return self._dict.values()
def items(self) -> ItemsView[str, T]:
return self._dict.items()
def get(self, key: str, default: T | None = None) -> T | None:
return self._dict.get(key, default)
def __repr__(self) -> str:
return repr(self._dict)
def __bool__(self) -> bool:
return bool(self._dict)
class StateProxy(Generic[T]):
"""Proxy that provides thread-safe access to flow state.
@@ -423,7 +556,13 @@ class StateProxy(Generic[T]):
object.__setattr__(self, "_proxy_lock", lock)
def __getattr__(self, name: str) -> Any:
return getattr(object.__getattribute__(self, "_proxy_state"), name)
value = getattr(object.__getattribute__(self, "_proxy_state"), name)
lock = object.__getattribute__(self, "_proxy_lock")
if isinstance(value, list):
return LockedListProxy(value, lock)
if isinstance(value, dict):
return LockedDictProxy(value, lock)
return value
def __setattr__(self, name: str, value: Any) -> None:
if name in ("_proxy_state", "_proxy_lock"):
@@ -1593,7 +1732,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
reset_emission_counter()
reset_last_event_id()
# Emit FlowStartedEvent and log the start of the flow.
if not self.suppress_flow_events:
future = crewai_event_bus.emit(
self,
@@ -1604,7 +1742,10 @@ class Flow(Generic[T], metaclass=FlowMeta):
),
)
if future:
self._event_futures.append(future)
try:
await asyncio.wrap_future(future)
except Exception:
logger.warning("FlowStartedEvent handler failed", exc_info=True)
self._log_flow_event(
f"Flow started with ID: {self.flow_id}", color="bold magenta"
)
@@ -1696,6 +1837,12 @@ class Flow(Generic[T], metaclass=FlowMeta):
final_output = self._method_outputs[-1] if self._method_outputs else None
if self._event_futures:
await asyncio.gather(
*[asyncio.wrap_future(f) for f in self._event_futures]
)
self._event_futures.clear()
if not self.suppress_flow_events:
future = crewai_event_bus.emit(
self,
@@ -1707,13 +1854,12 @@ class Flow(Generic[T], metaclass=FlowMeta):
),
)
if future:
self._event_futures.append(future)
if self._event_futures:
await asyncio.gather(
*[asyncio.wrap_future(f) for f in self._event_futures]
)
self._event_futures.clear()
try:
await asyncio.wrap_future(future)
except Exception:
logger.warning(
"FlowFinishedEvent handler failed", exc_info=True
)
if not self.suppress_flow_events:
trace_listener = TraceCollectionListener()
@@ -1788,40 +1934,14 @@ class Flow(Generic[T], metaclass=FlowMeta):
await self._execute_listeners(start_method_name, result, finished_event_id)
# Then execute listeners for the router result (e.g., "approved")
router_result_trigger = FlowMethodName(str(result))
listeners_for_result = self._find_triggered_methods(
router_result_trigger, router_only=False
listener_result = (
self.last_human_feedback
if self.last_human_feedback is not None
else result
)
await self._execute_listeners(
router_result_trigger, listener_result, finished_event_id
)
if listeners_for_result:
# Pass the HumanFeedbackResult if available
listener_result = (
self.last_human_feedback
if self.last_human_feedback is not None
else result
)
racing_group = self._get_racing_group_for_listeners(
listeners_for_result
)
if racing_group:
racing_members, _ = racing_group
other_listeners = [
name
for name in listeners_for_result
if name not in racing_members
]
await self._execute_racing_listeners(
racing_members,
other_listeners,
listener_result,
finished_event_id,
)
else:
tasks = [
self._execute_single_listener(
listener_name, listener_result, finished_event_id
)
for listener_name in listeners_for_result
]
await asyncio.gather(*tasks)
else:
await self._execute_listeners(start_method_name, result, finished_event_id)
@@ -2027,15 +2147,14 @@ class Flow(Generic[T], metaclass=FlowMeta):
router_input = router_result_to_feedback.get(
str(current_trigger), current_result
)
current_triggering_event_id = await self._execute_single_listener(
(
router_result,
current_triggering_event_id,
) = await self._execute_single_listener(
router_name, router_input, current_triggering_event_id
)
# After executing router, the router's result is the path
router_result = (
self._method_outputs[-1] if self._method_outputs else None
)
if router_result: # Only add non-None results
router_results.append(router_result)
router_results.append(FlowMethodName(str(router_result)))
# If this was a human_feedback router, map the outcome to the feedback
if self.last_human_feedback is not None:
router_result_to_feedback[str(router_result)] = (
@@ -2265,7 +2384,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
listener_name: FlowMethodName,
result: Any,
triggering_event_id: str | None = None,
) -> str | None:
) -> tuple[Any, str | None]:
"""Executes a single listener method with proper event handling.
This internal method manages the execution of an individual listener,
@@ -2278,8 +2397,9 @@ class Flow(Generic[T], metaclass=FlowMeta):
used for causal chain tracking.
Returns:
The event_id of the MethodExecutionFinishedEvent emitted by this listener,
or None if events are suppressed.
A tuple of (listener_result, event_id) where listener_result is the return
value of the listener method and event_id is the MethodExecutionFinishedEvent
id, or (None, None) if skipped during resumption.
Note:
- Inspects method signature to determine if it accepts the trigger result
@@ -2305,7 +2425,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
):
# This conditional start was executed, continue its chain
await self._execute_start_method(start_method_name)
return None
return (None, None)
# For cyclic flows, clear from completed to allow re-execution
self._completed_methods.discard(listener_name)
# Also clear from fired OR listeners for cyclic flows
@@ -2343,46 +2463,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
listener_name, listener_result, finished_event_id
)
# If this listener is also a router (e.g., has @human_feedback with emit),
# we need to trigger listeners for the router result as well
if listener_name in self._routers and listener_result is not None:
router_result_trigger = FlowMethodName(str(listener_result))
listeners_for_result = self._find_triggered_methods(
router_result_trigger, router_only=False
)
if listeners_for_result:
# Pass the HumanFeedbackResult if available
feedback_result = (
self.last_human_feedback
if self.last_human_feedback is not None
else listener_result
)
racing_group = self._get_racing_group_for_listeners(
listeners_for_result
)
if racing_group:
racing_members, _ = racing_group
other_listeners = [
name
for name in listeners_for_result
if name not in racing_members
]
await self._execute_racing_listeners(
racing_members,
other_listeners,
feedback_result,
finished_event_id,
)
else:
tasks = [
self._execute_single_listener(
name, feedback_result, finished_event_id
)
for name in listeners_for_result
]
await asyncio.gather(*tasks)
return finished_event_id
return (listener_result, finished_event_id)
except Exception as e:
# Don't log HumanFeedbackPending as an error - it's expected control flow

View File

@@ -31,6 +31,7 @@ from pydantic_core import PydanticCustomError
from typing_extensions import Self
from crewai.agents.agent_builder.base_agent import BaseAgent
from crewai.context import reset_current_task_id, set_current_task_id
from crewai.core.providers.content_processor import process_content
from crewai.events.event_bus import crewai_event_bus
from crewai.events.types.task_events import (
@@ -561,6 +562,7 @@ class Task(BaseModel):
tools: list[Any] | None,
) -> TaskOutput:
"""Run the core execution logic of the task asynchronously."""
task_id_token = set_current_task_id(str(self.id))
self._store_input_files()
try:
agent = agent or self.agent
@@ -648,6 +650,7 @@ class Task(BaseModel):
raise e # Re-raise the exception after emitting the event
finally:
clear_task_files(self.id)
reset_current_task_id(task_id_token)
def _execute_core(
self,
@@ -656,6 +659,7 @@ class Task(BaseModel):
tools: list[Any] | None,
) -> TaskOutput:
"""Run the core execution logic of the task."""
task_id_token = set_current_task_id(str(self.id))
self._store_input_files()
try:
agent = agent or self.agent
@@ -744,6 +748,7 @@ class Task(BaseModel):
raise e # Re-raise the exception after emitting the event
finally:
clear_task_files(self.id)
reset_current_task_id(task_id_token)
def _post_agent_execution(self, agent: BaseAgent) -> None:
pass

View File

@@ -1,37 +0,0 @@
"""Human-in-the-loop (HITL) type definitions.
This module provides type definitions for human-in-the-loop interactions
in crew executions.
"""
from typing import TypedDict
class HITLResumeInfo(TypedDict, total=False):
"""HITL resume information passed from flow to crew.
Attributes:
task_id: Unique identifier for the task.
crew_execution_id: Unique identifier for the crew execution.
task_key: Key identifying the specific task.
task_output: Output from the task before human intervention.
human_feedback: Feedback provided by the human.
previous_messages: History of messages in the conversation.
"""
task_id: str
crew_execution_id: str
task_key: str
task_output: str
human_feedback: str
previous_messages: list[dict[str, str]]
class CrewInputsWithHITL(TypedDict, total=False):
"""Crew inputs that may contain HITL resume information.
Attributes:
_hitl_resume: Optional HITL resume information for continuing execution.
"""
_hitl_resume: HITLResumeInfo

View File

@@ -832,7 +832,7 @@ def load_agent_from_repository(from_repository: str) -> dict[str, Any]:
client = PlusAPI(api_key=get_auth_token())
_print_current_organization()
response = client.get_agent(from_repository)
response = asyncio.run(client.get_agent(from_repository))
if response.status_code == 404:
raise AgentRepositoryError(
f"Agent {from_repository} does not exist, make sure the name is correct or the agent is available on your organization."

View File

@@ -606,9 +606,10 @@ def test_lite_agent_with_invalid_llm():
@patch.dict("os.environ", {"CREWAI_PLATFORM_INTEGRATION_TOKEN": "test_token"})
@patch("crewai_tools.tools.crewai_platform_tools.crewai_platform_action_tool.requests.post")
@patch("crewai_tools.tools.crewai_platform_tools.crewai_platform_tool_builder.requests.get")
@pytest.mark.vcr()
def test_agent_kickoff_with_platform_tools(mock_get):
def test_agent_kickoff_with_platform_tools(mock_get, mock_post):
"""Test that Agent.kickoff() properly integrates platform tools with LiteAgent"""
mock_response = Mock()
mock_response.raise_for_status.return_value = None
@@ -632,6 +633,15 @@ def test_agent_kickoff_with_platform_tools(mock_get):
}
mock_get.return_value = mock_response
# Mock the platform tool execution
mock_post_response = Mock()
mock_post_response.ok = True
mock_post_response.json.return_value = {
"success": True,
"issue_url": "https://github.com/test/repo/issues/1"
}
mock_post.return_value = mock_post_response
agent = Agent(
role="Test Agent",
goal="Test goal",

View File

@@ -1,98 +1,227 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test backstory\nYour personal goal is: Test goal\n\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: create_issue\nTool Arguments: {''title'': {''description'': ''Issue title'', ''type'': ''str''}, ''body'': {''description'': ''Issue body'', ''type'': ''Union[str, NoneType]''}}\nTool Description: Create a GitHub issue\nDetailed Parameter Structure:\nObject with properties:\n - title: Issue title (required)\n - body: Issue body (optional)\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [create_issue], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information
is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n```"}, {"role": "user", "content": "Create a GitHub issue"}], "model": "gpt-3.5-turbo", "stream": false}'
body: '{"messages":[{"role":"system","content":"You are Test Agent. Test backstory\nYour
personal goal is: Test goal"},{"role":"user","content":"\nCurrent Task: Create
a GitHub issue"}],"model":"gpt-3.5-turbo","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_issue","description":"Create
a GitHub issue","strict":true,"parameters":{"additionalProperties":false,"properties":{"title":{"description":"Issue
title","title":"Title","type":"string"},"body":{"default":null,"description":"Issue
body","title":"Body","type":"string"}},"required":["title","body"],"type":"object"}}}]}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- gzip, deflate
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1233'
- '596'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.109.1
x-stainless-arch:
- arm64
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.109.1
- 1.83.0
x-stainless-read-timeout:
- '600'
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
- 3.13.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-CULxKTEIB85AVItcEQ09z4Xi0JCID\",\n \"object\": \"chat.completion\",\n \"created\": 1761350274,\n \"model\": \"gpt-3.5-turbo-0125\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I will need more specific information to create a GitHub issue. Could you please provide more details such as the title and body of the issue you would like to create?\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 255,\n \"completion_tokens\": 33,\n \"total_tokens\": 288,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n \
\ }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": null\n}\n"
string: "{\n \"id\": \"chatcmpl-D6L3fqygkUIZ3bN4wvSpAhdaSk7MF\",\n \"object\":
\"chat.completion\",\n \"created\": 1770403287,\n \"model\": \"gpt-3.5-turbo-0125\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_RuWuYzjzgRL3byVGhLlPi0rq\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"create_issue\",\n
\ \"arguments\": \"{\\\"title\\\":\\\"Test issue\\\",\\\"body\\\":\\\"This
is a test issue created for testing purposes.\\\"}\"\n }\n }\n
\ ],\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 93,\n \"completion_tokens\":
28,\n \"total_tokens\": 121,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": null\n}\n"
headers:
CF-RAY:
- 993d6b4be9862379-SJC
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Fri, 24 Oct 2025 23:57:54 GMT
- Fri, 06 Feb 2026 18:41:28 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=WY9bgemMDI_hUYISAPlQ2a.DBGeZfM6AjVEa3SKNg1c-1761350274-1.0.1.1-K3Qm2cl6IlDAgmocoKZ8IMUTmue6Q81hH9stECprUq_SM8LF8rR9d1sHktvRCN3.jEM.twEuFFYDNpBnN8NBRJFZcea1yvpm8Uo0G_UhyDs; path=/; expires=Sat, 25-Oct-25 00:27:54 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
- _cfuvid=JklLS4i3hBGELpS9cz1KMpTbj72hCwP41LyXDSxWIv8-1761350274521-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
- SET-COOKIE-XXX
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- X-Request-ID
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
- OPENAI-ORG-XXX
openai-processing-ms:
- '487'
- '1406'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '526'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- '10000'
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- '50000000'
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- '9999'
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- '49999727'
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- 6ms
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- 0s
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- req_1708dc0928c64882aaa5bc2c168c140f
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
- request:
body: '{"messages":[{"role":"system","content":"You are Test Agent. Test backstory\nYour
personal goal is: Test goal"},{"role":"user","content":"\nCurrent Task: Create
a GitHub issue"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_RuWuYzjzgRL3byVGhLlPi0rq","type":"function","function":{"name":"create_issue","arguments":"{\"title\":\"Test
issue\",\"body\":\"This is a test issue created for testing purposes.\"}"}}]},{"role":"tool","tool_call_id":"call_RuWuYzjzgRL3byVGhLlPi0rq","name":"create_issue","content":"{\n \"success\":
true,\n \"issue_url\": \"https://github.com/test/repo/issues/1\"\n}"}],"model":"gpt-3.5-turbo","tool_choice":"auto","tools":[{"type":"function","function":{"name":"create_issue","description":"Create
a GitHub issue","strict":true,"parameters":{"additionalProperties":false,"properties":{"title":{"description":"Issue
title","title":"Title","type":"string"},"body":{"default":null,"description":"Issue
body","title":"Body","type":"string"}},"required":["title","body"],"type":"object"}}}]}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1028'
content-type:
- application/json
cookie:
- COOKIE-XXX
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.83.0
x-stainless-read-timeout:
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D6L3hfuBxk36LIb3ekD1IVwFD5VVL\",\n \"object\":
\"chat.completion\",\n \"created\": 1770403289,\n \"model\": \"gpt-3.5-turbo-0125\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I have successfully created a GitHub
issue for testing purposes. You can view the issue at this URL: [Test issue](https://github.com/test/repo/issues/1)\",\n
\ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
154,\n \"completion_tokens\": 36,\n \"total_tokens\": 190,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": null\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Fri, 06 Feb 2026 18:41:29 GMT
Server:
- cloudflare
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '888'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK

View File

@@ -1,400 +1,428 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Sports Analyst. You are an expert at gathering and organizing information. You carefully collect details and present them in a structured way.\nYour personal goal is: Gather information about the best soccer players\n\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your 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!"}, {"role": "user", "content": "Top 10 best players in the world?"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
body: '{"messages":[{"role":"system","content":"You are Sports Analyst. You are
an expert at gathering and organizing information. You carefully collect details
and present them in a structured way.\nYour personal goal is: Gather information
about the best soccer players"},{"role":"user","content":"\nCurrent Task: Top
10 best players in the world?\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '694'
- '404'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.78.0
x-stainless-arch:
- arm64
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.78.0
x-stainless-raw-response:
- 'true'
- 1.83.0
x-stainless-read-timeout:
- '600.0'
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
- 3.13.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-BgufUtDqGzvqPZx2NmkqqxdW4G8rQ\",\n \"object\": \"chat.completion\",\n \"created\": 1749567308,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer \\nFinal Answer: The top 10 best soccer players in the world, as of October 2023, can be identified based on their recent performances, skills, impact on games, and overall contributions to their teams. Here is the structured list:\\n\\n1. **Lionel Messi (Inter Miami CF)**\\n - Position: Forward\\n - Key Attributes: Dribbling, vision, goal-scoring ability.\\n - Achievements: Multiple Ballon d'Or winner, Copa America champion, World Cup champion (2022).\\n\\n2. **Kylian Mbappé (Paris Saint-Germain)**\\n - Position: Forward\\n - Key Attributes: Speed, technique, finishing.\\n - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple\
\ domestic cups.\\n\\n3. **Erling Haaland (Manchester City)**\\n - Position: Forward\\n - Key Attributes: Power, speed, goal-scoring instinct.\\n - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\\n\\n4. **Kevin De Bruyne (Manchester City)**\\n - Position: Midfielder\\n - Key Attributes: Passing, vision, creativity.\\n - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\\n\\n5. **Karim Benzema (Al-Ittihad)**\\n - Position: Forward\\n - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\\n - Achievements: 2022 Ballon d'Or winner, multiple Champions Leagues with Real Madrid.\\n\\n6. **Neymar Jr. (Al Hilal)**\\n - Position: Forward\\n - Key Attributes: Flair, dribbling, creativity.\\n - Achievements: Multiple domestic league titles, Champions League runner-up.\\n\\n7. **Robert Lewandowski (FC Barcelona)**\\n - Position: Forward\\n - Key Attributes: Finishing,\
\ positioning, aerial ability.\\n - Achievements: FIFA Best Men's Player, multiple Bundesliga titles, La Liga champion (2023).\\n\\n8. **Mohamed Salah (Liverpool)**\\n - Position: Forward\\n - Key Attributes: Speed, finishing, dribbling.\\n - Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\\n\\n9. **Vinícius Júnior (Real Madrid)**\\n - Position: Forward\\n - Key Attributes: Speed, dribbling, creativity.\\n - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\\n\\n10. **Luka Modrić (Real Madrid)**\\n - Position: Midfielder\\n - Key Attributes: Passing, vision, tactical intelligence.\\n - Achievements: Multiple Champions League titles, Ballon d'Or winner (2018).\\n\\nThis list is compiled based on their current form, past performances, and contributions to their respective teams in both domestic and international competitions. Player rankings can vary based on personal opinion and specific criteria used for\
\ evaluation, but these players have consistently been regarded as some of the best in the world as of October 2023.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 122,\n \"completion_tokens\": 643,\n \"total_tokens\": 765,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_34a54ae93c\"\n}\n"
string: "{\n \"id\": \"chatcmpl-D6L3hzoRVVEa07HZsM9wpi2RVRKQp\",\n \"object\":
\"chat.completion\",\n \"created\": 1770403289,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Here is a structured list of the top
10 best soccer players in the world as of 2024, based on recent performances,
awards, and overall impact on the game:\\n\\n1. **Kylian Mbapp\xE9** \\n
\ - Nationality: French \\n - Club: Paris Saint-Germain (PSG) \\n -
Position: Forward \\n - Key Highlights: Multiple Ligue 1 titles, World
Cup winner (2018), known for speed, dribbling, and scoring prowess.\\n\\n2.
**Erling Haaland** \\n - Nationality: Norwegian \\n - Club: Manchester
City \\n - Position: Striker \\n - Key Highlights: Premier League Golden
Boot winner, incredible goal-scoring record, physical presence, and finishing
skills.\\n\\n3. **Lionel Messi** \\n - Nationality: Argentine \\n -
Club: Inter Miami \\n - Position: Forward/Attacking Midfielder \\n -
Key Highlights: Seven Ballon d\u2019Or awards, World Cup winner (2022), exceptional
playmaking and dribbling ability.\\n\\n4. **Kevin De Bruyne** \\n - Nationality:
Belgian \\n - Club: Manchester City \\n - Position: Midfielder \\n
\ - Key Highlights: One of the best playmakers globally, assists leader,
consistent high-level performance in the Premier League.\\n\\n5. **Robert
Lewandowski** \\n - Nationality: Polish \\n - Club: FC Barcelona \\n
\ - Position: Striker \\n - Key Highlights: Exceptional goal-scoring record,
multiple Bundesliga top scorer awards, key figure in Bayern Munich\u2019s
dominance before transferring.\\n\\n6. **Karim Benzema** \\n - Nationality:
French \\n - Club: Al-Ittihad \\n - Position: Striker \\n - Key Highlights:
Ballon d\u2019Or winner (2022), excellent technical skills, leadership at
Real Madrid before recent transfer.\\n\\n7. **Mohamed Salah** \\n - Nationality:
Egyptian \\n - Club: Liverpool \\n - Position: Forward \\n - Key
Highlights: Premier League Golden Boot winner, known for speed, dribbling,
and goal-scoring consistency.\\n\\n8. **Vin\xEDcius J\xFAnior** \\n - Nationality:
Brazilian \\n - Club: Real Madrid \\n - Position: Winger \\n - Key
Highlights: Key player for Real Madrid, exceptional dribbling and pace, rising
star in world football.\\n\\n9. **Jude Bellingham** \\n - Nationality:
English \\n - Club: Real Madrid \\n - Position: Midfielder \\n -
Key Highlights: Young talent with maturity beyond years, influential midfielder
with great vision and work rate.\\n\\n10. **Thibaut Courtois** \\n - Nationality:
Belgian \\n - Club: Real Madrid \\n - Position: Goalkeeper \\n -
Key Highlights: One of the best goalkeepers globally, crucial performances
in La Liga and Champions League.\\n\\nThese rankings consider individual talent,
recent achievements, influence on matches, and overall contribution to club
and country.\",\n \"refusal\": null,\n \"annotations\": []\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 68,\n \"completion_tokens\":
621,\n \"total_tokens\": 689,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_75546bd1a7\"\n}\n"
headers:
CF-RAY:
- 94d9b5400dcd624b-GRU
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 10 Jun 2025 14:55:42 GMT
- Fri, 06 Feb 2026 18:41:40 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=8Yv8F0ZCFAo2lf.qoqxao70yxyjVvIV90zQqVF6bVzQ-1749567342-1.0.1.1-fZgnv3RDfunvCO1koxwwFJrHnxSx_rwS_FHvQ6xxDPpKHwYr7dTqIQLZrNgSX5twGyK4F22rUmkuiS6KMVogcinChk8lmHtJBTUVTFjr2KU; path=/; expires=Tue, 10-Jun-25 15:25:42 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
- _cfuvid=wzh8YnmXvLq1G0RcIVijtzboQtCZyIe2uZiochkBLqE-1749567342267-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
- SET-COOKIE-XXX
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- X-Request-ID
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
- OPENAI-ORG-XXX
openai-processing-ms:
- '33288'
- '10634'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-envoy-upstream-service-time:
- '33292'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- '30000'
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- '150000000'
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- '29999'
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- '149999859'
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- 2ms
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- 0s
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- req_6a587ea22edef774ecdada790a320cab
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Sports Analyst. You are an expert at gathering and organizing information. You carefully collect details and present them in a structured way.\nYour personal goal is: Gather information about the best soccer players\n\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your 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!"}, {"role": "user", "content": "Top 10 best players in the world?"}, {"role": "assistant", "content": "Thought: I now can give a great answer \nFinal Answer: The top 10 best soccer players in the world, as of October 2023, can be identified based on their recent performances, skills, impact on games, and overall contributions to their teams. Here is the structured list:\n\n1. **Lionel Messi (Inter Miami CF)**\n -
Position: Forward\n - Key Attributes: Dribbling, vision, goal-scoring ability.\n - Achievements: Multiple Ballon d''Or winner, Copa America champion, World Cup champion (2022).\n\n2. **Kylian Mbapp\u00e9 (Paris Saint-Germain)**\n - Position: Forward\n - Key Attributes: Speed, technique, finishing.\n - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple domestic cups.\n\n3. **Erling Haaland (Manchester City)**\n - Position: Forward\n - Key Attributes: Power, speed, goal-scoring instinct.\n - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\n\n4. **Kevin De Bruyne (Manchester City)**\n - Position: Midfielder\n - Key Attributes: Passing, vision, creativity.\n - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\n\n5. **Karim Benzema (Al-Ittihad)**\n - Position: Forward\n - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\n - Achievements:
2022 Ballon d''Or winner, multiple Champions Leagues with Real Madrid.\n\n6. **Neymar Jr. (Al Hilal)**\n - Position: Forward\n - Key Attributes: Flair, dribbling, creativity.\n - Achievements: Multiple domestic league titles, Champions League runner-up.\n\n7. **Robert Lewandowski (FC Barcelona)**\n - Position: Forward\n - Key Attributes: Finishing, positioning, aerial ability.\n - Achievements: FIFA Best Men''s Player, multiple Bundesliga titles, La Liga champion (2023).\n\n8. **Mohamed Salah (Liverpool)**\n - Position: Forward\n - Key Attributes: Speed, finishing, dribbling.\n - Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\n\n9. **Vin\u00edcius J\u00fanior (Real Madrid)**\n - Position: Forward\n - Key Attributes: Speed, dribbling, creativity.\n - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\n\n10. **Luka Modri\u0107 (Real Madrid)**\n - Position: Midfielder\n - Key Attributes: Passing, vision,
tactical intelligence.\n - Achievements: Multiple Champions League titles, Ballon d''Or winner (2018).\n\nThis list is compiled based on their current form, past performances, and contributions to their respective teams in both domestic and international competitions. Player rankings can vary based on personal opinion and specific criteria used for evaluation, but these players have consistently been regarded as some of the best in the world as of October 2023."}, {"role": "user", "content": "You are not allowed to include Brazilian players"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
body: '{"messages":[{"role":"system","content":"You are Sports Analyst. You are
an expert at gathering and organizing information. You carefully collect details
and present them in a structured way.\nYour personal goal is: Gather information
about the best soccer players"},{"role":"user","content":"\nCurrent Task: Top
10 best players in the world?\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '3594'
- '404'
content-type:
- application/json
cookie:
- __cf_bm=8Yv8F0ZCFAo2lf.qoqxao70yxyjVvIV90zQqVF6bVzQ-1749567342-1.0.1.1-fZgnv3RDfunvCO1koxwwFJrHnxSx_rwS_FHvQ6xxDPpKHwYr7dTqIQLZrNgSX5twGyK4F22rUmkuiS6KMVogcinChk8lmHtJBTUVTFjr2KU; _cfuvid=wzh8YnmXvLq1G0RcIVijtzboQtCZyIe2uZiochkBLqE-1749567342267-0.0.1.1-604800000
- COOKIE-XXX
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.78.0
x-stainless-arch:
- arm64
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.78.0
x-stainless-raw-response:
- 'true'
- 1.83.0
x-stainless-read-timeout:
- '600.0'
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
- 3.13.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-BgugJkCDtB2EfvAMiIFK0reeLKFBl\",\n \"object\": \"chat.completion\",\n \"created\": 1749567359,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer \\nFinal Answer: Here is an updated list of the top 10 best soccer players in the world as of October 2023, excluding Brazilian players:\\n\\n1. **Lionel Messi (Inter Miami CF)**\\n - Position: Forward\\n - Key Attributes: Dribbling, vision, goal-scoring ability.\\n - Achievements: Multiple Ballon d'Or winner, Copa America champion, World Cup champion (2022).\\n\\n2. **Kylian Mbappé (Paris Saint-Germain)**\\n - Position: Forward\\n - Key Attributes: Speed, technique, finishing.\\n - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple domestic cups.\\n\\n3. **Erling Haaland (Manchester City)**\\n - Position: Forward\\\
n - Key Attributes: Power, speed, goal-scoring instinct.\\n - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\\n\\n4. **Kevin De Bruyne (Manchester City)**\\n - Position: Midfielder\\n - Key Attributes: Passing, vision, creativity.\\n - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\\n\\n5. **Karim Benzema (Al-Ittihad)**\\n - Position: Forward\\n - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\\n - Achievements: 2022 Ballon d'Or winner, multiple Champions Leagues with Real Madrid.\\n\\n6. **Robert Lewandowski (FC Barcelona)**\\n - Position: Forward\\n - Key Attributes: Finishing, positioning, aerial ability.\\n - Achievements: FIFA Best Men's Player, multiple Bundesliga titles, La Liga champion (2023).\\n\\n7. **Mohamed Salah (Liverpool)**\\n - Position: Forward\\n - Key Attributes: Speed, finishing, dribbling.\\n - Achievements: Premier League\
\ champion, FA Cup, UEFA Champions League winner.\\n\\n8. **Vinícius Júnior (Real Madrid)**\\n - Position: Forward\\n - Key Attributes: Speed, dribbling, creativity.\\n - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\\n\\n9. **Luka Modrić (Real Madrid)**\\n - Position: Midfielder\\n - Key Attributes: Passing, vision, tactical intelligence.\\n - Achievements: Multiple Champions League titles, Ballon d'Or winner (2018).\\n\\n10. **Harry Kane (Bayern Munich)**\\n - Position: Forward\\n - Key Attributes: Goal-scoring, technique, playmaking.\\n - Achievements: Golden Boot winner, Premier League titles, UEFA European Championship runner-up.\\n\\nThis list has been adjusted to exclude Brazilian players and focuses on those who have made significant impacts in their clubs and on the international stage as of October 2023. Each player is recognized for their exceptional skills, performances, and achievements.\",\n \"refusal\": null,\n\
\ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 781,\n \"completion_tokens\": 610,\n \"total_tokens\": 1391,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_34a54ae93c\"\n}\n"
string: "{\n \"id\": \"chatcmpl-D6L3sn9nSnGGOMKrS88avliVF7XTv\",\n \"object\":
\"chat.completion\",\n \"created\": 1770403300,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Certainly! Here's a structured list
of the top 10 best soccer players in the world as of 2024, considering their
performance, skills, achievements, and impact in recent seasons:\\n\\n###
Top 10 Best Soccer Players in the World (2024)\\n\\n| Rank | Player Name |
Nationality | Club (2023/24 Season) | Position | Key Attributes
\ | Recent Achievements |\\n|-------|---------------------|-------------|----------------------------|------------------|---------------------------------|------------------------------------|\\n|
1 | Lionel Messi | Argentina | Paris Saint-Germain (PSG) |
Forward/Playmaker| Dribbling, Vision, Free kicks | 2023 World Cup Golden
Ball, Club Successes |\\n| 2 | Kylian Mbapp\xE9 | France |
Paris Saint-Germain (PSG) | Forward | Speed, Finishing, Dribbling
\ | Ligue 1 Top Scorer, World Cup Winner 2018|\\n| 3 | Erling Haaland
\ | Norway | Manchester City | Striker | Strength,
Finishing, Positioning| Premier League Golden Boot, Champions League Impact|\\n|
4 | Kevin De Bruyne | Belgium | Manchester City |
Midfielder | Passing, Vision, Creativity | Premier League Titles,
Key Playmaker|\\n| 5 | Robert Lewandowski | Poland | FC Barcelona
\ | Striker | Finishing, Positioning, Composure| La
Liga Top Scorer, Consistent Scorer|\\n| 6 | Neymar Jr. | Brazil
\ | Al-Hilal | Forward/Winger | Dribbling, Creativity,
Flair | Copa America Titles, Club Success |\\n| 7 | Mohamed Salah |
Egypt | Liverpool | Forward/Winger | Pace, Finishing,
Work Rate | Premier League Golden Boot, Champions League Winner|\\n|
8 | Vin\xEDcius Jr. | Brazil | Real Madrid |
Winger | Speed, Dribbling, Crossing | La Liga Titles, UEFA Champions
League Winner|\\n| 9 | Luka Modri\u0107 | Croatia | Real Madrid
\ | Midfielder | Passing, Control, Experience | Ballon
d\u2019Or 2018, Multiple Champions League Titles|\\n| 10 | Karim Benzema
\ | France | Al-Ittihad | Striker | Finishing,
Link-up Play, Movements| Ballon d\u2019Or 2022, UEFA Champions League Top
Scorer |\\n\\n### Notes:\\n- The rankings reflect a combination of individual
skill, recent performance, consistency, and influence on the game.\\n- Players\u2019
clubs are based on the 2023/24 season affiliations.\\n- Achievements highlight
recent titles, awards, or standout contributions.\\n\\nIf you would like me
to focus on specific leagues, historical players, or emerging talents, just
let me know!\",\n \"refusal\": null,\n \"annotations\": []\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 68,\n \"completion_tokens\":
605,\n \"total_tokens\": 673,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_75546bd1a7\"\n}\n"
headers:
CF-RAY:
- 94d9b6782db84d3b-GRU
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 10 Jun 2025 14:56:30 GMT
- Fri, 06 Feb 2026 18:41:49 GMT
Server:
- cloudflare
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- X-Request-ID
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
- OPENAI-ORG-XXX
openai-processing-ms:
- '31484'
- '9044'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-envoy-upstream-service-time:
- '31490'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- '30000'
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- '150000000'
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- '29999'
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- '149999166'
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- 2ms
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- 0s
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- req_aa737cf40bb76af9f458bfd35f7a77a1
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Sports Analyst. You are an expert at gathering and organizing information. You carefully collect details and present them in a structured way.\nYour personal goal is: Gather information about the best soccer players\n\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your 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!"}, {"role": "user", "content": "Top 10 best players in the world?"}, {"role": "assistant", "content": "Thought: I now can give a great answer \nFinal Answer: The top 10 best soccer players in the world, as of October 2023, can be identified based on their recent performances, skills, impact on games, and overall contributions to their teams. Here is the structured list:\n\n1. **Lionel Messi (Inter Miami CF)**\n -
Position: Forward\n - Key Attributes: Dribbling, vision, goal-scoring ability.\n - Achievements: Multiple Ballon d''Or winner, Copa America champion, World Cup champion (2022).\n\n2. **Kylian Mbapp\u00e9 (Paris Saint-Germain)**\n - Position: Forward\n - Key Attributes: Speed, technique, finishing.\n - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple domestic cups.\n\n3. **Erling Haaland (Manchester City)**\n - Position: Forward\n - Key Attributes: Power, speed, goal-scoring instinct.\n - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\n\n4. **Kevin De Bruyne (Manchester City)**\n - Position: Midfielder\n - Key Attributes: Passing, vision, creativity.\n - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\n\n5. **Karim Benzema (Al-Ittihad)**\n - Position: Forward\n - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\n - Achievements:
2022 Ballon d''Or winner, multiple Champions Leagues with Real Madrid.\n\n6. **Neymar Jr. (Al Hilal)**\n - Position: Forward\n - Key Attributes: Flair, dribbling, creativity.\n - Achievements: Multiple domestic league titles, Champions League runner-up.\n\n7. **Robert Lewandowski (FC Barcelona)**\n - Position: Forward\n - Key Attributes: Finishing, positioning, aerial ability.\n - Achievements: FIFA Best Men''s Player, multiple Bundesliga titles, La Liga champion (2023).\n\n8. **Mohamed Salah (Liverpool)**\n - Position: Forward\n - Key Attributes: Speed, finishing, dribbling.\n - Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\n\n9. **Vin\u00edcius J\u00fanior (Real Madrid)**\n - Position: Forward\n - Key Attributes: Speed, dribbling, creativity.\n - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\n\n10. **Luka Modri\u0107 (Real Madrid)**\n - Position: Midfielder\n - Key Attributes: Passing, vision,
tactical intelligence.\n - Achievements: Multiple Champions League titles, Ballon d''Or winner (2018).\n\nThis list is compiled based on their current form, past performances, and contributions to their respective teams in both domestic and international competitions. Player rankings can vary based on personal opinion and specific criteria used for evaluation, but these players have consistently been regarded as some of the best in the world as of October 2023."}, {"role": "user", "content": "You are not allowed to include Brazilian players"}, {"role": "assistant", "content": "Thought: I now can give a great answer \nFinal Answer: Here is an updated list of the top 10 best soccer players in the world as of October 2023, excluding Brazilian players:\n\n1. **Lionel Messi (Inter Miami CF)**\n - Position: Forward\n - Key Attributes: Dribbling, vision, goal-scoring ability.\n - Achievements: Multiple Ballon d''Or winner, Copa America champion, World Cup champion (2022).\n\n2.
**Kylian Mbapp\u00e9 (Paris Saint-Germain)**\n - Position: Forward\n - Key Attributes: Speed, technique, finishing.\n - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple domestic cups.\n\n3. **Erling Haaland (Manchester City)**\n - Position: Forward\n - Key Attributes: Power, speed, goal-scoring instinct.\n - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\n\n4. **Kevin De Bruyne (Manchester City)**\n - Position: Midfielder\n - Key Attributes: Passing, vision, creativity.\n - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\n\n5. **Karim Benzema (Al-Ittihad)**\n - Position: Forward\n - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\n - Achievements: 2022 Ballon d''Or winner, multiple Champions Leagues with Real Madrid.\n\n6. **Robert Lewandowski (FC Barcelona)**\n - Position: Forward\n - Key Attributes: Finishing, positioning,
aerial ability.\n - Achievements: FIFA Best Men''s Player, multiple Bundesliga titles, La Liga champion (2023).\n\n7. **Mohamed Salah (Liverpool)**\n - Position: Forward\n - Key Attributes: Speed, finishing, dribbling.\n - Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\n\n8. **Vin\u00edcius J\u00fanior (Real Madrid)**\n - Position: Forward\n - Key Attributes: Speed, dribbling, creativity.\n - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\n\n9. **Luka Modri\u0107 (Real Madrid)**\n - Position: Midfielder\n - Key Attributes: Passing, vision, tactical intelligence.\n - Achievements: Multiple Champions League titles, Ballon d''Or winner (2018).\n\n10. **Harry Kane (Bayern Munich)**\n - Position: Forward\n - Key Attributes: Goal-scoring, technique, playmaking.\n - Achievements: Golden Boot winner, Premier League titles, UEFA European Championship runner-up.\n\nThis list has been adjusted to exclude Brazilian
players and focuses on those who have made significant impacts in their clubs and on the international stage as of October 2023. Each player is recognized for their exceptional skills, performances, and achievements."}, {"role": "user", "content": "You are not allowed to include Brazilian players"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
body: '{"messages":[{"role":"system","content":"You are Sports Analyst. You are
an expert at gathering and organizing information. You carefully collect details
and present them in a structured way.\nYour personal goal is: Gather information
about the best soccer players"},{"role":"user","content":"\nCurrent Task: Top
10 best players in the world?\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '6337'
- '404'
content-type:
- application/json
cookie:
- __cf_bm=8Yv8F0ZCFAo2lf.qoqxao70yxyjVvIV90zQqVF6bVzQ-1749567342-1.0.1.1-fZgnv3RDfunvCO1koxwwFJrHnxSx_rwS_FHvQ6xxDPpKHwYr7dTqIQLZrNgSX5twGyK4F22rUmkuiS6KMVogcinChk8lmHtJBTUVTFjr2KU; _cfuvid=wzh8YnmXvLq1G0RcIVijtzboQtCZyIe2uZiochkBLqE-1749567342267-0.0.1.1-604800000
- COOKIE-XXX
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.78.0
x-stainless-arch:
- arm64
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.78.0
x-stainless-raw-response:
- 'true'
- 1.83.0
x-stainless-read-timeout:
- '600.0'
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
- 3.13.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-BgugsAmyI50uQ6SpCp89ZZY4eD1Pz\",\n \"object\": \"chat.completion\",\n \"created\": 1749567394,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer \\nFinal Answer: Here is the revised list of the top 10 best soccer players in the world as of October 2023, explicitly excluding Brazilian players:\\n\\n1. **Lionel Messi (Inter Miami CF)**\\n - Position: Forward\\n - Key Attributes: Dribbling, vision, goal-scoring ability.\\n - Achievements: Multiple Ballon d'Or winner, Copa America champion, World Cup champion (2022).\\n\\n2. **Kylian Mbappé (Paris Saint-Germain)**\\n - Position: Forward\\n - Key Attributes: Speed, technique, finishing.\\n - Achievements: FIFA World Cup champion (2018), multiple Ligue 1 titles, and various domestic cups.\\n\\n3. **Erling Haaland (Manchester City)**\\n\
\ - Position: Forward\\n - Key Attributes: Power, speed, goal-scoring instinct.\\n - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\\n\\n4. **Kevin De Bruyne (Manchester City)**\\n - Position: Midfielder\\n - Key Attributes: Passing, vision, creativity.\\n - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\\n\\n5. **Karim Benzema (Al-Ittihad)**\\n - Position: Forward\\n - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\\n - Achievements: 2022 Ballon d'Or winner, multiple Champions Leagues with Real Madrid.\\n\\n6. **Robert Lewandowski (FC Barcelona)**\\n - Position: Forward\\n - Key Attributes: Finishing, positioning, aerial ability.\\n - Achievements: FIFA Best Men's Player, multiple Bundesliga titles, La Liga champion (2023).\\n\\n7. **Mohamed Salah (Liverpool)**\\n - Position: Forward\\n - Key Attributes: Speed, finishing, dribbling.\\n -\
\ Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\\n\\n8. **Luka Modrić (Real Madrid)**\\n - Position: Midfielder\\n - Key Attributes: Passing, vision, tactical intelligence.\\n - Achievements: Multiple Champions League titles, Ballon d'Or winner (2018).\\n\\n9. **Harry Kane (Bayern Munich)**\\n - Position: Forward\\n - Key Attributes: Goal-scoring, technique, playmaking.\\n - Achievements: Golden Boot winner, Premier League titles, UEFA European Championship runner-up.\\n\\n10. **Rodri (Manchester City)**\\n - Position: Midfielder\\n - Key Attributes: Defensive skills, passing, positional awareness.\\n - Achievements: Premier League titles, UEFA Champions League winner (2023).\\n\\nThis list is curated while adhering to the restriction of excluding Brazilian players. Each player included has demonstrated exceptional skills and remarkable performances, solidifying their status as some of the best in the world as of October 2023.\"\
,\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 1407,\n \"completion_tokens\": 605,\n \"total_tokens\": 2012,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_62a23a81ef\"\n}\n"
string: "{\n \"id\": \"chatcmpl-D6L4102eMwTEPeHxfyN9Kh7rjBoX6\",\n \"object\":
\"chat.completion\",\n \"created\": 1770403309,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Certainly! Here is a list of the top
10 best soccer players in the world as of 2024, considering their recent performances,
skills, impact, and accolades:\\n\\n1. **Lionel Messi** \\n - Nationality:
Argentine \\n - Position: Forward \\n - Key Achievements: 7 Ballon d'Or
awards, led Argentina to 2021 Copa Am\xE9rica victory and 2022 FIFA World
Cup triumph, exceptional dribbling and playmaking skills.\\n\\n2. **Kylian
Mbapp\xE9** \\n - Nationality: French \\n - Position: Forward \\n -
Key Achievements: FIFA World Cup winner (2018), multiple Ligue 1 titles, known
for incredible speed, finishing, and consistency.\\n\\n3. **Erling Haaland**
\ \\n - Nationality: Norwegian \\n - Position: Striker \\n - Key Achievements:
Premier League Golden Boot winner (2022-23), prolific goal scorer, physical
presence, and finishing ability.\\n\\n4. **Karim Benzema** \\n - Nationality:
French \\n - Position: Forward \\n - Key Achievements: 2022 Ballon d'Or
winner, key player for Real Madrid\u2019s recent Champions League victories,
excellent technical skills and leadership.\\n\\n5. **Kevin De Bruyne** \\n
\ - Nationality: Belgian \\n - Position: Midfielder \\n - Key Achievements:
Premier League playmaker, known for vision, passing accuracy, and creativity.\\n\\n6.
**Robert Lewandowski** \\n - Nationality: Polish \\n - Position: Striker
\ \\n - Key Achievements: Multiple Bundesliga top scorer titles, consistent
goal scorer, known for positioning and finishing.\\n\\n7. **Neymar Jr.** \\n
\ - Nationality: Brazilian \\n - Position: Forward \\n - Key Achievements:
Exceptional dribbling, creativity, and flair; multiple domestic titles and
Copa Libertadores winner.\\n\\n8. **Mohamed Salah** \\n - Nationality:
Egyptian \\n - Position: Forward \\n - Key Achievements: Premier League
Golden Boot, consistent goal scoring with Liverpool, known for speed and finishing.\\n\\n9.
**Luka Modri\u0107** \\n - Nationality: Croatian \\n - Position: Midfielder
\ \\n - Key Achievements: 2018 Ballon d\u2019Or winner, pivotal midfield
maestro, excellent passing and control.\\n\\n10. **Thibaut Courtois** \\n
\ - Nationality: Belgian \\n - Position: Goalkeeper \\n - Key Achievements:
Exceptional shot-stopper, key player in Real Madrid's recent successes.\\n\\nThis
list includes a blend of forwards, midfielders, and a goalkeeper, showcasing
the best talents in various positions worldwide. The rankings may vary slightly
depending on current form and opinions, but these players consistently rank
among the best globally.\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 68,\n \"completion_tokens\":
575,\n \"total_tokens\": 643,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_75546bd1a7\"\n}\n"
headers:
CF-RAY:
- 94d9b7561f204d3b-GRU
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 10 Jun 2025 14:56:46 GMT
- Fri, 06 Feb 2026 18:41:57 GMT
Server:
- cloudflare
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- X-Request-ID
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
- OPENAI-ORG-XXX
openai-processing-ms:
- '12189'
- '7948'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-envoy-upstream-service-time:
- '12193'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- '30000'
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- '150000000'
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- '29999'
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- '149998513'
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- 2ms
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- 0s
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- req_1098f5a5384f4a26aecf0c9e4e4d1fc0
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Sports Analyst. You are an expert at gathering and organizing information. You carefully collect details and present them in a structured way.\nYour personal goal is: Gather information about the best soccer players\n\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your 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!"}, {"role": "user", "content": "Top 10 best players in the world?"}, {"role": "assistant", "content": "Thought: I now can give a great answer \nFinal Answer: The top 10 best soccer players in the world, as of October 2023, can be identified based on their recent performances, skills, impact on games, and overall contributions to their teams. Here is the structured list:\n\n1. **Lionel Messi (Inter Miami CF)**\n -
Position: Forward\n - Key Attributes: Dribbling, vision, goal-scoring ability.\n - Achievements: Multiple Ballon d''Or winner, Copa America champion, World Cup champion (2022).\n\n2. **Kylian Mbapp\u00e9 (Paris Saint-Germain)**\n - Position: Forward\n - Key Attributes: Speed, technique, finishing.\n - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple domestic cups.\n\n3. **Erling Haaland (Manchester City)**\n - Position: Forward\n - Key Attributes: Power, speed, goal-scoring instinct.\n - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\n\n4. **Kevin De Bruyne (Manchester City)**\n - Position: Midfielder\n - Key Attributes: Passing, vision, creativity.\n - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\n\n5. **Karim Benzema (Al-Ittihad)**\n - Position: Forward\n - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\n - Achievements:
2022 Ballon d''Or winner, multiple Champions Leagues with Real Madrid.\n\n6. **Neymar Jr. (Al Hilal)**\n - Position: Forward\n - Key Attributes: Flair, dribbling, creativity.\n - Achievements: Multiple domestic league titles, Champions League runner-up.\n\n7. **Robert Lewandowski (FC Barcelona)**\n - Position: Forward\n - Key Attributes: Finishing, positioning, aerial ability.\n - Achievements: FIFA Best Men''s Player, multiple Bundesliga titles, La Liga champion (2023).\n\n8. **Mohamed Salah (Liverpool)**\n - Position: Forward\n - Key Attributes: Speed, finishing, dribbling.\n - Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\n\n9. **Vin\u00edcius J\u00fanior (Real Madrid)**\n - Position: Forward\n - Key Attributes: Speed, dribbling, creativity.\n - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\n\n10. **Luka Modri\u0107 (Real Madrid)**\n - Position: Midfielder\n - Key Attributes: Passing, vision,
tactical intelligence.\n - Achievements: Multiple Champions League titles, Ballon d''Or winner (2018).\n\nThis list is compiled based on their current form, past performances, and contributions to their respective teams in both domestic and international competitions. Player rankings can vary based on personal opinion and specific criteria used for evaluation, but these players have consistently been regarded as some of the best in the world as of October 2023."}, {"role": "user", "content": "You are not allowed to include Brazilian players"}, {"role": "assistant", "content": "Thought: I now can give a great answer \nFinal Answer: Here is an updated list of the top 10 best soccer players in the world as of October 2023, excluding Brazilian players:\n\n1. **Lionel Messi (Inter Miami CF)**\n - Position: Forward\n - Key Attributes: Dribbling, vision, goal-scoring ability.\n - Achievements: Multiple Ballon d''Or winner, Copa America champion, World Cup champion (2022).\n\n2.
**Kylian Mbapp\u00e9 (Paris Saint-Germain)**\n - Position: Forward\n - Key Attributes: Speed, technique, finishing.\n - Achievements: FIFA World Cup champion (2018), Ligue 1 titles, multiple domestic cups.\n\n3. **Erling Haaland (Manchester City)**\n - Position: Forward\n - Key Attributes: Power, speed, goal-scoring instinct.\n - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\n\n4. **Kevin De Bruyne (Manchester City)**\n - Position: Midfielder\n - Key Attributes: Passing, vision, creativity.\n - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\n\n5. **Karim Benzema (Al-Ittihad)**\n - Position: Forward\n - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\n - Achievements: 2022 Ballon d''Or winner, multiple Champions Leagues with Real Madrid.\n\n6. **Robert Lewandowski (FC Barcelona)**\n - Position: Forward\n - Key Attributes: Finishing, positioning,
aerial ability.\n - Achievements: FIFA Best Men''s Player, multiple Bundesliga titles, La Liga champion (2023).\n\n7. **Mohamed Salah (Liverpool)**\n - Position: Forward\n - Key Attributes: Speed, finishing, dribbling.\n - Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\n\n8. **Vin\u00edcius J\u00fanior (Real Madrid)**\n - Position: Forward\n - Key Attributes: Speed, dribbling, creativity.\n - Achievements: UEFA Champions League winner (2022), La Liga champion (2023).\n\n9. **Luka Modri\u0107 (Real Madrid)**\n - Position: Midfielder\n - Key Attributes: Passing, vision, tactical intelligence.\n - Achievements: Multiple Champions League titles, Ballon d''Or winner (2018).\n\n10. **Harry Kane (Bayern Munich)**\n - Position: Forward\n - Key Attributes: Goal-scoring, technique, playmaking.\n - Achievements: Golden Boot winner, Premier League titles, UEFA European Championship runner-up.\n\nThis list has been adjusted to exclude Brazilian
players and focuses on those who have made significant impacts in their clubs and on the international stage as of October 2023. Each player is recognized for their exceptional skills, performances, and achievements."}, {"role": "user", "content": "You are not allowed to include Brazilian players"}, {"role": "assistant", "content": "Thought: I now can give a great answer \nFinal Answer: Here is the revised list of the top 10 best soccer players in the world as of October 2023, explicitly excluding Brazilian players:\n\n1. **Lionel Messi (Inter Miami CF)**\n - Position: Forward\n - Key Attributes: Dribbling, vision, goal-scoring ability.\n - Achievements: Multiple Ballon d''Or winner, Copa America champion, World Cup champion (2022).\n\n2. **Kylian Mbapp\u00e9 (Paris Saint-Germain)**\n - Position: Forward\n - Key Attributes: Speed, technique, finishing.\n - Achievements: FIFA World Cup champion (2018), multiple Ligue 1 titles, and various domestic cups.\n\n3. **Erling Haaland
(Manchester City)**\n - Position: Forward\n - Key Attributes: Power, speed, goal-scoring instinct.\n - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\n\n4. **Kevin De Bruyne (Manchester City)**\n - Position: Midfielder\n - Key Attributes: Passing, vision, creativity.\n - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\n\n5. **Karim Benzema (Al-Ittihad)**\n - Position: Forward\n - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\n - Achievements: 2022 Ballon d''Or winner, multiple Champions Leagues with Real Madrid.\n\n6. **Robert Lewandowski (FC Barcelona)**\n - Position: Forward\n - Key Attributes: Finishing, positioning, aerial ability.\n - Achievements: FIFA Best Men''s Player, multiple Bundesliga titles, La Liga champion (2023).\n\n7. **Mohamed Salah (Liverpool)**\n - Position: Forward\n - Key Attributes: Speed, finishing, dribbling.\n - Achievements:
Premier League champion, FA Cup, UEFA Champions League winner.\n\n8. **Luka Modri\u0107 (Real Madrid)**\n - Position: Midfielder\n - Key Attributes: Passing, vision, tactical intelligence.\n - Achievements: Multiple Champions League titles, Ballon d''Or winner (2018).\n\n9. **Harry Kane (Bayern Munich)**\n - Position: Forward\n - Key Attributes: Goal-scoring, technique, playmaking.\n - Achievements: Golden Boot winner, Premier League titles, UEFA European Championship runner-up.\n\n10. **Rodri (Manchester City)**\n - Position: Midfielder\n - Key Attributes: Defensive skills, passing, positional awareness.\n - Achievements: Premier League titles, UEFA Champions League winner (2023).\n\nThis list is curated while adhering to the restriction of excluding Brazilian players. Each player included has demonstrated exceptional skills and remarkable performances, solidifying their status as some of the best in the world as of October 2023."}, {"role": "user", "content":
"You are not allowed to include Brazilian players"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '9093'
content-type:
- application/json
cookie:
- __cf_bm=8Yv8F0ZCFAo2lf.qoqxao70yxyjVvIV90zQqVF6bVzQ-1749567342-1.0.1.1-fZgnv3RDfunvCO1koxwwFJrHnxSx_rwS_FHvQ6xxDPpKHwYr7dTqIQLZrNgSX5twGyK4F22rUmkuiS6KMVogcinChk8lmHtJBTUVTFjr2KU; _cfuvid=wzh8YnmXvLq1G0RcIVijtzboQtCZyIe2uZiochkBLqE-1749567342267-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.78.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.78.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-BguhCefN1bN2OeYRo5ChhUqNBLUda\",\n \"object\": \"chat.completion\",\n \"created\": 1749567414,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer \\nFinal Answer: Here is a refined list of the top 10 best soccer players in the world as of October 2023, ensuring that no Brazilian players are included:\\n\\n1. **Lionel Messi (Inter Miami CF)**\\n - Position: Forward\\n - Key Attributes: Dribbling, vision, goal-scoring ability.\\n - Achievements: Multiple Ballon d'Or winner, Copa America champion, World Cup champion (2022).\\n\\n2. **Kylian Mbappé (Paris Saint-Germain)**\\n - Position: Forward\\n - Key Attributes: Speed, technique, finishing.\\n - Achievements: FIFA World Cup champion (2018), multiple Ligue 1 titles, various domestic cups.\\n\\n3. **Erling Haaland (Manchester City)**\\\
n - Position: Forward\\n - Key Attributes: Power, speed, goal-scoring instinct.\\n - Achievements: Bundesliga top scorer, UEFA Champions League winner (2023), Premier League titles.\\n\\n4. **Kevin De Bruyne (Manchester City)**\\n - Position: Midfielder\\n - Key Attributes: Passing, vision, creativity.\\n - Achievements: Multiple Premier League titles, FA Cups, UEFA Champions League winner (2023).\\n\\n5. **Karim Benzema (Al-Ittihad)**\\n - Position: Forward\\n - Key Attributes: Goal-scoring, playmaking, tactical intelligence.\\n - Achievements: 2022 Ballon d'Or winner, multiple Champions Leagues with Real Madrid.\\n\\n6. **Robert Lewandowski (FC Barcelona)**\\n - Position: Forward\\n - Key Attributes: Finishing, positioning, aerial ability.\\n - Achievements: FIFA Best Men's Player, multiple Bundesliga titles, La Liga champion (2023).\\n\\n7. **Mohamed Salah (Liverpool)**\\n - Position: Forward\\n - Key Attributes: Speed, finishing, dribbling.\\n -\
\ Achievements: Premier League champion, FA Cup, UEFA Champions League winner.\\n\\n8. **Luka Modrić (Real Madrid)**\\n - Position: Midfielder\\n - Key Attributes: Passing, vision, tactical intelligence.\\n - Achievements: Multiple Champions League titles, Ballon d'Or winner (2018).\\n\\n9. **Harry Kane (Bayern Munich)**\\n - Position: Forward\\n - Key Attributes: Goal-scoring, technique, playmaking.\\n - Achievements: Golden Boot winner, multiple Premier League titles, UEFA European Championship runner-up.\\n\\n10. **Son Heung-min (Tottenham Hotspur)**\\n - Position: Forward\\n - Key Attributes: Speed, finishing, playmaking.\\n - Achievements: Premier League Golden Boot winner, multiple domestic cup titles.\\n\\nThis list has been carefully revised to exclude all Brazilian players while highlighting some of the most talented individuals in soccer as of October 2023. Each player has showcased remarkable effectiveness and skill, contributing significantly to their\
\ teams on both domestic and international stages.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 2028,\n \"completion_tokens\": 614,\n \"total_tokens\": 2642,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 1280,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_34a54ae93c\"\n}\n"
headers:
CF-RAY:
- 94d9b7d24d991d2c-GRU
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 10 Jun 2025 14:57:29 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '35291'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-envoy-upstream-service-time:
- '35294'
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149997855'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_4676152d4227ac1825d1240ddef231d6
- X-REQUEST-ID-XXX
status:
code: 200
message: OK

View File

@@ -1,14 +1,8 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Test Agent. A helpful
test assistant\nYour personal goal is: Answer questions\nTo give my best complete
final answer to the task respond using the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your 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!"},{"role":"user","content":"\nCurrent Task:
What is 2+2? Reply with just the number.\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:"}],"model":"gpt-4o-mini"}'
test assistant\nYour personal goal is: Answer questions"},{"role":"user","content":"\nCurrent
Task: What is 2+2? Reply with just the number.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
@@ -21,7 +15,7 @@ interactions:
connection:
- keep-alive
content-length:
- '673'
- '272'
content-type:
- application/json
host:
@@ -43,23 +37,22 @@ interactions:
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
- 3.13.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-Cy7b0HjL79y39EkUcMLrRhPFe3XGj\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444914,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
string: "{\n \"id\": \"chatcmpl-D6L4AzMHXLXDfyclWS6fJSwS0cvOl\",\n \"object\":
\"chat.completion\",\n \"created\": 1770403318,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: 4\",\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 136,\n \"completion_tokens\": 13,\n
\ \"total_tokens\": 149,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
\"assistant\",\n \"content\": \"4\",\n \"refusal\": null,\n
\ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 50,\n \"completion_tokens\":
1,\n \"total_tokens\": 51,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_8bbc38b4db\"\n}\n"
\"default\",\n \"system_fingerprint\": \"fp_f4ae844694\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
@@ -68,7 +61,7 @@ interactions:
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:55 GMT
- Fri, 06 Feb 2026 18:41:58 GMT
Server:
- cloudflare
Set-Cookie:
@@ -85,18 +78,14 @@ interactions:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '857'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '341'
- '264'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '358'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:

View File

@@ -1,14 +1,8 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Standalone Agent. A helpful
assistant\nYour personal goal is: Answer questions\nTo give my best complete
final answer to the task respond using the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your 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!"},{"role":"user","content":"\nCurrent Task:
What is 5+5? Reply with just the number.\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:"}],"model":"gpt-4o-mini"}'
assistant\nYour personal goal is: Answer questions"},{"role":"user","content":"\nCurrent
Task: What is 5+5? Reply with just the number.\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
@@ -21,7 +15,7 @@ interactions:
connection:
- keep-alive
content-length:
- '674'
- '273'
content-type:
- application/json
host:
@@ -43,23 +37,22 @@ interactions:
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
- 3.13.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-Cy7azhPwUHQ0p5tdhxSAmLPoE8UgC\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444913,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
string: "{\n \"id\": \"chatcmpl-D6L3cLs2ndBaXV2wnqYCdi6X1ykvv\",\n \"object\":
\"chat.completion\",\n \"created\": 1770403284,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: 10\",\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 136,\n \"completion_tokens\": 13,\n
\ \"total_tokens\": 149,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
\"assistant\",\n \"content\": \"10\",\n \"refusal\": null,\n
\ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 50,\n \"completion_tokens\":
1,\n \"total_tokens\": 51,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_29330a9688\"\n}\n"
\"default\",\n \"system_fingerprint\": \"fp_f4ae844694\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
@@ -68,7 +61,7 @@ interactions:
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:54 GMT
- Fri, 06 Feb 2026 18:41:25 GMT
Server:
- cloudflare
Set-Cookie:
@@ -85,18 +78,14 @@ interactions:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '858'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '455'
- '270'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '583'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:

View File

@@ -1,13 +1,8 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are First Agent. A friendly
greeter\nYour personal goal is: Greet users\nTo give my best complete final
answer to the task respond using the exact following format:\n\nThought: I now
can give a great answer\nFinal Answer: Your 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!"},{"role":"user","content":"\nCurrent Task: Say
hello\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:"}],"model":"gpt-4o-mini"}'
greeter\nYour personal goal is: Greet users"},{"role":"user","content":"\nCurrent
Task: Say hello\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
@@ -20,7 +15,7 @@ interactions:
connection:
- keep-alive
content-length:
- '632'
- '231'
content-type:
- application/json
host:
@@ -42,24 +37,22 @@ interactions:
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
- 3.13.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-CyRKzgODZ9yn3F9OkaXsscLk2Ln3N\",\n \"object\":
\"chat.completion\",\n \"created\": 1768520801,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
string: "{\n \"id\": \"chatcmpl-D6L4A8Aad6P1YUxWjQpvyltn8GaKT\",\n \"object\":
\"chat.completion\",\n \"created\": 1770403318,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: Hello! Welcome! I'm so glad to see you here. If you need any assistance
or have any questions, feel free to ask. Have a wonderful day!\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
127,\n \"completion_tokens\": 43,\n \"total_tokens\": 170,\n \"prompt_tokens_details\":
\"assistant\",\n \"content\": \"Hello! \U0001F60A How are you today?\",\n
\ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
41,\n \"completion_tokens\": 8,\n \"total_tokens\": 49,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_c4585b5b9c\"\n}\n"
\"default\",\n \"system_fingerprint\": \"fp_f4ae844694\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
@@ -68,7 +61,7 @@ interactions:
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 23:46:42 GMT
- Fri, 06 Feb 2026 18:41:58 GMT
Server:
- cloudflare
Set-Cookie:
@@ -85,18 +78,14 @@ interactions:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '990'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '880'
- '325'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1160'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
@@ -118,13 +107,8 @@ interactions:
message: OK
- request:
body: '{"messages":[{"role":"system","content":"You are Second Agent. A polite
farewell agent\nYour personal goal is: Say goodbye\nTo give my best complete
final answer to the task respond using the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your 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!"},{"role":"user","content":"\nCurrent Task:
Say goodbye\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:"}],"model":"gpt-4o-mini"}'
farewell agent\nYour personal goal is: Say goodbye"},{"role":"user","content":"\nCurrent
Task: Say goodbye\n\nProvide your complete response:"}],"model":"gpt-4o-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
@@ -137,7 +121,7 @@ interactions:
connection:
- keep-alive
content-length:
- '640'
- '239'
content-type:
- application/json
host:
@@ -159,27 +143,24 @@ interactions:
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
- 3.13.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-CyRL1Ua2PkK5xXPp3KeF0AnGAk3JP\",\n \"object\":
\"chat.completion\",\n \"created\": 1768520803,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
string: "{\n \"id\": \"chatcmpl-D6L4BLMYC3ODccwbKfBIdtrEyd3no\",\n \"object\":
\"chat.completion\",\n \"created\": 1770403319,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: As we reach the end of our conversation, I want to express my gratitude
for the time we've shared. It's been a pleasure assisting you, and I hope
you found our interaction helpful and enjoyable. Remember, whenever you need
assistance, I'm just a message away. Wishing you all the best in your future
endeavors. Goodbye and take care!\",\n \"refusal\": null,\n \"annotations\":
\"assistant\",\n \"content\": \"Thank you for the time we've spent
together! I wish you all the best in your future endeavors. Take care, and
until we meet again, goodbye!\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 126,\n \"completion_tokens\":
79,\n \"total_tokens\": 205,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 40,\n \"completion_tokens\":
31,\n \"total_tokens\": 71,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_29330a9688\"\n}\n"
\"default\",\n \"system_fingerprint\": \"fp_f4ae844694\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
@@ -188,7 +169,7 @@ interactions:
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 23:46:44 GMT
- Fri, 06 Feb 2026 18:41:59 GMT
Server:
- cloudflare
Set-Cookie:
@@ -205,18 +186,14 @@ interactions:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '1189'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '1363'
- '726'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1605'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:

View File

@@ -2,9 +2,8 @@ interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Calculator. You calculate
things.\nYour personal goal is: Perform calculations efficiently"},{"role":"user","content":"\nCurrent
Task: Use the failing_tool to do something.\n\nThis is VERY important to you,
your job depends on it!"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"failing_tool","description":"This
tool always fails","parameters":{"properties":{},"type":"object"}}}]}'
Task: Use the failing_tool to do something."}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"failing_tool","description":"This
tool always fails","strict":true,"parameters":{"properties":{},"type":"object","additionalProperties":false,"required":[]}}}]}'
headers:
User-Agent:
- X-USER-AGENT-XXX
@@ -17,7 +16,7 @@ interactions:
connection:
- keep-alive
content-length:
- '477'
- '476'
content-type:
- application/json
host:
@@ -39,26 +38,26 @@ interactions:
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
- 3.13.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D0vm2JDsOmy0czXPAr4vnw3wvuqYZ\",\n \"object\":
\"chat.completion\",\n \"created\": 1769114454,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
string: "{\n \"id\": \"chatcmpl-D6L3dV6acwapgRyxmnzGfuOXemtjJ\",\n \"object\":
\"chat.completion\",\n \"created\": 1770403285,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_8xr8rPUDWzLfQ3LOWPHtBUjK\",\n \"type\":
\ \"id\": \"call_GCdaOdo32pr1sSk4RzO0tiB9\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"failing_tool\",\n
\ \"arguments\": \"{}\"\n }\n }\n ],\n
\ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
null,\n \"finish_reason\": \"tool_calls\"\n }\n ],\n \"usage\":
{\n \"prompt_tokens\": 78,\n \"completion_tokens\": 11,\n \"total_tokens\":
89,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\":
{\n \"prompt_tokens\": 65,\n \"completion_tokens\": 11,\n \"total_tokens\":
76,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\":
0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n
\ \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_c4585b5b9c\"\n}\n"
\"default\",\n \"system_fingerprint\": \"fp_6c0d1490cb\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
@@ -67,7 +66,7 @@ interactions:
Content-Type:
- application/json
Date:
- Thu, 22 Jan 2026 20:40:54 GMT
- Fri, 06 Feb 2026 18:41:25 GMT
Server:
- cloudflare
Set-Cookie:
@@ -87,13 +86,11 @@ interactions:
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '593'
- '436'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '621'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
@@ -116,12 +113,9 @@ interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Calculator. You calculate
things.\nYour personal goal is: Perform calculations efficiently"},{"role":"user","content":"\nCurrent
Task: Use the failing_tool to do something.\n\nThis is VERY important to you,
your job depends on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_8xr8rPUDWzLfQ3LOWPHtBUjK","type":"function","function":{"name":"failing_tool","arguments":"{}"}}]},{"role":"tool","tool_call_id":"call_8xr8rPUDWzLfQ3LOWPHtBUjK","content":"Error
executing tool: This tool always fails"},{"role":"user","content":"Analyze the
tool result. If requirements are met, provide the Final Answer. Otherwise, call
the next tool. Deliver only the answer without meta-commentary."}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"failing_tool","description":"This
tool always fails","parameters":{"properties":{},"type":"object"}}}]}'
Task: Use the failing_tool to do something."},{"role":"assistant","content":null,"tool_calls":[{"id":"call_GCdaOdo32pr1sSk4RzO0tiB9","type":"function","function":{"name":"failing_tool","arguments":"{}"}}]},{"role":"tool","tool_call_id":"call_GCdaOdo32pr1sSk4RzO0tiB9","name":"failing_tool","content":"Error
executing tool: This tool always fails"}],"model":"gpt-4o-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"failing_tool","description":"This
tool always fails","strict":true,"parameters":{"properties":{},"type":"object","additionalProperties":false,"required":[]}}}]}'
headers:
User-Agent:
- X-USER-AGENT-XXX
@@ -134,7 +128,7 @@ interactions:
connection:
- keep-alive
content-length:
- '941'
- '778'
content-type:
- application/json
cookie:
@@ -158,22 +152,25 @@ interactions:
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
- 3.13.5
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D0vm3xcywoKBW75bhBXfkGJNim6Th\",\n \"object\":
\"chat.completion\",\n \"created\": 1769114455,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
string: "{\n \"id\": \"chatcmpl-D6L3dhjDZOoihHvXvRpbJD3ReGu0z\",\n \"object\":
\"chat.completion\",\n \"created\": 1770403285,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Error: This tool always fails.\",\n
\ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
141,\n \"completion_tokens\": 8,\n \"total_tokens\": 149,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
\"assistant\",\n \"content\": \"The attempt to use the failing tool
resulted in an error, as expected since it is designed to always fail. If
there's anything else you would like to calculate or explore, please let me
know!\",\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 93,\n \"completion_tokens\": 40,\n
\ \"total_tokens\": 133,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_c4585b5b9c\"\n}\n"
\"default\",\n \"system_fingerprint\": \"fp_6c0d1490cb\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
@@ -182,7 +179,7 @@ interactions:
Content-Type:
- application/json
Date:
- Thu, 22 Jan 2026 20:40:55 GMT
- Fri, 06 Feb 2026 18:41:26 GMT
Server:
- cloudflare
Strict-Transport-Security:
@@ -200,13 +197,11 @@ interactions:
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '420'
- '776'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '436'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:

View File

@@ -43,15 +43,15 @@ interactions:
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
- 3.13.5
x-stainless-timeout:
- NOT_GIVEN
method: POST
uri: https://api.anthropic.com/v1/messages
response:
body:
string: '{"model":"claude-3-5-haiku-20241022","id":"msg_0149zKBgM47utdBdrfJjM6YZ","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_011jnBYLgtzXqdmSi7JDyQHj","name":"structured_output","input":{"operation":"Addition","result":42,"explanation":"Adding
15 and 27 together results in 42"}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":573,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":79,"service_tier":"standard"}}'
string: '{"model":"claude-3-5-haiku-20241022","id":"msg_01A41GpDoJbZLUhR8dQzUcUX","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01UNPdzpayoWyqDYVE7fR5oA","name":"structured_output","input":{"operation":"Addition","result":42,"explanation":"Added
15 and 27 together"}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":573,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":75,"service_tier":"standard","inference_geo":"not_available"}}'
headers:
CF-RAY:
- CF-RAY-XXX
@@ -62,7 +62,7 @@ interactions:
Content-Type:
- application/json
Date:
- Fri, 30 Jan 2026 18:56:15 GMT
- Fri, 06 Feb 2026 18:41:25 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -88,7 +88,7 @@ interactions:
anthropic-ratelimit-requests-remaining:
- '3999'
anthropic-ratelimit-requests-reset:
- '2026-01-30T18:56:14Z'
- '2026-02-06T18:41:24Z'
anthropic-ratelimit-tokens-limit:
- ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
anthropic-ratelimit-tokens-remaining:
@@ -102,7 +102,7 @@ interactions:
strict-transport-security:
- STS-XXX
x-envoy-upstream-service-time:
- '1473'
- '1247'
status:
code: 200
message: OK

View File

@@ -44,21 +44,20 @@ interactions:
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
- 3.13.5
x-stainless-timeout:
- NOT_GIVEN
method: POST
uri: https://api.anthropic.com/v1/messages
response:
body:
string: '{"model":"claude-3-5-haiku-20241022","id":"msg_013iHkpmto99iyH5kDvn8uER","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01Kpda2DzHBqWq9a2FS2Bdw6","name":"structured_output","input":{"topic":"Benefits
string: '{"model":"claude-3-5-haiku-20241022","id":"msg_016wrV83wm3FLYD4JoTy2Piw","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01V6Pzr7eGfuG4Q3mc25ZXwN","name":"structured_output","input":{"topic":"Benefits
of Remote Work","summary":"Remote work offers significant advantages for both
employees and employers, transforming traditional work paradigms by providing
flexibility, increased productivity, and cost savings.","key_points":["Increased
employee flexibility and work-life balance","Reduced commuting time and associated
stress","Cost savings for companies on office infrastructure","Access to a
global talent pool","Higher employee productivity and job satisfaction","Lower
carbon footprint due to reduced travel"]}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":589,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":153,"service_tier":"standard"}}'
employees and employers, transforming traditional workplace dynamics.","key_points":["Increased
flexibility in work schedule","Reduced commute time and transportation costs","Improved
work-life balance","Higher productivity for many employees","Cost savings
for companies on office infrastructure","Expanded talent pool for hiring","Enhanced
employee job satisfaction"]}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":589,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":142,"service_tier":"standard","inference_geo":"not_available"}}'
headers:
CF-RAY:
- CF-RAY-XXX
@@ -69,7 +68,7 @@ interactions:
Content-Type:
- application/json
Date:
- Fri, 30 Jan 2026 18:56:19 GMT
- Fri, 06 Feb 2026 18:41:28 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -95,7 +94,7 @@ interactions:
anthropic-ratelimit-requests-remaining:
- '3999'
anthropic-ratelimit-requests-reset:
- '2026-01-30T18:56:16Z'
- '2026-02-06T18:41:26Z'
anthropic-ratelimit-tokens-limit:
- ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
anthropic-ratelimit-tokens-remaining:
@@ -109,7 +108,7 @@ interactions:
strict-transport-security:
- STS-XXX
x-envoy-upstream-service-time:
- '3107'
- '2650'
status:
code: 200
message: OK

View File

@@ -1,6 +1,8 @@
import os
import unittest
from unittest.mock import ANY, MagicMock, patch
from unittest.mock import ANY, AsyncMock, MagicMock, patch
import pytest
from crewai.cli.plus_api import PlusAPI
@@ -68,37 +70,6 @@ class TestPlusAPI(unittest.TestCase):
)
self.assertEqual(response, mock_response)
@patch("crewai.cli.plus_api.PlusAPI._make_request")
def test_get_agent(self, mock_make_request):
mock_response = MagicMock()
mock_make_request.return_value = mock_response
response = self.api.get_agent("test_agent_handle")
mock_make_request.assert_called_once_with(
"GET", "/crewai_plus/api/v1/agents/test_agent_handle"
)
self.assertEqual(response, mock_response)
@patch("crewai.cli.plus_api.Settings")
@patch("requests.Session.request")
def test_get_agent_with_org_uuid(self, mock_make_request, mock_settings_class):
mock_settings = MagicMock()
mock_settings.org_uuid = self.org_uuid
mock_settings.enterprise_base_url = os.getenv('CREWAI_PLUS_URL')
mock_settings_class.return_value = mock_settings
# re-initialize Client
self.api = PlusAPI(self.api_key)
mock_response = MagicMock()
mock_make_request.return_value = mock_response
response = self.api.get_agent("test_agent_handle")
self.assert_request_with_org_id(
mock_make_request, "GET", "/crewai_plus/api/v1/agents/test_agent_handle"
)
self.assertEqual(response, mock_response)
@patch("crewai.cli.plus_api.PlusAPI._make_request")
def test_get_tool(self, mock_make_request):
mock_response = MagicMock()
@@ -338,3 +309,49 @@ class TestPlusAPI(unittest.TestCase):
custom_api.base_url,
"https://custom-url-from-env.com",
)
@pytest.mark.asyncio
@patch("httpx.AsyncClient")
async def test_get_agent(mock_async_client_class):
api = PlusAPI("test_api_key")
mock_response = MagicMock()
mock_client_instance = AsyncMock()
mock_client_instance.get.return_value = mock_response
mock_async_client_class.return_value.__aenter__.return_value = mock_client_instance
response = await api.get_agent("test_agent_handle")
mock_client_instance.get.assert_called_once_with(
f"{api.base_url}/crewai_plus/api/v1/agents/test_agent_handle",
headers=api.headers,
)
assert response == mock_response
@pytest.mark.asyncio
@patch("httpx.AsyncClient")
@patch("crewai.cli.plus_api.Settings")
async def test_get_agent_with_org_uuid(mock_settings_class, mock_async_client_class):
org_uuid = "test-org-uuid"
mock_settings = MagicMock()
mock_settings.org_uuid = org_uuid
mock_settings.enterprise_base_url = os.getenv("CREWAI_PLUS_URL")
mock_settings_class.return_value = mock_settings
api = PlusAPI("test_api_key")
mock_response = MagicMock()
mock_client_instance = AsyncMock()
mock_client_instance.get.return_value = mock_response
mock_async_client_class.return_value.__aenter__.return_value = mock_client_instance
response = await api.get_agent("test_agent_handle")
mock_client_instance.get.assert_called_once_with(
f"{api.base_url}/crewai_plus/api/v1/agents/test_agent_handle",
headers=api.headers,
)
assert "X-Crewai-Organization-Id" in api.headers
assert api.headers["X-Crewai-Organization-Id"] == org_uuid
assert response == mock_response

View File

@@ -157,6 +157,176 @@ class TestMultiStepFlows:
assert execution_order == ["generate", "review", "finalize"]
def test_chained_router_feedback_steps(self):
"""Test that a router outcome can trigger another router method.
Regression test: @listen("outcome") combined with @human_feedback(emit=...)
creates a method that is both a listener and a router. The flow must find
and execute it when the upstream router emits the matching outcome.
"""
execution_order: list[str] = []
class ChainedRouterFlow(Flow):
@start()
@human_feedback(
message="First review:",
emit=["approved", "rejected"],
llm="gpt-4o-mini",
)
def draft(self):
execution_order.append("draft")
return "draft content"
@listen("approved")
@human_feedback(
message="Final review:",
emit=["publish", "revise"],
llm="gpt-4o-mini",
)
def final_review(self, prev: HumanFeedbackResult):
execution_order.append("final_review")
return "final content"
@listen("rejected")
def on_rejected(self, prev: HumanFeedbackResult):
execution_order.append("on_rejected")
return "rejected"
@listen("publish")
def on_publish(self, prev: HumanFeedbackResult):
execution_order.append("on_publish")
return "published"
@listen("revise")
def on_revise(self, prev: HumanFeedbackResult):
execution_order.append("on_revise")
return "revised"
flow = ChainedRouterFlow()
with (
patch.object(
flow,
"_request_human_feedback",
side_effect=["looks good", "ship it"],
),
patch.object(
flow,
"_collapse_to_outcome",
side_effect=["approved", "publish"],
),
):
result = flow.kickoff()
assert execution_order == ["draft", "final_review", "on_publish"]
assert result == "published"
assert len(flow.human_feedback_history) == 2
assert flow.human_feedback_history[0].outcome == "approved"
assert flow.human_feedback_history[1].outcome == "publish"
def test_chained_router_rejected_path(self):
"""Test that a start-router outcome routes to a non-router listener."""
execution_order: list[str] = []
class ChainedRouterFlow(Flow):
@start()
@human_feedback(
message="Review:",
emit=["approved", "rejected"],
llm="gpt-4o-mini",
)
def draft(self):
execution_order.append("draft")
return "draft"
@listen("approved")
@human_feedback(
message="Final:",
emit=["publish", "revise"],
llm="gpt-4o-mini",
)
def final_review(self, prev: HumanFeedbackResult):
execution_order.append("final_review")
return "final"
@listen("rejected")
def on_rejected(self, prev: HumanFeedbackResult):
execution_order.append("on_rejected")
return "rejected"
flow = ChainedRouterFlow()
with (
patch.object(
flow, "_request_human_feedback", return_value="bad"
),
patch.object(
flow, "_collapse_to_outcome", return_value="rejected"
),
):
result = flow.kickoff()
assert execution_order == ["draft", "on_rejected"]
assert result == "rejected"
assert len(flow.human_feedback_history) == 1
assert flow.human_feedback_history[0].outcome == "rejected"
def test_router_and_non_router_listeners_for_same_outcome(self):
"""Test that both router and non-router listeners fire for the same outcome."""
execution_order: list[str] = []
class MixedListenerFlow(Flow):
@start()
@human_feedback(
message="Review:",
emit=["approved", "rejected"],
llm="gpt-4o-mini",
)
def draft(self):
execution_order.append("draft")
return "draft"
@listen("approved")
@human_feedback(
message="Final:",
emit=["publish", "revise"],
llm="gpt-4o-mini",
)
def router_listener(self, prev: HumanFeedbackResult):
execution_order.append("router_listener")
return "final"
@listen("approved")
def plain_listener(self, prev: HumanFeedbackResult):
execution_order.append("plain_listener")
return "logged"
@listen("publish")
def on_publish(self, prev: HumanFeedbackResult):
execution_order.append("on_publish")
return "published"
flow = MixedListenerFlow()
with (
patch.object(
flow,
"_request_human_feedback",
side_effect=["approve it", "publish it"],
),
patch.object(
flow,
"_collapse_to_outcome",
side_effect=["approved", "publish"],
),
):
flow.kickoff()
assert "draft" in execution_order
assert "router_listener" in execution_order
assert "plain_listener" in execution_order
assert "on_publish" in execution_order
class TestStateManagement:
"""Tests for state management with human feedback."""