andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-05-05 01:02:37 +00:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity

Merge branch 'main' of github.com:crewAIInc/crewAI into lorenze/feat/file-discovery-tools

Browse Source
This commit is contained in:
lorenzejay
2026-02-12 10:31:20 -08:00
parent 6996a37e23 6c0fb7f970
commit e2ae700b18
129 changed files with 14540 additions and 2796 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
lib/crewai-tools/tests/tools/brave_search_tool_test.py
View File

@@ -33,8 +33,11 @@ def test_brave_tool_search(mock_get, brave_tool):
mock_get.return_value.json.return_value = mock_response
result = brave_tool.run(query="test")
assert "Test Title" in result
assert "http://test.com" in result
data = json.loads(result)
assert isinstance(data, list)
assert len(data) >= 1
assert data[0]["title"] == "Test Title"
assert data[0]["url"] == "http://test.com"
@patch("requests.get")

4
lib/crewai/pyproject.toml
View File

@@ -14,7 +14,7 @@ dependencies = [
"instructor>=1.3.3",
# Text Processing
"pdfplumber~=0.11.4",
"regex~=2024.9.11",
"regex~=2026.1.15",
# Telemetry and Monitoring
"opentelemetry-api~=1.34.0",
"opentelemetry-sdk~=1.34.0",
@@ -36,7 +36,7 @@ dependencies = [
"json5~=0.10.0",
"portalocker~=2.7.0",
"pydantic-settings~=2.10.1",
"mcp~=1.23.1",
"mcp~=1.26.0",
"uv~=0.9.13",
"aiosqlite~=0.21.0",
]

6
lib/crewai/src/crewai/agent/core.py
View File

@@ -118,6 +118,8 @@ MCP_TOOL_EXECUTION_TIMEOUT: Final[int] = 30
MCP_DISCOVERY_TIMEOUT: Final[int] = 15
MCP_MAX_RETRIES: Final[int] = 3
_passthrough_exceptions: tuple[type[Exception], ...] = ()
# Simple in-memory cache for MCP tool schemas (duration: 5 minutes)
_mcp_schema_cache: dict[str, Any] = {}
_cache_ttl: Final[int] = 300 # 5 minutes
@@ -479,6 +481,8 @@ class Agent(BaseAgent):
),
)
raise e
if isinstance(e, _passthrough_exceptions):
raise
self._times_executed += 1
if self._times_executed > self.max_retry_limit:
crewai_event_bus.emit(
@@ -711,6 +715,8 @@ class Agent(BaseAgent):
),
)
raise e
if isinstance(e, _passthrough_exceptions):
raise
self._times_executed += 1
if self._times_executed > self.max_retry_limit:
crewai_event_bus.emit(

5
lib/crewai/src/crewai/agents/agent_adapters/base_agent_adapter.py
View File

@@ -37,9 +37,10 @@ class BaseAgentAdapter(BaseAgent, ABC):
tools: Optional list of BaseTool instances to be configured
"""
def configure_structured_output(self, structured_output: Any) -> None:
@abstractmethod
def configure_structured_output(self, task: Any) -> None:
"""Configure the structured output for the specific agent implementation.
Args:
structured_output: The structured output to be configured
task: The task object containing output format specifications.
"""

50
lib/crewai/src/crewai/agents/agent_builder/base_agent_executor_mixin.py
View File

@@ -4,7 +4,6 @@ import time
from typing import TYPE_CHECKING
from crewai.agents.parser import AgentFinish
from crewai.events.event_listener import event_listener
from crewai.memory.entity.entity_memory_item import EntityMemoryItem
from crewai.memory.long_term.long_term_memory_item import LongTermMemoryItem
from crewai.utilities.converter import ConverterError
@@ -138,52 +137,3 @@ class CrewAgentExecutorMixin:
content="Long term memory is enabled, but entity memory is not enabled. Please configure entity memory or set memory=True to automatically enable it.",
color="bold_yellow",
)
def _ask_human_input(self, final_answer: str) -> str:
"""Prompt human input with mode-appropriate messaging.
Note: The final answer is already displayed via the AgentLogsExecutionEvent
panel, so we only show the feedback prompt here.
"""
from rich.panel import Panel
from rich.text import Text
formatter = event_listener.formatter
formatter.pause_live_updates()
try:
# Training mode prompt (single iteration)
if self.crew and getattr(self.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"
# Regular human-in-the-loop prompt (multiple iterations)
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 = input()
if response.strip() != "":
formatter.console.print("\n[cyan]Processing your feedback...[/cyan]")
return response
finally:
formatter.resume_live_updates()

163
lib/crewai/src/crewai/agents/crew_agent_executor.py
View File

@@ -19,6 +19,7 @@ from crewai.agents.parser import (
AgentFinish,
OutputParserError,
)
from crewai.core.providers.human_input import ExecutorContext, get_provider
from crewai.events.event_bus import crewai_event_bus
from crewai.events.types.logging_events import (
AgentLogsExecutionEvent,
@@ -175,15 +176,16 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
"""
return self.llm.supports_stop_words() if self.llm else False
def invoke(self, inputs: dict[str, Any]) -> dict[str, Any]:
"""Execute the agent with given inputs.
def _setup_messages(self, inputs: dict[str, Any]) -> None:
"""Set up messages for the agent execution.
Args:
inputs: Input dictionary containing prompt variables.
Returns:
Dictionary with agent output.
"""
provider = get_provider()
if provider.setup_messages(cast(ExecutorContext, cast(object, self))):
return
if "system" in self.prompt:
system_prompt = self._format_prompt(
cast(str, self.prompt.get("system", "")), inputs
@@ -197,6 +199,19 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
user_prompt = self._format_prompt(self.prompt.get("prompt", ""), inputs)
self.messages.append(format_message_for_llm(user_prompt))
provider.post_setup_messages(cast(ExecutorContext, cast(object, self)))
def invoke(self, inputs: dict[str, Any]) -> dict[str, Any]:
"""Execute the agent with given inputs.
Args:
inputs: Input dictionary containing prompt variables.
Returns:
Dictionary with agent output.
"""
self._setup_messages(inputs)
self._inject_multimodal_files(inputs)
self._show_start_logs()
@@ -799,6 +814,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
agent_key=agent_key,
),
)
error_event_emitted = False
track_delegation_if_needed(func_name, args_dict, self.task)
@@ -881,6 +897,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
error=e,
),
)
error_event_emitted = True
elif max_usage_reached and original_tool:
# Return error message when max usage limit is reached
result = f"Tool '{func_name}' has reached its usage limit of {original_tool.max_usage_count} times and cannot be used anymore."
@@ -908,20 +925,20 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
color="red",
)
# Emit tool usage finished event
crewai_event_bus.emit(
self,
event=ToolUsageFinishedEvent(
output=result,
tool_name=func_name,
tool_args=args_dict,
from_agent=self.agent,
from_task=self.task,
agent_key=agent_key,
started_at=started_at,
finished_at=datetime.now(),
),
)
if not error_event_emitted:
crewai_event_bus.emit(
self,
event=ToolUsageFinishedEvent(
output=result,
tool_name=func_name,
tool_args=args_dict,
from_agent=self.agent,
from_task=self.task,
agent_key=agent_key,
started_at=started_at,
finished_at=datetime.now(),
),
)
# Append tool result message
tool_message: LLMMessage = {
@@ -970,18 +987,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
Returns:
Dictionary with agent output.
"""
if "system" in self.prompt:
system_prompt = self._format_prompt(
cast(str, self.prompt.get("system", "")), inputs
)
user_prompt = self._format_prompt(
cast(str, self.prompt.get("user", "")), inputs
)
self.messages.append(format_message_for_llm(system_prompt, role="system"))
self.messages.append(format_message_for_llm(user_prompt))
else:
user_prompt = self._format_prompt(self.prompt.get("prompt", ""), inputs)
self.messages.append(format_message_for_llm(user_prompt))
self._setup_messages(inputs)
await self._ainject_multimodal_files(inputs)
@@ -1003,7 +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)
@@ -1491,7 +1497,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
return prompt.replace("{tools}", inputs["tools"])
def _handle_human_feedback(self, formatted_answer: AgentFinish) -> AgentFinish:
"""Process human feedback.
"""Process human feedback via the configured provider.
Args:
formatted_answer: Initial agent result.
@@ -1499,17 +1505,22 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
Returns:
Final answer after feedback.
"""
output_str = (
formatted_answer.output
if isinstance(formatted_answer.output, str)
else formatted_answer.output.model_dump_json()
)
human_feedback = self._ask_human_input(output_str)
provider = get_provider()
return provider.handle_feedback(formatted_answer, self)
if self._is_training_mode():
return self._handle_training_feedback(formatted_answer, human_feedback)
async def _ahandle_human_feedback(
self, formatted_answer: AgentFinish
) -> AgentFinish:
"""Process human feedback asynchronously via the configured provider.
return self._handle_regular_feedback(formatted_answer, human_feedback)
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.
@@ -1519,74 +1530,18 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
"""
return bool(self.crew and self.crew._train)
def _handle_training_feedback(
self, initial_answer: AgentFinish, feedback: str
) -> AgentFinish:
"""Process training feedback.
def _format_feedback_message(self, feedback: str) -> LLMMessage:
"""Format feedback as a message for the LLM.
Args:
initial_answer: Initial agent output.
feedback: Training feedback.
feedback: User feedback string.
Returns:
Improved answer.
Formatted message dict.
"""
self._handle_crew_training_output(initial_answer, feedback)
self.messages.append(
format_message_for_llm(
self._i18n.slice("feedback_instructions").format(feedback=feedback)
)
return format_message_for_llm(
self._i18n.slice("feedback_instructions").format(feedback=feedback)
)
improved_answer = self._invoke_loop()
self._handle_crew_training_output(improved_answer)
self.ask_for_human_input = False
return improved_answer
def _handle_regular_feedback(
self, current_answer: AgentFinish, initial_feedback: str
) -> AgentFinish:
"""Process regular feedback iteratively.
Args:
current_answer: Current agent output.
initial_feedback: Initial user feedback.
Returns:
Final answer after iterations.
"""
feedback = initial_feedback
answer = current_answer
while self.ask_for_human_input:
# If the user provides a blank response, assume they are happy with the result
if feedback.strip() == "":
self.ask_for_human_input = False
else:
answer = self._process_feedback_iteration(feedback)
output_str = (
answer.output
if isinstance(answer.output, str)
else answer.output.model_dump_json()
)
feedback = self._ask_human_input(output_str)
return answer
def _process_feedback_iteration(self, feedback: str) -> AgentFinish:
"""Process single feedback iteration.
Args:
feedback: User feedback.
Returns:
Updated agent response.
"""
self.messages.append(
format_message_for_llm(
self._i18n.slice("feedback_instructions").format(feedback=feedback)
)
)
return self._invoke_loop()
@classmethod
def __get_pydantic_core_schema__(

6
lib/crewai/src/crewai/cli/create_crew.py
View File

@@ -143,6 +143,12 @@ def create_folder_structure(
(folder_path / "src" / folder_name).mkdir(parents=True)
(folder_path / "src" / folder_name / "tools").mkdir(parents=True)
(folder_path / "src" / folder_name / "config").mkdir(parents=True)
# Copy AGENTS.md to project root (top-level projects only)
package_dir = Path(__file__).parent
agents_md_src = package_dir / "templates" / "AGENTS.md"
if agents_md_src.exists():
shutil.copy2(agents_md_src, folder_path / "AGENTS.md")
return folder_path, folder_name, class_name

6
lib/crewai/src/crewai/cli/create_flow.py
View File

@@ -1,3 +1,4 @@
import shutil
from pathlib import Path
import click
@@ -34,6 +35,11 @@ def create_flow(name):
package_dir = Path(__file__).parent
templates_dir = package_dir / "templates" / "flow"
# Copy AGENTS.md to project root
agents_md_src = package_dir / "templates" / "AGENTS.md"
if agents_md_src.exists():
shutil.copy2(agents_md_src, project_root / "AGENTS.md")
# List of template files to copy
root_template_files = [".gitignore", "pyproject.toml", "README.md"]
src_template_files = ["__init__.py", "main.py"]

16
lib/crewai/src/crewai/cli/plus_api.py
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,

1017
lib/crewai/src/crewai/cli/templates/AGENTS.md Normal file
View File

File diff suppressed because it is too large Load Diff

6
lib/crewai/src/crewai/cli/tools/main.py
View File

@@ -2,6 +2,7 @@ import base64
from json import JSONDecodeError
import os
from pathlib import Path
import shutil
import subprocess
import tempfile
from typing import Any
@@ -55,6 +56,11 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
tree_find_and_replace(project_root, "{{folder_name}}", folder_name)
tree_find_and_replace(project_root, "{{class_name}}", class_name)
# Copy AGENTS.md to project root
agents_md_src = Path(__file__).parent.parent / "templates" / "AGENTS.md"
if agents_md_src.exists():
shutil.copy2(agents_md_src, project_root / "AGENTS.md")
old_directory = os.getcwd()
os.chdir(project_root)
try:

122
lib/crewai/src/crewai/cli/version.py
View File

@@ -6,12 +6,12 @@ from functools import lru_cache
import importlib.metadata
import json
from pathlib import Path
from typing import Any, cast
from typing import Any
from urllib import request
from urllib.error import URLError
import appdirs
from packaging.version import InvalidVersion, parse
from packaging.version import InvalidVersion, Version, parse
@lru_cache(maxsize=1)
@@ -42,21 +42,88 @@ def _is_cache_valid(cache_data: Mapping[str, Any]) -> bool:
return False
def _find_latest_non_yanked_version(
releases: Mapping[str, list[dict[str, Any]]],
) -> str | None:
"""Find the latest non-yanked version from PyPI releases data.
Args:
releases: PyPI releases dict mapping version strings to file info lists.
Returns:
The latest non-yanked version string, or None if all versions are yanked.
"""
best_version: Version | None = None
best_version_str: str | None = None
for version_str, files in releases.items():
try:
v = parse(version_str)
except InvalidVersion:
continue
if v.is_prerelease or v.is_devrelease:
continue
if not files:
continue
all_yanked = all(f.get("yanked", False) for f in files)
if all_yanked:
continue
if best_version is None or v > best_version:
best_version = v
best_version_str = version_str
return best_version_str
def _is_version_yanked(
version_str: str,
releases: Mapping[str, list[dict[str, Any]]],
) -> tuple[bool, str]:
"""Check if a specific version is yanked.
Args:
version_str: The version string to check.
releases: PyPI releases dict mapping version strings to file info lists.
Returns:
Tuple of (is_yanked, yanked_reason).
"""
files = releases.get(version_str, [])
if not files:
return False, ""
all_yanked = all(f.get("yanked", False) for f in files)
if not all_yanked:
return False, ""
for f in files:
reason = f.get("yanked_reason", "")
if reason:
return True, str(reason)
return True, ""
def get_latest_version_from_pypi(timeout: int = 2) -> str | None:
"""Get the latest version of CrewAI from PyPI.
"""Get the latest non-yanked version of CrewAI from PyPI.
Args:
timeout: Request timeout in seconds.
Returns:
Latest version string or None if unable to fetch.
Latest non-yanked version string or None if unable to fetch.
"""
cache_file = _get_cache_file()
if cache_file.exists():
try:
cache_data = json.loads(cache_file.read_text())
if _is_cache_valid(cache_data):
return cast(str | None, cache_data.get("version"))
if _is_cache_valid(cache_data) and "current_version" in cache_data:
version: str | None = cache_data.get("version")
return version
except (json.JSONDecodeError, OSError):
pass
@@ -65,11 +132,18 @@ def get_latest_version_from_pypi(timeout: int = 2) -> str | None:
"https://pypi.org/pypi/crewai/json", timeout=timeout
) as response:
data = json.loads(response.read())
latest_version = cast(str, data["info"]["version"])
releases: dict[str, list[dict[str, Any]]] = data["releases"]
latest_version = _find_latest_non_yanked_version(releases)
current_version = get_crewai_version()
is_yanked, yanked_reason = _is_version_yanked(current_version, releases)
cache_data = {
"version": latest_version,
"timestamp": datetime.now().isoformat(),
"current_version": current_version,
"current_version_yanked": is_yanked,
"current_version_yanked_reason": yanked_reason,
}
cache_file.write_text(json.dumps(cache_data))
@@ -78,6 +152,40 @@ def get_latest_version_from_pypi(timeout: int = 2) -> str | None:
return None
def is_current_version_yanked() -> tuple[bool, str]:
"""Check if the currently installed version has been yanked on PyPI.
Reads from cache if available, otherwise triggers a fetch.
Returns:
Tuple of (is_yanked, yanked_reason).
"""
cache_file = _get_cache_file()
if cache_file.exists():
try:
cache_data = json.loads(cache_file.read_text())
if _is_cache_valid(cache_data) and "current_version" in cache_data:
current = get_crewai_version()
if cache_data.get("current_version") == current:
return (
bool(cache_data.get("current_version_yanked", False)),
str(cache_data.get("current_version_yanked_reason", "")),
)
except (json.JSONDecodeError, OSError):
pass
get_latest_version_from_pypi()
try:
cache_data = json.loads(cache_file.read_text())
return (
bool(cache_data.get("current_version_yanked", False)),
str(cache_data.get("current_version_yanked_reason", "")),
)
except (json.JSONDecodeError, OSError):
return False, ""
def check_version() -> tuple[str, str | None]:
"""Check current and latest versions.

20
lib/crewai/src/crewai/context.py
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()

1
lib/crewai/src/crewai/core/__init__.py Normal file
View File

@@ -0,0 +1 @@
"""Core crewAI components and interfaces."""

1
lib/crewai/src/crewai/core/providers/__init__.py Normal file
View File

@@ -0,0 +1 @@
"""Provider interfaces for extensible crewAI components."""

78
lib/crewai/src/crewai/core/providers/content_processor.py Normal file
View File

@@ -0,0 +1,78 @@
"""Content processor provider for extensible content processing."""
from contextvars import ContextVar
from typing import Any, Protocol, runtime_checkable
@runtime_checkable
class ContentProcessorProvider(Protocol):
"""Protocol for content processing during task execution."""
def process(self, content: str, context: dict[str, Any] | None = None) -> str:
"""Process content before use.
Args:
content: The content to process.
context: Optional context information.
Returns:
The processed content.
"""
...
class NoOpContentProcessor:
"""Default processor that returns content unchanged."""
def process(self, content: str, context: dict[str, Any] | None = None) -> str:
"""Return content unchanged.
Args:
content: The content to process.
context: Optional context information (unused).
Returns:
The original content unchanged.
"""
return content
_content_processor: ContextVar[ContentProcessorProvider | None] = ContextVar(
"_content_processor", default=None
)
_default_processor = NoOpContentProcessor()
def get_processor() -> ContentProcessorProvider:
"""Get the current content processor.
Returns:
The registered content processor or the default no-op processor.
"""
processor = _content_processor.get()
if processor is not None:
return processor
return _default_processor
def set_processor(processor: ContentProcessorProvider) -> None:
"""Set the content processor for the current context.
Args:
processor: The content processor to use.
"""
_content_processor.set(processor)
def process_content(content: str, context: dict[str, Any] | None = None) -> str:
"""Process content using the registered processor.
Args:
content: The content to process.
context: Optional context information.
Returns:
The processed content.
"""
return get_processor().process(content, context)

489
lib/crewai/src/crewai/core/providers/human_input.py Normal file
View File

@@ -0,0 +1,489 @@
"""Human input provider for HITL (Human-in-the-Loop) flows."""
from __future__ import annotations
import asyncio
from contextvars import ContextVar, Token
import sys
from typing import TYPE_CHECKING, Protocol, runtime_checkable
if TYPE_CHECKING:
from crewai.agent.core import Agent
from crewai.agents.parser import AgentFinish
from crewai.crew import Crew
from crewai.llms.base_llm import BaseLLM
from crewai.task import Task
from crewai.utilities.types import LLMMessage
class ExecutorContext(Protocol):
"""Context interface for human input providers to interact with executor."""
task: Task | None
crew: Crew | None
messages: list[LLMMessage]
ask_for_human_input: bool
llm: BaseLLM
agent: Agent
def _invoke_loop(self) -> AgentFinish:
"""Invoke the agent loop and return the result."""
...
def _is_training_mode(self) -> bool:
"""Check if training mode is active."""
...
def _handle_crew_training_output(
self,
result: AgentFinish,
human_feedback: str | None = None,
) -> None:
"""Handle training output."""
...
def _format_feedback_message(self, feedback: str) -> LLMMessage:
"""Format feedback as a message."""
...
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: use non-blocking I/O and async invoke loop
"""
def setup_messages(self, context: ExecutorContext) -> bool:
"""Set up messages for execution.
Called before standard message setup. Allows providers to handle
conversation resumption or other custom message initialization.
Args:
context: Executor context with messages list to modify.
Returns:
True if messages were set up (skip standard setup),
False to use standard setup.
"""
...
def post_setup_messages(self, context: ExecutorContext) -> None:
"""Called after standard message setup.
Allows providers to modify messages after standard setup completes.
Only called when setup_messages returned False.
Args:
context: Executor context with messages list to modify.
"""
...
def handle_feedback(
self,
formatted_answer: AgentFinish,
context: ExecutorContext,
) -> AgentFinish:
"""Handle the full human feedback flow synchronously.
Args:
formatted_answer: The agent's current answer.
context: Executor context for callbacks.
Returns:
The final answer after feedback processing.
Raises:
Exception: Async implementations may raise to signal external handling.
"""
...
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.
Args:
answer: The agent's finished answer.
Returns:
String representation of the output.
"""
if isinstance(answer.output, str):
return answer.output
return answer.output.model_dump_json()
class SyncHumanInputProvider(HumanInputProvider):
"""Default human input provider with sync and async support."""
def setup_messages(self, context: ExecutorContext) -> bool:
"""Use standard message setup.
Args:
context: Executor context (unused).
Returns:
False to use standard setup.
"""
return False
def post_setup_messages(self, context: ExecutorContext) -> None:
"""No-op for sync provider.
Args:
context: Executor context (unused).
"""
def handle_feedback(
self,
formatted_answer: AgentFinish,
context: ExecutorContext,
) -> AgentFinish:
"""Handle feedback synchronously with terminal prompts.
Args:
formatted_answer: The agent's current answer.
context: Executor context for callbacks.
Returns:
The final answer after feedback processing.
"""
feedback = self._prompt_input(context.crew)
if context._is_training_mode():
return self._handle_training_feedback(formatted_answer, feedback, context)
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,
feedback: str,
context: ExecutorContext,
) -> AgentFinish:
"""Process training feedback (single iteration).
Args:
initial_answer: The agent's initial answer.
feedback: Human feedback string.
context: 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 = context._invoke_loop()
context._handle_crew_training_output(improved_answer)
context.ask_for_human_input = False
return improved_answer
def _handle_regular_feedback(
self,
current_answer: AgentFinish,
initial_feedback: str,
context: ExecutorContext,
) -> AgentFinish:
"""Process regular feedback with iteration loop.
Args:
current_answer: The agent's current answer.
initial_feedback: Initial human feedback string.
context: 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 = context._invoke_loop()
feedback = self._prompt_input(context.crew)
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.
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 = input()
if response.strip() != "":
formatter.console.print("\n[cyan]Processing your feedback...[/cyan]")
return response
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",
default=None,
)
def get_provider() -> HumanInputProvider:
"""Get the current human input provider.
Returns:
The current provider, or a new SyncHumanInputProvider if none set.
"""
provider = _provider.get()
if provider is None:
initialized_provider = SyncHumanInputProvider()
set_provider(initialized_provider)
return initialized_provider
return provider
def set_provider(provider: HumanInputProvider) -> Token[HumanInputProvider | None]:
"""Set the human input provider for the current context.
Args:
provider: The provider to use.
Returns:
Token that can be used to reset to previous value.
"""
return _provider.set(provider)
def reset_provider(token: Token[HumanInputProvider | None]) -> None:
"""Reset the provider to its previous value.
Args:
token: Token returned from set_provider.
"""
_provider.reset(token)

42
lib/crewai/src/crewai/crew.py
View File

@@ -187,6 +187,7 @@ class Crew(FlowTrackable, BaseModel):
_task_output_handler: TaskOutputStorageHandler = PrivateAttr(
default_factory=TaskOutputStorageHandler
)
_kickoff_event_id: str | None = PrivateAttr(default=None)
name: str | None = Field(default="crew")
cache: bool = Field(default=True)
@@ -751,19 +752,28 @@ class Crew(FlowTrackable, BaseModel):
for after_callback in self.after_kickoff_callbacks:
result = after_callback(result)
result = self._post_kickoff(result)
self.usage_metrics = self.calculate_usage_metrics()
return result
except Exception as e:
crewai_event_bus.emit(
self,
CrewKickoffFailedEvent(error=str(e), crew_name=self.name),
CrewKickoffFailedEvent(
error=str(e),
crew_name=self.name,
started_event_id=self._kickoff_event_id,
),
)
raise
finally:
clear_files(self.id)
detach(token)
def _post_kickoff(self, result: CrewOutput) -> CrewOutput:
return result
def kickoff_for_each(
self,
inputs: list[dict[str, Any]],
@@ -936,13 +946,19 @@ class Crew(FlowTrackable, BaseModel):
for after_callback in self.after_kickoff_callbacks:
result = after_callback(result)
result = self._post_kickoff(result)
self.usage_metrics = self.calculate_usage_metrics()
return result
except Exception as e:
crewai_event_bus.emit(
self,
CrewKickoffFailedEvent(error=str(e), crew_name=self.name),
CrewKickoffFailedEvent(
error=str(e),
crew_name=self.name,
started_event_id=self._kickoff_event_id,
),
)
raise
finally:
@@ -1181,6 +1197,9 @@ class Crew(FlowTrackable, BaseModel):
self.manager_agent = manager
manager.crew = self
def _get_execution_start_index(self, tasks: list[Task]) -> int | None:
return None
def _execute_tasks(
self,
tasks: list[Task],
@@ -1197,6 +1216,9 @@ class Crew(FlowTrackable, BaseModel):
Returns:
CrewOutput: Final output of the crew
"""
custom_start = self._get_execution_start_index(tasks)
if custom_start is not None:
start_index = custom_start
task_outputs: list[TaskOutput] = []
futures: list[tuple[Task, Future[TaskOutput], int]] = []
@@ -1305,8 +1327,10 @@ class Crew(FlowTrackable, BaseModel):
if files:
supported_types: list[str] = []
if agent and agent.llm and agent.llm.supports_multimodal():
provider = getattr(agent.llm, "provider", None) or getattr(
agent.llm, "model", "openai"
provider = (
getattr(agent.llm, "provider", None)
or getattr(agent.llm, "model", None)
or "openai"
)
api = getattr(agent.llm, "api", None)
supported_types = get_supported_content_types(provider, api)
@@ -1502,12 +1526,14 @@ 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(
crew_name=self.name,
output=final_task_output,
total_tokens=self.token_usage.total_tokens,
started_event_id=self._kickoff_event_id,
),
)
@@ -2011,7 +2037,13 @@ class Crew(FlowTrackable, BaseModel):
@staticmethod
def _show_tracing_disabled_message() -> None:
"""Show a message when tracing is disabled."""
from crewai.events.listeners.tracing.utils import has_user_declined_tracing
from crewai.events.listeners.tracing.utils import (
has_user_declined_tracing,
should_suppress_tracing_messages,
)
if should_suppress_tracing_messages():
return
console = Console()

7
lib/crewai/src/crewai/crews/utils.py
View File

@@ -265,10 +265,9 @@ def prepare_kickoff(
normalized = {}
normalized = before_callback(normalized)
future = crewai_event_bus.emit(
crew,
CrewKickoffStartedEvent(crew_name=crew.name, inputs=normalized),
)
started_event = CrewKickoffStartedEvent(crew_name=crew.name, inputs=normalized)
crew._kickoff_event_id = started_event.event_id
future = crewai_event_bus.emit(crew, started_event)
if future is not None:
try:
future.result()

18
lib/crewai/src/crewai/events/__init__.py
View File

@@ -195,6 +195,7 @@ __all__ = [
"ToolUsageFinishedEvent",
"ToolUsageStartedEvent",
"ToolValidateInputErrorEvent",
"_extension_exports",
"crewai_event_bus",
]
@@ -210,14 +211,29 @@ _AGENT_EVENT_MAPPING = {
"LiteAgentExecutionStartedEvent": "crewai.events.types.agent_events",
}
_extension_exports: dict[str, Any] = {}
def __getattr__(name: str) -> Any:
"""Lazy import for agent events to avoid circular imports."""
"""Lazy import for agent events and registered extensions."""
if name in _AGENT_EVENT_MAPPING:
import importlib
module_path = _AGENT_EVENT_MAPPING[name]
module = importlib.import_module(module_path)
return getattr(module, name)
if name in _extension_exports:
import importlib
value = _extension_exports[name]
if isinstance(value, str):
module_path, _, attr_name = value.rpartition(".")
if module_path:
module = importlib.import_module(module_path)
return getattr(module, attr_name)
return importlib.import_module(value)
return value
msg = f"module {__name__!r} has no attribute {name!r}"
raise AttributeError(msg)

1
lib/crewai/src/crewai/events/base_events.py
View File

@@ -63,6 +63,7 @@ class BaseEvent(BaseModel):
parent_event_id: str | None = None
previous_event_id: str | None = None
triggered_by_event_id: str | None = None
started_event_id: str | None = None
emission_sequence: int | None = None
def to_json(self, exclude: set[str] | None = None) -> Serializable:

92
lib/crewai/src/crewai/events/event_bus.py
View File

@@ -227,6 +227,39 @@ class CrewAIEventsBus:
return decorator
def off(
self,
event_type: type[BaseEvent],
handler: Callable[..., Any],
) -> None:
"""Unregister an event handler for a specific event type.
Args:
event_type: The event class to stop listening for
handler: The handler function to unregister
"""
with self._rwlock.w_locked():
if event_type in self._sync_handlers:
existing_sync = self._sync_handlers[event_type]
if handler in existing_sync:
self._sync_handlers[event_type] = existing_sync - {handler}
if not self._sync_handlers[event_type]:
del self._sync_handlers[event_type]
if event_type in self._async_handlers:
existing_async = self._async_handlers[event_type]
if handler in existing_async:
self._async_handlers[event_type] = existing_async - {handler}
if not self._async_handlers[event_type]:
del self._async_handlers[event_type]
if event_type in self._handler_dependencies:
self._handler_dependencies[event_type].pop(handler, None)
if not self._handler_dependencies[event_type]:
del self._handler_dependencies[event_type]
self._execution_plan_cache.pop(event_type, None)
def _call_handlers(
self,
source: Any,
@@ -374,7 +407,8 @@ class CrewAIEventsBus:
if popped is None:
handle_empty_pop(event_type_name)
else:
_, popped_type = popped
popped_event_id, popped_type = popped
event.started_event_id = popped_event_id
expected_start = VALID_EVENT_PAIRS.get(event_type_name)
if expected_start and popped_type and popped_type != expected_start:
handle_mismatch(event_type_name, popped_type, expected_start)
@@ -536,24 +570,52 @@ class CrewAIEventsBus:
... # Do stuff...
... # Handlers are cleared after the context
"""
with self._rwlock.w_locked():
prev_sync = self._sync_handlers
prev_async = self._async_handlers
prev_deps = self._handler_dependencies
prev_cache = self._execution_plan_cache
self._sync_handlers = {}
self._async_handlers = {}
self._handler_dependencies = {}
self._execution_plan_cache = {}
with self._rwlock.r_locked():
saved_sync: dict[type[BaseEvent], frozenset[SyncHandler]] = dict(
self._sync_handlers
)
saved_async: dict[type[BaseEvent], frozenset[AsyncHandler]] = dict(
self._async_handlers
)
saved_deps: dict[type[BaseEvent], dict[Handler, list[Depends[Any]]]] = {
event_type: dict(handlers)
for event_type, handlers in self._handler_dependencies.items()
}
for event_type, sync_handlers in saved_sync.items():
for sync_handler in sync_handlers:
self.off(event_type, sync_handler)
for event_type, async_handlers in saved_async.items():
for async_handler in async_handlers:
self.off(event_type, async_handler)
try:
yield
finally:
with self._rwlock.w_locked():
self._sync_handlers = prev_sync
self._async_handlers = prev_async
self._handler_dependencies = prev_deps
self._execution_plan_cache = prev_cache
with self._rwlock.r_locked():
current_sync = dict(self._sync_handlers)
current_async = dict(self._async_handlers)
for event_type, cur_sync in current_sync.items():
orig_sync = saved_sync.get(event_type, frozenset())
for new_handler in cur_sync - orig_sync:
self.off(event_type, new_handler)
for event_type, cur_async in current_async.items():
orig_async = saved_async.get(event_type, frozenset())
for new_async_handler in cur_async - orig_async:
self.off(event_type, new_async_handler)
for event_type, sync_handlers in saved_sync.items():
for sync_handler in sync_handlers:
deps = saved_deps.get(event_type, {}).get(sync_handler)
self._register_handler(event_type, sync_handler, deps)
for event_type, async_handlers in saved_async.items():
for async_handler in async_handlers:
deps = saved_deps.get(event_type, {}).get(async_handler)
self._register_handler(event_type, async_handler, deps)
def shutdown(self, wait: bool = True) -> None:
"""Gracefully shutdown the event loop and wait for all tasks to finish.

8
lib/crewai/src/crewai/events/listeners/tracing/trace_listener.py
View File

@@ -797,7 +797,13 @@ class TraceCollectionListener(BaseEventListener):
from rich.console import Console
from rich.panel import Panel
from crewai.events.listeners.tracing.utils import has_user_declined_tracing
from crewai.events.listeners.tracing.utils import (
has_user_declined_tracing,
should_suppress_tracing_messages,
)
if should_suppress_tracing_messages():
return
console = Console()

38
lib/crewai/src/crewai/events/listeners/tracing/utils.py
View File

@@ -1,3 +1,4 @@
from collections.abc import Callable
from contextvars import ContextVar, Token
from datetime import datetime
import getpass
@@ -26,6 +27,35 @@ logger = logging.getLogger(__name__)
_tracing_enabled: ContextVar[bool | None] = ContextVar("_tracing_enabled", default=None)
_first_time_trace_hook: ContextVar[Callable[[], bool] | None] = ContextVar(
"_first_time_trace_hook", default=None
)
_suppress_tracing_messages: ContextVar[bool] = ContextVar(
"_suppress_tracing_messages", default=False
)
def set_suppress_tracing_messages(suppress: bool) -> object:
"""Set whether to suppress tracing-related console messages.
Args:
suppress: True to suppress messages, False to show them.
Returns:
A token that can be used to restore the previous value.
"""
return _suppress_tracing_messages.set(suppress)
def should_suppress_tracing_messages() -> bool:
"""Check if tracing messages should be suppressed.
Returns:
True if messages should be suppressed, False otherwise.
"""
return _suppress_tracing_messages.get()
def should_enable_tracing(*, override: bool | None = None) -> bool:
"""Determine if tracing should be enabled.
@@ -407,10 +437,13 @@ def truncate_messages(
def should_auto_collect_first_time_traces() -> bool:
"""True if we should auto-collect traces for first-time user.
Returns:
True if first-time user AND telemetry not disabled AND tracing not explicitly enabled, False otherwise.
"""
hook = _first_time_trace_hook.get()
if hook is not None:
return hook()
if _is_test_environment():
return False
@@ -432,6 +465,9 @@ def prompt_user_for_trace_viewing(timeout_seconds: int = 20) -> bool:
if _is_test_environment():
return False
if should_suppress_tracing_messages():
return False
try:
import threading

8
lib/crewai/src/crewai/events/types/tool_usage_events.py
View File

@@ -16,7 +16,7 @@ class ToolUsageEvent(BaseEvent):
tool_name: str
tool_args: dict[str, Any] | str
tool_class: str | None = None
run_attempts: int | None = None
run_attempts: int = 0
delegations: int | None = None
agent: Any | None = None
task_name: str | None = None
@@ -26,7 +26,7 @@ class ToolUsageEvent(BaseEvent):
model_config = ConfigDict(arbitrary_types_allowed=True)
def __init__(self, **data):
def __init__(self, **data: Any) -> None:
if data.get("from_task"):
task = data["from_task"]
data["task_id"] = str(task.id)
@@ -96,10 +96,10 @@ class ToolExecutionErrorEvent(BaseEvent):
type: str = "tool_execution_error"
tool_name: str
tool_args: dict[str, Any]
tool_class: Callable
tool_class: Callable[..., Any]
agent: Any | None = None
def __init__(self, **data):
def __init__(self, **data: Any) -> None:
super().__init__(**data)
# Set fingerprint data from the agent
if self.agent and hasattr(self.agent, "fingerprint") and self.agent.fingerprint:

64
lib/crewai/src/crewai/events/utils/console_formatter.py
View File

@@ -1,3 +1,4 @@
from contextvars import ContextVar
import os
import threading
from typing import Any, ClassVar, cast
@@ -7,7 +8,37 @@ from rich.live import Live
from rich.panel import Panel
from rich.text import Text
from crewai.cli.version import is_newer_version_available
from crewai.cli.version import is_current_version_yanked, is_newer_version_available
_disable_version_check: ContextVar[bool] = ContextVar(
"_disable_version_check", default=False
)
_suppress_console_output: ContextVar[bool] = ContextVar(
"_suppress_console_output", default=False
)
def set_suppress_console_output(suppress: bool) -> object:
"""Set whether to suppress all console output.
Args:
suppress: True to suppress output, False to show it.
Returns:
A token that can be used to restore the previous value.
"""
return _suppress_console_output.set(suppress)
def should_suppress_console_output() -> bool:
"""Check if console output should be suppressed.
Returns:
True if output should be suppressed, False otherwise.
"""
return _suppress_console_output.get()
class ConsoleFormatter:
@@ -46,9 +77,15 @@ class ConsoleFormatter:
if not self.verbose:
return
if _disable_version_check.get():
return
if os.getenv("CI", "").lower() in ("true", "1"):
return
if os.getenv("CREWAI_DISABLE_VERSION_CHECK", "").lower() in ("true", "1"):
return
try:
is_newer, current, latest = is_newer_version_available()
if is_newer and latest:
@@ -67,6 +104,22 @@ To update, run: uv sync --upgrade-package crewai"""
)
self.console.print(panel)
self.console.print()
is_yanked, yanked_reason = is_current_version_yanked()
if is_yanked:
yanked_message = f"Version {current} has been yanked from PyPI."
if yanked_reason:
yanked_message += f"\nReason: {yanked_reason}"
yanked_message += "\n\nTo update, run: uv sync --upgrade-package crewai"
yanked_panel = Panel(
yanked_message,
title="Yanked Version",
border_style="red",
padding=(1, 2),
)
self.console.print(yanked_panel)
self.console.print()
except Exception: # noqa: S110
# Silently ignore errors in version check - it's non-critical
pass
@@ -76,8 +129,12 @@ To update, run: uv sync --upgrade-package crewai"""
from crewai.events.listeners.tracing.utils import (
has_user_declined_tracing,
is_tracing_enabled_in_context,
should_suppress_tracing_messages,
)
if should_suppress_tracing_messages():
return
if not is_tracing_enabled_in_context():
if has_user_declined_tracing():
message = """Info: Tracing is disabled.
@@ -129,6 +186,8 @@ To enable tracing, do any one of these:
def print(self, *args: Any, **kwargs: Any) -> None:
"""Print to console. Simplified to only handle panel-based output."""
if should_suppress_console_output():
return
# Skip blank lines during streaming
if len(args) == 0 and self._is_streaming:
return
@@ -485,6 +544,9 @@ To enable tracing, do any one of these:
if not self.verbose:
return
if should_suppress_console_output():
return
self._is_streaming = True
self._last_stream_call_type = call_type

286
lib/crewai/src/crewai/experimental/agent_executor.py
View File

@@ -18,6 +18,7 @@ from crewai.agents.parser import (
AgentFinish,
OutputParserError,
)
from crewai.core.providers.human_input import get_provider
from crewai.events.event_bus import crewai_event_bus
from crewai.events.listeners.tracing.utils import (
is_tracing_enabled_in_context,
@@ -31,7 +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,
@@ -41,7 +43,12 @@ from crewai.hooks.tool_hooks import (
get_after_tool_call_hooks,
get_before_tool_call_hooks,
)
from crewai.hooks.types import AfterLLMCallHookType, BeforeLLMCallHookType
from crewai.hooks.types import (
AfterLLMCallHookCallable,
AfterLLMCallHookType,
BeforeLLMCallHookCallable,
BeforeLLMCallHookType,
)
from crewai.utilities.agent_utils import (
convert_tools_to_openai_schema,
enforce_rpm_limit,
@@ -191,8 +198,12 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
self._instance_id = str(uuid4())[:8]
self.before_llm_call_hooks: list[BeforeLLMCallHookType] = []
self.after_llm_call_hooks: list[AfterLLMCallHookType] = []
self.before_llm_call_hooks: list[
BeforeLLMCallHookType | BeforeLLMCallHookCallable
] = []
self.after_llm_call_hooks: list[
AfterLLMCallHookType | AfterLLMCallHookCallable
] = []
self.before_llm_call_hooks.extend(get_before_llm_call_hooks())
self.after_llm_call_hooks.extend(get_after_llm_call_hooks())
@@ -207,6 +218,71 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
)
self._state = AgentReActState()
@property
def messages(self) -> list[LLMMessage]:
"""Delegate to state for ExecutorContext conformance."""
return self._state.messages
@messages.setter
def messages(self, value: list[LLMMessage]) -> None:
"""Delegate to state for ExecutorContext conformance."""
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:
"""Delegate to state for ExecutorContext conformance."""
return self._state.ask_for_human_input
@ask_for_human_input.setter
def ask_for_human_input(self, value: bool) -> None:
"""Delegate to state for ExecutorContext conformance."""
self._state.ask_for_human_input = value
def _invoke_loop(self) -> AgentFinish:
"""Invoke the agent loop and return the result.
Required by ExecutorContext protocol.
"""
self._state.iterations = 0
self._state.is_finished = False
self._state.current_answer = None
self.kickoff()
answer = self._state.current_answer
if not isinstance(answer, AgentFinish):
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.
Required by ExecutorContext protocol.
"""
return format_message_for_llm(
self._i18n.slice("feedback_instructions").format(feedback=feedback)
)
def _ensure_flow_initialized(self) -> None:
"""Ensure Flow.__init__() has been called.
@@ -298,18 +374,10 @@ 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
def messages(self) -> list[LLMMessage]:
"""Compatibility property for mixin - returns state messages."""
return self._state.messages
@messages.setter
def messages(self, value: list[LLMMessage]) -> None:
"""Set state messages."""
self._state.messages = value
@property
def iterations(self) -> int:
"""Compatibility property for mixin - returns state iterations."""
@@ -416,15 +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
@@ -454,8 +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(
@@ -465,7 +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):
@@ -476,8 +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(
@@ -487,13 +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)
@@ -506,6 +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."""
@@ -689,6 +769,7 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
agent_key=agent_key,
),
)
error_event_emitted = False
track_delegation_if_needed(func_name, args_dict, self.task)
@@ -764,6 +845,7 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
error=e,
),
)
error_event_emitted = True
elif max_usage_reached and original_tool:
# Return error message when max usage limit is reached
result = f"Tool '{func_name}' has reached its usage limit of {original_tool.max_usage_count} times and cannot be used anymore."
@@ -792,20 +874,20 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
color="red",
)
# Emit tool usage finished event
crewai_event_bus.emit(
self,
event=ToolUsageFinishedEvent(
output=result,
tool_name=func_name,
tool_args=args_dict,
from_agent=self.agent,
from_task=self.task,
agent_key=agent_key,
started_at=started_at,
finished_at=datetime.now(),
),
)
if not error_event_emitted:
crewai_event_bus.emit(
self,
event=ToolUsageFinishedEvent(
output=result,
tool_name=func_name,
tool_args=args_dict,
from_agent=self.agent,
from_task=self.task,
agent_key=agent_key,
started_at=started_at,
finished_at=datetime.now(),
),
)
# Append tool result message
tool_message: LLMMessage = {
@@ -861,9 +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))
@@ -1105,7 +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)
@@ -1319,17 +1403,22 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
Returns:
Final answer after feedback.
"""
output_str = (
str(formatted_answer.output)
if isinstance(formatted_answer.output, BaseModel)
else formatted_answer.output
)
human_feedback = self._ask_human_input(output_str)
provider = get_provider()
return provider.handle_feedback(formatted_answer, self)
if self._is_training_mode():
return self._handle_training_feedback(formatted_answer, human_feedback)
async def _ahandle_human_feedback(
self, formatted_answer: AgentFinish
) -> AgentFinish:
"""Process human feedback asynchronously and refine answer.
return self._handle_regular_feedback(formatted_answer, human_feedback)
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.
@@ -1339,101 +1428,6 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
"""
return bool(self.crew and self.crew._train)
def _handle_training_feedback(
self, initial_answer: AgentFinish, feedback: str
) -> AgentFinish:
"""Process training feedback and generate improved answer.
Args:
initial_answer: Initial agent output.
feedback: Training feedback.
Returns:
Improved answer.
"""
self._handle_crew_training_output(initial_answer, feedback)
self.state.messages.append(
format_message_for_llm(
self._i18n.slice("feedback_instructions").format(feedback=feedback)
)
)
# Re-run flow for improved answer
self.state.iterations = 0
self.state.is_finished = False
self.state.current_answer = None
self.kickoff()
# Get improved answer from state
improved_answer = self.state.current_answer
if not isinstance(improved_answer, AgentFinish):
raise RuntimeError(
"Training feedback iteration did not produce final answer"
)
self._handle_crew_training_output(improved_answer)
self.state.ask_for_human_input = False
return improved_answer
def _handle_regular_feedback(
self, current_answer: AgentFinish, initial_feedback: str
) -> AgentFinish:
"""Process regular feedback iteratively until user is satisfied.
Args:
current_answer: Current agent output.
initial_feedback: Initial user feedback.
Returns:
Final answer after iterations.
"""
feedback = initial_feedback
answer = current_answer
while self.state.ask_for_human_input:
if feedback.strip() == "":
self.state.ask_for_human_input = False
else:
answer = self._process_feedback_iteration(feedback)
output_str = (
str(answer.output)
if isinstance(answer.output, BaseModel)
else answer.output
)
feedback = self._ask_human_input(output_str)
return answer
def _process_feedback_iteration(self, feedback: str) -> AgentFinish:
"""Process a single feedback iteration and generate updated response.
Args:
feedback: User feedback.
Returns:
Updated agent response.
"""
self.state.messages.append(
format_message_for_llm(
self._i18n.slice("feedback_instructions").format(feedback=feedback)
)
)
# Re-run flow
self.state.iterations = 0
self.state.is_finished = False
self.state.current_answer = None
self.kickoff()
# Get answer from state
answer = self.state.current_answer
if not isinstance(answer, AgentFinish):
raise RuntimeError("Feedback iteration did not produce final answer")
return answer
@classmethod
def __get_pydantic_core_schema__(
cls, _source_type: Any, _handler: GetCoreSchemaHandler

13
lib/crewai/src/crewai/flow/async_feedback/__init__.py
View File

@@ -28,6 +28,8 @@ Example:
```
"""
from typing import Any
from crewai.flow.async_feedback.providers import ConsoleProvider
from crewai.flow.async_feedback.types import (
HumanFeedbackPending,
@@ -41,4 +43,15 @@ __all__ = [
"HumanFeedbackPending",
"HumanFeedbackProvider",
"PendingFeedbackContext",
"_extension_exports",
]
_extension_exports: dict[str, Any] = {}
def __getattr__(name: str) -> Any:
"""Support extensions via dynamic attribute lookup."""
if name in _extension_exports:
return _extension_exports[name]
msg = f"module {__name__!r} has no attribute {name!r}"
raise AttributeError(msg)

278
lib/crewai/src/crewai/flow/flow.py
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
@@ -45,6 +52,7 @@ from crewai.events.listeners.tracing.utils import (
has_user_declined_tracing,
set_tracing_enabled,
should_enable_tracing,
should_suppress_tracing_messages,
)
from crewai.events.types.flow_events import (
FlowCreatedEvent,
@@ -408,6 +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.
@@ -422,7 +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"):
@@ -1592,7 +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,
@@ -1603,7 +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"
)
@@ -1695,6 +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,
@@ -1706,13 +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()
@@ -1787,40 +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)
@@ -2026,15 +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)] = (
@@ -2074,12 +2194,14 @@ class Flow(Generic[T], metaclass=FlowMeta):
racing_members,
other_listeners,
listener_result,
triggering_event_id,
current_triggering_event_id,
)
else:
tasks = [
self._execute_single_listener(
listener_name, listener_result, triggering_event_id
listener_name,
listener_result,
current_triggering_event_id,
)
for listener_name in listeners_triggered
]
@@ -2262,7 +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,
@@ -2275,8 +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
@@ -2302,7 +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
@@ -2340,46 +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
@@ -2626,6 +2710,8 @@ class Flow(Generic[T], metaclass=FlowMeta):
@staticmethod
def _show_tracing_disabled_message() -> None:
"""Show a message when tracing is disabled."""
if should_suppress_tracing_messages():
return
console = Console()

25
lib/crewai/src/crewai/hooks/llm_hooks.py
View File

@@ -3,7 +3,12 @@ from __future__ import annotations
from typing import TYPE_CHECKING, Any, cast
from crewai.events.event_listener import event_listener
from crewai.hooks.types import AfterLLMCallHookType, BeforeLLMCallHookType
from crewai.hooks.types import (
AfterLLMCallHookCallable,
AfterLLMCallHookType,
BeforeLLMCallHookCallable,
BeforeLLMCallHookType,
)
from crewai.utilities.printer import Printer
@@ -149,12 +154,12 @@ class LLMCallHookContext:
event_listener.formatter.resume_live_updates()
_before_llm_call_hooks: list[BeforeLLMCallHookType] = []
_after_llm_call_hooks: list[AfterLLMCallHookType] = []
_before_llm_call_hooks: list[BeforeLLMCallHookType | BeforeLLMCallHookCallable] = []
_after_llm_call_hooks: list[AfterLLMCallHookType | AfterLLMCallHookCallable] = []
def register_before_llm_call_hook(
hook: BeforeLLMCallHookType,
hook: BeforeLLMCallHookType | BeforeLLMCallHookCallable,
) -> None:
"""Register a global before_llm_call hook.
@@ -190,7 +195,7 @@ def register_before_llm_call_hook(
def register_after_llm_call_hook(
hook: AfterLLMCallHookType,
hook: AfterLLMCallHookType | AfterLLMCallHookCallable,
) -> None:
"""Register a global after_llm_call hook.
@@ -217,7 +222,9 @@ def register_after_llm_call_hook(
_after_llm_call_hooks.append(hook)
def get_before_llm_call_hooks() -> list[BeforeLLMCallHookType]:
def get_before_llm_call_hooks() -> list[
BeforeLLMCallHookType | BeforeLLMCallHookCallable
]:
"""Get all registered global before_llm_call hooks.
Returns:
@@ -226,7 +233,7 @@ def get_before_llm_call_hooks() -> list[BeforeLLMCallHookType]:
return _before_llm_call_hooks.copy()
def get_after_llm_call_hooks() -> list[AfterLLMCallHookType]:
def get_after_llm_call_hooks() -> list[AfterLLMCallHookType | AfterLLMCallHookCallable]:
"""Get all registered global after_llm_call hooks.
Returns:
@@ -236,7 +243,7 @@ def get_after_llm_call_hooks() -> list[AfterLLMCallHookType]:
def unregister_before_llm_call_hook(
hook: BeforeLLMCallHookType,
hook: BeforeLLMCallHookType | BeforeLLMCallHookCallable,
) -> bool:
"""Unregister a specific global before_llm_call hook.
@@ -262,7 +269,7 @@ def unregister_before_llm_call_hook(
def unregister_after_llm_call_hook(
hook: AfterLLMCallHookType,
hook: AfterLLMCallHookType | AfterLLMCallHookCallable,
) -> bool:
"""Unregister a specific global after_llm_call hook.

27
lib/crewai/src/crewai/hooks/tool_hooks.py
View File

@@ -3,7 +3,12 @@ from __future__ import annotations
from typing import TYPE_CHECKING, Any
from crewai.events.event_listener import event_listener
from crewai.hooks.types import AfterToolCallHookType, BeforeToolCallHookType
from crewai.hooks.types import (
AfterToolCallHookCallable,
AfterToolCallHookType,
BeforeToolCallHookCallable,
BeforeToolCallHookType,
)
from crewai.utilities.printer import Printer
@@ -112,12 +117,12 @@ class ToolCallHookContext:
# Global hook registries
_before_tool_call_hooks: list[BeforeToolCallHookType] = []
_after_tool_call_hooks: list[AfterToolCallHookType] = []
_before_tool_call_hooks: list[BeforeToolCallHookType | BeforeToolCallHookCallable] = []
_after_tool_call_hooks: list[AfterToolCallHookType | AfterToolCallHookCallable] = []
def register_before_tool_call_hook(
hook: BeforeToolCallHookType,
hook: BeforeToolCallHookType | BeforeToolCallHookCallable,
) -> None:
"""Register a global before_tool_call hook.
@@ -154,7 +159,7 @@ def register_before_tool_call_hook(
def register_after_tool_call_hook(
hook: AfterToolCallHookType,
hook: AfterToolCallHookType | AfterToolCallHookCallable,
) -> None:
"""Register a global after_tool_call hook.
@@ -184,7 +189,9 @@ def register_after_tool_call_hook(
_after_tool_call_hooks.append(hook)
def get_before_tool_call_hooks() -> list[BeforeToolCallHookType]:
def get_before_tool_call_hooks() -> list[
BeforeToolCallHookType | BeforeToolCallHookCallable
]:
"""Get all registered global before_tool_call hooks.
Returns:
@@ -193,7 +200,9 @@ def get_before_tool_call_hooks() -> list[BeforeToolCallHookType]:
return _before_tool_call_hooks.copy()
def get_after_tool_call_hooks() -> list[AfterToolCallHookType]:
def get_after_tool_call_hooks() -> list[
AfterToolCallHookType | AfterToolCallHookCallable
]:
"""Get all registered global after_tool_call hooks.
Returns:
@@ -203,7 +212,7 @@ def get_after_tool_call_hooks() -> list[AfterToolCallHookType]:
def unregister_before_tool_call_hook(
hook: BeforeToolCallHookType,
hook: BeforeToolCallHookType | BeforeToolCallHookCallable,
) -> bool:
"""Unregister a specific global before_tool_call hook.
@@ -229,7 +238,7 @@ def unregister_before_tool_call_hook(
def unregister_after_tool_call_hook(
hook: AfterToolCallHookType,
hook: AfterToolCallHookType | AfterToolCallHookCallable,
) -> bool:
"""Unregister a specific global after_tool_call hook.

1
lib/crewai/src/crewai/knowledge/source/utils/__init__.py Normal file
View File

@@ -0,0 +1 @@
"""Knowledge source utilities."""

70
lib/crewai/src/crewai/knowledge/source/utils/source_helper.py Normal file
View File

@@ -0,0 +1,70 @@
"""Helper utilities for knowledge sources."""
from typing import Any, ClassVar
from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
from crewai.knowledge.source.csv_knowledge_source import CSVKnowledgeSource
from crewai.knowledge.source.excel_knowledge_source import ExcelKnowledgeSource
from crewai.knowledge.source.json_knowledge_source import JSONKnowledgeSource
from crewai.knowledge.source.pdf_knowledge_source import PDFKnowledgeSource
from crewai.knowledge.source.text_file_knowledge_source import TextFileKnowledgeSource
class SourceHelper:
"""Helper class for creating and managing knowledge sources."""
SUPPORTED_FILE_TYPES: ClassVar[list[str]] = [
".csv",
".pdf",
".json",
".txt",
".xlsx",
".xls",
]
_FILE_TYPE_MAP: ClassVar[dict[str, type[BaseKnowledgeSource]]] = {
".csv": CSVKnowledgeSource,
".pdf": PDFKnowledgeSource,
".json": JSONKnowledgeSource,
".txt": TextFileKnowledgeSource,
".xlsx": ExcelKnowledgeSource,
".xls": ExcelKnowledgeSource,
}
@classmethod
def is_supported_file(cls, file_path: str) -> bool:
"""Check if a file type is supported.
Args:
file_path: Path to the file.
Returns:
True if the file type is supported.
"""
return file_path.lower().endswith(tuple(cls.SUPPORTED_FILE_TYPES))
@classmethod
def get_source(
cls, file_path: str, metadata: dict[str, Any] | None = None
) -> BaseKnowledgeSource:
"""Create appropriate KnowledgeSource based on file extension.
Args:
file_path: Path to the file.
metadata: Optional metadata to attach to the source.
Returns:
The appropriate KnowledgeSource instance.
Raises:
ValueError: If the file type is not supported.
"""
if not cls.is_supported_file(file_path):
raise ValueError(f"Unsupported file type: {file_path}")
lower_path = file_path.lower()
for ext, source_cls in cls._FILE_TYPE_MAP.items():
if lower_path.endswith(ext):
return source_cls(file_path=[file_path], metadata=metadata)
raise ValueError(f"Unsupported file type: {file_path}")

2
lib/crewai/src/crewai/llms/providers/anthropic/completion.py
View File

@@ -1580,10 +1580,12 @@ class AnthropicCompletion(BaseLLM):
usage = response.usage
input_tokens = getattr(usage, "input_tokens", 0)
output_tokens = getattr(usage, "output_tokens", 0)
cache_read_tokens = getattr(usage, "cache_read_input_tokens", 0) or 0
return {
"input_tokens": input_tokens,
"output_tokens": output_tokens,
"total_tokens": input_tokens + output_tokens,
"cached_prompt_tokens": cache_read_tokens,
}
return {"total_tokens": 0}

15
lib/crewai/src/crewai/llms/providers/azure/completion.py
View File

@@ -425,8 +425,9 @@ class AzureCompletion(BaseLLM):
"stream": self.stream,
}
model_extras: dict[str, Any] = {}
if self.stream:
params["model_extras"] = {"stream_options": {"include_usage": True}}
model_extras["stream_options"] = {"include_usage": True}
if response_model and self.is_openai_model:
model_description = generate_model_description(response_model)
@@ -464,6 +465,13 @@ class AzureCompletion(BaseLLM):
params["tools"] = self._convert_tools_for_interference(tools)
params["tool_choice"] = "auto"
prompt_cache_key = self.additional_params.get("prompt_cache_key")
if prompt_cache_key:
model_extras["prompt_cache_key"] = prompt_cache_key
if model_extras:
params["model_extras"] = model_extras
additional_params = self.additional_params
additional_drop_params = additional_params.get("additional_drop_params")
drop_params = additional_params.get("drop_params")
@@ -1063,10 +1071,15 @@ class AzureCompletion(BaseLLM):
"""Extract token usage from Azure response."""
if hasattr(response, "usage") and response.usage:
usage = response.usage
cached_tokens = 0
prompt_details = getattr(usage, "prompt_tokens_details", None)
if prompt_details:
cached_tokens = getattr(prompt_details, "cached_tokens", 0) or 0
return {
"prompt_tokens": getattr(usage, "prompt_tokens", 0),
"completion_tokens": getattr(usage, "completion_tokens", 0),
"total_tokens": getattr(usage, "total_tokens", 0),
"cached_prompt_tokens": cached_tokens,
}
return {"total_tokens": 0}

2
lib/crewai/src/crewai/llms/providers/gemini/completion.py
View File

@@ -1295,11 +1295,13 @@ class GeminiCompletion(BaseLLM):
"""Extract token usage from Gemini response."""
if response.usage_metadata:
usage = response.usage_metadata
cached_tokens = getattr(usage, "cached_content_token_count", 0) or 0
return {
"prompt_token_count": getattr(usage, "prompt_token_count", 0),
"candidates_token_count": getattr(usage, "candidates_token_count", 0),
"total_token_count": getattr(usage, "total_token_count", 0),
"total_tokens": getattr(usage, "total_token_count", 0),
"cached_prompt_tokens": cached_tokens,
}
return {"total_tokens": 0}

230
lib/crewai/src/crewai/llms/providers/openai/completion.py
View File

@@ -1094,11 +1094,7 @@ class OpenAICompletion(BaseLLM):
if reasoning_items:
self._last_reasoning_items = reasoning_items
if event.response and event.response.usage:
usage = {
"prompt_tokens": event.response.usage.input_tokens,
"completion_tokens": event.response.usage.output_tokens,
"total_tokens": event.response.usage.total_tokens,
}
usage = self._extract_responses_token_usage(event.response)
self._track_token_usage_internal(usage)
# If parse_tool_outputs is enabled, return structured result
@@ -1222,11 +1218,7 @@ class OpenAICompletion(BaseLLM):
if reasoning_items:
self._last_reasoning_items = reasoning_items
if event.response and event.response.usage:
usage = {
"prompt_tokens": event.response.usage.input_tokens,
"completion_tokens": event.response.usage.output_tokens,
"total_tokens": event.response.usage.total_tokens,
}
usage = self._extract_responses_token_usage(event.response)
self._track_token_usage_internal(usage)
# If parse_tool_outputs is enabled, return structured result
@@ -1310,11 +1302,18 @@ class OpenAICompletion(BaseLLM):
def _extract_responses_token_usage(self, response: Response) -> dict[str, Any]:
"""Extract token usage from Responses API response."""
if response.usage:
return {
result = {
"prompt_tokens": response.usage.input_tokens,
"completion_tokens": response.usage.output_tokens,
"total_tokens": response.usage.total_tokens,
}
# Extract cached prompt tokens from input_tokens_details
input_details = getattr(response.usage, "input_tokens_details", None)
if input_details:
result["cached_prompt_tokens"] = (
getattr(input_details, "cached_tokens", 0) or 0
)
return result
return {"total_tokens": 0}
def _extract_builtin_tool_outputs(self, response: Response) -> ResponsesAPIResult:
@@ -1696,6 +1695,99 @@ class OpenAICompletion(BaseLLM):
return content
def _finalize_streaming_response(
self,
full_response: str,
tool_calls: dict[int, dict[str, Any]],
usage_data: dict[str, int],
params: dict[str, Any],
available_functions: dict[str, Any] | None = None,
from_task: Any | None = None,
from_agent: Any | None = None,
) -> str | list[dict[str, Any]]:
"""Finalize a streaming response with usage tracking, tool call handling, and events.
Args:
full_response: The accumulated text response from the stream.
tool_calls: Accumulated tool calls from the stream, keyed by index.
usage_data: Token usage data from the stream.
params: The completion parameters containing messages.
available_functions: Available functions for tool calling.
from_task: Task that initiated the call.
from_agent: Agent that initiated the call.
Returns:
Tool calls list when tools were invoked without available_functions,
tool execution result when available_functions is provided,
or the text response string.
"""
self._track_token_usage_internal(usage_data)
if tool_calls and not available_functions:
tool_calls_list = [
{
"id": call_data["id"],
"type": "function",
"function": {
"name": call_data["name"],
"arguments": call_data["arguments"],
},
"index": call_data["index"],
}
for call_data in tool_calls.values()
]
self._emit_call_completed_event(
response=tool_calls_list,
call_type=LLMCallType.TOOL_CALL,
from_task=from_task,
from_agent=from_agent,
messages=params["messages"],
)
return tool_calls_list
if tool_calls and available_functions:
for call_data in tool_calls.values():
function_name = call_data["name"]
arguments = call_data["arguments"]
if not function_name or not arguments:
continue
if function_name not in available_functions:
logging.warning(
f"Function '{function_name}' not found in available functions"
)
continue
try:
function_args = json.loads(arguments)
except json.JSONDecodeError as e:
logging.error(f"Failed to parse streamed tool arguments: {e}")
continue
result = self._handle_tool_execution(
function_name=function_name,
function_args=function_args,
available_functions=available_functions,
from_task=from_task,
from_agent=from_agent,
)
if result is not None:
return result
full_response = self._apply_stop_words(full_response)
self._emit_call_completed_event(
response=full_response,
call_type=LLMCallType.LLM_CALL,
from_task=from_task,
from_agent=from_agent,
messages=params["messages"],
)
return full_response
def _handle_streaming_completion(
self,
params: dict[str, Any],
@@ -1703,7 +1795,7 @@ class OpenAICompletion(BaseLLM):
from_task: Any | None = None,
from_agent: Any | None = None,
response_model: type[BaseModel] | None = None,
) -> str | BaseModel:
) -> str | list[dict[str, Any]] | BaseModel:
"""Handle streaming chat completion."""
full_response = ""
tool_calls: dict[int, dict[str, Any]] = {}
@@ -1820,54 +1912,20 @@ class OpenAICompletion(BaseLLM):
response_id=response_id_stream,
)
self._track_token_usage_internal(usage_data)
if tool_calls and available_functions:
for call_data in tool_calls.values():
function_name = call_data["name"]
arguments = call_data["arguments"]
# Skip if function name is empty or arguments are empty
if not function_name or not arguments:
continue
# Check if function exists in available functions
if function_name not in available_functions:
logging.warning(
f"Function '{function_name}' not found in available functions"
)
continue
try:
function_args = json.loads(arguments)
except json.JSONDecodeError as e:
logging.error(f"Failed to parse streamed tool arguments: {e}")
continue
result = self._handle_tool_execution(
function_name=function_name,
function_args=function_args,
available_functions=available_functions,
from_task=from_task,
from_agent=from_agent,
)
if result is not None:
return result
full_response = self._apply_stop_words(full_response)
self._emit_call_completed_event(
response=full_response,
call_type=LLMCallType.LLM_CALL,
result = self._finalize_streaming_response(
full_response=full_response,
tool_calls=tool_calls,
usage_data=usage_data,
params=params,
available_functions=available_functions,
from_task=from_task,
from_agent=from_agent,
messages=params["messages"],
)
return self._invoke_after_llm_call_hooks(
params["messages"], full_response, from_agent
)
if isinstance(result, str):
return self._invoke_after_llm_call_hooks(
params["messages"], result, from_agent
)
return result
async def _ahandle_completion(
self,
@@ -2016,7 +2074,7 @@ class OpenAICompletion(BaseLLM):
from_task: Any | None = None,
from_agent: Any | None = None,
response_model: type[BaseModel] | None = None,
) -> str | BaseModel:
) -> str | list[dict[str, Any]] | BaseModel:
"""Handle async streaming chat completion."""
full_response = ""
tool_calls: dict[int, dict[str, Any]] = {}
@@ -2142,51 +2200,16 @@ class OpenAICompletion(BaseLLM):
response_id=response_id_stream,
)
self._track_token_usage_internal(usage_data)
if tool_calls and available_functions:
for call_data in tool_calls.values():
function_name = call_data["name"]
arguments = call_data["arguments"]
if not function_name or not arguments:
continue
if function_name not in available_functions:
logging.warning(
f"Function '{function_name}' not found in available functions"
)
continue
try:
function_args = json.loads(arguments)
except json.JSONDecodeError as e:
logging.error(f"Failed to parse streamed tool arguments: {e}")
continue
result = self._handle_tool_execution(
function_name=function_name,
function_args=function_args,
available_functions=available_functions,
from_task=from_task,
from_agent=from_agent,
)
if result is not None:
return result
full_response = self._apply_stop_words(full_response)
self._emit_call_completed_event(
response=full_response,
call_type=LLMCallType.LLM_CALL,
return self._finalize_streaming_response(
full_response=full_response,
tool_calls=tool_calls,
usage_data=usage_data,
params=params,
available_functions=available_functions,
from_task=from_task,
from_agent=from_agent,
messages=params["messages"],
)
return full_response
def supports_function_calling(self) -> bool:
"""Check if the model supports function calling."""
return not self.is_o1_model
@@ -2240,11 +2263,18 @@ class OpenAICompletion(BaseLLM):
"""Extract token usage from OpenAI ChatCompletion or ChatCompletionChunk response."""
if hasattr(response, "usage") and response.usage:
usage = response.usage
return {
result = {
"prompt_tokens": getattr(usage, "prompt_tokens", 0),
"completion_tokens": getattr(usage, "completion_tokens", 0),
"total_tokens": getattr(usage, "total_tokens", 0),
}
# Extract cached prompt tokens from prompt_tokens_details
prompt_details = getattr(usage, "prompt_tokens_details", None)
if prompt_details:
result["cached_prompt_tokens"] = (
getattr(prompt_details, "cached_tokens", 0) or 0
)
return result
return {"total_tokens": 0}
def _format_messages(self, messages: str | list[LLMMessage]) -> list[LLMMessage]:

77
lib/crewai/src/crewai/project/crew_base.py
View File

@@ -27,6 +27,8 @@ if TYPE_CHECKING:
from crewai import Agent, Task
from crewai.agents.cache.cache_handler import CacheHandler
from crewai.crews.crew_output import CrewOutput
from crewai.hooks.llm_hooks import LLMCallHookContext
from crewai.hooks.tool_hooks import ToolCallHookContext
from crewai.project.wrappers import (
CrewInstance,
OutputJsonClass,
@@ -34,6 +36,8 @@ if TYPE_CHECKING:
)
from crewai.tasks.task_output import TaskOutput
_post_initialize_crew_hooks: list[Callable[[Any], None]] = []
class AgentConfig(TypedDict, total=False):
"""Type definition for agent configuration dictionary.
@@ -266,6 +270,9 @@ class CrewBaseMeta(type):
instance.map_all_agent_variables()
instance.map_all_task_variables()
for hook in _post_initialize_crew_hooks:
hook(instance)
original_methods = {
name: method
for name, method in cls.__dict__.items()
@@ -485,47 +492,61 @@ def _register_crew_hooks(instance: CrewInstance, cls: type) -> None:
if has_agent_filter:
agents_filter = hook_method._filter_agents
def make_filtered_before_llm(bound_fn, agents_list):
def filtered(context):
def make_filtered_before_llm(
bound_fn: Callable[[LLMCallHookContext], bool | None],
agents_list: list[str],
) -> Callable[[LLMCallHookContext], bool | None]:
def filtered(context: LLMCallHookContext) -> bool | None:
if context.agent and context.agent.role not in agents_list:
return None
return bound_fn(context)
return filtered
final_hook = make_filtered_before_llm(bound_hook, agents_filter)
before_llm_hook = make_filtered_before_llm(bound_hook, agents_filter)
else:
final_hook = bound_hook
before_llm_hook = bound_hook
register_before_llm_call_hook(final_hook)
instance._registered_hook_functions.append(("before_llm_call", final_hook))
register_before_llm_call_hook(before_llm_hook)
instance._registered_hook_functions.append(
("before_llm_call", before_llm_hook)
)
if hasattr(hook_method, "is_after_llm_call_hook"):
if has_agent_filter:
agents_filter = hook_method._filter_agents
def make_filtered_after_llm(bound_fn, agents_list):
def filtered(context):
def make_filtered_after_llm(
bound_fn: Callable[[LLMCallHookContext], str | None],
agents_list: list[str],
) -> Callable[[LLMCallHookContext], str | None]:
def filtered(context: LLMCallHookContext) -> str | None:
if context.agent and context.agent.role not in agents_list:
return None
return bound_fn(context)
return filtered
final_hook = make_filtered_after_llm(bound_hook, agents_filter)
after_llm_hook = make_filtered_after_llm(bound_hook, agents_filter)
else:
final_hook = bound_hook
after_llm_hook = bound_hook
register_after_llm_call_hook(final_hook)
instance._registered_hook_functions.append(("after_llm_call", final_hook))
register_after_llm_call_hook(after_llm_hook)
instance._registered_hook_functions.append(
("after_llm_call", after_llm_hook)
)
if hasattr(hook_method, "is_before_tool_call_hook"):
if has_tool_filter or has_agent_filter:
tools_filter = getattr(hook_method, "_filter_tools", None)
agents_filter = getattr(hook_method, "_filter_agents", None)
def make_filtered_before_tool(bound_fn, tools_list, agents_list):
def filtered(context):
def make_filtered_before_tool(
bound_fn: Callable[[ToolCallHookContext], bool | None],
tools_list: list[str] | None,
agents_list: list[str] | None,
) -> Callable[[ToolCallHookContext], bool | None]:
def filtered(context: ToolCallHookContext) -> bool | None:
if tools_list and context.tool_name not in tools_list:
return None
if (
@@ -538,22 +559,28 @@ def _register_crew_hooks(instance: CrewInstance, cls: type) -> None:
return filtered
final_hook = make_filtered_before_tool(
before_tool_hook = make_filtered_before_tool(
bound_hook, tools_filter, agents_filter
)
else:
final_hook = bound_hook
before_tool_hook = bound_hook
register_before_tool_call_hook(final_hook)
instance._registered_hook_functions.append(("before_tool_call", final_hook))
register_before_tool_call_hook(before_tool_hook)
instance._registered_hook_functions.append(
("before_tool_call", before_tool_hook)
)
if hasattr(hook_method, "is_after_tool_call_hook"):
if has_tool_filter or has_agent_filter:
tools_filter = getattr(hook_method, "_filter_tools", None)
agents_filter = getattr(hook_method, "_filter_agents", None)
def make_filtered_after_tool(bound_fn, tools_list, agents_list):
def filtered(context):
def make_filtered_after_tool(
bound_fn: Callable[[ToolCallHookContext], str | None],
tools_list: list[str] | None,
agents_list: list[str] | None,
) -> Callable[[ToolCallHookContext], str | None]:
def filtered(context: ToolCallHookContext) -> str | None:
if tools_list and context.tool_name not in tools_list:
return None
if (
@@ -566,14 +593,16 @@ def _register_crew_hooks(instance: CrewInstance, cls: type) -> None:
return filtered
final_hook = make_filtered_after_tool(
after_tool_hook = make_filtered_after_tool(
bound_hook, tools_filter, agents_filter
)
else:
final_hook = bound_hook
after_tool_hook = bound_hook
register_after_tool_call_hook(final_hook)
instance._registered_hook_functions.append(("after_tool_call", final_hook))
register_after_tool_call_hook(after_tool_hook)
instance._registered_hook_functions.append(
("after_tool_call", after_tool_hook)
)
instance._hooks_being_registered = False

2
lib/crewai/src/crewai/project/wrappers.py
View File

@@ -72,6 +72,8 @@ class CrewInstance(Protocol):
__crew_metadata__: CrewMetadata
_mcp_server_adapter: Any
_all_methods: dict[str, Callable[..., Any]]
_registered_hook_functions: list[tuple[str, Callable[..., Any]]]
_hooks_being_registered: bool
agents: list[Agent]
tasks: list[Task]
base_directory: Path

25
lib/crewai/src/crewai/task.py
View File

@@ -31,6 +31,8 @@ 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 (
TaskCompletedEvent,
@@ -496,6 +498,7 @@ class Task(BaseModel):
tools: list[BaseTool] | None = None,
) -> TaskOutput:
"""Execute the task synchronously."""
self.start_time = datetime.datetime.now()
return self._execute_core(agent, context, tools)
@property
@@ -536,6 +539,7 @@ class Task(BaseModel):
) -> None:
"""Execute the task asynchronously with context handling."""
try:
self.start_time = datetime.datetime.now()
result = self._execute_core(agent, context, tools)
future.set_result(result)
except Exception as e:
@@ -548,6 +552,7 @@ class Task(BaseModel):
tools: list[BaseTool] | None = None,
) -> TaskOutput:
"""Execute the task asynchronously using native async/await."""
self.start_time = datetime.datetime.now()
return await self._aexecute_core(agent, context, tools)
async def _aexecute_core(
@@ -557,6 +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
@@ -566,8 +572,6 @@ class Task(BaseModel):
f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly and should be executed in a Crew using a specific process that support that, like hierarchical."
)
self.start_time = datetime.datetime.now()
self.prompt_context = context
tools = tools or self.tools or []
@@ -579,6 +583,8 @@ class Task(BaseModel):
tools=tools,
)
self._post_agent_execution(agent)
if not self._guardrails and not self._guardrail:
pydantic_output, json_output = self._export_output(result)
else:
@@ -644,6 +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,
@@ -652,6 +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
@@ -661,8 +669,6 @@ class Task(BaseModel):
f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly and should be executed in a Crew using a specific process that support that, like hierarchical."
)
self.start_time = datetime.datetime.now()
self.prompt_context = context
tools = tools or self.tools or []
@@ -674,6 +680,8 @@ class Task(BaseModel):
tools=tools,
)
self._post_agent_execution(agent)
if not self._guardrails and not self._guardrail:
pydantic_output, json_output = self._export_output(result)
else:
@@ -740,6 +748,10 @@ 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
def prompt(self) -> str:
"""Generates the task prompt with optional markdown formatting.
@@ -863,6 +875,11 @@ Follow these guidelines:
except ValueError as e:
raise ValueError(f"Error interpolating description: {e!s}") from e
self.description = process_content(self.description, {"task": self})
self._original_expected_output = process_content(
self._original_expected_output, {"task": self}
)
try:
self.expected_output = interpolate_only(
input_string=self._original_expected_output, inputs=inputs

31
lib/crewai/src/crewai/tasks/hallucination_guardrail.py
View File

@@ -6,6 +6,7 @@ Classes:
HallucinationGuardrail: Placeholder guardrail that validates task outputs.
"""
from collections.abc import Callable
from typing import Any
from crewai.llm import LLM
@@ -13,32 +14,36 @@ from crewai.tasks.task_output import TaskOutput
from crewai.utilities.logger import Logger
_validate_output_hook: Callable[..., tuple[bool, Any]] | None = None
class HallucinationGuardrail:
"""Placeholder for the HallucinationGuardrail feature.
Attributes:
context: The reference context that outputs would be checked against.
context: Optional reference context that outputs would be checked against.
llm: The language model that would be used for evaluation.
threshold: Optional minimum faithfulness score that would be required to pass.
tool_response: Optional tool response information that would be used in evaluation.
Examples:
>>> # Basic usage with default verdict logic
>>> # Basic usage without context (uses task expected_output as context)
>>> guardrail = HallucinationGuardrail(llm=agent.llm)
>>> # With context for reference
>>> guardrail = HallucinationGuardrail(
... context="AI helps with various tasks including analysis and generation.",
... llm=agent.llm,
... context="AI helps with various tasks including analysis and generation.",
... )
>>> # With custom threshold for stricter validation
>>> strict_guardrail = HallucinationGuardrail(
... context="Quantum computing uses qubits in superposition.",
... llm=agent.llm,
... threshold=8.0, # Would require score >= 8 to pass in enterprise version
... threshold=8.0, # Require score >= 8 to pass
... )
>>> # With tool response for additional context
>>> guardrail_with_tools = HallucinationGuardrail(
... context="The current weather data",
... llm=agent.llm,
... tool_response="Weather API returned: Temperature 22°C, Humidity 65%",
... )
@@ -46,16 +51,17 @@ class HallucinationGuardrail:
def __init__(
self,
context: str,
llm: LLM,
context: str | None = None,
threshold: float | None = None,
tool_response: str = "",
):
"""Initialize the HallucinationGuardrail placeholder.
Args:
context: The reference context that outputs would be checked against.
llm: The language model that would be used for evaluation.
context: Optional reference context that outputs would be checked against.
If not provided, the task's expected_output will be used as context.
threshold: Optional minimum faithfulness score that would be required to pass.
tool_response: Optional tool response information that would be used in evaluation.
"""
@@ -78,16 +84,17 @@ class HallucinationGuardrail:
def __call__(self, task_output: TaskOutput) -> tuple[bool, Any]:
"""Validate a task output against hallucination criteria.
In the open source, this method always returns that the output is valid.
Args:
task_output: The output to be validated.
Returns:
A tuple containing:
- True
- The raw task output
- True if validation passed, False otherwise
- The raw task output if valid, or error feedback if invalid
"""
if callable(_validate_output_hook):
return _validate_output_hook(self, task_output)
self._logger.log(
"warning",
"Premium hallucination detection skipped (use for free at https://app.crewai.com)\n",

16
lib/crewai/src/crewai/tasks/llm_guardrail.py
View File

@@ -1,6 +1,10 @@
import asyncio
from collections.abc import Coroutine
import inspect
from typing import Any
from pydantic import BaseModel, Field
from typing_extensions import TypeIs
from crewai.agent import Agent
from crewai.lite_agent_output import LiteAgentOutput
@@ -8,6 +12,13 @@ from crewai.llms.base_llm import BaseLLM
from crewai.tasks.task_output import TaskOutput
def _is_coroutine(
obj: LiteAgentOutput | Coroutine[Any, Any, LiteAgentOutput],
) -> TypeIs[Coroutine[Any, Any, LiteAgentOutput]]:
"""Check if obj is a coroutine for type narrowing."""
return inspect.iscoroutine(obj)
class LLMGuardrailResult(BaseModel):
valid: bool = Field(
description="Whether the task output complies with the guardrail"
@@ -62,7 +73,10 @@ class LLMGuardrail:
- If the Task result complies with the guardrail, saying that is valid
"""
return agent.kickoff(query, response_format=LLMGuardrailResult)
kickoff_result = agent.kickoff(query, response_format=LLMGuardrailResult)
if _is_coroutine(kickoff_result):
return asyncio.run(kickoff_result)
return kickoff_result
def __call__(self, task_output: TaskOutput) -> tuple[bool, Any]:
"""Validates the output of a task based on specified criteria.

5
lib/crewai/src/crewai/telemetry/telemetry.py
View File

@@ -903,7 +903,7 @@ class Telemetry:
{
"id": str(task.id),
"description": task.description,
"output": task.output.raw_output,
"output": task.output.raw if task.output else "",
}
for task in crew.tasks
]
@@ -923,6 +923,9 @@ class Telemetry:
value: The attribute value.
"""
if span is None:
return
def _operation() -> None:
return span.set_attribute(key, value)

8
lib/crewai/src/crewai/tools/tool_usage.py
View File

@@ -270,6 +270,7 @@ class ToolUsage:
result = None # type: ignore
should_retry = False
available_tool = None
error_event_emitted = False
try:
if self.tools_handler and self.tools_handler.cache:
@@ -408,6 +409,7 @@ class ToolUsage:
except Exception as e:
self.on_tool_error(tool=tool, tool_calling=calling, e=e)
error_event_emitted = True
self._run_attempts += 1
if self._run_attempts > self._max_parsing_attempts:
self._telemetry.tool_usage_error(llm=self.function_calling_llm)
@@ -435,7 +437,7 @@ class ToolUsage:
result = self._format_result(result=result)
finally:
if started_event_emitted:
if started_event_emitted and not error_event_emitted:
self.on_tool_use_finished(
tool=tool,
tool_calling=calling,
@@ -500,6 +502,7 @@ class ToolUsage:
result = None # type: ignore
should_retry = False
available_tool = None
error_event_emitted = False
try:
if self.tools_handler and self.tools_handler.cache:
@@ -638,6 +641,7 @@ class ToolUsage:
except Exception as e:
self.on_tool_error(tool=tool, tool_calling=calling, e=e)
error_event_emitted = True
self._run_attempts += 1
if self._run_attempts > self._max_parsing_attempts:
self._telemetry.tool_usage_error(llm=self.function_calling_llm)
@@ -665,7 +669,7 @@ class ToolUsage:
result = self._format_result(result=result)
finally:
if started_event_emitted:
if started_event_emitted and not error_event_emitted:
self.on_tool_use_finished(
tool=tool,
tool_calling=calling,

6
lib/crewai/src/crewai/translations/en.json
View File

@@ -22,9 +22,9 @@
"expected_output": "\nThis is the expected criteria for your final answer: {expected_output}\nyou MUST return the actual complete content as the final answer, not a summary.",
"human_feedback": "You got human feedback on your work, re-evaluate it and give a new Final Answer when ready.\n {human_feedback}",
"getting_input": "This is the agent's final answer: {final_answer}\n\n",
"summarizer_system_message": "You are a helpful assistant that summarizes text.",
"summarize_instruction": "Summarize the following text, make sure to include all the important information: {group}",
"summary": "This is a summary of our conversation so far:\n{merged_summary}",
"summarizer_system_message": "You are a precise assistant that creates structured summaries of agent conversations. You preserve critical context needed for seamless task continuation.",
"summarize_instruction": "Analyze the following conversation and create a structured summary that preserves all information needed to continue the task seamlessly.\n\n<conversation>\n{conversation}\n</conversation>\n\nCreate a summary with these sections:\n1. **Task Overview**: What is the agent trying to accomplish?\n2. **Current State**: What has been completed so far? What step is the agent on?\n3. **Important Discoveries**: Key facts, data, tool results, or findings that must not be lost.\n4. **Next Steps**: What should the agent do next based on the conversation?\n5. **Context to Preserve**: Any specific values, names, URLs, code snippets, or details referenced in the conversation.\n\nWrap your entire summary in <summary> tags.\n\n<summary>\n[Your structured summary here]\n</summary>",
"summary": "<summary>\n{merged_summary}\n</summary>\n\nContinue the task from where the conversation left off. The above is a structured summary of prior context.",
"manager_request": "Your best answer to your coworker asking you this, accounting for the context shared.",
"formatted_task_instructions": "Format your final answer according to the following OpenAPI schema: {output_format}\n\nIMPORTANT: Preserve the original content exactly as-is. Do NOT rewrite, paraphrase, or modify the meaning of the content. Only structure it to match the schema format.\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.",
"conversation_history_instruction": "You are a member of a crew collaborating to achieve a common goal. Your task is a specific action that contributes to this larger objective. For additional context, please review the conversation history between you and the user that led to the initiation of this crew. Use any relevant information or feedback from the conversation to inform your task execution and ensure your response aligns with both the immediate task and the crew's overall goals.",

37
lib/crewai/src/crewai/types/hitl.py
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

275
lib/crewai/src/crewai/utilities/agent_utils.py
View File

@@ -2,6 +2,7 @@ from __future__ import annotations
import asyncio
from collections.abc import Callable, Sequence
import concurrent.futures
import json
import re
from typing import TYPE_CHECKING, Any, Final, Literal, TypedDict
@@ -42,6 +43,8 @@ if TYPE_CHECKING:
from crewai.llm import LLM
from crewai.task import Task
_create_plus_client_hook: Callable[[], Any] | None = None
class SummaryContent(TypedDict):
"""Structure for summary content entries.
@@ -91,7 +94,11 @@ def parse_tools(tools: list[BaseTool]) -> list[CrewStructuredTool]:
for tool in tools:
if isinstance(tool, CrewAITool):
tools_list.append(tool.to_structured_tool())
structured_tool = tool.to_structured_tool()
structured_tool.current_usage_count = 0
if structured_tool._original_tool:
structured_tool._original_tool.current_usage_count = 0
tools_list.append(structured_tool)
else:
raise ValueError("Tool is not a CrewStructuredTool or BaseTool")
@@ -634,6 +641,180 @@ def handle_context_length(
)
def _estimate_token_count(text: str) -> int:
"""Estimate token count using a conservative cross-provider heuristic.
Args:
text: The text to estimate tokens for.
Returns:
Estimated token count (roughly 1 token per 4 characters).
"""
return len(text) // 4
def _format_messages_for_summary(messages: list[LLMMessage]) -> str:
"""Format messages with role labels for summarization.
Skips system messages. Handles None content, tool_calls, and
multimodal content blocks.
Args:
messages: List of messages to format.
Returns:
Role-labeled conversation text.
"""
lines: list[str] = []
for msg in messages:
role = msg.get("role", "user")
if role == "system":
continue
content = msg.get("content")
if content is None:
# Check for tool_calls on assistant messages with no content
tool_calls = msg.get("tool_calls")
if tool_calls:
tool_names = []
for tc in tool_calls:
func = tc.get("function", {})
name = (
func.get("name", "unknown")
if isinstance(func, dict)
else "unknown"
)
tool_names.append(name)
content = f"[Called tools: {', '.join(tool_names)}]"
else:
content = ""
elif isinstance(content, list):
# Multimodal content blocks — extract text parts
text_parts = [
block.get("text", "")
for block in content
if isinstance(block, dict) and block.get("type") == "text"
]
content = " ".join(text_parts) if text_parts else "[multimodal content]"
if role == "assistant":
label = "[ASSISTANT]:"
elif role == "tool":
tool_name = msg.get("name", "unknown")
label = f"[TOOL_RESULT ({tool_name})]:"
else:
label = "[USER]:"
lines.append(f"{label} {content}")
return "\n\n".join(lines)
def _split_messages_into_chunks(
messages: list[LLMMessage], max_tokens: int
) -> list[list[LLMMessage]]:
"""Split messages into chunks at message boundaries.
Excludes system messages from chunks. Each chunk stays under
max_tokens based on estimated token count.
Args:
messages: List of messages to split.
max_tokens: Maximum estimated tokens per chunk.
Returns:
List of message chunks.
"""
non_system = [m for m in messages if m.get("role") != "system"]
if not non_system:
return []
chunks: list[list[LLMMessage]] = []
current_chunk: list[LLMMessage] = []
current_tokens = 0
for msg in non_system:
content = msg.get("content")
if content is None:
msg_text = ""
elif isinstance(content, list):
msg_text = str(content)
else:
msg_text = str(content)
msg_tokens = _estimate_token_count(msg_text)
# If adding this message would exceed the limit and we already have
# messages in the current chunk, start a new chunk
if current_chunk and (current_tokens + msg_tokens) > max_tokens:
chunks.append(current_chunk)
current_chunk = []
current_tokens = 0
current_chunk.append(msg)
current_tokens += msg_tokens
if current_chunk:
chunks.append(current_chunk)
return chunks
def _extract_summary_tags(text: str) -> str:
"""Extract content between <summary></summary> tags.
Falls back to the full text if no tags are found.
Args:
text: Text potentially containing summary tags.
Returns:
Extracted summary content, or full text if no tags found.
"""
match = re.search(r"<summary>(.*?)</summary>", text, re.DOTALL)
if match:
return match.group(1).strip()
return text.strip()
async def _asummarize_chunks(
chunks: list[list[LLMMessage]],
llm: LLM | BaseLLM,
callbacks: list[TokenCalcHandler],
i18n: I18N,
) -> list[SummaryContent]:
"""Summarize multiple message chunks concurrently using asyncio.
Args:
chunks: List of message chunks to summarize.
llm: LLM instance (must support ``acall``).
callbacks: List of callbacks for the LLM.
i18n: I18N instance for prompt templates.
Returns:
Ordered list of summary contents, one per chunk.
"""
async def _summarize_one(chunk: list[LLMMessage]) -> SummaryContent:
conversation_text = _format_messages_for_summary(chunk)
summarization_messages = [
format_message_for_llm(
i18n.slice("summarizer_system_message"), role="system"
),
format_message_for_llm(
i18n.slice("summarize_instruction").format(
conversation=conversation_text
),
),
]
summary = await llm.acall(summarization_messages, callbacks=callbacks)
extracted = _extract_summary_tags(str(summary))
return {"content": extracted}
results = await asyncio.gather(*[_summarize_one(chunk) for chunk in chunks])
return list(results)
def summarize_messages(
messages: list[LLMMessage],
llm: LLM | BaseLLM,
@@ -643,6 +824,10 @@ def summarize_messages(
) -> None:
"""Summarize messages to fit within context window.
Uses structured context compaction: preserves system messages,
splits at message boundaries, formats with role labels, and
produces structured summaries for seamless task continuation.
Preserves any files attached to user messages and re-attaches them to
the summarized message. Files from all user messages are merged.
@@ -651,49 +836,74 @@ def summarize_messages(
llm: LLM instance for summarization
callbacks: List of callbacks for LLM
i18n: I18N instance for messages
verbose: Whether to print progress.
"""
# 1. Extract & preserve file attachments from user messages
preserved_files: dict[str, Any] = {}
for msg in messages:
if msg.get("role") == "user" and msg.get("files"):
preserved_files.update(msg["files"])
messages_string = " ".join(
[str(message.get("content", "")) for message in messages]
)
cut_size = llm.get_context_window_size()
# 2. Extract system messages — never summarize them
system_messages = [m for m in messages if m.get("role") == "system"]
non_system_messages = [m for m in messages if m.get("role") != "system"]
messages_groups = [
{"content": messages_string[i : i + cut_size]}
for i in range(0, len(messages_string), cut_size)
]
# If there are only system messages (or no non-system messages), nothing to summarize
if not non_system_messages:
return
summarized_contents: list[SummaryContent] = []
# 3. Split non-system messages into chunks at message boundaries
max_tokens = llm.get_context_window_size()
chunks = _split_messages_into_chunks(non_system_messages, max_tokens)
total_groups = len(messages_groups)
for idx, group in enumerate(messages_groups, 1):
# 4. Summarize each chunk with role-labeled formatting
total_chunks = len(chunks)
if total_chunks <= 1:
# Single chunk — no benefit from async overhead
summarized_contents: list[SummaryContent] = []
for idx, chunk in enumerate(chunks, 1):
if verbose:
Printer().print(
content=f"Summarizing {idx}/{total_chunks}...",
color="yellow",
)
conversation_text = _format_messages_for_summary(chunk)
summarization_messages = [
format_message_for_llm(
i18n.slice("summarizer_system_message"), role="system"
),
format_message_for_llm(
i18n.slice("summarize_instruction").format(
conversation=conversation_text
),
),
]
summary = llm.call(summarization_messages, callbacks=callbacks)
extracted = _extract_summary_tags(str(summary))
summarized_contents.append({"content": extracted})
else:
# Multiple chunks — summarize in parallel via asyncio
if verbose:
Printer().print(
content=f"Summarizing {idx}/{total_groups}...",
content=f"Summarizing {total_chunks} chunks in parallel...",
color="yellow",
)
summarization_messages = [
format_message_for_llm(
i18n.slice("summarizer_system_message"), role="system"
),
format_message_for_llm(
i18n.slice("summarize_instruction").format(group=group["content"]),
),
]
summary = llm.call(
summarization_messages,
callbacks=callbacks,
coro = _asummarize_chunks(
chunks=chunks, llm=llm, callbacks=callbacks, i18n=i18n
)
summarized_contents.append({"content": str(summary)})
if is_inside_event_loop():
with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
summarized_contents = pool.submit(asyncio.run, coro).result()
else:
summarized_contents = asyncio.run(coro)
merged_summary = " ".join(content["content"] for content in summarized_contents)
merged_summary = "\n\n".join(content["content"] for content in summarized_contents)
# 6. Reconstruct messages: [system messages...] + [summary user message]
messages.clear()
messages.extend(system_messages)
summary_message = format_message_for_llm(
i18n.slice("summary").format(merged_summary=merged_summary)
)
@@ -818,12 +1028,15 @@ def load_agent_from_repository(from_repository: str) -> dict[str, Any]:
if from_repository:
import importlib
from crewai.cli.authentication.token import get_auth_token
from crewai.cli.plus_api import PlusAPI
if callable(_create_plus_client_hook):
client = _create_plus_client_hook()
else:
from crewai.cli.authentication.token import get_auth_token
from crewai.cli.plus_api import PlusAPI
client = PlusAPI(api_key=get_auth_token())
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."

16
lib/crewai/src/crewai/utilities/evaluators/crew_evaluator_handler.py
View File

@@ -1,7 +1,7 @@
from __future__ import annotations
from collections import defaultdict
from typing import TYPE_CHECKING
from typing import TYPE_CHECKING, Any
from pydantic import BaseModel, Field, InstanceOf
from rich.box import HEAVY_EDGE
@@ -36,7 +36,13 @@ class CrewEvaluator:
iteration: The current iteration of the evaluation.
"""
def __init__(self, crew: Crew, eval_llm: InstanceOf[BaseLLM]) -> None:
def __init__(
self,
crew: Crew,
eval_llm: InstanceOf[BaseLLM] | str | None = None,
openai_model_name: str | None = None,
llm: InstanceOf[BaseLLM] | str | None = None,
) -> None:
self.crew = crew
self.llm = eval_llm
self.tasks_scores: defaultdict[int, list[float]] = defaultdict(list)
@@ -86,7 +92,9 @@ class CrewEvaluator:
"""
self.iteration = iteration
def print_crew_evaluation_result(self) -> None:
def print_crew_evaluation_result(
self, token_usage: list[dict[str, Any]] | None = None
) -> None:
"""
Prints the evaluation result of the crew in a table.
A Crew with 2 tasks using the command crewai test -n 3
@@ -204,7 +212,7 @@ class CrewEvaluator:
CrewTestResultEvent(
quality=quality_score,
execution_duration=current_task.execution_duration,
model=self.llm.model,
model=getattr(self.llm, "model", str(self.llm)),
crew_name=self.crew.name,
crew=self.crew,
),

4
lib/crewai/src/crewai/utilities/printer.py
View File

@@ -4,6 +4,8 @@ from __future__ import annotations
from typing import TYPE_CHECKING, Final, Literal, NamedTuple
from crewai.events.utils.console_formatter import should_suppress_console_output
if TYPE_CHECKING:
from _typeshed import SupportsWrite
@@ -77,6 +79,8 @@ class Printer:
file: A file-like object (stream); defaults to the current sys.stdout.
flush: Whether to forcibly flush the stream.
"""
if should_suppress_console_output():
return
if isinstance(content, str):
content = [ColoredText(content, color)]
print(

24
lib/crewai/src/crewai/utilities/serialization.py
View File

@@ -19,6 +19,7 @@ def to_serializable(
exclude: set[str] | None = None,
max_depth: int = 5,
_current_depth: int = 0,
_ancestors: set[int] | None = None,
) -> Serializable:
"""Converts a Python object into a JSON-compatible representation.
@@ -31,6 +32,7 @@ def to_serializable(
exclude: Set of keys to exclude from the result.
max_depth: Maximum recursion depth. Defaults to 5.
_current_depth: Current recursion depth (for internal use).
_ancestors: Set of ancestor object ids for cycle detection (for internal use).
Returns:
Serializable: A JSON-compatible structure.
@@ -41,16 +43,29 @@ def to_serializable(
if exclude is None:
exclude = set()
if _ancestors is None:
_ancestors = set()
if isinstance(obj, (str, int, float, bool, type(None))):
return obj
if isinstance(obj, uuid.UUID):
return str(obj)
if isinstance(obj, (date, datetime)):
return obj.isoformat()
object_id = id(obj)
if object_id in _ancestors:
return f"<circular_ref:{type(obj).__name__}>"
new_ancestors = _ancestors | {object_id}
if isinstance(obj, (list, tuple, set)):
return [
to_serializable(
item, max_depth=max_depth, _current_depth=_current_depth + 1
item,
exclude=exclude,
max_depth=max_depth,
_current_depth=_current_depth + 1,
_ancestors=new_ancestors,
)
for item in obj
]
@@ -61,6 +76,7 @@ def to_serializable(
exclude=exclude,
max_depth=max_depth,
_current_depth=_current_depth + 1,
_ancestors=new_ancestors,
)
for key, value in obj.items()
if key not in exclude
@@ -71,12 +87,16 @@ def to_serializable(
obj=obj.model_dump(exclude=exclude),
max_depth=max_depth,
_current_depth=_current_depth + 1,
_ancestors=new_ancestors,
)
except Exception:
try:
return {
_to_serializable_key(k): to_serializable(
v, max_depth=max_depth, _current_depth=_current_depth + 1
v,
max_depth=max_depth,
_current_depth=_current_depth + 1,
_ancestors=new_ancestors,
)
for k, v in obj.__dict__.items()
if k not in (exclude or set())

4
lib/crewai/tests/agents/agent_adapters/test_base_agent_adapter.py
View File

@@ -51,6 +51,10 @@ class ConcreteAgentAdapter(BaseAgentAdapter):
# Dummy implementation for MCP tools
return []
def configure_structured_output(self, task: Any) -> None:
# Dummy implementation for structured output
pass
async def aexecute_task(
self,
task: Any,

18
lib/crewai/tests/agents/test_agent.py
View File

@@ -703,6 +703,8 @@ def test_agent_definition_based_on_dict():
# test for human input
@pytest.mark.vcr()
def test_agent_human_input():
from crewai.core.providers.human_input import SyncHumanInputProvider
# Agent configuration
config = {
"role": "test role",
@@ -720,7 +722,7 @@ def test_agent_human_input():
human_input=True,
)
# Side effect function for _ask_human_input to simulate multiple feedback iterations
# Side effect function for _prompt_input to simulate multiple feedback iterations
feedback_responses = iter(
[
"Don't say hi, say Hello instead!", # First feedback: instruct change
@@ -728,16 +730,16 @@ def test_agent_human_input():
]
)
def ask_human_input_side_effect(*args, **kwargs):
def prompt_input_side_effect(*args, **kwargs):
return next(feedback_responses)
# Patch both _ask_human_input and _invoke_loop to avoid real API/network calls.
# Patch both _prompt_input on provider and _invoke_loop to avoid real API/network calls.
with (
patch.object(
CrewAgentExecutor,
"_ask_human_input",
side_effect=ask_human_input_side_effect,
) as mock_human_input,
SyncHumanInputProvider,
"_prompt_input",
side_effect=prompt_input_side_effect,
) as mock_prompt_input,
patch.object(
CrewAgentExecutor,
"_invoke_loop",
@@ -749,7 +751,7 @@ def test_agent_human_input():
# Assertions to ensure the agent behaves correctly.
# It should have requested feedback twice.
assert mock_human_input.call_count == 2
assert mock_prompt_input.call_count == 2
# The final result should be processed to "Hello"
assert output.strip().lower() == "hello"

12
lib/crewai/tests/agents/test_lite_agent.py
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",

193
lib/crewai/tests/cassettes/agents/test_agent_kickoff_with_platform_tools.yaml
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

460
lib/crewai/tests/cassettes/agents/test_guardrail_reached_attempt_limit.yaml
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

37
lib/crewai/tests/cassettes/agents/test_lite_agent_inside_flow_sync.yaml
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:

37
lib/crewai/tests/cassettes/agents/test_lite_agent_standalone_still_works.yaml
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:

77
lib/crewai/tests/cassettes/agents/test_multiple_agents_in_same_flow.yaml
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:

65
lib/crewai/tests/cassettes/agents/test_native_tool_calling_error_handling.yaml
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:

12
lib/crewai/tests/cassettes/llms/anthropic/test_anthropic_agent_kickoff_structured_output_with_tools.yaml
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

21
lib/crewai/tests/cassettes/llms/anthropic/test_anthropic_agent_kickoff_structured_output_without_tools.yaml
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

332
lib/crewai/tests/cassettes/llms/anthropic/test_anthropic_cached_prompt_tokens.yaml Normal file
View File

@@ -0,0 +1,332 @@
interactions:
- request:
body: '{"max_tokens":4096,"messages":[{"role":"user","content":[{"type":"text","text":"Say
hello in one word.","cache_control":{"type":"ephemeral"}}]}],"model":"claude-sonnet-4-5-20250929","stream":false,"system":"You
are a helpful assistant. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. "}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
anthropic-version:
- '2023-06-01'
connection:
- keep-alive
content-length:
- '5918'
content-type:
- application/json
host:
- api.anthropic.com
x-api-key:
- X-API-KEY-XXX
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:
- 0.73.0
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
x-stainless-timeout:
- NOT_GIVEN
method: POST
uri: https://api.anthropic.com/v1/messages
response:
body:
string: '{"model":"claude-sonnet-4-5-20250929","id":"msg_013xTaKq41TFn6drdxt1mFdx","type":"message","role":"assistant","content":[{"type":"text","text":"Hello!"}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":0,"cache_read_input_tokens":1217,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":5,"service_tier":"standard","inference_geo":"not_available"}}'
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Security-Policy:
- CSP-FILTERED
Content-Type:
- application/json
Date:
- Tue, 10 Feb 2026 18:27:40 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Robots-Tag:
- none
anthropic-organization-id:
- ANTHROPIC-ORGANIZATION-ID-XXX
anthropic-ratelimit-input-tokens-limit:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-input-tokens-remaining:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-input-tokens-reset:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-RESET-XXX
anthropic-ratelimit-output-tokens-limit:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-output-tokens-remaining:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-output-tokens-reset:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-RESET-XXX
anthropic-ratelimit-tokens-limit:
- ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
anthropic-ratelimit-tokens-remaining:
- ANTHROPIC-RATELIMIT-TOKENS-REMAINING-XXX
anthropic-ratelimit-tokens-reset:
- ANTHROPIC-RATELIMIT-TOKENS-RESET-XXX
cf-cache-status:
- DYNAMIC
request-id:
- REQUEST-ID-XXX
strict-transport-security:
- STS-XXX
x-envoy-upstream-service-time:
- '726'
status:
code: 200
message: OK
- request:
body: '{"max_tokens":4096,"messages":[{"role":"user","content":[{"type":"text","text":"Say
goodbye in one word.","cache_control":{"type":"ephemeral"}}]}],"model":"claude-sonnet-4-5-20250929","stream":false,"system":"You
are a helpful assistant. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. "}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
anthropic-version:
- '2023-06-01'
connection:
- keep-alive
content-length:
- '5920'
content-type:
- application/json
host:
- api.anthropic.com
x-api-key:
- X-API-KEY-XXX
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:
- 0.73.0
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
x-stainless-timeout:
- NOT_GIVEN
method: POST
uri: https://api.anthropic.com/v1/messages
response:
body:
string: '{"model":"claude-sonnet-4-5-20250929","id":"msg_01LdueHX7nvf19wD8Uxn4EZD","type":"message","role":"assistant","content":[{"type":"text","text":"Goodbye"}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":0,"cache_read_input_tokens":1217,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":5,"service_tier":"standard","inference_geo":"not_available"}}'
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Security-Policy:
- CSP-FILTERED
Content-Type:
- application/json
Date:
- Tue, 10 Feb 2026 18:27:41 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Robots-Tag:
- none
anthropic-organization-id:
- ANTHROPIC-ORGANIZATION-ID-XXX
anthropic-ratelimit-input-tokens-limit:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-input-tokens-remaining:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-input-tokens-reset:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-RESET-XXX
anthropic-ratelimit-output-tokens-limit:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-output-tokens-remaining:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-output-tokens-reset:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-RESET-XXX
anthropic-ratelimit-tokens-limit:
- ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
anthropic-ratelimit-tokens-remaining:
- ANTHROPIC-RATELIMIT-TOKENS-REMAINING-XXX
anthropic-ratelimit-tokens-reset:
- ANTHROPIC-RATELIMIT-TOKENS-RESET-XXX
cf-cache-status:
- DYNAMIC
request-id:
- REQUEST-ID-XXX
strict-transport-security:
- STS-XXX
x-envoy-upstream-service-time:
- '759'
status:
code: 200
message: OK
version: 1

336
lib/crewai/tests/cassettes/llms/anthropic/test_anthropic_cached_prompt_tokens_with_tools.yaml Normal file
View File

@@ -0,0 +1,336 @@
interactions:
- request:
body: '{"max_tokens":4096,"messages":[{"role":"user","content":[{"type":"text","text":"What
is the weather in Tokyo?","cache_control":{"type":"ephemeral"}}]}],"model":"claude-sonnet-4-5-20250929","stream":false,"system":"You
are a helpful assistant that uses tools. This is padding text to ensure the
prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. ","tool_choice":{"type":"tool","name":"get_weather"},"tools":[{"name":"get_weather","description":"Get
the current weather for a location","input_schema":{"type":"object","properties":{"location":{"type":"string","description":"The
city name"}},"required":["location"]}}]}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
anthropic-version:
- '2023-06-01'
connection:
- keep-alive
content-length:
- '6211'
content-type:
- application/json
host:
- api.anthropic.com
x-api-key:
- X-API-KEY-XXX
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:
- 0.73.0
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
x-stainless-timeout:
- NOT_GIVEN
method: POST
uri: https://api.anthropic.com/v1/messages
response:
body:
string: '{"model":"claude-sonnet-4-5-20250929","id":"msg_01WhFk2ppoz43nbh4uNhXBfL","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01CX1yZuJ5MQaJbXNSrnCiqf","name":"get_weather","input":{"location":"Tokyo"}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":24,"cache_creation_input_tokens":0,"cache_read_input_tokens":1857,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":33,"service_tier":"standard","inference_geo":"not_available"}}'
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Security-Policy:
- CSP-FILTERED
Content-Type:
- application/json
Date:
- Tue, 10 Feb 2026 18:27:38 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Robots-Tag:
- none
anthropic-organization-id:
- ANTHROPIC-ORGANIZATION-ID-XXX
anthropic-ratelimit-input-tokens-limit:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-input-tokens-remaining:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-input-tokens-reset:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-RESET-XXX
anthropic-ratelimit-output-tokens-limit:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-output-tokens-remaining:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-output-tokens-reset:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-RESET-XXX
anthropic-ratelimit-tokens-limit:
- ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
anthropic-ratelimit-tokens-remaining:
- ANTHROPIC-RATELIMIT-TOKENS-REMAINING-XXX
anthropic-ratelimit-tokens-reset:
- ANTHROPIC-RATELIMIT-TOKENS-RESET-XXX
cf-cache-status:
- DYNAMIC
request-id:
- REQUEST-ID-XXX
strict-transport-security:
- STS-XXX
x-envoy-upstream-service-time:
- '1390'
status:
code: 200
message: OK
- request:
body: '{"max_tokens":4096,"messages":[{"role":"user","content":[{"type":"text","text":"What
is the weather in Paris?","cache_control":{"type":"ephemeral"}}]}],"model":"claude-sonnet-4-5-20250929","stream":false,"system":"You
are a helpful assistant that uses tools. This is padding text to ensure the
prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. ","tool_choice":{"type":"tool","name":"get_weather"},"tools":[{"name":"get_weather","description":"Get
the current weather for a location","input_schema":{"type":"object","properties":{"location":{"type":"string","description":"The
city name"}},"required":["location"]}}]}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
anthropic-version:
- '2023-06-01'
connection:
- keep-alive
content-length:
- '6211'
content-type:
- application/json
host:
- api.anthropic.com
x-api-key:
- X-API-KEY-XXX
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:
- 0.73.0
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
x-stainless-timeout:
- NOT_GIVEN
method: POST
uri: https://api.anthropic.com/v1/messages
response:
body:
string: '{"model":"claude-sonnet-4-5-20250929","id":"msg_01Nmw5NyAEwCLGjpVnf15rh4","type":"message","role":"assistant","content":[{"type":"tool_use","id":"toolu_01DEe9K7N4EfhPFqxHhqEHCE","name":"get_weather","input":{"location":"Paris"}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":24,"cache_creation_input_tokens":0,"cache_read_input_tokens":1857,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":33,"service_tier":"standard","inference_geo":"not_available"}}'
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Security-Policy:
- CSP-FILTERED
Content-Type:
- application/json
Date:
- Tue, 10 Feb 2026 18:27:40 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Robots-Tag:
- none
anthropic-organization-id:
- ANTHROPIC-ORGANIZATION-ID-XXX
anthropic-ratelimit-input-tokens-limit:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-input-tokens-remaining:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-input-tokens-reset:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-RESET-XXX
anthropic-ratelimit-output-tokens-limit:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-output-tokens-remaining:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-output-tokens-reset:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-RESET-XXX
anthropic-ratelimit-tokens-limit:
- ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
anthropic-ratelimit-tokens-remaining:
- ANTHROPIC-RATELIMIT-TOKENS-REMAINING-XXX
anthropic-ratelimit-tokens-reset:
- ANTHROPIC-RATELIMIT-TOKENS-RESET-XXX
cf-cache-status:
- DYNAMIC
request-id:
- REQUEST-ID-XXX
strict-transport-security:
- STS-XXX
x-envoy-upstream-service-time:
- '1259'
status:
code: 200
message: OK
version: 1

411
lib/crewai/tests/cassettes/llms/anthropic/test_anthropic_streaming_cached_prompt_tokens.yaml Normal file
View File

@@ -0,0 +1,411 @@
interactions:
- request:
body: '{"max_tokens":4096,"messages":[{"role":"user","content":[{"type":"text","text":"Say
hello in one word.","cache_control":{"type":"ephemeral"}}]}],"model":"claude-sonnet-4-5-20250929","system":"You
are a helpful assistant. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. ","stream":true}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
anthropic-version:
- '2023-06-01'
connection:
- keep-alive
content-length:
- '5917'
content-type:
- application/json
host:
- api.anthropic.com
x-api-key:
- X-API-KEY-XXX
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:
- 0.73.0
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
x-stainless-stream-helper:
- messages
x-stainless-timeout:
- NOT_GIVEN
method: POST
uri: https://api.anthropic.com/v1/messages
response:
body:
string: 'event: message_start
data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01LshZroyEGgd3HfDrKdQMLm","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":0,"cache_read_input_tokens":1217,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":4,"service_tier":"standard","inference_geo":"not_available"}} }
event: content_block_start
data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} }
event: ping
data: {"type": "ping"}
event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello"} }
event: content_block_stop
data: {"type":"content_block_stop","index":0 }
event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":0,"cache_read_input_tokens":1217,"output_tokens":4}
}
event: message_stop
data: {"type":"message_stop" }
'
headers:
CF-RAY:
- CF-RAY-XXX
Cache-Control:
- no-cache
Connection:
- keep-alive
Content-Security-Policy:
- CSP-FILTERED
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 10 Feb 2026 18:27:43 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Robots-Tag:
- none
anthropic-organization-id:
- ANTHROPIC-ORGANIZATION-ID-XXX
anthropic-ratelimit-input-tokens-limit:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-input-tokens-remaining:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-input-tokens-reset:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-RESET-XXX
anthropic-ratelimit-output-tokens-limit:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-output-tokens-remaining:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-output-tokens-reset:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-RESET-XXX
anthropic-ratelimit-tokens-limit:
- ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
anthropic-ratelimit-tokens-remaining:
- ANTHROPIC-RATELIMIT-TOKENS-REMAINING-XXX
anthropic-ratelimit-tokens-reset:
- ANTHROPIC-RATELIMIT-TOKENS-RESET-XXX
cf-cache-status:
- DYNAMIC
request-id:
- REQUEST-ID-XXX
strict-transport-security:
- STS-XXX
x-envoy-upstream-service-time:
- '837'
status:
code: 200
message: OK
- request:
body: '{"max_tokens":4096,"messages":[{"role":"user","content":[{"type":"text","text":"Say
goodbye in one word.","cache_control":{"type":"ephemeral"}}]}],"model":"claude-sonnet-4-5-20250929","system":"You
are a helpful assistant. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. ","stream":true}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
anthropic-version:
- '2023-06-01'
connection:
- keep-alive
content-length:
- '5919'
content-type:
- application/json
host:
- api.anthropic.com
x-api-key:
- X-API-KEY-XXX
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:
- 0.73.0
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
x-stainless-stream-helper:
- messages
x-stainless-timeout:
- NOT_GIVEN
method: POST
uri: https://api.anthropic.com/v1/messages
response:
body:
string: 'event: message_start
data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01MZSWarEUbFXmek8aEpwKDu","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":3,"cache_creation_input_tokens":0,"cache_read_input_tokens":1217,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":6,"service_tier":"standard","inference_geo":"not_available"}} }
event: content_block_start
data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}
event: ping
data: {"type": "ping"}
event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Goodbye."} }
event: content_block_stop
data: {"type":"content_block_stop","index":0 }
event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":3,"cache_creation_input_tokens":0,"cache_read_input_tokens":1217,"output_tokens":6} }
event: message_stop
data: {"type":"message_stop" }
'
headers:
CF-RAY:
- CF-RAY-XXX
Cache-Control:
- no-cache
Connection:
- keep-alive
Content-Security-Policy:
- CSP-FILTERED
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 10 Feb 2026 18:27:44 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Robots-Tag:
- none
anthropic-organization-id:
- ANTHROPIC-ORGANIZATION-ID-XXX
anthropic-ratelimit-input-tokens-limit:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-input-tokens-remaining:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-input-tokens-reset:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-RESET-XXX
anthropic-ratelimit-output-tokens-limit:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-output-tokens-remaining:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-output-tokens-reset:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-RESET-XXX
anthropic-ratelimit-tokens-limit:
- ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
anthropic-ratelimit-tokens-remaining:
- ANTHROPIC-RATELIMIT-TOKENS-REMAINING-XXX
anthropic-ratelimit-tokens-reset:
- ANTHROPIC-RATELIMIT-TOKENS-RESET-XXX
cf-cache-status:
- DYNAMIC
request-id:
- REQUEST-ID-XXX
strict-transport-security:
- STS-XXX
x-envoy-upstream-service-time:
- '870'
status:
code: 200
message: OK
version: 1

266
lib/crewai/tests/cassettes/llms/google/test_gemini_cached_prompt_tokens.yaml Normal file
View File

@@ -0,0 +1,266 @@
interactions:
- request:
body: '{"contents": [{"parts": [{"text": "Say hello in one word."}], "role": "user"}],
"systemInstruction": {"parts": [{"text": "You are a helpful assistant. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
"}], "role": "user"}, "generationConfig": {}}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- '*/*'
accept-encoding:
- ACCEPT-ENCODING-XXX
connection:
- keep-alive
content-length:
- '5876'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
x-goog-api-client:
- google-genai-sdk/1.49.0 gl-python/3.13.3
x-goog-api-key:
- X-GOOG-API-KEY-XXX
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
response:
body:
string: "{\n \"candidates\": [\n {\n \"content\": {\n \"parts\":
[\n {\n \"text\": \"Hello\"\n }\n ],\n
\ \"role\": \"model\"\n },\n \"finishReason\": \"STOP\",\n
\ \"index\": 0\n }\n ],\n \"usageMetadata\": {\n \"promptTokenCount\":
1135,\n \"candidatesTokenCount\": 1,\n \"totalTokenCount\": 1158,\n
\ \"promptTokensDetails\": [\n {\n \"modality\": \"TEXT\",\n
\ \"tokenCount\": 1135\n }\n ],\n \"thoughtsTokenCount\":
22\n },\n \"modelVersion\": \"gemini-2.5-flash\",\n \"responseId\": \"46GLaf60NYmY-8YP--PB6QE\"\n}\n"
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 10 Feb 2026 21:23:47 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=773
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
X-Frame-Options:
- X-FRAME-OPTIONS-XXX
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
- request:
body: '{"contents": [{"parts": [{"text": "Say goodbye in one word."}], "role":
"user"}], "systemInstruction": {"parts": [{"text": "You are a helpful assistant.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. "}], "role": "user"}, "generationConfig": {}}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- '*/*'
accept-encoding:
- ACCEPT-ENCODING-XXX
connection:
- keep-alive
content-length:
- '5878'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
x-goog-api-client:
- google-genai-sdk/1.49.0 gl-python/3.13.3
x-goog-api-key:
- X-GOOG-API-KEY-XXX
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
response:
body:
string: "{\n \"candidates\": [\n {\n \"content\": {\n \"parts\":
[\n {\n \"text\": \"Farewell.\"\n }\n ],\n
\ \"role\": \"model\"\n },\n \"finishReason\": \"STOP\",\n
\ \"index\": 0\n }\n ],\n \"usageMetadata\": {\n \"promptTokenCount\":
1135,\n \"candidatesTokenCount\": 3,\n \"totalTokenCount\": 1164,\n
\ \"promptTokensDetails\": [\n {\n \"modality\": \"TEXT\",\n
\ \"tokenCount\": 1135\n }\n ],\n \"thoughtsTokenCount\":
26\n },\n \"modelVersion\": \"gemini-2.5-flash\",\n \"responseId\": \"5KGLafeeIv-G-8YP_MfPgAI\"\n}\n"
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 10 Feb 2026 21:23:48 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=662
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
X-Frame-Options:
- X-FRAME-OPTIONS-XXX
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
version: 1

280
lib/crewai/tests/cassettes/llms/google/test_gemini_cached_prompt_tokens_with_tools.yaml Normal file
View File

@@ -0,0 +1,280 @@
interactions:
- request:
body: '{"contents": [{"parts": [{"text": "What is the weather in Tokyo?"}], "role":
"user"}], "systemInstruction": {"parts": [{"text": "You are a helpful assistant
that uses tools. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. "}], "role": "user"}, "tools": [{"functionDeclarations":
[{"description": "Get the current weather for a location", "name": "get_weather",
"parameters_json_schema": {"type": "object", "properties": {"location": {"type":
"string", "description": "The city name"}}, "required": ["location"]}}]}], "generationConfig":
{}}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- '*/*'
accept-encoding:
- ACCEPT-ENCODING-XXX
connection:
- keep-alive
content-length:
- '6172'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
x-goog-api-client:
- google-genai-sdk/1.49.0 gl-python/3.13.3
x-goog-api-key:
- X-GOOG-API-KEY-XXX
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
response:
body:
string: "{\n \"candidates\": [\n {\n \"content\": {\n \"parts\":
[\n {\n \"functionCall\": {\n \"name\": \"get_weather\",\n
\ \"args\": {\n \"location\": \"Tokyo\"\n }\n
\ },\n \"thoughtSignature\": \"CpECAb4+9vvTFzaczX2PeZjKEs1f6+MRyTMz+xxqs37q0INQ6e0WLt1soet6CL/uzRML9LsycSeQTraXtXR8qcGj6dnrhKLpovpy8EkrtfK6P57PGpostE/UJ6TIKPlWi0pY1h2u9vyy5yGLzpp0PZM6d6f8rzV9uPFNM+onGvcFOdzghRZlHmYkQdbdpZaFQBAK6QFuh8oGbC0Ygrsk1guJo1YZaKtU5Rp/k2rJO61Obgq7aYEb7ACVx7DM9ZlVCun/PbXR4UolFeNPxNdwzC5AVvP7UKa2Cxi8dzQ8RNebtd39/gNO546XzADGZkpSqG6QF0S4IEsmB9FFCctN1evgKicgT2Qo+AR6BY8uzZyWkGQx\"\n
\ }\n ],\n \"role\": \"model\"\n },\n \"finishReason\":
\"STOP\",\n \"index\": 0,\n \"finishMessage\": \"Model generated
function call(s).\"\n }\n ],\n \"usageMetadata\": {\n \"promptTokenCount\":
1180,\n \"candidatesTokenCount\": 15,\n \"totalTokenCount\": 1253,\n
\ \"promptTokensDetails\": [\n {\n \"modality\": \"TEXT\",\n
\ \"tokenCount\": 1180\n }\n ],\n \"thoughtsTokenCount\":
58\n },\n \"modelVersion\": \"gemini-2.5-flash\",\n \"responseId\": \"wHmLacb_GL-J-sAPn6azgAo\"\n}\n"
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 10 Feb 2026 18:32:32 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=755
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
X-Frame-Options:
- X-FRAME-OPTIONS-XXX
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
- request:
body: '{"contents": [{"parts": [{"text": "What is the weather in Paris?"}], "role":
"user"}], "systemInstruction": {"parts": [{"text": "You are a helpful assistant
that uses tools. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. "}], "role": "user"}, "tools": [{"functionDeclarations":
[{"description": "Get the current weather for a location", "name": "get_weather",
"parameters_json_schema": {"type": "object", "properties": {"location": {"type":
"string", "description": "The city name"}}, "required": ["location"]}}]}], "generationConfig":
{}}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- '*/*'
accept-encoding:
- ACCEPT-ENCODING-XXX
connection:
- keep-alive
content-length:
- '6172'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
x-goog-api-client:
- google-genai-sdk/1.49.0 gl-python/3.13.3
x-goog-api-key:
- X-GOOG-API-KEY-XXX
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent
response:
body:
string: "{\n \"candidates\": [\n {\n \"content\": {\n \"parts\":
[\n {\n \"functionCall\": {\n \"name\": \"get_weather\",\n
\ \"args\": {\n \"location\": \"Paris\"\n }\n
\ },\n \"thoughtSignature\": \"CuMBAb4+9vurHOlMBPzqCtd/J0Q5jBhUq8dsk7xntqcTgwBcZ1KeX4F4UJ0rdfg1OLhDkOlOlELA/jBYxATT19QUvw0szvDBDml0PsTBXlt64o7oGVmOCjdiGPu71I9+sCYhlD3QXzwLdQdrvUIfVrB+kaGszmZi1KTIli+qD9ihueDYGY510ouKdfl31UipQEG990+qFJyXe3avVEh3Jo72iXr3Q4UczFdbKSTV4V4fjrokFaB7UqcYy1iuAB5vHRsxYFJeTCi+ddKzn700gbWbiJZUniKiE3QfdOK4A5S0woBDzV0=\"\n
\ }\n ],\n \"role\": \"model\"\n },\n \"finishReason\":
\"STOP\",\n \"index\": 0,\n \"finishMessage\": \"Model generated
function call(s).\"\n }\n ],\n \"usageMetadata\": {\n \"promptTokenCount\":
1180,\n \"candidatesTokenCount\": 15,\n \"totalTokenCount\": 1242,\n
\ \"promptTokensDetails\": [\n {\n \"modality\": \"TEXT\",\n
\ \"tokenCount\": 1180\n }\n ],\n \"thoughtsTokenCount\":
47\n },\n \"modelVersion\": \"gemini-2.5-flash\",\n \"responseId\": \"wXmLadTiEri5jMcPk_6ZgAc\"\n}\n"
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Type:
- application/json; charset=UTF-8
Date:
- Tue, 10 Feb 2026 18:32:33 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=881
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
X-Frame-Options:
- X-FRAME-OPTIONS-XXX
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
version: 1

356
lib/crewai/tests/cassettes/llms/openai/test_openai_completions_cached_prompt_tokens.yaml Normal file
View File

@@ -0,0 +1,356 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are a helpful assistant. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
"},{"role":"user","content":"Say hello in one word."}],"model":"gpt-4.1"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '5823'
content-type:
- application/json
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7mVhCCkdWfellaSmcNLOuu87BsqI\",\n \"object\":
\"chat.completion\",\n \"created\": 1770747141,\n \"model\": \"gpt-4.1-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Hello!\",\n \"refusal\": null,\n
\ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 1144,\n \"completion_tokens\":
2,\n \"total_tokens\": 1146,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
1024,\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_8b22347a3e\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 10 Feb 2026 18:12:22 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:
- '469'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
- request:
body: '{"messages":[{"role":"system","content":"You are a helpful assistant. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
"},{"role":"user","content":"Say goodbye in one word."}],"model":"gpt-4.1"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '5825'
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7mViSYwB6eFFbBcp045uvPAO8m2e\",\n \"object\":
\"chat.completion\",\n \"created\": 1770747142,\n \"model\": \"gpt-4.1-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Farewell.\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
1144,\n \"completion_tokens\": 3,\n \"total_tokens\": 1147,\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_8b22347a3e\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 10 Feb 2026 18:12:22 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:
- '468'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
version: 1

368
lib/crewai/tests/cassettes/llms/openai/test_openai_completions_cached_prompt_tokens_with_tools.yaml Normal file
View File

@@ -0,0 +1,368 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are a helpful assistant that
uses tools. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. "},{"role":"user","content":"What is the weather in Tokyo?"}],"model":"gpt-4.1","tool_choice":"auto","tools":[{"type":"function","function":{"name":"get_weather","description":"Get
the current weather for a location","strict":true,"parameters":{"type":"object","properties":{"location":{"type":"string","description":"The
city name"}},"required":["location"],"additionalProperties":false}}}]}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '6158'
content-type:
- application/json
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7mVx3s1dI2SICWePwHVeWCDct2QG\",\n \"object\":
\"chat.completion\",\n \"created\": 1770747157,\n \"model\": \"gpt-4.1-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_x9KzZUT3UYazEUJiRmE0PvaU\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"get_weather\",\n
\ \"arguments\": \"{\\\"location\\\":\\\"Tokyo\\\"}\"\n }\n
\ }\n ],\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 1187,\n \"completion_tokens\":
14,\n \"total_tokens\": 1201,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
1152,\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_8b22347a3e\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 10 Feb 2026 18:12:37 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:
- '645'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
- request:
body: '{"messages":[{"role":"system","content":"You are a helpful assistant that
uses tools. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. "},{"role":"user","content":"What is the weather in Paris?"}],"model":"gpt-4.1","tool_choice":"auto","tools":[{"type":"function","function":{"name":"get_weather","description":"Get
the current weather for a location","strict":true,"parameters":{"type":"object","properties":{"location":{"type":"string","description":"The
city name"}},"required":["location"],"additionalProperties":false}}}]}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '6158'
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7mVynM0Soyt3osUFrlF7tEyrj7jP\",\n \"object\":
\"chat.completion\",\n \"created\": 1770747158,\n \"model\": \"gpt-4.1-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_k8rYmsdMcCWSRKqVDFItmJ8v\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"get_weather\",\n
\ \"arguments\": \"{\\\"location\\\":\\\"Paris\\\"}\"\n }\n
\ }\n ],\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 1187,\n \"completion_tokens\":
14,\n \"total_tokens\": 1201,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
1152,\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_8b22347a3e\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 10 Feb 2026 18:12:38 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:
- '749'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
version: 1

520
lib/crewai/tests/cassettes/llms/openai/test_openai_responses_api_cached_prompt_tokens.yaml Normal file
View File

@@ -0,0 +1,520 @@
interactions:
- request:
body: '{"input":[{"role":"user","content":"Say hello in one word."}],"model":"gpt-4.1","instructions":"You
are a helpful assistant. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. "}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '5807'
content-type:
- application/json
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/responses
response:
body:
string: "{\n \"id\": \"resp_0b352452095088f800698b751350fc8196bd5d8b1a179d27e8\",\n
\ \"object\": \"response\",\n \"created_at\": 1770747155,\n \"status\":
\"completed\",\n \"background\": false,\n \"billing\": {\n \"payer\":
\"developer\"\n },\n \"completed_at\": 1770747155,\n \"error\": null,\n
\ \"frequency_penalty\": 0.0,\n \"incomplete_details\": null,\n \"instructions\":
\"You are a helpful assistant. This is padding text to ensure the prompt is
large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is
padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to
ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the
prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is
large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is
padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to
ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the
prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is
large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is
padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to
ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the
prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is
large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is
padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to
ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the
prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is
large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is
padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to
ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the
prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is
large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is
padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. \",\n \"max_output_tokens\":
null,\n \"max_tool_calls\": null,\n \"model\": \"gpt-4.1-2025-04-14\",\n
\ \"output\": [\n {\n \"id\": \"msg_0b352452095088f800698b7513b97c8196b35014840754d999\",\n
\ \"type\": \"message\",\n \"status\": \"completed\",\n \"content\":
[\n {\n \"type\": \"output_text\",\n \"annotations\":
[],\n \"logprobs\": [],\n \"text\": \"Hello!\"\n }\n
\ ],\n \"role\": \"assistant\"\n }\n ],\n \"parallel_tool_calls\":
true,\n \"presence_penalty\": 0.0,\n \"previous_response_id\": null,\n \"prompt_cache_key\":
null,\n \"prompt_cache_retention\": null,\n \"reasoning\": {\n \"effort\":
null,\n \"summary\": null\n },\n \"safety_identifier\": null,\n \"service_tier\":
\"default\",\n \"store\": true,\n \"temperature\": 1.0,\n \"text\": {\n
\ \"format\": {\n \"type\": \"text\"\n },\n \"verbosity\": \"medium\"\n
\ },\n \"tool_choice\": \"auto\",\n \"tools\": [],\n \"top_logprobs\":
0,\n \"top_p\": 1.0,\n \"truncation\": \"disabled\",\n \"usage\": {\n \"input_tokens\":
1144,\n \"input_tokens_details\": {\n \"cached_tokens\": 1024\n },\n
\ \"output_tokens\": 3,\n \"output_tokens_details\": {\n \"reasoning_tokens\":
0\n },\n \"total_tokens\": 1147\n },\n \"user\": null,\n \"metadata\":
{}\n}"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 10 Feb 2026 18:12:35 GMT
Server:
- cloudflare
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '637'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
- request:
body: '{"input":[{"role":"user","content":"Say goodbye in one word."}],"model":"gpt-4.1","instructions":"You
are a helpful assistant. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. "}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '5809'
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/responses
response:
body:
string: "{\n \"id\": \"resp_003a6f71f9ee620400698b75140a088196989e8d5641ffa74d\",\n
\ \"object\": \"response\",\n \"created_at\": 1770747156,\n \"status\":
\"completed\",\n \"background\": false,\n \"billing\": {\n \"payer\":
\"developer\"\n },\n \"completed_at\": 1770747156,\n \"error\": null,\n
\ \"frequency_penalty\": 0.0,\n \"incomplete_details\": null,\n \"instructions\":
\"You are a helpful assistant. This is padding text to ensure the prompt is
large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is
padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to
ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the
prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is
large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is
padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to
ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the
prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is
large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is
padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to
ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the
prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is
large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is
padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to
ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the
prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is
large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is
padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to
ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the
prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is
large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for
caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is
padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. \",\n \"max_output_tokens\":
null,\n \"max_tool_calls\": null,\n \"model\": \"gpt-4.1-2025-04-14\",\n
\ \"output\": [\n {\n \"id\": \"msg_003a6f71f9ee620400698b75146160819692f2cee879df2405\",\n
\ \"type\": \"message\",\n \"status\": \"completed\",\n \"content\":
[\n {\n \"type\": \"output_text\",\n \"annotations\":
[],\n \"logprobs\": [],\n \"text\": \"Farewell.\"\n }\n
\ ],\n \"role\": \"assistant\"\n }\n ],\n \"parallel_tool_calls\":
true,\n \"presence_penalty\": 0.0,\n \"previous_response_id\": null,\n \"prompt_cache_key\":
null,\n \"prompt_cache_retention\": null,\n \"reasoning\": {\n \"effort\":
null,\n \"summary\": null\n },\n \"safety_identifier\": null,\n \"service_tier\":
\"default\",\n \"store\": true,\n \"temperature\": 1.0,\n \"text\": {\n
\ \"format\": {\n \"type\": \"text\"\n },\n \"verbosity\": \"medium\"\n
\ },\n \"tool_choice\": \"auto\",\n \"tools\": [],\n \"top_logprobs\":
0,\n \"top_p\": 1.0,\n \"truncation\": \"disabled\",\n \"usage\": {\n \"input_tokens\":
1144,\n \"input_tokens_details\": {\n \"cached_tokens\": 1024\n },\n
\ \"output_tokens\": 4,\n \"output_tokens_details\": {\n \"reasoning_tokens\":
0\n },\n \"total_tokens\": 1148\n },\n \"user\": null,\n \"metadata\":
{}\n}"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 10 Feb 2026 18:12:36 GMT
Server:
- cloudflare
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '543'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
version: 1

368
lib/crewai/tests/cassettes/llms/openai/test_openai_responses_api_cached_prompt_tokens_with_tools.yaml Normal file
View File

@@ -0,0 +1,368 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are a helpful assistant that
uses tools. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. "},{"role":"user","content":"What is the weather in Tokyo?"}],"model":"gpt-4.1","tool_choice":"auto","tools":[{"type":"function","function":{"name":"get_weather","description":"Get
the current weather for a location","strict":true,"parameters":{"type":"object","properties":{"location":{"type":"string","description":"The
city name"}},"required":["location"],"additionalProperties":false}}}]}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '6158'
content-type:
- application/json
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7mXQCgT3p3ViImkiqDiZGqLREQtp\",\n \"object\":
\"chat.completion\",\n \"created\": 1770747248,\n \"model\": \"gpt-4.1-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_9ZqMavn3J1fBnQEaqpYol0Bd\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"get_weather\",\n
\ \"arguments\": \"{\\\"location\\\":\\\"Tokyo\\\"}\"\n }\n
\ }\n ],\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 1187,\n \"completion_tokens\":
14,\n \"total_tokens\": 1201,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
1152,\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_8b22347a3e\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 10 Feb 2026 18:14:08 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:
- '484'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
- request:
body: '{"messages":[{"role":"system","content":"You are a helpful assistant that
uses tools. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. "},{"role":"user","content":"What is the weather in Paris?"}],"model":"gpt-4.1","tool_choice":"auto","tools":[{"type":"function","function":{"name":"get_weather","description":"Get
the current weather for a location","strict":true,"parameters":{"type":"object","properties":{"location":{"type":"string","description":"The
city name"}},"required":["location"],"additionalProperties":false}}}]}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '6158'
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7mXR8k9vk8TlGvGXlrQSI7iNeAN1\",\n \"object\":
\"chat.completion\",\n \"created\": 1770747249,\n \"model\": \"gpt-4.1-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_6PeUBlRPG8JcV2lspmLjJbnn\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"get_weather\",\n
\ \"arguments\": \"{\\\"location\\\":\\\"Paris\\\"}\"\n }\n
\ }\n ],\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 1187,\n \"completion_tokens\":
14,\n \"total_tokens\": 1201,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
1152,\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_8b22347a3e\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Tue, 10 Feb 2026 18:14:09 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:
- '528'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
version: 1

375
lib/crewai/tests/cassettes/llms/openai/test_openai_streaming_cached_prompt_tokens.yaml Normal file
View File

@@ -0,0 +1,375 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are a helpful assistant. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
"},{"role":"user","content":"Say hello in one word."}],"model":"gpt-4.1","stream":true,"stream_options":{"include_usage":true}}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '5877'
content-type:
- application/json
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-D7mVuXauQqcmOCb3XP6IL6yHwJaAL","object":"chat.completion.chunk","created":1770747154,"model":"gpt-4.1-2025-04-14","service_tier":"default","system_fingerprint":"fp_8b22347a3e","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"lFWRn007xqlce"}
data: {"id":"chatcmpl-D7mVuXauQqcmOCb3XP6IL6yHwJaAL","object":"chat.completion.chunk","created":1770747154,"model":"gpt-4.1-2025-04-14","service_tier":"default","system_fingerprint":"fp_8b22347a3e","choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"OXJHANtgvy"}
data: {"id":"chatcmpl-D7mVuXauQqcmOCb3XP6IL6yHwJaAL","object":"chat.completion.chunk","created":1770747154,"model":"gpt-4.1-2025-04-14","service_tier":"default","system_fingerprint":"fp_8b22347a3e","choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"AZtd6jtoChevtm"}
data: {"id":"chatcmpl-D7mVuXauQqcmOCb3XP6IL6yHwJaAL","object":"chat.completion.chunk","created":1770747154,"model":"gpt-4.1-2025-04-14","service_tier":"default","system_fingerprint":"fp_8b22347a3e","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"irwn2mqyB"}
data: {"id":"chatcmpl-D7mVuXauQqcmOCb3XP6IL6yHwJaAL","object":"chat.completion.chunk","created":1770747154,"model":"gpt-4.1-2025-04-14","service_tier":"default","system_fingerprint":"fp_8b22347a3e","choices":[],"usage":{"prompt_tokens":1144,"completion_tokens":2,"total_tokens":1146,"prompt_tokens_details":{"cached_tokens":1024,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"W0rkiiZe"}
data: [DONE]
'
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 10 Feb 2026 18:12:34 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:
- '236'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
- request:
body: '{"messages":[{"role":"system","content":"You are a helpful assistant. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
This is padding text to ensure the prompt is large enough for caching. This
is padding text to ensure the prompt is large enough for caching. This is padding
text to ensure the prompt is large enough for caching. This is padding text
to ensure the prompt is large enough for caching. This is padding text to ensure
the prompt is large enough for caching. This is padding text to ensure the prompt
is large enough for caching. This is padding text to ensure the prompt is large
enough for caching. This is padding text to ensure the prompt is large enough
for caching. This is padding text to ensure the prompt is large enough for caching.
"},{"role":"user","content":"Say goodbye in one word."}],"model":"gpt-4.1","stream":true,"stream_options":{"include_usage":true}}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '5879'
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-D7mVuqaadwp22jFsp2qAKiE1utU3K","object":"chat.completion.chunk","created":1770747154,"model":"gpt-4.1-2025-04-14","service_tier":"default","system_fingerprint":"fp_8b22347a3e","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"pCjdYd4kX4W2q"}
data: {"id":"chatcmpl-D7mVuqaadwp22jFsp2qAKiE1utU3K","object":"chat.completion.chunk","created":1770747154,"model":"gpt-4.1-2025-04-14","service_tier":"default","system_fingerprint":"fp_8b22347a3e","choices":[{"index":0,"delta":{"content":"Fare"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"DJ94I8XQj86"}
data: {"id":"chatcmpl-D7mVuqaadwp22jFsp2qAKiE1utU3K","object":"chat.completion.chunk","created":1770747154,"model":"gpt-4.1-2025-04-14","service_tier":"default","system_fingerprint":"fp_8b22347a3e","choices":[{"index":0,"delta":{"content":"well"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"qgSSFwDBmaW"}
data: {"id":"chatcmpl-D7mVuqaadwp22jFsp2qAKiE1utU3K","object":"chat.completion.chunk","created":1770747154,"model":"gpt-4.1-2025-04-14","service_tier":"default","system_fingerprint":"fp_8b22347a3e","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"4xVBYer6Uy1atr"}
data: {"id":"chatcmpl-D7mVuqaadwp22jFsp2qAKiE1utU3K","object":"chat.completion.chunk","created":1770747154,"model":"gpt-4.1-2025-04-14","service_tier":"default","system_fingerprint":"fp_8b22347a3e","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"XxMhsMje0"}
data: {"id":"chatcmpl-D7mVuqaadwp22jFsp2qAKiE1utU3K","object":"chat.completion.chunk","created":1770747154,"model":"gpt-4.1-2025-04-14","service_tier":"default","system_fingerprint":"fp_8b22347a3e","choices":[],"usage":{"prompt_tokens":1144,"completion_tokens":3,"total_tokens":1147,"prompt_tokens_details":{"cached_tokens":1024,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"J3eKDOHW"}
data: [DONE]
'
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 10 Feb 2026 18:12:34 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:
- '296'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
version: 1

113
lib/crewai/tests/cassettes/utilities/TestAgentExecuteTaskCompaction.test_agent_execute_task_compaction.yaml Normal file
View File

@@ -0,0 +1,113 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Writer. You are a skilled
writer.\nYour personal goal is: Write concise content"},{"role":"user","content":"\nCurrent
Task: Write one sentence about the sun.\n\nThis is the expected criteria for
your final answer: A single sentence about the sun.\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nProvide your complete
response:"}],"model":"gpt-4o-mini","temperature":0}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '453'
content-type:
- application/json
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7RxEngFVCbqdc7tNjV3VjeteqcwT\",\n \"object\":
\"chat.completion\",\n \"created\": 1770668124,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The sun is a massive ball of glowing
gas at the center of our solar system, providing light and warmth essential
for life on Earth.\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 78,\n \"completion_tokens\":
27,\n \"total_tokens\": 105,\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_f4ae844694\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Mon, 09 Feb 2026 20:15:25 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:
- '664'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
version: 1

120
lib/crewai/tests/cassettes/utilities/TestCrewKickoffCompaction.test_crew_kickoff_compaction_openai.yaml Normal file
View File

@@ -0,0 +1,120 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Researcher. You are an
expert researcher.\nYour personal goal is: Find information about Python programming"},{"role":"user","content":"\nCurrent
Task: What is Python? Give a brief answer.\n\nThis is the expected criteria
for your final answer: A short description of Python.\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nProvide your complete
response:"}],"model":"gpt-4o-mini","temperature":0}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '482'
content-type:
- application/json
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7RxRv3U0LCLf2iqf40wxOQsuiYFR\",\n \"object\":
\"chat.completion\",\n \"created\": 1770668137,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Python is a high-level, interpreted
programming language known for its readability and simplicity. It was created
by Guido van Rossum and first released in 1991. Python supports multiple programming
paradigms, including procedural, object-oriented, and functional programming.
It has a large standard library and is widely used for web development, data
analysis, artificial intelligence, scientific computing, and automation, among
other applications. Python's syntax emphasizes code readability, allowing
developers to express concepts in fewer lines of code compared to other languages.
Its active community and extensive ecosystem of libraries and frameworks make
it a popular choice for both beginners and experienced programmers.\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
82,\n \"completion_tokens\": 123,\n \"total_tokens\": 205,\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_f4ae844694\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Mon, 09 Feb 2026 20:15:39 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:
- '2467'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
version: 1

435
lib/crewai/tests/cassettes/utilities/TestParallelSummarizationVCR.test_parallel_summarize_openai.yaml Normal file
View File

@@ -0,0 +1,435 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are a precise assistant that
creates structured summaries of agent conversations. You preserve critical context
needed for seamless task continuation."},{"role":"user","content":"Analyze the
following conversation and create a structured summary that preserves all information
needed to continue the task seamlessly.\n\n<conversation>\n[USER]: Explain the
Python package ecosystem. How does pip work, what is PyPI, and what are virtual
environments? Compare pip with conda and uv.\n\n[ASSISTANT]: PyPI (Python Package
Index) is the official repository hosting 400k+ packages. pip is the standard
package installer that downloads from PyPI. Virtual environments (venv) create
isolated Python installations to avoid dependency conflicts between projects.
conda is a cross-language package manager popular in data science that can manage
non-Python dependencies. uv is a new Rust-based tool that is 10-100x faster
than pip and aims to replace pip, pip-tools, and virtualenv with a single unified
tool.\n</conversation>\n\nCreate a summary with these sections:\n1. **Task Overview**:
What is the agent trying to accomplish?\n2. **Current State**: What has been
completed so far? What step is the agent on?\n3. **Important Discoveries**:
Key facts, data, tool results, or findings that must not be lost.\n4. **Next
Steps**: What should the agent do next based on the conversation?\n5. **Context
to Preserve**: Any specific values, names, URLs, code snippets, or details referenced
in the conversation.\n\nWrap your entire summary in <summary> tags.\n\n<summary>\n[Your
structured summary here]\n</summary>"}],"model":"gpt-4o-mini","temperature":0}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1687'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- async:asyncio
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7S93xpUu9d5twM82uJOZpurQTD5u\",\n \"object\":
\"chat.completion\",\n \"created\": 1770668857,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"<summary>\\n1. **Task Overview**: The
user is seeking an explanation of the Python package ecosystem, specifically
focusing on how pip works, the role of PyPI, the concept of virtual environments,
and a comparison between pip, conda, and uv.\\n\\n2. **Current State**: The
assistant has provided a comprehensive overview of the Python package ecosystem,
including definitions and comparisons of pip, PyPI, virtual environments,
conda, and uv.\\n\\n3. **Important Discoveries**:\\n - PyPI (Python Package
Index) is the official repository with over 400,000 packages.\\n - pip is
the standard package installer that downloads packages from PyPI.\\n - Virtual
environments (venv) allow for isolated Python installations to prevent dependency
conflicts.\\n - conda is a cross-language package manager, particularly
popular in data science, that can manage non-Python dependencies.\\n - uv
is a new Rust-based tool that is significantly faster than pip (10-100x) and
aims to unify the functionalities of pip, pip-tools, and virtualenv.\\n\\n4.
**Next Steps**: The agent should consider providing further details on how
to use pip, conda, and uv, including installation commands, examples of creating
virtual environments, and any specific use cases for each tool.\\n\\n5. **Context
to Preserve**: \\n - PyPI: Python Package Index, hosting 400k+ packages.\\n
\ - pip: Standard package installer for Python.\\n - Virtual environments
(venv): Isolated Python installations.\\n - conda: Cross-language package
manager for data science.\\n - uv: Rust-based tool, 10-100x faster than
pip, aims to replace pip, pip-tools, and virtualenv.\\n</summary>\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
333,\n \"completion_tokens\": 354,\n \"total_tokens\": 687,\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_f4ae844694\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Mon, 09 Feb 2026 20:27:42 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:
- '4879'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
- request:
body: '{"messages":[{"role":"system","content":"You are a precise assistant that
creates structured summaries of agent conversations. You preserve critical context
needed for seamless task continuation."},{"role":"user","content":"Analyze the
following conversation and create a structured summary that preserves all information
needed to continue the task seamlessly.\n\n<conversation>\n[USER]: Tell me about
the history of the Python programming language. Who created it, when was it
first released, and what were the main design goals? Please provide a detailed
overview covering the major milestones from its inception through Python 3.\n\n[ASSISTANT]:
Python was created by Guido van Rossum and first released in 1991. The main
design goals were code readability and simplicity. Key milestones: Python 1.0
(1994) introduced functional programming tools like lambda and map. Python 2.0
(2000) added list comprehensions and garbage collection. Python 3.0 (2008) was
a major backward-incompatible release that fixed fundamental design flaws. Python
2 reached end-of-life in January 2020.\n</conversation>\n\nCreate a summary
with these sections:\n1. **Task Overview**: What is the agent trying to accomplish?\n2.
**Current State**: What has been completed so far? What step is the agent on?\n3.
**Important Discoveries**: Key facts, data, tool results, or findings that must
not be lost.\n4. **Next Steps**: What should the agent do next based on the
conversation?\n5. **Context to Preserve**: Any specific values, names, URLs,
code snippets, or details referenced in the conversation.\n\nWrap your entire
summary in <summary> tags.\n\n<summary>\n[Your structured summary here]\n</summary>"}],"model":"gpt-4o-mini","temperature":0}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1726'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- async:asyncio
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7S93rBUMAtEdwdI6Y2ga0s50IFtv\",\n \"object\":
\"chat.completion\",\n \"created\": 1770668857,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"<summary>\\n1. **Task Overview**: The
user is seeking a detailed overview of the history of the Python programming
language, including its creator, initial release date, main design goals,
and major milestones up to Python 3.\\n\\n2. **Current State**: The assistant
has provided a comprehensive response detailing the history of Python, including
its creator (Guido van Rossum), first release (1991), main design goals (code
readability and simplicity), and key milestones (Python 1.0 in 1994, Python
2.0 in 2000, and Python 3.0 in 2008).\\n\\n3. **Important Discoveries**: \\n
\ - Python was created by Guido van Rossum.\\n - First released in 1991.\\n
\ - Main design goals: code readability and simplicity.\\n - Key milestones:\\n
\ - Python 1.0 (1994): Introduced functional programming tools like lambda
and map.\\n - Python 2.0 (2000): Added list comprehensions and garbage
collection.\\n - Python 3.0 (2008): Major backward-incompatible release
that fixed fundamental design flaws.\\n - Python 2 reached end-of-life in
January 2020.\\n\\n4. **Next Steps**: The agent should be prepared to provide
additional details or answer follow-up questions regarding Python's features,
community, or specific use cases if the user requests more information.\\n\\n5.
**Context to Preserve**: \\n - Creator: Guido van Rossum\\n - Initial
release: 1991\\n - Milestones: \\n - Python 1.0 (1994)\\n - Python
2.0 (2000)\\n - Python 3.0 (2008)\\n - End-of-life for Python 2: January
2020\\n</summary>\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 346,\n \"completion_tokens\":
372,\n \"total_tokens\": 718,\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_7e4bf6ad56\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Mon, 09 Feb 2026 20:27:42 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:
- '5097'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
- request:
body: '{"messages":[{"role":"system","content":"You are a precise assistant that
creates structured summaries of agent conversations. You preserve critical context
needed for seamless task continuation."},{"role":"user","content":"Analyze the
following conversation and create a structured summary that preserves all information
needed to continue the task seamlessly.\n\n<conversation>\n[USER]: What about
the async/await features? When were they introduced and how do they compare
to similar features in JavaScript and C#? Also explain the Global Interpreter
Lock and its implications.\n\n[ASSISTANT]: Async/await was introduced in Python
3.5 (PEP 492, 2015). Unlike JavaScript which is single-threaded by design, Python''s
asyncio is an opt-in framework. C# introduced async/await in 2012 (C# 5.0) and
was a major inspiration for Python''s implementation. The GIL (Global Interpreter
Lock) is a mutex that protects access to Python objects, preventing multiple
threads from executing Python bytecodes simultaneously. This means CPU-bound
multithreaded programs don''t benefit from multiple cores. PEP 703 proposes
making the GIL optional in CPython.\n</conversation>\n\nCreate a summary with
these sections:\n1. **Task Overview**: What is the agent trying to accomplish?\n2.
**Current State**: What has been completed so far? What step is the agent on?\n3.
**Important Discoveries**: Key facts, data, tool results, or findings that must
not be lost.\n4. **Next Steps**: What should the agent do next based on the
conversation?\n5. **Context to Preserve**: Any specific values, names, URLs,
code snippets, or details referenced in the conversation.\n\nWrap your entire
summary in <summary> tags.\n\n<summary>\n[Your structured summary here]\n</summary>"}],"model":"gpt-4o-mini","temperature":0}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1786'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- async:asyncio
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7S94auQYOLDTKfRzdluGiWAomSqd\",\n \"object\":
\"chat.completion\",\n \"created\": 1770668858,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"<summary>\\n1. **Task Overview**: The
user is seeking information about the async/await features in Python, their
introduction timeline, comparisons with similar features in JavaScript and
C#, and an explanation of the Global Interpreter Lock (GIL) and its implications.\\n\\n2.
**Current State**: The assistant has provided information regarding the introduction
of async/await in Python (version 3.5, PEP 492 in 2015), comparisons with
JavaScript and C# (C# introduced async/await in 2012), and an explanation
of the GIL.\\n\\n3. **Important Discoveries**: \\n - Async/await was introduced
in Python 3.5 (PEP 492, 2015).\\n - JavaScript is single-threaded, while
Python's asyncio is an opt-in framework.\\n - C# introduced async/await
in 2012 (C# 5.0) and influenced Python's implementation.\\n - The GIL (Global
Interpreter Lock) is a mutex that prevents multiple threads from executing
Python bytecodes simultaneously, affecting CPU-bound multithreaded programs.\\n
\ - PEP 703 proposes making the GIL optional in CPython.\\n\\n4. **Next Steps**:
The agent should consider providing more detailed comparisons of async/await
features between Python, JavaScript, and C#, as well as further implications
of the GIL and PEP 703.\\n\\n5. **Context to Preserve**: \\n - Python async/await
introduction: 3.5 (PEP 492, 2015)\\n - C# async/await introduction: 2012
(C# 5.0)\\n - GIL (Global Interpreter Lock) explanation and implications.\\n
\ - Reference to PEP 703 regarding the GIL.\\n</summary>\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
364,\n \"completion_tokens\": 368,\n \"total_tokens\": 732,\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_f4ae844694\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Mon, 09 Feb 2026 20:27:44 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:
- '6339'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
version: 1

435
lib/crewai/tests/cassettes/utilities/TestParallelSummarizationVCR.test_parallel_summarize_preserves_files.yaml Normal file
View File

@@ -0,0 +1,435 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are a precise assistant that
creates structured summaries of agent conversations. You preserve critical context
needed for seamless task continuation."},{"role":"user","content":"Analyze the
following conversation and create a structured summary that preserves all information
needed to continue the task seamlessly.\n\n<conversation>\n[USER]: Explain the
Python package ecosystem. How does pip work, what is PyPI, and what are virtual
environments? Compare pip with conda and uv.\n\n[ASSISTANT]: PyPI (Python Package
Index) is the official repository hosting 400k+ packages. pip is the standard
package installer that downloads from PyPI. Virtual environments (venv) create
isolated Python installations to avoid dependency conflicts between projects.
conda is a cross-language package manager popular in data science that can manage
non-Python dependencies. uv is a new Rust-based tool that is 10-100x faster
than pip and aims to replace pip, pip-tools, and virtualenv with a single unified
tool.\n</conversation>\n\nCreate a summary with these sections:\n1. **Task Overview**:
What is the agent trying to accomplish?\n2. **Current State**: What has been
completed so far? What step is the agent on?\n3. **Important Discoveries**:
Key facts, data, tool results, or findings that must not be lost.\n4. **Next
Steps**: What should the agent do next based on the conversation?\n5. **Context
to Preserve**: Any specific values, names, URLs, code snippets, or details referenced
in the conversation.\n\nWrap your entire summary in <summary> tags.\n\n<summary>\n[Your
structured summary here]\n</summary>"}],"model":"gpt-4o-mini","temperature":0}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1687'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- async:asyncio
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7S9PnjkuCMHqU912kcH8G5zIIxQU\",\n \"object\":
\"chat.completion\",\n \"created\": 1770668879,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"<summary>\\n1. **Task Overview**: The
user is seeking an explanation of the Python package ecosystem, specifically
focusing on how pip works, the role of PyPI, the concept of virtual environments,
and a comparison between pip, conda, and uv.\\n\\n2. **Current State**: The
assistant has provided a comprehensive overview of the Python package ecosystem,
including definitions and comparisons of pip, PyPI, virtual environments,
conda, and uv.\\n\\n3. **Important Discoveries**:\\n - PyPI (Python Package
Index) is the official repository with over 400,000 packages.\\n - pip is
the standard package installer that downloads packages from PyPI.\\n - Virtual
environments (venv) allow for isolated Python installations to prevent dependency
conflicts.\\n - conda is a cross-language package manager, particularly
popular in data science, that can manage non-Python dependencies.\\n - uv
is a new Rust-based tool that is significantly faster than pip (10-100x) and
aims to unify the functionalities of pip, pip-tools, and virtualenv.\\n\\n4.
**Next Steps**: The agent should consider providing further details or examples
on how to use pip, conda, and uv, as well as practical applications of virtual
environments in Python projects.\\n\\n5. **Context to Preserve**: \\n -
PyPI: Python Package Index, hosting 400k+ packages.\\n - pip: Standard package
installer for Python.\\n - Virtual environments (venv): Isolated Python
installations.\\n - conda: Cross-language package manager for data science.\\n
\ - uv: Rust-based tool, 10-100x faster than pip, aims to replace pip, pip-tools,
and virtualenv.\\n</summary>\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 333,\n \"completion_tokens\":
349,\n \"total_tokens\": 682,\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_f4ae844694\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Mon, 09 Feb 2026 20:28:04 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:
- '4979'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
- request:
body: '{"messages":[{"role":"system","content":"You are a precise assistant that
creates structured summaries of agent conversations. You preserve critical context
needed for seamless task continuation."},{"role":"user","content":"Analyze the
following conversation and create a structured summary that preserves all information
needed to continue the task seamlessly.\n\n<conversation>\n[USER]: Tell me about
the history of the Python programming language. Who created it, when was it
first released, and what were the main design goals? Please provide a detailed
overview covering the major milestones from its inception through Python 3.\n\n[ASSISTANT]:
Python was created by Guido van Rossum and first released in 1991. The main
design goals were code readability and simplicity. Key milestones: Python 1.0
(1994) introduced functional programming tools like lambda and map. Python 2.0
(2000) added list comprehensions and garbage collection. Python 3.0 (2008) was
a major backward-incompatible release that fixed fundamental design flaws. Python
2 reached end-of-life in January 2020.\n</conversation>\n\nCreate a summary
with these sections:\n1. **Task Overview**: What is the agent trying to accomplish?\n2.
**Current State**: What has been completed so far? What step is the agent on?\n3.
**Important Discoveries**: Key facts, data, tool results, or findings that must
not be lost.\n4. **Next Steps**: What should the agent do next based on the
conversation?\n5. **Context to Preserve**: Any specific values, names, URLs,
code snippets, or details referenced in the conversation.\n\nWrap your entire
summary in <summary> tags.\n\n<summary>\n[Your structured summary here]\n</summary>"}],"model":"gpt-4o-mini","temperature":0}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1726'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- async:asyncio
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7S9PqglWRu0PEoMRHyOiRnpn3yqU\",\n \"object\":
\"chat.completion\",\n \"created\": 1770668879,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"<summary>\\n1. **Task Overview**: The
user is seeking a detailed overview of the history of the Python programming
language, including its creator, initial release date, main design goals,
and major milestones up to Python 3.\\n\\n2. **Current State**: The assistant
has provided a comprehensive response detailing the history of Python, including
its creator (Guido van Rossum), first release (1991), main design goals (code
readability and simplicity), and key milestones (Python 1.0 in 1994, Python
2.0 in 2000, and Python 3.0 in 2008).\\n\\n3. **Important Discoveries**: \\n
\ - Python was created by Guido van Rossum.\\n - First released in 1991.\\n
\ - Main design goals: code readability and simplicity.\\n - Key milestones:\\n
\ - Python 1.0 (1994): Introduced functional programming tools like lambda
and map.\\n - Python 2.0 (2000): Added list comprehensions and garbage
collection.\\n - Python 3.0 (2008): Major backward-incompatible release
that fixed fundamental design flaws.\\n - Python 2 reached end-of-life in
January 2020.\\n\\n4. **Next Steps**: The agent should be prepared to provide
further details or answer any follow-up questions the user may have regarding
Python's history or its features.\\n\\n5. **Context to Preserve**: \\n -
Creator: Guido van Rossum\\n - First release: 1991\\n - Milestones: \\n
\ - Python 1.0 (1994)\\n - Python 2.0 (2000)\\n - Python 3.0 (2008)\\n
\ - End-of-life for Python 2: January 2020\\n</summary>\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
346,\n \"completion_tokens\": 367,\n \"total_tokens\": 713,\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_7e4bf6ad56\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Mon, 09 Feb 2026 20:28:04 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:
- '5368'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
- request:
body: '{"messages":[{"role":"system","content":"You are a precise assistant that
creates structured summaries of agent conversations. You preserve critical context
needed for seamless task continuation."},{"role":"user","content":"Analyze the
following conversation and create a structured summary that preserves all information
needed to continue the task seamlessly.\n\n<conversation>\n[USER]: What about
the async/await features? When were they introduced and how do they compare
to similar features in JavaScript and C#? Also explain the Global Interpreter
Lock and its implications.\n\n[ASSISTANT]: Async/await was introduced in Python
3.5 (PEP 492, 2015). Unlike JavaScript which is single-threaded by design, Python''s
asyncio is an opt-in framework. C# introduced async/await in 2012 (C# 5.0) and
was a major inspiration for Python''s implementation. The GIL (Global Interpreter
Lock) is a mutex that protects access to Python objects, preventing multiple
threads from executing Python bytecodes simultaneously. This means CPU-bound
multithreaded programs don''t benefit from multiple cores. PEP 703 proposes
making the GIL optional in CPython.\n</conversation>\n\nCreate a summary with
these sections:\n1. **Task Overview**: What is the agent trying to accomplish?\n2.
**Current State**: What has been completed so far? What step is the agent on?\n3.
**Important Discoveries**: Key facts, data, tool results, or findings that must
not be lost.\n4. **Next Steps**: What should the agent do next based on the
conversation?\n5. **Context to Preserve**: Any specific values, names, URLs,
code snippets, or details referenced in the conversation.\n\nWrap your entire
summary in <summary> tags.\n\n<summary>\n[Your structured summary here]\n</summary>"}],"model":"gpt-4o-mini","temperature":0}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1786'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- async:asyncio
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7S9Pcl5ybKLH8cSEZ6hgPuvj5iCv\",\n \"object\":
\"chat.completion\",\n \"created\": 1770668879,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"<summary>\\n1. **Task Overview**: The
user is seeking information about the async/await features in Python, their
introduction timeline, comparisons with similar features in JavaScript and
C#, and an explanation of the Global Interpreter Lock (GIL) and its implications.\\n\\n2.
**Current State**: The assistant has provided information regarding the introduction
of async/await in Python (version 3.5, PEP 492 in 2015), comparisons with
JavaScript and C# (C# introduced async/await in 2012), and an explanation
of the GIL.\\n\\n3. **Important Discoveries**: \\n - Async/await was introduced
in Python 3.5 (PEP 492, 2015).\\n - JavaScript is single-threaded, while
Python's asyncio is an opt-in framework.\\n - C# introduced async/await
in 2012 (C# 5.0) and influenced Python's implementation.\\n - The GIL (Global
Interpreter Lock) is a mutex that prevents multiple threads from executing
Python bytecodes simultaneously, affecting CPU-bound multithreaded programs.\\n
\ - PEP 703 proposes making the GIL optional in CPython.\\n\\n4. **Next Steps**:
The agent should consider providing further details on how async/await is
implemented in Python, JavaScript, and C#, and explore the implications of
the GIL in more depth, including potential alternatives or workarounds.\\n\\n5.
**Context to Preserve**: \\n - Python async/await introduction: version
3.5, PEP 492, 2015.\\n - C# async/await introduction: 2012, C# 5.0.\\n -
GIL (Global Interpreter Lock) and its implications on multithreading in Python.\\n
\ - Reference to PEP 703 regarding the GIL.\\n</summary>\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
364,\n \"completion_tokens\": 381,\n \"total_tokens\": 745,\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_f4ae844694\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Mon, 09 Feb 2026 20:28:04 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:
- '5489'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
version: 1

136
lib/crewai/tests/cassettes/utilities/TestSummarizeDirectAnthropic.test_summarize_direct_anthropic.yaml Normal file
View File

@@ -0,0 +1,136 @@
interactions:
- request:
body: '{"max_tokens":4096,"messages":[{"role":"user","content":"Analyze the following
conversation and create a structured summary that preserves all information
needed to continue the task seamlessly.\n\n<conversation>\n[USER]: Research
the latest developments in large language models. Focus on architecture improvements
and training techniques.\n\n[ASSISTANT]: I''ll research the latest developments
in large language models. Based on my knowledge, recent advances include:\n1.
Mixture of Experts (MoE) architectures\n2. Improved attention mechanisms like
Flash Attention\n3. Better training data curation techniques\n4. Constitutional
AI and RLHF improvements\n\n[USER]: Can you go deeper on the MoE architectures?
What are the key papers?\n\n[ASSISTANT]: Key papers on Mixture of Experts:\n-
Switch Transformers (Google, 2021) - simplified MoE routing\n- GShard - scaling
to 600B parameters\n- Mixtral (Mistral AI) - open-source MoE model\nThe main
advantage is computational efficiency: only a subset of experts is activated
per token.\n</conversation>\n\nCreate a summary with these sections:\n1. **Task
Overview**: What is the agent trying to accomplish?\n2. **Current State**: What
has been completed so far? What step is the agent on?\n3. **Important Discoveries**:
Key facts, data, tool results, or findings that must not be lost.\n4. **Next
Steps**: What should the agent do next based on the conversation?\n5. **Context
to Preserve**: Any specific values, names, URLs, code snippets, or details referenced
in the conversation.\n\nWrap your entire summary in <summary> tags.\n\n<summary>\n[Your
structured summary here]\n</summary>"}],"model":"claude-3-5-haiku-latest","stream":false,"system":"You
are a precise assistant that creates structured summaries of agent conversations.
You preserve critical context needed for seamless task continuation.","temperature":0}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
anthropic-version:
- '2023-06-01'
connection:
- keep-alive
content-length:
- '1870'
content-type:
- application/json
host:
- api.anthropic.com
x-api-key:
- X-API-KEY-XXX
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:
- 0.73.0
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
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_01SK3LP6RedPBmpvD1HfKD23","type":"message","role":"assistant","content":[{"type":"text","text":"<summary>\n1.
**Task Overview**:\n- Research latest developments in large language models\n-
Focus on architecture improvements and training techniques\n\n2. **Current
State**:\n- Initial research completed on broad developments\n- Currently
exploring Mixture of Experts (MoE) architectures in depth\n- Detailed discussion
of key MoE research papers initiated\n\n3. **Important Discoveries**:\nMoE
Architecture Insights:\n- Computational efficiency through selective expert
activation\n- Key research papers:\n * Switch Transformers (Google, 2021)\n *
GShard\n * Mixtral (Mistral AI)\n- Main benefit: Only subset of experts activated
per token\n\n4. **Next Steps**:\n- Conduct deeper analysis of MoE architecture
mechanisms\n- Compare routing strategies across different MoE implementations\n-
Investigate performance metrics and scalability of MoE models\n\n5. **Context
to Preserve**:\n- Research Focus: Large Language Model Architectures\n- Specific
Interest: Mixture of Experts (MoE) Architectures\n- Key Researchers/Organizations:
Google, Mistral AI\n- Years of Significant Papers: 2021 onwards\n</summary>"}],"stop_reason":"end_turn","stop_sequence":null,"usage":{"input_tokens":400,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":270,"service_tier":"standard","inference_geo":"not_available"}}'
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Security-Policy:
- CSP-FILTERED
Content-Type:
- application/json
Date:
- Mon, 09 Feb 2026 20:18:41 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Robots-Tag:
- none
anthropic-organization-id:
- ANTHROPIC-ORGANIZATION-ID-XXX
anthropic-ratelimit-input-tokens-limit:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-input-tokens-remaining:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-input-tokens-reset:
- ANTHROPIC-RATELIMIT-INPUT-TOKENS-RESET-XXX
anthropic-ratelimit-output-tokens-limit:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-LIMIT-XXX
anthropic-ratelimit-output-tokens-remaining:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-REMAINING-XXX
anthropic-ratelimit-output-tokens-reset:
- ANTHROPIC-RATELIMIT-OUTPUT-TOKENS-RESET-XXX
anthropic-ratelimit-requests-limit:
- '4000'
anthropic-ratelimit-requests-remaining:
- '3999'
anthropic-ratelimit-requests-reset:
- '2026-02-09T20:18:35Z'
anthropic-ratelimit-tokens-limit:
- ANTHROPIC-RATELIMIT-TOKENS-LIMIT-XXX
anthropic-ratelimit-tokens-remaining:
- ANTHROPIC-RATELIMIT-TOKENS-REMAINING-XXX
anthropic-ratelimit-tokens-reset:
- ANTHROPIC-RATELIMIT-TOKENS-RESET-XXX
cf-cache-status:
- DYNAMIC
request-id:
- REQUEST-ID-XXX
strict-transport-security:
- STS-XXX
x-envoy-upstream-service-time:
- '5639'
status:
code: 200
message: OK
version: 1

110
lib/crewai/tests/cassettes/utilities/TestSummarizeDirectAzure.test_summarize_direct_azure.yaml Normal file
View File

@@ -0,0 +1,110 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are a precise assistant
that creates structured summaries of agent conversations. You preserve critical
context needed for seamless task continuation."}, {"role": "user", "content":
"Analyze the following conversation and create a structured summary that preserves
all information needed to continue the task seamlessly.\n\n<conversation>\n[USER]:
Research the latest developments in large language models. Focus on architecture
improvements and training techniques.\n\n[ASSISTANT]: I''ll research the latest
developments in large language models. Based on my knowledge, recent advances
include:\n1. Mixture of Experts (MoE) architectures\n2. Improved attention mechanisms
like Flash Attention\n3. Better training data curation techniques\n4. Constitutional
AI and RLHF improvements\n\n[USER]: Can you go deeper on the MoE architectures?
What are the key papers?\n\n[ASSISTANT]: Key papers on Mixture of Experts:\n-
Switch Transformers (Google, 2021) - simplified MoE routing\n- GShard - scaling
to 600B parameters\n- Mixtral (Mistral AI) - open-source MoE model\nThe main
advantage is computational efficiency: only a subset of experts is activated
per token.\n</conversation>\n\nCreate a summary with these sections:\n1. **Task
Overview**: What is the agent trying to accomplish?\n2. **Current State**: What
has been completed so far? What step is the agent on?\n3. **Important Discoveries**:
Key facts, data, tool results, or findings that must not be lost.\n4. **Next
Steps**: What should the agent do next based on the conversation?\n5. **Context
to Preserve**: Any specific values, names, URLs, code snippets, or details referenced
in the conversation.\n\nWrap your entire summary in <summary> tags.\n\n<summary>\n[Your
structured summary here]\n</summary>"}], "stream": false, "temperature": 0}'
headers:
Accept:
- application/json
Connection:
- keep-alive
Content-Length:
- '1849'
Content-Type:
- application/json
User-Agent:
- X-USER-AGENT-XXX
accept-encoding:
- ACCEPT-ENCODING-XXX
api-key:
- X-API-KEY-XXX
authorization:
- AUTHORIZATION-XXX
x-ms-client-request-id:
- X-MS-CLIENT-REQUEST-ID-XXX
method: POST
uri: https://fake-azure-endpoint.openai.azure.com/openai/deployments/gpt-4o-mini/chat/completions?api-version=2024-12-01-preview
response:
body:
string: '{"choices":[{"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"protected_material_code":{"filtered":false,"detected":false},"protected_material_text":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"finish_reason":"stop","index":0,"logprobs":null,"message":{"annotations":[],"content":"\u003csummary\u003e\n1.
**Task Overview**: The user has requested research on the latest developments
in large language models, specifically focusing on architecture improvements
and training techniques.\n\n2. **Current State**: The assistant has provided
an initial overview of recent advances in large language models, including
Mixture of Experts (MoE) architectures, improved attention mechanisms, better
training data curation techniques, and advancements in Constitutional AI and
Reinforcement Learning from Human Feedback (RLHF).\n\n3. **Important Discoveries**:
\n - Recent advances in large language models include:\n 1. Mixture
of Experts (MoE) architectures\n 2. Improved attention mechanisms like
Flash Attention\n 3. Better training data curation techniques\n 4.
Constitutional AI and RLHF improvements\n - Key papers on Mixture of Experts:\n -
Switch Transformers (Google, 2021) - simplified MoE routing\n - GShard
- scaling to 600B parameters\n - Mixtral (Mistral AI) - open-source MoE
model\n - The main advantage of MoE architectures is computational efficiency,
as only a subset of experts is activated per token.\n\n4. **Next Steps**:
The assistant should delve deeper into the Mixture of Experts architectures,
potentially summarizing the key findings and implications from the identified
papers.\n\n5. **Context to Preserve**: \n - Key papers: \n - Switch
Transformers (Google, 2021)\n - GShard\n - Mixtral (Mistral AI)\n -
Focus on computational efficiency of MoE architectures.\n\u003c/summary\u003e","refusal":null,"role":"assistant"}}],"created":1770849953,"id":"chatcmpl-D8DFx1H1zzEerW5H0BWfuwmio2sz1","model":"gpt-4o-mini-2024-07-18","object":"chat.completion","prompt_filter_results":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"jailbreak":{"filtered":false,"detected":false},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"system_fingerprint":"fp_f97eff32c5","usage":{"completion_tokens":328,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":0,"rejected_prediction_tokens":0},"prompt_tokens":368,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0},"total_tokens":696}}
'
headers:
Content-Length:
- '2786'
Content-Type:
- application/json
Date:
- Wed, 11 Feb 2026 22:45:56 GMT
Strict-Transport-Security:
- STS-XXX
apim-request-id:
- APIM-REQUEST-ID-XXX
azureml-model-session:
- AZUREML-MODEL-SESSION-XXX
x-accel-buffering:
- 'no'
x-content-type-options:
- X-CONTENT-TYPE-XXX
x-ms-client-request-id:
- X-MS-CLIENT-REQUEST-ID-XXX
x-ms-deployment-name:
- gpt-4o-mini
x-ms-rai-invoked:
- 'true'
x-ms-region:
- X-MS-REGION-XXX
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-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
version: 1

103
lib/crewai/tests/cassettes/utilities/TestSummarizeDirectGemini.test_summarize_direct_gemini.yaml Normal file
View File

@@ -0,0 +1,103 @@
interactions:
- request:
body: '{"contents": [{"parts": [{"text": "Analyze the following conversation and
create a structured summary that preserves all information needed to continue
the task seamlessly.\n\n<conversation>\n[USER]: Research the latest developments
in large language models. Focus on architecture improvements and training techniques.\n\n[ASSISTANT]:
I''ll research the latest developments in large language models. Based on my
knowledge, recent advances include:\n1. Mixture of Experts (MoE) architectures\n2.
Improved attention mechanisms like Flash Attention\n3. Better training data
curation techniques\n4. Constitutional AI and RLHF improvements\n\n[USER]: Can
you go deeper on the MoE architectures? What are the key papers?\n\n[ASSISTANT]:
Key papers on Mixture of Experts:\n- Switch Transformers (Google, 2021) - simplified
MoE routing\n- GShard - scaling to 600B parameters\n- Mixtral (Mistral AI) -
open-source MoE model\nThe main advantage is computational efficiency: only
a subset of experts is activated per token.\n</conversation>\n\nCreate a summary
with these sections:\n1. **Task Overview**: What is the agent trying to accomplish?\n2.
**Current State**: What has been completed so far? What step is the agent on?\n3.
**Important Discoveries**: Key facts, data, tool results, or findings that must
not be lost.\n4. **Next Steps**: What should the agent do next based on the
conversation?\n5. **Context to Preserve**: Any specific values, names, URLs,
code snippets, or details referenced in the conversation.\n\nWrap your entire
summary in <summary> tags.\n\n<summary>\n[Your structured summary here]\n</summary>"}],
"role": "user"}], "systemInstruction": {"parts": [{"text": "You are a precise
assistant that creates structured summaries of agent conversations. You preserve
critical context needed for seamless task continuation."}], "role": "user"},
"generationConfig": {"temperature": 0.0}}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- '*/*'
accept-encoding:
- ACCEPT-ENCODING-XXX
connection:
- keep-alive
content-length:
- '1895'
content-type:
- application/json
host:
- generativelanguage.googleapis.com
x-goog-api-client:
- google-genai-sdk/1.49.0 gl-python/3.13.3
x-goog-api-key:
- X-GOOG-API-KEY-XXX
method: POST
uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent
response:
body:
string: "{\n \"candidates\": [\n {\n \"content\": {\n \"parts\":
[\n {\n \"text\": \"```xml\\n\\u003csummary\\u003e\\n**Task
Overview**: Research the latest developments in large language models, focusing
on architecture improvements and training techniques.\\n\\n**Current State**:
The agent has identified several key areas of advancement in LLMs: Mixture
of Experts (MoE) architectures, improved attention mechanisms (Flash Attention),
better training data curation, and Constitutional AI/RLHF improvements. The
user has requested a deeper dive into MoE architectures. The agent has provided
an initial overview of MoE architectures and listed some key papers.\\n\\n**Important
Discoveries**:\\n* Key MoE papers: Switch Transformers (Google, 2021), GShard,
Mixtral (Mistral AI).\\n* MoE advantage: Computational efficiency through
selective activation of experts.\\n\\n**Next Steps**: Continue researching
MoE architectures based on the user's request for more detail. The agent should
elaborate further on the listed papers and potentially find more recent or
relevant publications.\\n\\n**Context to Preserve**:\\n* Focus areas: Architecture
improvements and training techniques for LLMs.\\n* Specific architectures:
Mixture of Experts (MoE), Flash Attention.\\n* Training techniques: Data
curation, Constitutional AI, RLHF.\\n* Specific papers: Switch Transformers
(Google, 2021), GShard, Mixtral (Mistral AI).\\n\\u003c/summary\\u003e\\n```\"\n
\ }\n ],\n \"role\": \"model\"\n },\n \"finishReason\":
\"STOP\",\n \"avgLogprobs\": -0.14186729703630721\n }\n ],\n \"usageMetadata\":
{\n \"promptTokenCount\": 373,\n \"candidatesTokenCount\": 280,\n \"totalTokenCount\":
653,\n \"promptTokensDetails\": [\n {\n \"modality\": \"TEXT\",\n
\ \"tokenCount\": 373\n }\n ],\n \"candidatesTokensDetails\":
[\n {\n \"modality\": \"TEXT\",\n \"tokenCount\": 280\n
\ }\n ]\n },\n \"modelVersion\": \"gemini-2.0-flash\",\n \"responseId\":
\"GEGKabP3OcGH-8YPzZCj2Ao\"\n}\n"
headers:
Alt-Svc:
- h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Content-Type:
- application/json; charset=UTF-8
Date:
- Mon, 09 Feb 2026 20:18:35 GMT
Server:
- scaffolding on HTTPServer2
Server-Timing:
- gfet4t7; dur=2310
Transfer-Encoding:
- chunked
Vary:
- Origin
- X-Origin
- Referer
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
X-Frame-Options:
- X-FRAME-OPTIONS-XXX
X-XSS-Protection:
- '0'
status:
code: 200
message: OK
version: 1

148
lib/crewai/tests/cassettes/utilities/TestSummarizeDirectOpenAI.test_summarize_direct_openai.yaml Normal file
View File

@@ -0,0 +1,148 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are a precise assistant that
creates structured summaries of agent conversations. You preserve critical context
needed for seamless task continuation."},{"role":"user","content":"Analyze the
following conversation and create a structured summary that preserves all information
needed to continue the task seamlessly.\n\n<conversation>\n[USER]: Research
the latest developments in large language models. Focus on architecture improvements
and training techniques.\n\n[ASSISTANT]: I''ll research the latest developments
in large language models. Based on my knowledge, recent advances include:\n1.
Mixture of Experts (MoE) architectures\n2. Improved attention mechanisms like
Flash Attention\n3. Better training data curation techniques\n4. Constitutional
AI and RLHF improvements\n\n[USER]: Can you go deeper on the MoE architectures?
What are the key papers?\n\n[ASSISTANT]: Key papers on Mixture of Experts:\n-
Switch Transformers (Google, 2021) - simplified MoE routing\n- GShard - scaling
to 600B parameters\n- Mixtral (Mistral AI) - open-source MoE model\nThe main
advantage is computational efficiency: only a subset of experts is activated
per token.\n</conversation>\n\nCreate a summary with these sections:\n1. **Task
Overview**: What is the agent trying to accomplish?\n2. **Current State**: What
has been completed so far? What step is the agent on?\n3. **Important Discoveries**:
Key facts, data, tool results, or findings that must not be lost.\n4. **Next
Steps**: What should the agent do next based on the conversation?\n5. **Context
to Preserve**: Any specific values, names, URLs, code snippets, or details referenced
in the conversation.\n\nWrap your entire summary in <summary> tags.\n\n<summary>\n[Your
structured summary here]\n</summary>"}],"model":"gpt-4o-mini","temperature":0}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1844'
content-type:
- application/json
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7RxGISdQet8JsWImiwzHQ2S9gSD4\",\n \"object\":
\"chat.completion\",\n \"created\": 1770668126,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"<summary>\\n1. **Task Overview**: The
agent is tasked with researching the latest developments in large language
models, specifically focusing on architecture improvements and training techniques.\\n\\n2.
**Current State**: The agent has identified several recent advances in large
language models, including Mixture of Experts (MoE) architectures, improved
attention mechanisms, better training data curation techniques, and advancements
in Constitutional AI and Reinforcement Learning from Human Feedback (RLHF).\\n\\n3.
**Important Discoveries**: \\n - Recent advances in large language models
include:\\n 1. Mixture of Experts (MoE) architectures\\n 2. Improved
attention mechanisms like Flash Attention\\n 3. Better training data curation
techniques\\n 4. Constitutional AI and RLHF improvements\\n - Key papers
on Mixture of Experts:\\n - Switch Transformers (Google, 2021) - simplified
MoE routing\\n - GShard - scaling to 600B parameters\\n - Mixtral
(Mistral AI) - open-source MoE model\\n - The main advantage of MoE architectures
is computational efficiency, as only a subset of experts is activated per
token.\\n\\n4. **Next Steps**: The agent should delve deeper into the Mixture
of Experts architectures, reviewing the key papers mentioned and summarizing
their contributions and implications for large language models.\\n\\n5. **Context
to Preserve**: \\n - Key papers: \\n - Switch Transformers (Google,
2021)\\n - GShard\\n - Mixtral (Mistral AI)\\n - Focus on computational
efficiency of MoE architectures.\\n</summary>\",\n \"refusal\": null,\n
\ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 368,\n \"completion_tokens\":
328,\n \"total_tokens\": 696,\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_f4ae844694\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Mon, 09 Feb 2026 20:15:32 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:
- '5395'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
version: 1

145
lib/crewai/tests/cassettes/utilities/TestSummarizePreservesFiles.test_summarize_preserves_files_integration.yaml Normal file
View File

@@ -0,0 +1,145 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are a precise assistant that
creates structured summaries of agent conversations. You preserve critical context
needed for seamless task continuation."},{"role":"user","content":"Analyze the
following conversation and create a structured summary that preserves all information
needed to continue the task seamlessly.\n\n<conversation>\n[USER]: Research
the latest developments in large language models. Focus on architecture improvements
and training techniques.\n\n[ASSISTANT]: I''ll research the latest developments
in large language models. Based on my knowledge, recent advances include:\n1.
Mixture of Experts (MoE) architectures\n2. Improved attention mechanisms like
Flash Attention\n3. Better training data curation techniques\n4. Constitutional
AI and RLHF improvements\n\n[USER]: Can you go deeper on the MoE architectures?
What are the key papers?\n\n[ASSISTANT]: Key papers on Mixture of Experts:\n-
Switch Transformers (Google, 2021) - simplified MoE routing\n- GShard - scaling
to 600B parameters\n- Mixtral (Mistral AI) - open-source MoE model\nThe main
advantage is computational efficiency: only a subset of experts is activated
per token.\n</conversation>\n\nCreate a summary with these sections:\n1. **Task
Overview**: What is the agent trying to accomplish?\n2. **Current State**: What
has been completed so far? What step is the agent on?\n3. **Important Discoveries**:
Key facts, data, tool results, or findings that must not be lost.\n4. **Next
Steps**: What should the agent do next based on the conversation?\n5. **Context
to Preserve**: Any specific values, names, URLs, code snippets, or details referenced
in the conversation.\n\nWrap your entire summary in <summary> tags.\n\n<summary>\n[Your
structured summary here]\n</summary>"}],"model":"gpt-4o-mini","temperature":0}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1844'
content-type:
- application/json
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:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-D7RxM4n36QoACHrC0QocV1pXIwvtD\",\n \"object\":
\"chat.completion\",\n \"created\": 1770668132,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"<summary>\\n1. **Task Overview**: The
user has requested research on the latest developments in large language models,
specifically focusing on architecture improvements and training techniques.\\n\\n2.
**Current State**: The assistant has identified several recent advances in
large language models, including Mixture of Experts (MoE) architectures, improved
attention mechanisms, better training data curation techniques, and advancements
in Constitutional AI and Reinforcement Learning from Human Feedback (RLHF).\\n\\n3.
**Important Discoveries**: \\n - Key papers on Mixture of Experts (MoE)
architectures:\\n - \\\"Switch Transformers\\\" (Google, 2021) - simplified
MoE routing.\\n - \\\"GShard\\\" - scaling to 600B parameters.\\n -
\\\"Mixtral\\\" (Mistral AI) - open-source MoE model.\\n - The main advantage
of MoE architectures is computational efficiency, as only a subset of experts
is activated per token.\\n\\n4. **Next Steps**: The assistant should delve
deeper into the Mixture of Experts architectures, potentially summarizing
the findings from the key papers mentioned.\\n\\n5. **Context to Preserve**:
\\n - Key papers: \\\"Switch Transformers,\\\" \\\"GShard,\\\" \\\"Mixtral.\\\"\\n
\ - Notable organizations: Google, Mistral AI.\\n - Focus areas: MoE architectures,
computational efficiency.\\n</summary>\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 368,\n \"completion_tokens\":
275,\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_f4ae844694\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Mon, 09 Feb 2026 20:15:36 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:
- '4188'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
set-cookie:
- SET-COOKIE-XXX
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
version: 1

81
lib/crewai/tests/cli/test_plus_api.py
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

311
lib/crewai/tests/cli/test_version.py
View File

@@ -1,15 +1,19 @@
"""Test for version management."""
import json
from datetime import datetime, timedelta
from pathlib import Path
from unittest.mock import MagicMock, patch
from crewai import __version__
from crewai.cli.version import (
_find_latest_non_yanked_version,
_get_cache_file,
_is_cache_valid,
_is_version_yanked,
get_crewai_version,
get_latest_version_from_pypi,
is_current_version_yanked,
is_newer_version_available,
)
@@ -19,10 +23,8 @@ def test_dynamic_versioning_consistency() -> None:
cli_version = get_crewai_version()
package_version = __version__
# Both should return the same version string
assert cli_version == package_version
# Version should not be empty
assert package_version is not None
assert len(package_version.strip()) > 0
@@ -63,12 +65,18 @@ class TestVersionChecking:
def test_get_latest_version_from_pypi_success(
self, mock_urlopen: MagicMock, mock_exists: MagicMock
) -> None:
"""Test successful PyPI version fetch."""
# Mock cache not existing to force fetch from PyPI
"""Test successful PyPI version fetch uses releases data."""
mock_exists.return_value = False
releases = {
"1.0.0": [{"yanked": False}],
"2.0.0": [{"yanked": False}],
"2.1.0": [{"yanked": True, "yanked_reason": "bad release"}],
}
mock_response = MagicMock()
mock_response.read.return_value = b'{"info": {"version": "2.0.0"}}'
mock_response.read.return_value = json.dumps(
{"info": {"version": "2.1.0"}, "releases": releases}
).encode()
mock_urlopen.return_value.__enter__.return_value = mock_response
version = get_latest_version_from_pypi()
@@ -82,7 +90,6 @@ class TestVersionChecking:
"""Test PyPI version fetch failure."""
from urllib.error import URLError
# Mock cache not existing to force fetch from PyPI
mock_exists.return_value = False
mock_urlopen.side_effect = URLError("Network error")
@@ -133,18 +140,247 @@ class TestVersionChecking:
assert latest is None
class TestFindLatestNonYankedVersion:
"""Test _find_latest_non_yanked_version helper."""
def test_skips_yanked_versions(self) -> None:
"""Test that yanked versions are skipped."""
releases = {
"1.0.0": [{"yanked": False}],
"2.0.0": [{"yanked": True}],
}
assert _find_latest_non_yanked_version(releases) == "1.0.0"
def test_returns_highest_non_yanked(self) -> None:
"""Test that the highest non-yanked version is returned."""
releases = {
"1.0.0": [{"yanked": False}],
"1.5.0": [{"yanked": False}],
"2.0.0": [{"yanked": True}],
}
assert _find_latest_non_yanked_version(releases) == "1.5.0"
def test_returns_none_when_all_yanked(self) -> None:
"""Test that None is returned when all versions are yanked."""
releases = {
"1.0.0": [{"yanked": True}],
"2.0.0": [{"yanked": True}],
}
assert _find_latest_non_yanked_version(releases) is None
def test_skips_prerelease_versions(self) -> None:
"""Test that pre-release versions are skipped."""
releases = {
"1.0.0": [{"yanked": False}],
"2.0.0a1": [{"yanked": False}],
"2.0.0rc1": [{"yanked": False}],
}
assert _find_latest_non_yanked_version(releases) == "1.0.0"
def test_skips_versions_with_empty_files(self) -> None:
"""Test that versions with no files are skipped."""
releases: dict[str, list[dict[str, bool]]] = {
"1.0.0": [{"yanked": False}],
"2.0.0": [],
}
assert _find_latest_non_yanked_version(releases) == "1.0.0"
def test_handles_invalid_version_strings(self) -> None:
"""Test that invalid version strings are skipped."""
releases = {
"1.0.0": [{"yanked": False}],
"not-a-version": [{"yanked": False}],
}
assert _find_latest_non_yanked_version(releases) == "1.0.0"
def test_partially_yanked_files_not_considered_yanked(self) -> None:
"""Test that a version with some non-yanked files is not yanked."""
releases = {
"1.0.0": [{"yanked": False}],
"2.0.0": [{"yanked": True}, {"yanked": False}],
}
assert _find_latest_non_yanked_version(releases) == "2.0.0"
class TestIsVersionYanked:
"""Test _is_version_yanked helper."""
def test_non_yanked_version(self) -> None:
"""Test a non-yanked version returns False."""
releases = {"1.0.0": [{"yanked": False}]}
is_yanked, reason = _is_version_yanked("1.0.0", releases)
assert is_yanked is False
assert reason == ""
def test_yanked_version_with_reason(self) -> None:
"""Test a yanked version returns True with reason."""
releases = {
"1.0.0": [{"yanked": True, "yanked_reason": "critical bug"}],
}
is_yanked, reason = _is_version_yanked("1.0.0", releases)
assert is_yanked is True
assert reason == "critical bug"
def test_yanked_version_without_reason(self) -> None:
"""Test a yanked version returns True with empty reason."""
releases = {"1.0.0": [{"yanked": True}]}
is_yanked, reason = _is_version_yanked("1.0.0", releases)
assert is_yanked is True
assert reason == ""
def test_unknown_version(self) -> None:
"""Test an unknown version returns False."""
releases = {"1.0.0": [{"yanked": False}]}
is_yanked, reason = _is_version_yanked("9.9.9", releases)
assert is_yanked is False
assert reason == ""
def test_partially_yanked_files(self) -> None:
"""Test a version with mixed yanked/non-yanked files is not yanked."""
releases = {
"1.0.0": [{"yanked": True}, {"yanked": False}],
}
is_yanked, reason = _is_version_yanked("1.0.0", releases)
assert is_yanked is False
assert reason == ""
def test_multiple_yanked_files_picks_first_reason(self) -> None:
"""Test that the first available reason is returned."""
releases = {
"1.0.0": [
{"yanked": True, "yanked_reason": ""},
{"yanked": True, "yanked_reason": "second reason"},
],
}
is_yanked, reason = _is_version_yanked("1.0.0", releases)
assert is_yanked is True
assert reason == "second reason"
class TestIsCurrentVersionYanked:
"""Test is_current_version_yanked public function."""
@patch("crewai.cli.version.get_crewai_version")
@patch("crewai.cli.version._get_cache_file")
def test_reads_from_valid_cache(
self, mock_cache_file: MagicMock, mock_version: MagicMock, tmp_path: Path
) -> None:
"""Test reading yanked status from a valid cache."""
mock_version.return_value = "1.0.0"
cache_file = tmp_path / "version_cache.json"
cache_data = {
"version": "2.0.0",
"timestamp": datetime.now().isoformat(),
"current_version": "1.0.0",
"current_version_yanked": True,
"current_version_yanked_reason": "bad release",
}
cache_file.write_text(json.dumps(cache_data))
mock_cache_file.return_value = cache_file
is_yanked, reason = is_current_version_yanked()
assert is_yanked is True
assert reason == "bad release"
@patch("crewai.cli.version.get_crewai_version")
@patch("crewai.cli.version._get_cache_file")
def test_not_yanked_from_cache(
self, mock_cache_file: MagicMock, mock_version: MagicMock, tmp_path: Path
) -> None:
"""Test non-yanked status from a valid cache."""
mock_version.return_value = "2.0.0"
cache_file = tmp_path / "version_cache.json"
cache_data = {
"version": "2.0.0",
"timestamp": datetime.now().isoformat(),
"current_version": "2.0.0",
"current_version_yanked": False,
"current_version_yanked_reason": "",
}
cache_file.write_text(json.dumps(cache_data))
mock_cache_file.return_value = cache_file
is_yanked, reason = is_current_version_yanked()
assert is_yanked is False
assert reason == ""
@patch("crewai.cli.version.get_latest_version_from_pypi")
@patch("crewai.cli.version.get_crewai_version")
@patch("crewai.cli.version._get_cache_file")
def test_triggers_fetch_on_stale_cache(
self,
mock_cache_file: MagicMock,
mock_version: MagicMock,
mock_fetch: MagicMock,
tmp_path: Path,
) -> None:
"""Test that a stale cache triggers a re-fetch."""
mock_version.return_value = "1.0.0"
cache_file = tmp_path / "version_cache.json"
old_time = datetime.now() - timedelta(hours=25)
cache_data = {
"version": "2.0.0",
"timestamp": old_time.isoformat(),
"current_version": "1.0.0",
"current_version_yanked": True,
"current_version_yanked_reason": "old reason",
}
cache_file.write_text(json.dumps(cache_data))
mock_cache_file.return_value = cache_file
fresh_cache = {
"version": "2.0.0",
"timestamp": datetime.now().isoformat(),
"current_version": "1.0.0",
"current_version_yanked": False,
"current_version_yanked_reason": "",
}
def write_fresh_cache() -> str:
cache_file.write_text(json.dumps(fresh_cache))
return "2.0.0"
mock_fetch.side_effect = lambda: write_fresh_cache()
is_yanked, reason = is_current_version_yanked()
assert is_yanked is False
mock_fetch.assert_called_once()
@patch("crewai.cli.version.get_latest_version_from_pypi")
@patch("crewai.cli.version.get_crewai_version")
@patch("crewai.cli.version._get_cache_file")
def test_returns_false_on_fetch_failure(
self,
mock_cache_file: MagicMock,
mock_version: MagicMock,
mock_fetch: MagicMock,
tmp_path: Path,
) -> None:
"""Test that fetch failure returns not yanked."""
mock_version.return_value = "1.0.0"
cache_file = tmp_path / "version_cache.json"
mock_cache_file.return_value = cache_file
mock_fetch.return_value = None
is_yanked, reason = is_current_version_yanked()
assert is_yanked is False
assert reason == ""
class TestConsoleFormatterVersionCheck:
"""Test version check display in ConsoleFormatter."""
@patch("crewai.events.utils.console_formatter.is_current_version_yanked")
@patch("crewai.events.utils.console_formatter.is_newer_version_available")
@patch.dict("os.environ", {"CI": ""})
def test_version_message_shows_when_update_available_and_verbose(
self, mock_check: MagicMock
self, mock_check: MagicMock, mock_yanked: MagicMock
) -> None:
"""Test version message shows when update available and verbose enabled."""
from crewai.events.utils.console_formatter import ConsoleFormatter
mock_check.return_value = (True, "1.0.0", "2.0.0")
mock_yanked.return_value = (False, "")
formatter = ConsoleFormatter(verbose=True)
with patch.object(formatter.console, "print") as mock_print:
@@ -165,14 +401,16 @@ class TestConsoleFormatterVersionCheck:
formatter._show_version_update_message_if_needed()
mock_print.assert_not_called()
@patch("crewai.events.utils.console_formatter.is_current_version_yanked")
@patch("crewai.events.utils.console_formatter.is_newer_version_available")
def test_version_message_hides_when_no_update_available(
self, mock_check: MagicMock
self, mock_check: MagicMock, mock_yanked: MagicMock
) -> None:
"""Test version message hidden when no update available."""
from crewai.events.utils.console_formatter import ConsoleFormatter
mock_check.return_value = (False, "2.0.0", "2.0.0")
mock_yanked.return_value = (False, "")
formatter = ConsoleFormatter(verbose=True)
with patch.object(formatter.console, "print") as mock_print:
@@ -208,3 +446,60 @@ class TestConsoleFormatterVersionCheck:
with patch.object(formatter.console, "print") as mock_print:
formatter._show_version_update_message_if_needed()
mock_print.assert_not_called()
@patch("crewai.events.utils.console_formatter.is_current_version_yanked")
@patch("crewai.events.utils.console_formatter.is_newer_version_available")
@patch.dict("os.environ", {"CI": ""})
def test_yanked_warning_shows_when_version_is_yanked(
self, mock_check: MagicMock, mock_yanked: MagicMock
) -> None:
"""Test yanked warning panel shows when current version is yanked."""
from crewai.events.utils.console_formatter import ConsoleFormatter
mock_check.return_value = (False, "1.0.0", "1.0.0")
mock_yanked.return_value = (True, "critical bug")
formatter = ConsoleFormatter(verbose=True)
with patch.object(formatter.console, "print") as mock_print:
formatter._show_version_update_message_if_needed()
assert mock_print.call_count == 2
panel = mock_print.call_args_list[0][0][0]
assert "Yanked Version" in panel.title
assert "critical bug" in str(panel.renderable)
@patch("crewai.events.utils.console_formatter.is_current_version_yanked")
@patch("crewai.events.utils.console_formatter.is_newer_version_available")
@patch.dict("os.environ", {"CI": ""})
def test_yanked_warning_shows_without_reason(
self, mock_check: MagicMock, mock_yanked: MagicMock
) -> None:
"""Test yanked warning panel shows even without a reason."""
from crewai.events.utils.console_formatter import ConsoleFormatter
mock_check.return_value = (False, "1.0.0", "1.0.0")
mock_yanked.return_value = (True, "")
formatter = ConsoleFormatter(verbose=True)
with patch.object(formatter.console, "print") as mock_print:
formatter._show_version_update_message_if_needed()
assert mock_print.call_count == 2
panel = mock_print.call_args_list[0][0][0]
assert "Yanked Version" in panel.title
assert "Reason:" not in str(panel.renderable)
@patch("crewai.events.utils.console_formatter.is_current_version_yanked")
@patch("crewai.events.utils.console_formatter.is_newer_version_available")
@patch.dict("os.environ", {"CI": ""})
def test_both_update_and_yanked_warning_show(
self, mock_check: MagicMock, mock_yanked: MagicMock
) -> None:
"""Test both update and yanked panels show when applicable."""
from crewai.events.utils.console_formatter import ConsoleFormatter
mock_check.return_value = (True, "1.0.0", "2.0.0")
mock_yanked.return_value = (True, "security issue")
formatter = ConsoleFormatter(verbose=True)
with patch.object(formatter.console, "print") as mock_print:
formatter._show_version_update_message_if_needed()
assert mock_print.call_count == 4

38
lib/crewai/tests/events/test_event_context.py
View File

@@ -177,4 +177,40 @@ class TestTriggeredByScope:
raise ValueError("test error")
except ValueError:
pass
assert get_triggering_event_id() is None
assert get_triggering_event_id() is None
def test_agent_scope_preserved_after_tool_error_event() -> None:
from crewai.events import crewai_event_bus
from crewai.events.types.tool_usage_events import (
ToolUsageErrorEvent,
ToolUsageStartedEvent,
)
push_event_scope("crew-1", "crew_kickoff_started")
push_event_scope("task-1", "task_started")
push_event_scope("agent-1", "agent_execution_started")
crewai_event_bus.emit(
None,
ToolUsageStartedEvent(
tool_name="test_tool",
tool_args={},
agent_key="test_agent",
)
)
crewai_event_bus.emit(
None,
ToolUsageErrorEvent(
tool_name="test_tool",
tool_args={},
agent_key="test_agent",
error=ValueError("test error"),
)
)
crewai_event_bus.flush()
assert get_current_parent_id() == "agent-1"

131
lib/crewai/tests/llms/anthropic/test_anthropic.py
View File

@@ -990,3 +990,134 @@ def test_anthropic_agent_kickoff_structured_output_with_tools():
assert result.pydantic.result == 42, f"Expected result 42 but got {result.pydantic.result}"
assert result.pydantic.operation, "Operation should not be empty"
assert result.pydantic.explanation, "Explanation should not be empty"
@pytest.mark.vcr()
def test_anthropic_cached_prompt_tokens():
"""
Test that Anthropic correctly extracts and tracks cached_prompt_tokens
from cache_read_input_tokens. Uses cache_control to enable prompt caching
and sends the same large prompt twice so the second call hits the cache.
"""
# Anthropic requires cache_control blocks and >=1024 tokens for caching
padding = "This is padding text to ensure the prompt is large enough for caching. " * 80
system_msg = f"You are a helpful assistant. {padding}"
llm = LLM(model="anthropic/claude-sonnet-4-5-20250929")
def _ephemeral_user(text: str):
return [{"type": "text", "text": text, "cache_control": {"type": "ephemeral"}}]
# First call: creates the cache
llm.call([
{"role": "system", "content": system_msg},
{"role": "user", "content": _ephemeral_user("Say hello in one word.")},
])
# Second call: same system prompt should hit the cache
llm.call([
{"role": "system", "content": system_msg},
{"role": "user", "content": _ephemeral_user("Say goodbye in one word.")},
])
usage = llm.get_token_usage_summary()
assert usage.total_tokens > 0
assert usage.prompt_tokens > 0
assert usage.completion_tokens > 0
assert usage.successful_requests == 2
# The second call should have cached prompt tokens
assert usage.cached_prompt_tokens > 0
@pytest.mark.vcr()
def test_anthropic_streaming_cached_prompt_tokens():
"""
Test that Anthropic streaming correctly extracts and tracks cached_prompt_tokens.
"""
padding = "This is padding text to ensure the prompt is large enough for caching. " * 80
system_msg = f"You are a helpful assistant. {padding}"
llm = LLM(model="anthropic/claude-sonnet-4-5-20250929", stream=True)
def _ephemeral_user(text: str):
return [{"type": "text", "text": text, "cache_control": {"type": "ephemeral"}}]
# First call: creates the cache
llm.call([
{"role": "system", "content": system_msg},
{"role": "user", "content": _ephemeral_user("Say hello in one word.")},
])
# Second call: same system prompt should hit the cache
llm.call([
{"role": "system", "content": system_msg},
{"role": "user", "content": _ephemeral_user("Say goodbye in one word.")},
])
usage = llm.get_token_usage_summary()
assert usage.total_tokens > 0
assert usage.successful_requests == 2
# The second call should have cached prompt tokens
assert usage.cached_prompt_tokens > 0
@pytest.mark.vcr()
def test_anthropic_cached_prompt_tokens_with_tools():
"""
Test that Anthropic correctly tracks cached_prompt_tokens when tools are used.
The large system prompt should be cached across tool-calling requests.
"""
padding = "This is padding text to ensure the prompt is large enough for caching. " * 80
system_msg = f"You are a helpful assistant that uses tools. {padding}"
def get_weather(location: str) -> str:
return f"The weather in {location} is sunny and 72°F"
tools = [
{
"name": "get_weather",
"description": "Get the current weather for a location",
"input_schema": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name"
}
},
"required": ["location"],
},
}
]
llm = LLM(model="anthropic/claude-sonnet-4-5-20250929")
def _ephemeral_user(text: str):
return [{"type": "text", "text": text, "cache_control": {"type": "ephemeral"}}]
# First call with tool: creates the cache
llm.call(
[
{"role": "system", "content": system_msg},
{"role": "user", "content": _ephemeral_user("What is the weather in Tokyo?")},
],
tools=tools,
available_functions={"get_weather": get_weather},
)
# Second call with same system prompt + tools: should hit the cache
llm.call(
[
{"role": "system", "content": system_msg},
{"role": "user", "content": _ephemeral_user("What is the weather in Paris?")},
],
tools=tools,
available_functions={"get_weather": get_weather},
)
usage = llm.get_token_usage_summary()
assert usage.total_tokens > 0
assert usage.prompt_tokens > 0
assert usage.successful_requests == 2
# The second call should have cached prompt tokens
assert usage.cached_prompt_tokens > 0

1
lib/crewai/tests/llms/azure/test_azure.py
View File

@@ -102,7 +102,6 @@ def test_azure_tool_use_conversation_flow():
# Verify that the API was called
assert mock_complete.called
@pytest.mark.usefixtures("mock_azure_credentials")
def test_azure_completion_module_is_imported():
"""

153
lib/crewai/tests/llms/google/test_google.py
View File

@@ -42,65 +42,6 @@ def test_gemini_completion_is_used_when_gemini_provider():
assert llm.provider == "gemini"
assert llm.model == "gemini-2.0-flash-001"
def test_gemini_tool_use_conversation_flow():
"""
Test that the Gemini completion properly handles tool use conversation flow
"""
from unittest.mock import Mock, patch
from crewai.llms.providers.gemini.completion import GeminiCompletion
# Create GeminiCompletion instance
completion = GeminiCompletion(model="gemini-2.0-flash-001")
# Mock tool function
def mock_weather_tool(location: str) -> str:
return f"The weather in {location} is sunny and 75°F"
available_functions = {"get_weather": mock_weather_tool}
# Mock the Google Gemini client responses
with patch.object(completion.client.models, 'generate_content') as mock_generate:
# Mock function call in response
mock_function_call = Mock()
mock_function_call.name = "get_weather"
mock_function_call.args = {"location": "San Francisco"}
mock_part = Mock()
mock_part.function_call = mock_function_call
mock_content = Mock()
mock_content.parts = [mock_part]
mock_candidate = Mock()
mock_candidate.content = mock_content
mock_response = Mock()
mock_response.candidates = [mock_candidate]
mock_response.text = "Based on the weather data, it's a beautiful day in San Francisco with sunny skies and 75°F temperature."
mock_response.usage_metadata = Mock()
mock_response.usage_metadata.prompt_token_count = 100
mock_response.usage_metadata.candidates_token_count = 50
mock_response.usage_metadata.total_token_count = 150
mock_generate.return_value = mock_response
# Test the call
messages = [{"role": "user", "content": "What's the weather like in San Francisco?"}]
result = completion.call(
messages=messages,
available_functions=available_functions
)
# Verify the tool was executed and returned the result
assert result == "The weather in San Francisco is sunny and 75°F"
# Verify that the API was called
assert mock_generate.called
def test_gemini_completion_module_is_imported():
"""
Test that the completion module is properly imported when using Google provider
@@ -1114,3 +1055,97 @@ def test_gemini_structured_output_preserves_json_with_stop_word_patterns():
assert "Action:" in result.action_taken
assert "Observation:" in result.observation_result
assert "Final Answer:" in result.final_answer
@pytest.mark.vcr()
def test_gemini_cached_prompt_tokens():
"""
Test that Gemini correctly extracts and tracks cached_prompt_tokens
from cached_content_token_count in the usage metadata.
Sends two calls with the same large prompt to trigger caching.
"""
padding = "This is padding text to ensure the prompt is large enough for caching. " * 80
system_msg = f"You are a helpful assistant. {padding}"
llm = LLM(model="google/gemini-2.5-flash")
# First call
llm.call([
{"role": "system", "content": system_msg},
{"role": "user", "content": "Say hello in one word."},
])
# Second call: same system prompt
llm.call([
{"role": "system", "content": system_msg},
{"role": "user", "content": "Say goodbye in one word."},
])
usage = llm.get_token_usage_summary()
assert usage.total_tokens > 0
assert usage.prompt_tokens > 0
assert usage.completion_tokens > 0
assert usage.successful_requests == 2
# cached_prompt_tokens should be populated (may be 0 if Gemini
# doesn't cache for this particular request, but the field should exist)
assert usage.cached_prompt_tokens >= 0
@pytest.mark.vcr()
def test_gemini_cached_prompt_tokens_with_tools():
"""
Test that Gemini correctly tracks cached_prompt_tokens when tools are used.
The large system prompt should be cached across tool-calling requests.
"""
padding = "This is padding text to ensure the prompt is large enough for caching. " * 80
system_msg = f"You are a helpful assistant that uses tools. {padding}"
def get_weather(location: str) -> str:
return f"The weather in {location} is sunny and 72°F"
tools = [
{
"name": "get_weather",
"description": "Get the current weather for a location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name"
}
},
"required": ["location"],
},
}
]
llm = LLM(model="google/gemini-2.5-flash")
# First call with tool
llm.call(
[
{"role": "system", "content": system_msg},
{"role": "user", "content": "What is the weather in Tokyo?"},
],
tools=tools,
available_functions={"get_weather": get_weather},
)
# Second call with same system prompt + tools
llm.call(
[
{"role": "system", "content": system_msg},
{"role": "user", "content": "What is the weather in Paris?"},
],
tools=tools,
available_functions={"get_weather": get_weather},
)
usage = llm.get_token_usage_summary()
assert usage.total_tokens > 0
assert usage.prompt_tokens > 0
assert usage.successful_requests == 2
# cached_prompt_tokens should be populated (may be 0 if Gemini
# doesn't cache for this particular request, but the field should exist)
assert usage.cached_prompt_tokens >= 0

377
lib/crewai/tests/llms/openai/test_openai.py
View File

@@ -1,6 +1,7 @@
import os
import sys
import types
from typing import Any
from unittest.mock import patch, MagicMock
import openai
import pytest
@@ -1578,3 +1579,379 @@ def test_openai_structured_output_preserves_json_with_stop_word_patterns():
assert "Action:" in result.action_taken
assert "Observation:" in result.observation_result
assert "Final Answer:" in result.final_answer
@pytest.mark.vcr()
def test_openai_completions_cached_prompt_tokens():
"""
Test that the Chat Completions API correctly extracts and tracks
cached_prompt_tokens from prompt_tokens_details.cached_tokens.
Sends the same large prompt twice so the second call hits the cache.
"""
# Build a large system prompt to trigger prompt caching (>1024 tokens)
padding = "This is padding text to ensure the prompt is large enough for caching. " * 80
system_msg = f"You are a helpful assistant. {padding}"
llm = OpenAICompletion(model="gpt-4.1")
# First call: creates the cache
llm.call([
{"role": "system", "content": system_msg},
{"role": "user", "content": "Say hello in one word."},
])
# Second call: same system prompt should hit the cache
llm.call([
{"role": "system", "content": system_msg},
{"role": "user", "content": "Say goodbye in one word."},
])
usage = llm.get_token_usage_summary()
assert usage.total_tokens > 0
assert usage.prompt_tokens > 0
assert usage.completion_tokens > 0
assert usage.successful_requests == 2
# The second call should have cached prompt tokens
assert usage.cached_prompt_tokens > 0
@pytest.mark.vcr()
def test_openai_responses_api_cached_prompt_tokens():
"""
Test that the Responses API correctly extracts and tracks
cached_prompt_tokens from input_tokens_details.cached_tokens.
"""
padding = "This is padding text to ensure the prompt is large enough for caching. " * 80
system_msg = f"You are a helpful assistant. {padding}"
llm = OpenAICompletion(model="gpt-4.1", api="responses")
# First call: creates the cache
llm.call([
{"role": "system", "content": system_msg},
{"role": "user", "content": "Say hello in one word."},
])
# Second call: same system prompt should hit the cache
llm.call([
{"role": "system", "content": system_msg},
{"role": "user", "content": "Say goodbye in one word."},
])
usage = llm.get_token_usage_summary()
assert usage.total_tokens > 0
assert usage.prompt_tokens > 0
assert usage.completion_tokens > 0
assert usage.successful_requests == 2
# The second call should have cached prompt tokens
assert usage.cached_prompt_tokens > 0
@pytest.mark.vcr()
def test_openai_streaming_cached_prompt_tokens():
"""
Test that streaming Chat Completions API correctly extracts and tracks
cached_prompt_tokens.
"""
padding = "This is padding text to ensure the prompt is large enough for caching. " * 80
system_msg = f"You are a helpful assistant. {padding}"
llm = OpenAICompletion(model="gpt-4.1", stream=True)
# First call: creates the cache
llm.call([
{"role": "system", "content": system_msg},
{"role": "user", "content": "Say hello in one word."},
])
# Second call: same system prompt should hit the cache
llm.call([
{"role": "system", "content": system_msg},
{"role": "user", "content": "Say goodbye in one word."},
])
usage = llm.get_token_usage_summary()
assert usage.total_tokens > 0
assert usage.successful_requests == 2
# The second call should have cached prompt tokens
assert usage.cached_prompt_tokens > 0
@pytest.mark.vcr()
def test_openai_completions_cached_prompt_tokens_with_tools():
"""
Test that the Chat Completions API correctly tracks cached_prompt_tokens
when tools are used. The large system prompt should be cached across calls.
"""
padding = "This is padding text to ensure the prompt is large enough for caching. " * 80
system_msg = f"You are a helpful assistant that uses tools. {padding}"
def get_weather(location: str) -> str:
return f"The weather in {location} is sunny and 72°F"
tools = [
{
"name": "get_weather",
"description": "Get the current weather for a location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name"
}
},
"required": ["location"],
"additionalProperties": False,
},
}
]
llm = OpenAICompletion(model="gpt-4.1")
# First call with tool: creates the cache
llm.call(
[
{"role": "system", "content": system_msg},
{"role": "user", "content": "What is the weather in Tokyo?"},
],
tools=tools,
available_functions={"get_weather": get_weather},
)
# Second call with same system prompt + tools: should hit the cache
llm.call(
[
{"role": "system", "content": system_msg},
{"role": "user", "content": "What is the weather in Paris?"},
],
tools=tools,
available_functions={"get_weather": get_weather},
)
usage = llm.get_token_usage_summary()
assert usage.total_tokens > 0
assert usage.prompt_tokens > 0
assert usage.successful_requests == 2
# The second call should have cached prompt tokens
assert usage.cached_prompt_tokens > 0
@pytest.mark.vcr()
def test_openai_responses_api_cached_prompt_tokens_with_tools():
"""
Test that the Responses API correctly tracks cached_prompt_tokens
when function tools are used.
"""
padding = "This is padding text to ensure the prompt is large enough for caching. " * 80
system_msg = f"You are a helpful assistant that uses tools. {padding}"
def get_weather(location: str) -> str:
return f"The weather in {location} is sunny and 72°F"
tools = [
{
"name": "get_weather",
"description": "Get the current weather for a location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name"
}
},
"required": ["location"],
},
}
]
llm = OpenAICompletion(model="gpt-4.1", api='response')
# First call with tool
llm.call(
[
{"role": "system", "content": system_msg},
{"role": "user", "content": "What is the weather in Tokyo?"},
],
tools=tools,
available_functions={"get_weather": get_weather},
)
# Second call: same system prompt + tools should hit cache
llm.call(
[
{"role": "system", "content": system_msg},
{"role": "user", "content": "What is the weather in Paris?"},
],
tools=tools,
available_functions={"get_weather": get_weather},
)
usage = llm.get_token_usage_summary()
assert usage.total_tokens > 0
assert usage.successful_requests == 2
assert usage.cached_prompt_tokens > 0
def test_openai_streaming_returns_tool_calls_without_available_functions():
"""Test that streaming returns tool calls list when available_functions is None.
This mirrors the non-streaming path where tool_calls are returned for
the executor to handle. Reproduces the bug where streaming with tool
calls would return empty text instead of tool_calls when
available_functions was not provided (as the crew executor does).
"""
llm = LLM(model="openai/gpt-4o-mini", stream=True)
mock_chunk_1 = MagicMock()
mock_chunk_1.choices = [MagicMock()]
mock_chunk_1.choices[0].delta = MagicMock()
mock_chunk_1.choices[0].delta.content = None
mock_chunk_1.choices[0].delta.tool_calls = [MagicMock()]
mock_chunk_1.choices[0].delta.tool_calls[0].index = 0
mock_chunk_1.choices[0].delta.tool_calls[0].id = "call_abc123"
mock_chunk_1.choices[0].delta.tool_calls[0].function = MagicMock()
mock_chunk_1.choices[0].delta.tool_calls[0].function.name = "calculator"
mock_chunk_1.choices[0].delta.tool_calls[0].function.arguments = '{"expr'
mock_chunk_1.choices[0].finish_reason = None
mock_chunk_1.usage = None
mock_chunk_1.id = "chatcmpl-1"
mock_chunk_2 = MagicMock()
mock_chunk_2.choices = [MagicMock()]
mock_chunk_2.choices[0].delta = MagicMock()
mock_chunk_2.choices[0].delta.content = None
mock_chunk_2.choices[0].delta.tool_calls = [MagicMock()]
mock_chunk_2.choices[0].delta.tool_calls[0].index = 0
mock_chunk_2.choices[0].delta.tool_calls[0].id = None
mock_chunk_2.choices[0].delta.tool_calls[0].function = MagicMock()
mock_chunk_2.choices[0].delta.tool_calls[0].function.name = None
mock_chunk_2.choices[0].delta.tool_calls[0].function.arguments = 'ession": "1+1"}'
mock_chunk_2.choices[0].finish_reason = None
mock_chunk_2.usage = None
mock_chunk_2.id = "chatcmpl-1"
mock_chunk_3 = MagicMock()
mock_chunk_3.choices = [MagicMock()]
mock_chunk_3.choices[0].delta = MagicMock()
mock_chunk_3.choices[0].delta.content = None
mock_chunk_3.choices[0].delta.tool_calls = None
mock_chunk_3.choices[0].finish_reason = "tool_calls"
mock_chunk_3.usage = MagicMock()
mock_chunk_3.usage.prompt_tokens = 10
mock_chunk_3.usage.completion_tokens = 5
mock_chunk_3.id = "chatcmpl-1"
with patch.object(
llm.client.chat.completions, "create", return_value=iter([mock_chunk_1, mock_chunk_2, mock_chunk_3])
):
result = llm.call(
messages=[{"role": "user", "content": "Calculate 1+1"}],
tools=[{
"type": "function",
"function": {
"name": "calculator",
"description": "Calculate expression",
"parameters": {"type": "object", "properties": {"expression": {"type": "string"}}},
},
}],
available_functions=None,
)
assert isinstance(result, list), f"Expected list of tool calls, got {type(result)}: {result}"
assert len(result) == 1
assert result[0]["function"]["name"] == "calculator"
assert result[0]["function"]["arguments"] == '{"expression": "1+1"}'
assert result[0]["id"] == "call_abc123"
assert result[0]["type"] == "function"
@pytest.mark.asyncio
async def test_openai_async_streaming_returns_tool_calls_without_available_functions():
"""Test that async streaming returns tool calls list when available_functions is None.
Same as the sync test but for the async path (_ahandle_streaming_completion).
"""
llm = LLM(model="openai/gpt-4o-mini", stream=True)
mock_chunk_1 = MagicMock()
mock_chunk_1.choices = [MagicMock()]
mock_chunk_1.choices[0].delta = MagicMock()
mock_chunk_1.choices[0].delta.content = None
mock_chunk_1.choices[0].delta.tool_calls = [MagicMock()]
mock_chunk_1.choices[0].delta.tool_calls[0].index = 0
mock_chunk_1.choices[0].delta.tool_calls[0].id = "call_abc123"
mock_chunk_1.choices[0].delta.tool_calls[0].function = MagicMock()
mock_chunk_1.choices[0].delta.tool_calls[0].function.name = "calculator"
mock_chunk_1.choices[0].delta.tool_calls[0].function.arguments = '{"expr'
mock_chunk_1.choices[0].finish_reason = None
mock_chunk_1.usage = None
mock_chunk_1.id = "chatcmpl-1"
mock_chunk_2 = MagicMock()
mock_chunk_2.choices = [MagicMock()]
mock_chunk_2.choices[0].delta = MagicMock()
mock_chunk_2.choices[0].delta.content = None
mock_chunk_2.choices[0].delta.tool_calls = [MagicMock()]
mock_chunk_2.choices[0].delta.tool_calls[0].index = 0
mock_chunk_2.choices[0].delta.tool_calls[0].id = None
mock_chunk_2.choices[0].delta.tool_calls[0].function = MagicMock()
mock_chunk_2.choices[0].delta.tool_calls[0].function.name = None
mock_chunk_2.choices[0].delta.tool_calls[0].function.arguments = 'ession": "1+1"}'
mock_chunk_2.choices[0].finish_reason = None
mock_chunk_2.usage = None
mock_chunk_2.id = "chatcmpl-1"
mock_chunk_3 = MagicMock()
mock_chunk_3.choices = [MagicMock()]
mock_chunk_3.choices[0].delta = MagicMock()
mock_chunk_3.choices[0].delta.content = None
mock_chunk_3.choices[0].delta.tool_calls = None
mock_chunk_3.choices[0].finish_reason = "tool_calls"
mock_chunk_3.usage = MagicMock()
mock_chunk_3.usage.prompt_tokens = 10
mock_chunk_3.usage.completion_tokens = 5
mock_chunk_3.id = "chatcmpl-1"
class MockAsyncStream:
"""Async iterator that mimics OpenAI's async streaming response."""
def __init__(self, chunks: list[Any]) -> None:
self._chunks = chunks
self._index = 0
def __aiter__(self) -> "MockAsyncStream":
return self
async def __anext__(self) -> Any:
if self._index >= len(self._chunks):
raise StopAsyncIteration
chunk = self._chunks[self._index]
self._index += 1
return chunk
async def mock_create(**kwargs: Any) -> MockAsyncStream:
return MockAsyncStream([mock_chunk_1, mock_chunk_2, mock_chunk_3])
with patch.object(
llm.async_client.chat.completions, "create", side_effect=mock_create
):
result = await llm.acall(
messages=[{"role": "user", "content": "Calculate 1+1"}],
tools=[{
"type": "function",
"function": {
"name": "calculator",
"description": "Calculate expression",
"parameters": {"type": "object", "properties": {"expression": {"type": "string"}}},
},
}],
available_functions=None,
)
assert isinstance(result, list), f"Expected list of tool calls, got {type(result)}: {result}"
assert len(result) == 1
assert result[0]["function"]["name"] == "calculator"
assert result[0]["function"]["arguments"] == '{"expression": "1+1"}'
assert result[0]["id"] == "call_abc123"
assert result[0]["type"] == "function"

4
lib/crewai/tests/memory/test_external_memory.py
View File

@@ -308,6 +308,7 @@ def test_external_memory_search_events(
"parent_event_id": None,
"previous_event_id": ANY,
"triggered_by_event_id": None,
"started_event_id": ANY,
"emission_sequence": ANY,
"query": "test value",
"limit": 3,
@@ -330,6 +331,7 @@ def test_external_memory_search_events(
"parent_event_id": ANY,
"previous_event_id": ANY,
"triggered_by_event_id": None,
"started_event_id": ANY,
"emission_sequence": ANY,
"query": "test value",
"results": [],
@@ -390,6 +392,7 @@ def test_external_memory_save_events(
"parent_event_id": None,
"previous_event_id": ANY,
"triggered_by_event_id": None,
"started_event_id": ANY,
"emission_sequence": ANY,
"value": "saving value",
"metadata": {"task": "test_task"},
@@ -411,6 +414,7 @@ def test_external_memory_save_events(
"parent_event_id": ANY,
"previous_event_id": ANY,
"triggered_by_event_id": None,
"started_event_id": ANY,
"emission_sequence": ANY,
"value": "saving value",
"metadata": {"task": "test_task"},

4
lib/crewai/tests/memory/test_long_term_memory.py
View File

@@ -74,6 +74,7 @@ def test_long_term_memory_save_events(long_term_memory):
"parent_event_id": None,
"previous_event_id": ANY,
"triggered_by_event_id": None,
"started_event_id": ANY,
"emission_sequence": ANY,
"value": "test_task",
"metadata": {"task": "test_task", "quality": 0.5},
@@ -94,6 +95,7 @@ def test_long_term_memory_save_events(long_term_memory):
"parent_event_id": None,
"previous_event_id": ANY,
"triggered_by_event_id": None,
"started_event_id": ANY,
"emission_sequence": ANY,
"value": "test_task",
"metadata": {
@@ -153,6 +155,7 @@ def test_long_term_memory_search_events(long_term_memory):
"parent_event_id": None,
"previous_event_id": ANY,
"triggered_by_event_id": None,
"started_event_id": ANY,
"emission_sequence": ANY,
"query": "test query",
"limit": 5,
@@ -175,6 +178,7 @@ def test_long_term_memory_search_events(long_term_memory):
"parent_event_id": ANY,
"previous_event_id": ANY,
"triggered_by_event_id": None,
"started_event_id": ANY,
"emission_sequence": ANY,
"query": "test query",
"results": None,

4
lib/crewai/tests/memory/test_short_term_memory.py
View File

@@ -85,6 +85,7 @@ def test_short_term_memory_search_events(short_term_memory):
"parent_event_id": None,
"previous_event_id": ANY,
"triggered_by_event_id": None,
"started_event_id": ANY,
"emission_sequence": ANY,
"query": "test value",
"limit": 3,
@@ -107,6 +108,7 @@ def test_short_term_memory_search_events(short_term_memory):
"parent_event_id": None,
"previous_event_id": ANY,
"triggered_by_event_id": None,
"started_event_id": ANY,
"emission_sequence": ANY,
"query": "test value",
"results": [],
@@ -164,6 +166,7 @@ def test_short_term_memory_save_events(short_term_memory):
"parent_event_id": None,
"previous_event_id": ANY,
"triggered_by_event_id": None,
"started_event_id": ANY,
"emission_sequence": ANY,
"value": "test value",
"metadata": {"task": "test_task"},
@@ -185,6 +188,7 @@ def test_short_term_memory_save_events(short_term_memory):
"parent_event_id": None,
"previous_event_id": ANY,
"triggered_by_event_id": None,
"started_event_id": ANY,
"emission_sequence": ANY,
"value": "test value",
"metadata": {"task": "test_task"},

57
lib/crewai/tests/test_flow_human_input_integration.py
View File

@@ -2,6 +2,7 @@ from unittest.mock import MagicMock, patch
import pytest
from crewai.events.event_listener import event_listener
from crewai.core.providers.human_input import SyncHumanInputProvider
class TestFlowHumanInputIntegration:
@@ -24,14 +25,9 @@ class TestFlowHumanInputIntegration:
@patch("builtins.input", return_value="")
def test_human_input_pauses_flow_updates(self, mock_input):
"""Test that human input pauses Flow status updates."""
from crewai.agents.agent_builder.base_agent_executor_mixin import (
CrewAgentExecutorMixin,
)
executor = CrewAgentExecutorMixin()
executor.crew = MagicMock()
executor.crew._train = False
executor._printer = MagicMock()
provider = SyncHumanInputProvider()
crew = MagicMock()
crew._train = False
formatter = event_listener.formatter
@@ -39,7 +35,7 @@ class TestFlowHumanInputIntegration:
patch.object(formatter, "pause_live_updates") as mock_pause,
patch.object(formatter, "resume_live_updates") as mock_resume,
):
result = executor._ask_human_input("Test result")
result = provider._prompt_input(crew)
mock_pause.assert_called_once()
mock_resume.assert_called_once()
@@ -49,14 +45,9 @@ class TestFlowHumanInputIntegration:
@patch("builtins.input", side_effect=["feedback", ""])
def test_multiple_human_input_rounds(self, mock_input):
"""Test multiple rounds of human input with Flow status management."""
from crewai.agents.agent_builder.base_agent_executor_mixin import (
CrewAgentExecutorMixin,
)
executor = CrewAgentExecutorMixin()
executor.crew = MagicMock()
executor.crew._train = False
executor._printer = MagicMock()
provider = SyncHumanInputProvider()
crew = MagicMock()
crew._train = False
formatter = event_listener.formatter
@@ -75,10 +66,10 @@ class TestFlowHumanInputIntegration:
formatter, "resume_live_updates", side_effect=track_resume
),
):
result1 = executor._ask_human_input("Test result 1")
result1 = provider._prompt_input(crew)
assert result1 == "feedback"
result2 = executor._ask_human_input("Test result 2")
result2 = provider._prompt_input(crew)
assert result2 == ""
assert len(pause_calls) == 2
@@ -103,14 +94,9 @@ class TestFlowHumanInputIntegration:
def test_pause_resume_exception_handling(self):
"""Test that resume is called even if exception occurs during human input."""
from crewai.agents.agent_builder.base_agent_executor_mixin import (
CrewAgentExecutorMixin,
)
executor = CrewAgentExecutorMixin()
executor.crew = MagicMock()
executor.crew._train = False
executor._printer = MagicMock()
provider = SyncHumanInputProvider()
crew = MagicMock()
crew._train = False
formatter = event_listener.formatter
@@ -122,21 +108,16 @@ class TestFlowHumanInputIntegration:
),
):
with pytest.raises(KeyboardInterrupt):
executor._ask_human_input("Test result")
provider._prompt_input(crew)
mock_pause.assert_called_once()
mock_resume.assert_called_once()
def test_training_mode_human_input(self):
"""Test human input in training mode."""
from crewai.agents.agent_builder.base_agent_executor_mixin import (
CrewAgentExecutorMixin,
)
executor = CrewAgentExecutorMixin()
executor.crew = MagicMock()
executor.crew._train = True
executor._printer = MagicMock()
provider = SyncHumanInputProvider()
crew = MagicMock()
crew._train = True
formatter = event_listener.formatter
@@ -146,7 +127,7 @@ class TestFlowHumanInputIntegration:
patch.object(formatter.console, "print") as mock_console_print,
patch("builtins.input", return_value="training feedback"),
):
result = executor._ask_human_input("Test result")
result = provider._prompt_input(crew)
mock_pause.assert_called_once()
mock_resume.assert_called_once()
@@ -161,4 +142,4 @@ class TestFlowHumanInputIntegration:
for call in call_args
if call[0]
)
assert training_panel_found
assert training_panel_found

170
lib/crewai/tests/test_human_feedback_integration.py
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."""

77
lib/crewai/tests/tools/test_tool_usage.py
View File

@@ -10,7 +10,9 @@ from crewai import Agent, Task
from crewai.events.event_bus import crewai_event_bus
from crewai.events.types.tool_usage_events import (
ToolSelectionErrorEvent,
ToolUsageErrorEvent,
ToolUsageFinishedEvent,
ToolUsageStartedEvent,
ToolValidateInputErrorEvent,
)
from crewai.tools import BaseTool
@@ -744,3 +746,78 @@ def test_tool_usage_finished_event_with_cached_result():
assert isinstance(event.started_at, datetime.datetime)
assert isinstance(event.finished_at, datetime.datetime)
assert event.type == "tool_usage_finished"
def test_tool_error_does_not_emit_finished_event():
from crewai.tools.tool_calling import ToolCalling
class FailingTool(BaseTool):
name: str = "Failing Tool"
description: str = "A tool that always fails"
def _run(self, **kwargs) -> str:
raise ValueError("Intentional failure")
failing_tool = FailingTool().to_structured_tool()
mock_agent = MagicMock()
mock_agent.key = "test_agent_key"
mock_agent.role = "test_agent_role"
mock_agent._original_role = "test_agent_role"
mock_agent.verbose = False
mock_agent.fingerprint = None
mock_agent.i18n.tools.return_value = {"name": "Add Image"}
mock_agent.i18n.errors.return_value = "Error: {error}"
mock_agent.i18n.slice.return_value = "Available tools: {tool_names}"
mock_task = MagicMock()
mock_task.delegations = 0
mock_task.name = "Test Task"
mock_task.description = "A test task"
mock_task.id = "test-task-id"
mock_action = MagicMock()
mock_action.tool = "failing_tool"
mock_action.tool_input = "{}"
tool_usage = ToolUsage(
tools_handler=MagicMock(cache=None, last_used_tool=None),
tools=[failing_tool],
task=mock_task,
function_calling_llm=None,
agent=mock_agent,
action=mock_action,
)
started_events = []
error_events = []
finished_events = []
error_received = threading.Event()
@crewai_event_bus.on(ToolUsageStartedEvent)
def on_started(source, event):
if event.tool_name == "failing_tool":
started_events.append(event)
@crewai_event_bus.on(ToolUsageErrorEvent)
def on_error(source, event):
if event.tool_name == "failing_tool":
error_events.append(event)
error_received.set()
@crewai_event_bus.on(ToolUsageFinishedEvent)
def on_finished(source, event):
if event.tool_name == "failing_tool":
finished_events.append(event)
tool_calling = ToolCalling(tool_name="failing_tool", arguments={})
tool_usage.use(calling=tool_calling, tool_string="Action: failing_tool")
assert error_received.wait(timeout=5), "Timeout waiting for error event"
crewai_event_bus.flush()
assert len(started_events) >= 1, "Expected at least one ToolUsageStartedEvent"
assert len(error_events) >= 1, "Expected at least one ToolUsageErrorEvent"
assert len(finished_events) == 0, (
"ToolUsageFinishedEvent should NOT be emitted after ToolUsageErrorEvent"
)

661
lib/crewai/tests/utilities/test_agent_utils.py
View File

@@ -2,13 +2,23 @@
from __future__ import annotations
import asyncio
from typing import Any
from unittest.mock import MagicMock, patch
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from pydantic import BaseModel, Field
from crewai.tools.base_tool import BaseTool
from crewai.utilities.agent_utils import convert_tools_to_openai_schema, summarize_messages
from crewai.utilities.agent_utils import (
_asummarize_chunks,
_estimate_token_count,
_extract_summary_tags,
_format_messages_for_summary,
_split_messages_into_chunks,
convert_tools_to_openai_schema,
summarize_messages,
)
class CalculatorInput(BaseModel):
@@ -214,6 +224,17 @@ class TestConvertToolsToOpenaiSchema:
assert max_results_prop["default"] == 10
def _make_mock_i18n() -> MagicMock:
"""Create a mock i18n with the new structured prompt keys."""
mock_i18n = MagicMock()
mock_i18n.slice.side_effect = lambda key: {
"summarizer_system_message": "You are a precise assistant that creates structured summaries.",
"summarize_instruction": "Summarize the conversation:\n{conversation}",
"summary": "<summary>\n{merged_summary}\n</summary>\nContinue the task.",
}.get(key, "")
return mock_i18n
class TestSummarizeMessages:
"""Tests for summarize_messages function."""
@@ -229,26 +250,22 @@ class TestSummarizeMessages:
mock_llm = MagicMock()
mock_llm.get_context_window_size.return_value = 1000
mock_llm.call.return_value = "Summarized conversation about image analysis."
mock_i18n = MagicMock()
mock_i18n.slice.side_effect = lambda key: {
"summarizer_system_message": "Summarize the following.",
"summarize_instruction": "Summarize: {group}",
"summary": "Summary: {merged_summary}",
}.get(key, "")
mock_llm.call.return_value = "<summary>Summarized conversation about image analysis.</summary>"
summarize_messages(
messages=messages,
llm=mock_llm,
callbacks=[],
i18n=mock_i18n,
i18n=_make_mock_i18n(),
)
assert len(messages) == 1
assert messages[0]["role"] == "user"
assert "files" in messages[0]
assert messages[0]["files"] == mock_files
# System message preserved + summary message = 2
assert len(messages) == 2
assert messages[0]["role"] == "system"
summary_msg = messages[1]
assert summary_msg["role"] == "user"
assert "files" in summary_msg
assert summary_msg["files"] == mock_files
def test_merges_files_from_multiple_user_messages(self) -> None:
"""Test that files from multiple user messages are merged."""
@@ -264,20 +281,13 @@ class TestSummarizeMessages:
mock_llm = MagicMock()
mock_llm.get_context_window_size.return_value = 1000
mock_llm.call.return_value = "Summarized conversation."
mock_i18n = MagicMock()
mock_i18n.slice.side_effect = lambda key: {
"summarizer_system_message": "Summarize the following.",
"summarize_instruction": "Summarize: {group}",
"summary": "Summary: {merged_summary}",
}.get(key, "")
mock_llm.call.return_value = "<summary>Summarized conversation.</summary>"
summarize_messages(
messages=messages,
llm=mock_llm,
callbacks=[],
i18n=mock_i18n,
i18n=_make_mock_i18n(),
)
assert len(messages) == 1
@@ -297,20 +307,13 @@ class TestSummarizeMessages:
mock_llm = MagicMock()
mock_llm.get_context_window_size.return_value = 1000
mock_llm.call.return_value = "A greeting exchange."
mock_i18n = MagicMock()
mock_i18n.slice.side_effect = lambda key: {
"summarizer_system_message": "Summarize the following.",
"summarize_instruction": "Summarize: {group}",
"summary": "Summary: {merged_summary}",
}.get(key, "")
mock_llm.call.return_value = "<summary>A greeting exchange.</summary>"
summarize_messages(
messages=messages,
llm=mock_llm,
callbacks=[],
i18n=mock_i18n,
i18n=_make_mock_i18n(),
)
assert len(messages) == 1
@@ -327,21 +330,595 @@ class TestSummarizeMessages:
mock_llm = MagicMock()
mock_llm.get_context_window_size.return_value = 1000
mock_llm.call.return_value = "Summary"
mock_i18n = MagicMock()
mock_i18n.slice.side_effect = lambda key: {
"summarizer_system_message": "Summarize.",
"summarize_instruction": "Summarize: {group}",
"summary": "Summary: {merged_summary}",
}.get(key, "")
mock_llm.call.return_value = "<summary>Summary</summary>"
summarize_messages(
messages=messages,
llm=mock_llm,
callbacks=[],
i18n=mock_i18n,
i18n=_make_mock_i18n(),
)
assert id(messages) == original_list_id
assert len(messages) == 1
def test_preserves_system_messages(self) -> None:
"""Test that system messages are preserved and not summarized."""
messages: list[dict[str, Any]] = [
{"role": "system", "content": "You are a research assistant."},
{"role": "user", "content": "Find information about AI."},
{"role": "assistant", "content": "I found several resources on AI."},
]
mock_llm = MagicMock()
mock_llm.get_context_window_size.return_value = 1000
mock_llm.call.return_value = "<summary>User asked about AI, assistant found resources.</summary>"
summarize_messages(
messages=messages,
llm=mock_llm,
callbacks=[],
i18n=_make_mock_i18n(),
)
assert len(messages) == 2
assert messages[0]["role"] == "system"
assert messages[0]["content"] == "You are a research assistant."
assert messages[1]["role"] == "user"
def test_formats_conversation_with_role_labels(self) -> None:
"""Test that the LLM receives role-labeled conversation text."""
messages: list[dict[str, Any]] = [
{"role": "system", "content": "System prompt."},
{"role": "user", "content": "Hello there"},
{"role": "assistant", "content": "Hi! How can I help?"},
]
mock_llm = MagicMock()
mock_llm.get_context_window_size.return_value = 1000
mock_llm.call.return_value = "<summary>Greeting exchange.</summary>"
summarize_messages(
messages=messages,
llm=mock_llm,
callbacks=[],
i18n=_make_mock_i18n(),
)
# Check what was passed to llm.call
call_args = mock_llm.call.call_args[0][0]
user_msg_content = call_args[1]["content"]
assert "[USER]:" in user_msg_content
assert "[ASSISTANT]:" in user_msg_content
# System content should NOT appear in summarization input
assert "System prompt." not in user_msg_content
def test_extracts_summary_from_tags(self) -> None:
"""Test that <summary> tags are extracted from LLM response."""
messages: list[dict[str, Any]] = [
{"role": "user", "content": "Do something."},
{"role": "assistant", "content": "Done."},
]
mock_llm = MagicMock()
mock_llm.get_context_window_size.return_value = 1000
mock_llm.call.return_value = "Here is the summary:\n<summary>The extracted summary content.</summary>\nExtra text."
summarize_messages(
messages=messages,
llm=mock_llm,
callbacks=[],
i18n=_make_mock_i18n(),
)
assert "The extracted summary content." in messages[0]["content"]
def test_handles_tool_messages(self) -> None:
"""Test that tool messages are properly formatted in summarization."""
messages: list[dict[str, Any]] = [
{"role": "user", "content": "Search for Python."},
{"role": "assistant", "content": None, "tool_calls": [
{"function": {"name": "web_search", "arguments": '{"query": "Python"}'}}
]},
{"role": "tool", "content": "Python is a programming language.", "name": "web_search"},
{"role": "assistant", "content": "Python is a programming language."},
]
mock_llm = MagicMock()
mock_llm.get_context_window_size.return_value = 1000
mock_llm.call.return_value = "<summary>User searched for Python info.</summary>"
summarize_messages(
messages=messages,
llm=mock_llm,
callbacks=[],
i18n=_make_mock_i18n(),
)
# Verify the conversation text sent to LLM contains tool labels
call_args = mock_llm.call.call_args[0][0]
user_msg_content = call_args[1]["content"]
assert "[TOOL_RESULT (web_search)]:" in user_msg_content
def test_only_system_messages_no_op(self) -> None:
"""Test that only system messages results in no-op (no summarization)."""
messages: list[dict[str, Any]] = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "system", "content": "Additional system instructions."},
]
mock_llm = MagicMock()
mock_llm.get_context_window_size.return_value = 1000
summarize_messages(
messages=messages,
llm=mock_llm,
callbacks=[],
i18n=_make_mock_i18n(),
)
# No LLM call should have been made
mock_llm.call.assert_not_called()
# System messages should remain untouched
assert len(messages) == 2
assert messages[0]["content"] == "You are a helpful assistant."
assert messages[1]["content"] == "Additional system instructions."
class TestFormatMessagesForSummary:
"""Tests for _format_messages_for_summary helper."""
def test_skips_system_messages(self) -> None:
messages: list[dict[str, Any]] = [
{"role": "system", "content": "System prompt"},
{"role": "user", "content": "Hello"},
]
result = _format_messages_for_summary(messages)
assert "System prompt" not in result
assert "[USER]: Hello" in result
def test_formats_user_and_assistant(self) -> None:
messages: list[dict[str, Any]] = [
{"role": "user", "content": "Question"},
{"role": "assistant", "content": "Answer"},
]
result = _format_messages_for_summary(messages)
assert "[USER]: Question" in result
assert "[ASSISTANT]: Answer" in result
def test_formats_tool_messages(self) -> None:
messages: list[dict[str, Any]] = [
{"role": "tool", "content": "Result data", "name": "search_tool"},
]
result = _format_messages_for_summary(messages)
assert "[TOOL_RESULT (search_tool)]:" in result
assert "Result data" in result
def test_handles_none_content_with_tool_calls(self) -> None:
messages: list[dict[str, Any]] = [
{"role": "assistant", "content": None, "tool_calls": [
{"function": {"name": "calculator", "arguments": "{}"}}
]},
]
result = _format_messages_for_summary(messages)
assert "[Called tools: calculator]" in result
def test_handles_none_content_without_tool_calls(self) -> None:
messages: list[dict[str, Any]] = [
{"role": "assistant", "content": None},
]
result = _format_messages_for_summary(messages)
assert "[ASSISTANT]:" in result
def test_handles_multimodal_content(self) -> None:
messages: list[dict[str, Any]] = [
{"role": "user", "content": [
{"type": "text", "text": "Describe this image"},
{"type": "image_url", "image_url": {"url": "data:image/png;base64,..."}}
]},
]
result = _format_messages_for_summary(messages)
assert "[USER]: Describe this image" in result
def test_empty_messages(self) -> None:
result = _format_messages_for_summary([])
assert result == ""
class TestExtractSummaryTags:
"""Tests for _extract_summary_tags helper."""
def test_extracts_content_from_tags(self) -> None:
text = "Preamble\n<summary>The actual summary.</summary>\nPostamble"
assert _extract_summary_tags(text) == "The actual summary."
def test_handles_multiline_content(self) -> None:
text = "<summary>\nLine 1\nLine 2\nLine 3\n</summary>"
result = _extract_summary_tags(text)
assert "Line 1" in result
assert "Line 2" in result
assert "Line 3" in result
def test_falls_back_when_no_tags(self) -> None:
text = "Just a plain summary without tags."
assert _extract_summary_tags(text) == text
def test_handles_empty_string(self) -> None:
assert _extract_summary_tags("") == ""
def test_extracts_first_match(self) -> None:
text = "<summary>First</summary> text <summary>Second</summary>"
assert _extract_summary_tags(text) == "First"
class TestSplitMessagesIntoChunks:
"""Tests for _split_messages_into_chunks helper."""
def test_single_chunk_when_under_limit(self) -> None:
messages: list[dict[str, Any]] = [
{"role": "user", "content": "Hello"},
{"role": "assistant", "content": "Hi"},
]
chunks = _split_messages_into_chunks(messages, max_tokens=1000)
assert len(chunks) == 1
assert len(chunks[0]) == 2
def test_splits_at_message_boundaries(self) -> None:
messages: list[dict[str, Any]] = [
{"role": "user", "content": "A" * 100}, # ~25 tokens
{"role": "assistant", "content": "B" * 100}, # ~25 tokens
{"role": "user", "content": "C" * 100}, # ~25 tokens
]
# max_tokens=30 should cause splits
chunks = _split_messages_into_chunks(messages, max_tokens=30)
assert len(chunks) == 3
def test_excludes_system_messages(self) -> None:
messages: list[dict[str, Any]] = [
{"role": "system", "content": "System prompt"},
{"role": "user", "content": "Hello"},
]
chunks = _split_messages_into_chunks(messages, max_tokens=1000)
assert len(chunks) == 1
# The system message should not be in any chunk
for chunk in chunks:
for msg in chunk:
assert msg.get("role") != "system"
def test_empty_messages(self) -> None:
chunks = _split_messages_into_chunks([], max_tokens=1000)
assert chunks == []
def test_only_system_messages(self) -> None:
messages: list[dict[str, Any]] = [
{"role": "system", "content": "System prompt"},
]
chunks = _split_messages_into_chunks(messages, max_tokens=1000)
assert chunks == []
def test_handles_none_content(self) -> None:
messages: list[dict[str, Any]] = [
{"role": "assistant", "content": None},
{"role": "user", "content": "Follow up"},
]
chunks = _split_messages_into_chunks(messages, max_tokens=1000)
assert len(chunks) == 1
assert len(chunks[0]) == 2
class TestEstimateTokenCount:
"""Tests for _estimate_token_count helper."""
def test_empty_string(self) -> None:
assert _estimate_token_count("") == 0
def test_short_string(self) -> None:
assert _estimate_token_count("hello") == 1 # 5 // 4 = 1
def test_longer_string(self) -> None:
assert _estimate_token_count("a" * 100) == 25 # 100 // 4 = 25
def test_approximation_is_conservative(self) -> None:
# For English text, actual token count is typically lower than char/4
text = "The quick brown fox jumps over the lazy dog."
estimated = _estimate_token_count(text)
assert estimated > 0
assert estimated == len(text) // 4
class TestParallelSummarization:
"""Tests for parallel chunk summarization via asyncio."""
def _make_messages_for_n_chunks(self, n: int) -> list[dict[str, Any]]:
"""Build a message list that will produce exactly *n* chunks.
Each message has 400 chars (~100 tokens). With max_tokens=100 returned
by the mock LLM, each message lands in its own chunk.
"""
msgs: list[dict[str, Any]] = []
for i in range(n):
msgs.append({"role": "user", "content": f"msg-{i} " + "x" * 400})
return msgs
def test_multiple_chunks_use_acall(self) -> None:
"""When there are multiple chunks, summarize_messages should use
llm.acall (parallel) instead of llm.call (sequential)."""
messages = self._make_messages_for_n_chunks(3)
mock_llm = MagicMock()
mock_llm.get_context_window_size.return_value = 100 # force multiple chunks
mock_llm.acall = AsyncMock(
side_effect=[
"<summary>Summary chunk 1</summary>",
"<summary>Summary chunk 2</summary>",
"<summary>Summary chunk 3</summary>",
]
)
summarize_messages(
messages=messages,
llm=mock_llm,
callbacks=[],
i18n=_make_mock_i18n(),
)
# acall should have been awaited once per chunk
assert mock_llm.acall.await_count == 3
# sync call should NOT have been used for chunk summarization
mock_llm.call.assert_not_called()
def test_single_chunk_uses_sync_call(self) -> None:
"""When there is only one chunk, summarize_messages should use
the sync llm.call path (no async overhead)."""
messages: list[dict[str, Any]] = [
{"role": "user", "content": "Short message"},
{"role": "assistant", "content": "Short reply"},
]
mock_llm = MagicMock()
mock_llm.get_context_window_size.return_value = 100_000
mock_llm.call.return_value = "<summary>Short summary</summary>"
summarize_messages(
messages=messages,
llm=mock_llm,
callbacks=[],
i18n=_make_mock_i18n(),
)
mock_llm.call.assert_called_once()
def test_parallel_results_preserve_order(self) -> None:
"""Summaries must appear in the same order as the original chunks,
regardless of which async call finishes first."""
messages = self._make_messages_for_n_chunks(3)
mock_llm = MagicMock()
mock_llm.get_context_window_size.return_value = 100
# Simulate varying latencies — chunk 2 finishes before chunk 0
async def _delayed_acall(msgs: Any, **kwargs: Any) -> str:
user_content = msgs[1]["content"]
if "msg-0" in user_content:
await asyncio.sleep(0.05)
return "<summary>Summary-A</summary>"
elif "msg-1" in user_content:
return "<summary>Summary-B</summary>" # fastest
else:
await asyncio.sleep(0.02)
return "<summary>Summary-C</summary>"
mock_llm.acall = _delayed_acall
summarize_messages(
messages=messages,
llm=mock_llm,
callbacks=[],
i18n=_make_mock_i18n(),
)
# The final summary message should have A, B, C in order
summary_content = messages[-1]["content"]
pos_a = summary_content.index("Summary-A")
pos_b = summary_content.index("Summary-B")
pos_c = summary_content.index("Summary-C")
assert pos_a < pos_b < pos_c
def test_asummarize_chunks_returns_ordered_results(self) -> None:
"""Direct test of the async helper _asummarize_chunks."""
chunk_a: list[dict[str, Any]] = [{"role": "user", "content": "Chunk A"}]
chunk_b: list[dict[str, Any]] = [{"role": "user", "content": "Chunk B"}]
mock_llm = MagicMock()
mock_llm.acall = AsyncMock(
side_effect=[
"<summary>Result A</summary>",
"<summary>Result B</summary>",
]
)
results = asyncio.run(
_asummarize_chunks(
chunks=[chunk_a, chunk_b],
llm=mock_llm,
callbacks=[],
i18n=_make_mock_i18n(),
)
)
assert len(results) == 2
assert results[0]["content"] == "Result A"
assert results[1]["content"] == "Result B"
@patch("crewai.utilities.agent_utils.is_inside_event_loop", return_value=True)
def test_works_inside_existing_event_loop(self, _mock_loop: Any) -> None:
"""When called from inside a running event loop (e.g. a Flow),
the ThreadPoolExecutor fallback should still work."""
messages = self._make_messages_for_n_chunks(2)
mock_llm = MagicMock()
mock_llm.get_context_window_size.return_value = 100
mock_llm.acall = AsyncMock(
side_effect=[
"<summary>Flow summary 1</summary>",
"<summary>Flow summary 2</summary>",
]
)
summarize_messages(
messages=messages,
llm=mock_llm,
callbacks=[],
i18n=_make_mock_i18n(),
)
assert mock_llm.acall.await_count == 2
# Verify the merged summary made it into messages
assert "Flow summary 1" in messages[-1]["content"]
assert "Flow summary 2" in messages[-1]["content"]
def _build_long_conversation() -> list[dict[str, Any]]:
"""Build a multi-turn conversation that produces multiple chunks at max_tokens=200.
Each non-system message is ~100-140 estimated tokens (400-560 chars),
so a max_tokens of 200 yields roughly 3 chunks from 6 messages.
"""
return [
{
"role": "system",
"content": "You are a helpful research assistant.",
},
{
"role": "user",
"content": (
"Tell me about the history of the Python programming language. "
"Who created it, when was it first released, and what were the "
"main design goals? Please provide a detailed overview covering "
"the major milestones from its inception through Python 3."
),
},
{
"role": "assistant",
"content": (
"Python was created by Guido van Rossum and first released in 1991. "
"The main design goals were code readability and simplicity. Key milestones: "
"Python 1.0 (1994) introduced functional programming tools like lambda and map. "
"Python 2.0 (2000) added list comprehensions and garbage collection. "
"Python 3.0 (2008) was a major backward-incompatible release that fixed "
"fundamental design flaws. Python 2 reached end-of-life in January 2020."
),
},
{
"role": "user",
"content": (
"What about the async/await features? When were they introduced "
"and how do they compare to similar features in JavaScript and C#? "
"Also explain the Global Interpreter Lock and its implications."
),
},
{
"role": "assistant",
"content": (
"Async/await was introduced in Python 3.5 (PEP 492, 2015). "
"Unlike JavaScript which is single-threaded by design, Python's asyncio "
"is an opt-in framework. C# introduced async/await in 2012 (C# 5.0) and "
"was a major inspiration for Python's implementation. "
"The GIL (Global Interpreter Lock) is a mutex that protects access to "
"Python objects, preventing multiple threads from executing Python bytecodes "
"simultaneously. This means CPU-bound multithreaded programs don't benefit "
"from multiple cores. PEP 703 proposes making the GIL optional in CPython."
),
},
{
"role": "user",
"content": (
"Explain the Python package ecosystem. How does pip work, what is PyPI, "
"and what are virtual environments? Compare pip with conda and uv."
),
},
{
"role": "assistant",
"content": (
"PyPI (Python Package Index) is the official repository hosting 400k+ packages. "
"pip is the standard package installer that downloads from PyPI. "
"Virtual environments (venv) create isolated Python installations to avoid "
"dependency conflicts between projects. conda is a cross-language package manager "
"popular in data science that can manage non-Python dependencies. "
"uv is a new Rust-based tool that is 10-100x faster than pip and aims to replace "
"pip, pip-tools, and virtualenv with a single unified tool."
),
},
]
class TestParallelSummarizationVCR:
"""VCR-backed integration tests for parallel summarization.
These tests use a real LLM but patch get_context_window_size to force
multiple chunks, exercising the asyncio.gather + acall parallel path.
To record cassettes:
PYTEST_VCR_RECORD_MODE=all uv run pytest lib/crewai/tests/utilities/test_agent_utils.py::TestParallelSummarizationVCR -v
"""
@pytest.mark.vcr()
def test_parallel_summarize_openai(self) -> None:
"""Test that parallel summarization with gpt-4o-mini produces a valid summary."""
from crewai.llm import LLM
from crewai.utilities.i18n import I18N
llm = LLM(model="gpt-4o-mini", temperature=0)
i18n = I18N()
messages = _build_long_conversation()
original_system = messages[0]["content"]
# Patch get_context_window_size to return 200 — forces multiple chunks
with patch.object(type(llm), "get_context_window_size", return_value=200):
# Verify we actually get multiple chunks with this window size
non_system = [m for m in messages if m.get("role") != "system"]
chunks = _split_messages_into_chunks(non_system, max_tokens=200)
assert len(chunks) > 1, f"Expected multiple chunks, got {len(chunks)}"
summarize_messages(
messages=messages,
llm=llm,
callbacks=[],
i18n=i18n,
)
# System message preserved
assert messages[0]["role"] == "system"
assert messages[0]["content"] == original_system
# Summary produced as a user message
summary_msg = messages[-1]
assert summary_msg["role"] == "user"
assert len(summary_msg["content"]) > 0
@pytest.mark.vcr()
def test_parallel_summarize_preserves_files(self) -> None:
"""Test that file references survive parallel summarization."""
from crewai.llm import LLM
from crewai.utilities.i18n import I18N
llm = LLM(model="gpt-4o-mini", temperature=0)
i18n = I18N()
messages = _build_long_conversation()
mock_file = MagicMock()
messages[1]["files"] = {"report.pdf": mock_file}
with patch.object(type(llm), "get_context_window_size", return_value=200):
summarize_messages(
messages=messages,
llm=llm,
callbacks=[],
i18n=i18n,
)
summary_msg = messages[-1]
assert summary_msg["role"] == "user"
assert "files" in summary_msg
assert "report.pdf" in summary_msg["files"]

284
lib/crewai/tests/utilities/test_summarize_integration.py Normal file
View File

@@ -0,0 +1,284 @@
"""
Integration tests for structured context compaction (summarize_messages).
"""
from __future__ import annotations
from typing import Any
from unittest.mock import MagicMock
import pytest
from crewai.agent import Agent
from crewai.crew import Crew
from crewai.llm import LLM
from crewai.task import Task
from crewai.utilities.agent_utils import summarize_messages
from crewai.utilities.i18n import I18N
def _build_conversation_messages(
*, include_system: bool = True, include_files: bool = False
) -> list[dict[str, Any]]:
"""Build a realistic multi-turn conversation for summarization tests."""
messages: list[dict[str, Any]] = []
if include_system:
messages.append(
{
"role": "system",
"content": (
"You are a research assistant specializing in AI topics. "
"Your goal is to find accurate, up-to-date information."
),
}
)
user_msg: dict[str, Any] = {
"role": "user",
"content": (
"Research the latest developments in large language models. "
"Focus on architecture improvements and training techniques."
),
}
if include_files:
user_msg["files"] = {"reference.pdf": MagicMock()}
messages.append(user_msg)
messages.append(
{
"role": "assistant",
"content": (
"I'll research the latest developments in large language models. "
"Based on my knowledge, recent advances include:\n"
"1. Mixture of Experts (MoE) architectures\n"
"2. Improved attention mechanisms like Flash Attention\n"
"3. Better training data curation techniques\n"
"4. Constitutional AI and RLHF improvements"
),
}
)
messages.append(
{
"role": "user",
"content": "Can you go deeper on the MoE architectures? What are the key papers?",
}
)
messages.append(
{
"role": "assistant",
"content": (
"Key papers on Mixture of Experts:\n"
"- Switch Transformers (Google, 2021) - simplified MoE routing\n"
"- GShard - scaling to 600B parameters\n"
"- Mixtral (Mistral AI) - open-source MoE model\n"
"The main advantage is computational efficiency: "
"only a subset of experts is activated per token."
),
}
)
return messages
class TestSummarizeDirectOpenAI:
"""Test direct summarize_messages calls with OpenAI."""
@pytest.mark.vcr()
def test_summarize_direct_openai(self) -> None:
"""Test summarize_messages with gpt-4o-mini preserves system messages."""
llm = LLM(model="gpt-4o-mini", temperature=0)
i18n = I18N()
messages = _build_conversation_messages(include_system=True)
original_system_content = messages[0]["content"]
summarize_messages(
messages=messages,
llm=llm,
callbacks=[],
i18n=i18n,
)
# System message should be preserved
assert len(messages) >= 2
assert messages[0]["role"] == "system"
assert messages[0]["content"] == original_system_content
# Summary should be a user message with <summary> block
summary_msg = messages[-1]
assert summary_msg["role"] == "user"
assert len(summary_msg["content"]) > 0
assert "<summary>" in summary_msg["content"]
assert "</summary>" in summary_msg["content"]
class TestSummarizeDirectAnthropic:
"""Test direct summarize_messages calls with Anthropic."""
@pytest.mark.vcr()
def test_summarize_direct_anthropic(self) -> None:
"""Test summarize_messages with claude-3-5-haiku."""
llm = LLM(model="anthropic/claude-3-5-haiku-latest", temperature=0)
i18n = I18N()
messages = _build_conversation_messages(include_system=True)
summarize_messages(
messages=messages,
llm=llm,
callbacks=[],
i18n=i18n,
)
assert len(messages) >= 2
assert messages[0]["role"] == "system"
summary_msg = messages[-1]
assert summary_msg["role"] == "user"
assert len(summary_msg["content"]) > 0
assert "<summary>" in summary_msg["content"]
assert "</summary>" in summary_msg["content"]
class TestSummarizeDirectGemini:
"""Test direct summarize_messages calls with Gemini."""
@pytest.mark.vcr()
def test_summarize_direct_gemini(self) -> None:
"""Test summarize_messages with gemini-2.0-flash."""
llm = LLM(model="gemini/gemini-2.0-flash", temperature=0)
i18n = I18N()
messages = _build_conversation_messages(include_system=True)
summarize_messages(
messages=messages,
llm=llm,
callbacks=[],
i18n=i18n,
)
assert len(messages) >= 2
assert messages[0]["role"] == "system"
summary_msg = messages[-1]
assert summary_msg["role"] == "user"
assert len(summary_msg["content"]) > 0
assert "<summary>" in summary_msg["content"]
assert "</summary>" in summary_msg["content"]
class TestSummarizeDirectAzure:
"""Test direct summarize_messages calls with Azure."""
@pytest.mark.vcr()
def test_summarize_direct_azure(self) -> None:
"""Test summarize_messages with azure/gpt-4o-mini."""
llm = LLM(model="azure/gpt-4o-mini", temperature=0)
i18n = I18N()
messages = _build_conversation_messages(include_system=True)
summarize_messages(
messages=messages,
llm=llm,
callbacks=[],
i18n=i18n,
)
assert len(messages) >= 2
assert messages[0]["role"] == "system"
summary_msg = messages[-1]
assert summary_msg["role"] == "user"
assert len(summary_msg["content"]) > 0
assert "<summary>" in summary_msg["content"]
assert "</summary>" in summary_msg["content"]
class TestCrewKickoffCompaction:
"""Test compaction triggered via Crew.kickoff() with small context window."""
@pytest.mark.vcr()
def test_crew_kickoff_compaction_openai(self) -> None:
"""Test that compaction is triggered during kickoff with small context_window_size."""
llm = LLM(model="gpt-4o-mini", temperature=0)
# Force a very small context window to trigger compaction
llm.context_window_size = 500
agent = Agent(
role="Researcher",
goal="Find information about Python programming",
backstory="You are an expert researcher.",
llm=llm,
verbose=False,
max_iter=2,
)
task = Task(
description="What is Python? Give a brief answer.",
expected_output="A short description of Python.",
agent=agent,
)
crew = Crew(agents=[agent], tasks=[task], verbose=False)
# This may or may not trigger compaction depending on actual response sizes.
# The test verifies the code path doesn't crash.
result = crew.kickoff()
assert result is not None
class TestAgentExecuteTaskCompaction:
"""Test compaction triggered via Agent.execute_task()."""
@pytest.mark.vcr()
def test_agent_execute_task_compaction(self) -> None:
"""Test that Agent.execute_task() works with small context_window_size."""
llm = LLM(model="gpt-4o-mini", temperature=0)
llm.context_window_size = 500
agent = Agent(
role="Writer",
goal="Write concise content",
backstory="You are a skilled writer.",
llm=llm,
verbose=False,
max_iter=2,
)
task = Task(
description="Write one sentence about the sun.",
expected_output="A single sentence about the sun.",
agent=agent,
)
result = agent.execute_task(task=task)
assert result is not None
class TestSummarizePreservesFiles:
"""Test that files are preserved through real summarization."""
@pytest.mark.vcr()
def test_summarize_preserves_files_integration(self) -> None:
"""Test that file references survive a real summarization call."""
llm = LLM(model="gpt-4o-mini", temperature=0)
i18n = I18N()
messages = _build_conversation_messages(
include_system=True, include_files=True
)
summarize_messages(
messages=messages,
llm=llm,
callbacks=[],
i18n=i18n,
)
# System message preserved
assert messages[0]["role"] == "system"
# Files should be on the summary message with <summary> block
summary_msg = messages[-1]
assert "<summary>" in summary_msg["content"]
assert "</summary>" in summary_msg["content"]
assert "files" in summary_msg
assert "reference.pdf" in summary_msg["files"]