andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-05-01 07:13:00 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

Code interpreter sandbox escape (#4791)
Some checks failed
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
Details
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Details
Mark stale issues and pull requests / stale (push) Has been cancelled
Details
Build uv cache / build-cache (3.10) (push) Has been cancelled
Details
Build uv cache / build-cache (3.11) (push) Has been cancelled
Details
Build uv cache / build-cache (3.12) (push) Has been cancelled
Details
Build uv cache / build-cache (3.13) (push) Has been cancelled
Details
Nightly Canary Release / Check for new commits (push) Has been cancelled
Details
Nightly Canary Release / Build nightly packages (push) Has been cancelled
Details
Nightly Canary Release / Publish nightly to PyPI (push) Has been cancelled
Details

Browse Source 
* [SECURITY] Fix sandbox escape vulnerability in CodeInterpreterTool (F-001)

This commit addresses a critical security vulnerability where the CodeInterpreterTool
could be exploited via sandbox escape attacks when Docker was unavailable.

Changes:
- Remove insecure fallback to restricted sandbox in run_code_safety()
- Now fails closed with RuntimeError when Docker is unavailable
- Mark run_code_in_restricted_sandbox() as deprecated and insecure
- Add clear security warnings to SandboxPython class documentation
- Update tests to reflect secure-by-default behavior
- Add test demonstrating the sandbox escape vulnerability
- Update README with security requirements and best practices

The previous implementation would fall back to a Python-based 'restricted sandbox'
when Docker was unavailable. However, this sandbox could be easily bypassed using
Python object introspection to recover the original __import__ function, allowing
arbitrary module access and command execution on the host.

The fix enforces Docker as a requirement for safe code execution. Users who cannot
use Docker must explicitly enable unsafe_mode=True, acknowledging the security risks.

Security Impact:
- Prevents RCE via sandbox escape when Docker is unavailable
- Enforces fail-closed security model
- Maintains backward compatibility via unsafe_mode flag

References:
- https://docs.crewai.com/tools/ai-ml/codeinterpretertool

Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>

* Add security fix documentation for F-001

Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>

* Add Slack summary for security fix

Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>

* Delete SECURITY_FIX_F001.md

* Delete SLACK_SUMMARY.md

* chore: regen cassettes

* chore: regen more cassettes

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>
Co-authored-by: Greyson LaLonde <greyson@crewai.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
Rip&Tear
2026-03-15 13:18:02 +08:00
committed by GitHub
parent e1d7de0dba
commit fb2323b3de
9 changed files with 2811 additions and 3056 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
lib/crewai-tools/src/crewai_tools/tools/code_interpreter_tool/README.md
View File

@@ -1,13 +1,27 @@
# CodeInterpreterTool # CodeInterpreterTool
## Description ## Description
This tool is used to give the Agent the ability to run code (Python3) from the code generated by the Agent itself. The code is executed in a sandboxed environment, so it is safe to run any code. This tool is used to give the Agent the ability to run code (Python3) from the code generated by the Agent itself. The code is executed in a Docker container for secure isolation.
It is incredible useful since it allows the Agent to generate code, run it in the same environment, get the result and use it to make decisions. It is incredibly useful since it allows the Agent to generate code, run it in an isolated environment, get the result and use it to make decisions.
## ⚠️ Security Requirements
**Docker is REQUIRED** for safe code execution. The tool will refuse to execute code without Docker to prevent security vulnerabilities.
### Why Docker is Required
Previous versions included a "restricted sandbox" fallback when Docker was unavailable. This has been **removed** due to critical security vulnerabilities:
- The Python-based sandbox could be escaped via object introspection
- Attackers could recover the original `__import__` function and access any module
- This allowed arbitrary command execution on the host system
**Docker provides real process isolation** and is the only secure way to execute untrusted code.
## Requirements ## Requirements
- Docker - **Docker (REQUIRED)** - Install from [docker.com](https://docs.docker.com/get-docker/)
## Installation ## Installation
Install the crewai_tools package Install the crewai_tools package
@@ -17,7 +31,9 @@ pip install 'crewai[tools]'
## Example ## Example
Remember that when using this tool, the code must be generated by the Agent itself. The code must be a Python3 code. And it will take some time for the first time to run because it needs to build the Docker image. Remember that when using this tool, the code must be generated by the Agent itself. The code must be Python3 code. It will take some time the first time to run because it needs to build the Docker image.
### Basic Usage (Docker Container - Recommended)
```python ```python
from crewai_tools import CodeInterpreterTool from crewai_tools import CodeInterpreterTool
@@ -28,7 +44,9 @@ Agent(
) )
``` ```
Or if you need to pass your own Dockerfile just do this ### Custom Dockerfile
If you need to pass your own Dockerfile:
```python ```python
from crewai_tools import CodeInterpreterTool from crewai_tools import CodeInterpreterTool
@@ -39,15 +57,39 @@ Agent(
) )
``` ```
If it is difficult to connect to docker daemon automatically (especially for macOS users), you can do this to setup docker host manually ### Manual Docker Host Configuration
If it is difficult to connect to the Docker daemon automatically (especially for macOS users), you can set up the Docker host manually:
```python ```python
from crewai_tools import CodeInterpreterTool from crewai_tools import CodeInterpreterTool
Agent( Agent(
... ...
tools=[CodeInterpreterTool(user_docker_base_url="<Docker Host Base Url>", tools=[CodeInterpreterTool(
user_dockerfile_path="<Dockerfile_path>")], user_docker_base_url="<Docker Host Base Url>",
user_dockerfile_path="<Dockerfile_path>"
)],
) )
``` ```
### Unsafe Mode (NOT RECOMMENDED)
If you absolutely cannot use Docker and **fully trust the code source**, you can use unsafe mode:
```python
from crewai_tools import CodeInterpreterTool
# WARNING: Only use with fully trusted code!
Agent(
...
tools=[CodeInterpreterTool(unsafe_mode=True)],
)
```
**⚠️ SECURITY WARNING:** `unsafe_mode=True` executes code directly on the host without any isolation. Only use this if:
- You completely trust the code being executed
- You understand the security risks
- You cannot install Docker in your environment
For production use, **always use Docker** (the default mode).

53
lib/crewai-tools/src/crewai_tools/tools/code_interpreter_tool/code_interpreter_tool.py
View File

@@ -50,11 +50,16 @@ class CodeInterpreterSchema(BaseModel):
class SandboxPython: class SandboxPython:
"""A restricted Python execution environment for running code safely. """INSECURE: A restricted Python execution environment with known vulnerabilities.
This class provides methods to safely execute Python code by restricting access to WARNING: This class does NOT provide real security isolation and is vulnerable to
potentially dangerous modules and built-in functions. It creates a sandboxed sandbox escape attacks via Python object introspection. Attackers can recover the
environment where harmful operations are blocked. original __import__ function and bypass all restrictions.
DO NOT USE for untrusted code execution. Use Docker containers instead.
This class attempts to restrict access to dangerous modules and built-in functions
but provides no real security boundary against a motivated attacker.
""" """
BLOCKED_MODULES: ClassVar[set[str]] = { BLOCKED_MODULES: ClassVar[set[str]] = {
@@ -299,8 +304,8 @@ class CodeInterpreterTool(BaseTool):
def run_code_safety(self, code: str, libraries_used: list[str]) -> str: def run_code_safety(self, code: str, libraries_used: list[str]) -> str:
"""Runs code in the safest available environment. """Runs code in the safest available environment.
Attempts to run code in Docker if available, falls back to a restricted Requires Docker to be available for secure code execution. Fails closed
sandbox if Docker is not available. if Docker is not available to prevent sandbox escape vulnerabilities.
Args: Args:
code: The Python code to execute as a string. code: The Python code to execute as a string.
@@ -308,10 +313,24 @@ class CodeInterpreterTool(BaseTool):
Returns: Returns:
The output of the executed code as a string. The output of the executed code as a string.
Raises:
RuntimeError: If Docker is not available, as the restricted sandbox
is vulnerable to escape attacks and should not be used
for untrusted code execution.
""" """
if self._check_docker_available(): if self._check_docker_available():
return self.run_code_in_docker(code, libraries_used) return self.run_code_in_docker(code, libraries_used)
return self.run_code_in_restricted_sandbox(code)
error_msg = (
"Docker is required for safe code execution but is not available. "
"The restricted sandbox fallback has been removed due to security vulnerabilities "
"that allow sandbox escape via Python object introspection. "
"Please install Docker (https://docs.docker.com/get-docker/) or use unsafe_mode=True "
"if you trust the code source and understand the security risks."
)
Printer.print(error_msg, color="bold_red")
raise RuntimeError(error_msg)
def run_code_in_docker(self, code: str, libraries_used: list[str]) -> str: def run_code_in_docker(self, code: str, libraries_used: list[str]) -> str:
"""Runs Python code in a Docker container for safe isolation. """Runs Python code in a Docker container for safe isolation.
@@ -342,10 +361,19 @@ class CodeInterpreterTool(BaseTool):
@staticmethod @staticmethod
def run_code_in_restricted_sandbox(code: str) -> str: def run_code_in_restricted_sandbox(code: str) -> str:
"""Runs Python code in a restricted sandbox environment. """DEPRECATED AND INSECURE: Runs Python code in a restricted sandbox environment.
Executes the code with restricted access to potentially dangerous modules and WARNING: This method is vulnerable to sandbox escape attacks via Python object
built-in functions for basic safety when Docker is not available. introspection and should NOT be used for untrusted code execution. It has been
deprecated and is only kept for backward compatibility with trusted code.
The "restricted" environment can be bypassed by attackers who can:
- Use object graph introspection to recover the original __import__ function
- Access any Python module including os, subprocess, sys, etc.
- Execute arbitrary commands on the host system
Use run_code_in_docker() for secure code execution, or run_code_unsafe()
if you explicitly acknowledge the security risks.
Args: Args:
code: The Python code to execute as a string. code: The Python code to execute as a string.
@@ -354,7 +382,10 @@ class CodeInterpreterTool(BaseTool):
The value of the 'result' variable from the executed code, The value of the 'result' variable from the executed code,
or an error message if execution failed. or an error message if execution failed.
""" """
Printer.print("Running code in restricted sandbox", color="yellow") Printer.print(
"WARNING: Running code in INSECURE restricted sandbox (vulnerable to escape attacks)",
color="bold_red"
)
exec_locals: dict[str, Any] = {} exec_locals: dict[str, Any] = {}
try: try:
SandboxPython.exec(code=code, locals_=exec_locals) SandboxPython.exec(code=code, locals_=exec_locals)

98
lib/crewai-tools/tests/tools/test_code_interpreter_tool.py
View File

@@ -76,24 +76,22 @@ print("This is line 2")"""
) )
def test_restricted_sandbox_basic_code_execution(printer_mock, docker_unavailable_mock): def test_docker_unavailable_raises_error(printer_mock, docker_unavailable_mock):
"""Test basic code execution.""" """Test that execution fails when Docker is unavailable in safe mode."""
tool = CodeInterpreterTool() tool = CodeInterpreterTool()
code = """ code = """
result = 2 + 2 result = 2 + 2
print(result) print(result)
""" """
result = tool.run(code=code, libraries_used=[]) with pytest.raises(RuntimeError) as exc_info:
printer_mock.assert_called_with( tool.run(code=code, libraries_used=[])
"Running code in restricted sandbox", color="yellow"
) assert "Docker is required for safe code execution" in str(exc_info.value)
assert result == 4 assert "sandbox escape" in str(exc_info.value)
def test_restricted_sandbox_running_with_blocked_modules( def test_restricted_sandbox_running_with_blocked_modules():
printer_mock, docker_unavailable_mock """Test that restricted modules cannot be imported when using the deprecated sandbox directly."""
):
"""Test that restricted modules cannot be imported."""
tool = CodeInterpreterTool() tool = CodeInterpreterTool()
restricted_modules = SandboxPython.BLOCKED_MODULES restricted_modules = SandboxPython.BLOCKED_MODULES
@@ -102,18 +100,15 @@ def test_restricted_sandbox_running_with_blocked_modules(
import {module} import {module}
result = "Import succeeded" result = "Import succeeded"
""" """
result = tool.run(code=code, libraries_used=[]) # Note: run_code_in_restricted_sandbox is deprecated and insecure
printer_mock.assert_called_with( # This test verifies the old behavior but should not be used in production
"Running code in restricted sandbox", color="yellow" result = tool.run_code_in_restricted_sandbox(code)
)
assert f"An error occurred: Importing '{module}' is not allowed" in result assert f"An error occurred: Importing '{module}' is not allowed" in result
def test_restricted_sandbox_running_with_blocked_builtins( def test_restricted_sandbox_running_with_blocked_builtins():
printer_mock, docker_unavailable_mock """Test that restricted builtins are not available when using the deprecated sandbox directly."""
):
"""Test that restricted builtins are not available."""
tool = CodeInterpreterTool() tool = CodeInterpreterTool()
restricted_builtins = SandboxPython.UNSAFE_BUILTINS restricted_builtins = SandboxPython.UNSAFE_BUILTINS
@@ -122,25 +117,23 @@ def test_restricted_sandbox_running_with_blocked_builtins(
{builtin}("test") {builtin}("test")
result = "Builtin available" result = "Builtin available"
""" """
result = tool.run(code=code, libraries_used=[]) # Note: run_code_in_restricted_sandbox is deprecated and insecure
printer_mock.assert_called_with( # This test verifies the old behavior but should not be used in production
"Running code in restricted sandbox", color="yellow" result = tool.run_code_in_restricted_sandbox(code)
)
assert f"An error occurred: name '{builtin}' is not defined" in result assert f"An error occurred: name '{builtin}' is not defined" in result
def test_restricted_sandbox_running_with_no_result_variable( def test_restricted_sandbox_running_with_no_result_variable(
printer_mock, docker_unavailable_mock printer_mock, docker_unavailable_mock
): ):
"""Test behavior when no result variable is set.""" """Test behavior when no result variable is set in deprecated sandbox."""
tool = CodeInterpreterTool() tool = CodeInterpreterTool()
code = """ code = """
x = 10 x = 10
""" """
result = tool.run(code=code, libraries_used=[]) # Note: run_code_in_restricted_sandbox is deprecated and insecure
printer_mock.assert_called_with( # This test verifies the old behavior but should not be used in production
"Running code in restricted sandbox", color="yellow" result = tool.run_code_in_restricted_sandbox(code)
)
assert result == "No result variable found." assert result == "No result variable found."
@@ -172,3 +165,50 @@ result = eval("5/1")
"WARNING: Running code in unsafe mode", color="bold_magenta" "WARNING: Running code in unsafe mode", color="bold_magenta"
) )
assert 5.0 == result assert 5.0 == result
@pytest.mark.xfail(
reason=(
"run_code_in_restricted_sandbox is known to be vulnerable to sandbox "
"escape via object introspection. This test encodes the desired secure "
"behavior (no escape possible) and will start passing once the "
"vulnerability is fixed or the function is removed."
)
)
def test_sandbox_escape_vulnerability_demonstration(printer_mock):
"""Demonstrate that the restricted sandbox is vulnerable to escape attacks.
This test shows that an attacker can use Python object introspection to bypass
the restricted sandbox and access blocked modules like 'os'. This is why the
sandbox should never be used for untrusted code execution.
NOTE: This test uses the deprecated run_code_in_restricted_sandbox directly
to demonstrate the vulnerability. In production, Docker is now required.
"""
tool = CodeInterpreterTool()
# Classic Python sandbox escape via object introspection
escape_code = """
# Recover the real __import__ function via object introspection
for cls in ().__class__.__bases__[0].__subclasses__():
if cls.__name__ == 'catch_warnings':
# Get the real builtins module
real_builtins = cls()._module.__builtins__
real_import = real_builtins['__import__']
# Now we can import os and execute commands
os = real_import('os')
# Demonstrate we have escaped the sandbox
result = "SANDBOX_ESCAPED" if hasattr(os, 'system') else "FAILED"
break
"""
# The deprecated sandbox is vulnerable to this attack
result = tool.run_code_in_restricted_sandbox(escape_code)
# Desired behavior: the restricted sandbox should prevent this escape.
# If this assertion fails, run_code_in_restricted_sandbox remains vulnerable.
assert result != "SANDBOX_ESCAPED", (
"The restricted sandbox was bypassed via object introspection. "
"This indicates run_code_in_restricted_sandbox is still vulnerable and "
"is why Docker is now required for safe code execution."
)

103
lib/crewai/tests/cassettes/test_agents_do_not_get_delegation_tools_with_there_is_only_one_agent.yaml
View File

@@ -1,104 +1,109 @@
interactions: interactions:
- request: - request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re body: '{"messages":[{"role":"system","content":"You are Researcher. You''re love
love to sey howdy.\nYour personal goal is: Be super empathetic.\nTo give my to sey howdy.\nYour personal goal is: Be super empathetic."},{"role":"user","content":"\nCurrent
best complete final answer to the task use the exact following format:\n\nThought: Task: say howdy\n\nThis is the expected criteria for your final answer: Howdy!\nyou
I now can give a great answer\nFinal Answer: Your final answer must be the great MUST return the actual complete content as the final answer, not a summary.\n\nProvide
and the most complete as possible, it must be outcome described.\n\nI MUST use your complete response:"}],"model":"gpt-4.1-mini"}'
these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent
Task: say howdy\n\nThis is the expect criteria for your final answer: Howdy!\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o"}'
headers: headers:
User-Agent:
- X-USER-AGENT-XXX
accept: accept:
- application/json - application/json
accept-encoding: accept-encoding:
- gzip, deflate - ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '784' - '391'
content-type: content-type:
- application/json - application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host: host:
- api.openai.com - api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch: x-stainless-arch:
- arm64 - X-STAINLESS-ARCH-XXX
x-stainless-async: x-stainless-async:
- 'false' - 'false'
x-stainless-lang: x-stainless-lang:
- python - python
x-stainless-os: x-stainless-os:
- MacOS - X-STAINLESS-OS-XXX
x-stainless-package-version: x-stainless-package-version:
- 1.47.0 - 1.83.0
x-stainless-raw-response: x-stainless-read-timeout:
- 'true' - X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime: x-stainless-runtime:
- CPython - CPython
x-stainless-runtime-version: x-stainless-runtime-version:
- 3.11.7 - 3.13.12
method: POST method: POST
uri: https://api.openai.com/v1/chat/completions uri: https://api.openai.com/v1/chat/completions
response: response:
body: body:
string: "{\n \"id\": \"chatcmpl-AB7cCuywn5zE7q0S8IXWVnXoVE81Y\",\n \"object\"\ string: "{\n \"id\": \"chatcmpl-DJVU3yUdUSuW0vgTcxubm9K2Q2cT6\",\n \"object\":
: \"chat.completion\",\n \"created\": 1727214244,\n \"model\": \"gpt-4o-2024-05-13\"\ \"chat.completion\",\n \"created\": 1773541627,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
,\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\ \"role\": \"assistant\",\n \"content\": \"I now can give a great\ \"assistant\",\n \"content\": \"Howdy!\",\n \"refusal\": null,\n
\ answer \\nFinal Answer: Howdy!\",\n \"refusal\": null\n },\n\ \ \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\":
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n\ \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 75,\n \"completion_tokens\":
\ \"usage\": {\n \"prompt_tokens\": 159,\n \"completion_tokens\": 14,\n\ 2,\n \"total_tokens\": 77,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
\ \"total_tokens\": 173,\n \"completion_tokens_details\": {\n \"\ 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_a2ff031fb5\"\ {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
\n}\n" 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_db58fd2815\"\n}\n"
headers: headers:
CF-Cache-Status: CF-Cache-Status:
- DYNAMIC - DYNAMIC
CF-RAY: CF-Ray:
- 8c85f41ffdb81cf3-GRU - 9dc813a23bf323dd-EWR
Connection: Connection:
- keep-alive - keep-alive
Content-Type: Content-Type:
- application/json - application/json
Date: Date:
- Tue, 24 Sep 2024 21:44:04 GMT - Sun, 15 Mar 2026 02:27:07 GMT
Server: Server:
- cloudflare - cloudflare
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding: Transfer-Encoding:
- chunked - chunked
X-Content-Type-Options: X-Content-Type-Options:
- nosniff - X-CONTENT-TYPE-XXX
access-control-expose-headers: access-control-expose-headers:
- X-Request-ID - ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
openai-organization: openai-organization:
- crewai-iuxna1 - OPENAI-ORG-XXX
openai-processing-ms: openai-processing-ms:
- '243' - '366'
openai-project:
- OPENAI-PROJECT-XXX
openai-version: openai-version:
- '2020-10-01' - '2020-10-01'
strict-transport-security: set-cookie:
- max-age=31536000; includeSubDomains; preload - SET-COOKIE-XXX
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests: x-ratelimit-limit-requests:
- '10000' - X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens: x-ratelimit-limit-tokens:
- '30000000' - X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests: x-ratelimit-remaining-requests:
- '9999' - X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens: x-ratelimit-remaining-tokens:
- '29999815' - X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests: x-ratelimit-reset-requests:
- 6ms - X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens: x-ratelimit-reset-tokens:
- 0s - X-RATELIMIT-RESET-TOKENS-XXX
x-request-id: x-request-id:
- req_50ed3333fd70ce8e32abd43dbe7f9362 - X-REQUEST-ID-XXX
status: status:
code: 200 code: 200
message: OK message: OK

14
lib/crewai/tests/cassettes/test_before_kickoff_callback.yaml
View File

@@ -39,13 +39,13 @@ interactions:
x-stainless-runtime: x-stainless-runtime:
- CPython - CPython
x-stainless-runtime-version: x-stainless-runtime-version:
- 3.13.3 - 3.13.12
method: POST method: POST
uri: https://api.openai.com/v1/chat/completions uri: https://api.openai.com/v1/chat/completions
response: response:
body: body:
string: "{\n \"id\": \"chatcmpl-DIqrxbdWncBetSyqX8P36UUXoil9d\",\n \"object\": string: "{\n \"id\": \"chatcmpl-DJVXy6jcneOpe2GdSSGfNO4TkB6np\",\n \"object\":
\"chat.completion\",\n \"created\": 1773385505,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"chat.completion\",\n \"created\": 1773541870,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Test expected output\",\n \"refusal\": \"assistant\",\n \"content\": \"Test expected output\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
@@ -54,18 +54,18 @@ interactions:
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_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\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_5e793402c9\"\n}\n" \"default\",\n \"system_fingerprint\": \"fp_db58fd2815\"\n}\n"
headers: headers:
CF-Cache-Status: CF-Cache-Status:
- DYNAMIC - DYNAMIC
CF-Ray: CF-Ray:
- 9db9302f7f411efc-EWR - 9dc819af5cbb8ce8-EWR
Connection: Connection:
- keep-alive - keep-alive
Content-Type: Content-Type:
- application/json - application/json
Date: Date:
- Fri, 13 Mar 2026 07:05:06 GMT - Sun, 15 Mar 2026 02:31:10 GMT
Server: Server:
- cloudflare - cloudflare
Strict-Transport-Security: Strict-Transport-Security:
@@ -81,7 +81,7 @@ interactions:
openai-organization: openai-organization:
- OPENAI-ORG-XXX - OPENAI-ORG-XXX
openai-processing-ms: openai-processing-ms:
- '376' - '351'
openai-project: openai-project:
- OPENAI-PROJECT-XXX - OPENAI-PROJECT-XXX
openai-version: openai-version:

367
lib/crewai/tests/cassettes/test_crew_with_delegating_agents.yaml
View File

@@ -7,22 +7,22 @@ interactions:
Task: Produce and amazing 1 paragraph draft of an article about AI Agents.\n\nThis Task: Produce and amazing 1 paragraph draft of an article about AI Agents.\n\nThis
is the expected criteria for your final answer: A 4 paragraph article about is the expected criteria for your final answer: A 4 paragraph article about
AI.\nyou MUST return the actual complete content as the final answer, not a AI.\nyou MUST return the actual complete content as the final answer, not a
summary.\n\nThis is VERY important to you, your job depends on it!"}],"model":"gpt-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"Delegate_work_to_coworker","description":"Delegate summary."}],"model":"gpt-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"delegate_work_to_coworker","description":"Delegate
a specific task to one of the following coworkers: Senior Writer\nThe input a specific task to one of the following coworkers: Senior Writer\nThe input
to this tool should be the coworker, the task you want them to do, and ALL necessary to this tool should be the coworker, the task you want them to do, and ALL necessary
context to execute the task, they know nothing about the task, so share absolutely context to execute the task, they know nothing about the task, so share absolutely
everything you know, don''t reference things but instead explain them.","parameters":{"properties":{"task":{"description":"The everything you know, don''t reference things but instead explain them.","strict":true,"parameters":{"properties":{"task":{"description":"The
task to delegate","title":"Task","type":"string"},"context":{"description":"The task to delegate","title":"Task","type":"string"},"context":{"description":"The
context for the task","title":"Context","type":"string"},"coworker":{"description":"The context for the task","title":"Context","type":"string"},"coworker":{"description":"The
role/name of the coworker to delegate to","title":"Coworker","type":"string"}},"required":["task","context","coworker"],"type":"object"}}},{"type":"function","function":{"name":"Ask_question_to_coworker","description":"Ask role/name of the coworker to delegate to","title":"Coworker","type":"string"}},"required":["task","context","coworker"],"type":"object","additionalProperties":false}}},{"type":"function","function":{"name":"ask_question_to_coworker","description":"Ask
a specific question to one of the following coworkers: Senior Writer\nThe input a specific question to one of the following coworkers: Senior Writer\nThe input
to this tool should be the coworker, the question you have for them, and ALL to this tool should be the coworker, the question you have for them, and ALL
necessary context to ask the question properly, they know nothing about the necessary context to ask the question properly, they know nothing about the
question, so share absolutely everything you know, don''t reference things but question, so share absolutely everything you know, don''t reference things but
instead explain them.","parameters":{"properties":{"question":{"description":"The instead explain them.","strict":true,"parameters":{"properties":{"question":{"description":"The
question to ask","title":"Question","type":"string"},"context":{"description":"The question to ask","title":"Question","type":"string"},"context":{"description":"The
context for the question","title":"Context","type":"string"},"coworker":{"description":"The context for the question","title":"Context","type":"string"},"coworker":{"description":"The
role/name of the coworker to ask","title":"Coworker","type":"string"}},"required":["question","context","coworker"],"type":"object"}}}]}' role/name of the coworker to ask","title":"Coworker","type":"string"}},"required":["question","context","coworker"],"type":"object","additionalProperties":false}}}]}'
headers: headers:
User-Agent: User-Agent:
- X-USER-AGENT-XXX - X-USER-AGENT-XXX
@@ -35,7 +35,7 @@ interactions:
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '2270' - '2298'
content-type: content-type:
- application/json - application/json
host: host:
@@ -57,48 +57,46 @@ interactions:
x-stainless-runtime: x-stainless-runtime:
- CPython - CPython
x-stainless-runtime-version: x-stainless-runtime-version:
- 3.13.3 - 3.13.12
method: POST method: POST
uri: https://api.openai.com/v1/chat/completions uri: https://api.openai.com/v1/chat/completions
response: response:
body: body:
string: "{\n \"id\": \"chatcmpl-D0uJLGWT3ELLQ84FugHD30N0rap1d\",\n \"object\": string: "{\n \"id\": \"chatcmpl-DJVUF1zvo6c1aeolU4hCgOK2XeUEK\",\n \"object\":
\"chat.completion\",\n \"created\": 1769108831,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"chat.completion\",\n \"created\": 1773541639,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n \"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_j5vDsg6M6N1UbDUrQTZnwKia\",\n \"type\": \ \"id\": \"call_wi7jZ8PKxWMadJufpDtwfLF3\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"Delegate_work_to_coworker\",\n \"function\",\n \"function\": {\n \"name\": \"delegate_work_to_coworker\",\n
\ \"arguments\": \"{\\\"coworker\\\":\\\"Senior Writer\\\",\\\"task\\\":\\\"Produce \ \"arguments\": \"{\\\"task\\\":\\\"Produce an amazing 1 paragraph
a 4-paragraph article about AI focusing on AI Agents, starting with a 1-paragraph draft of an article about AI Agents. This paragraph should be engaging, informative,
draft. The article should be engaging, informative, and demonstrate a deep and provide a clear introduction to the topic of AI Agents, capturing the
understanding of the topic, highlighting how AI Agents function, their applications, readers' interest and setting the stage for a longer article.\\\",\\\"context\\\":\\\"The
benefits and potential future developments.\\\",\\\"context\\\":\\\"The task article on AI Agents will be a 4 paragraph piece aiming to explain what AI
is to produce an amazing 4-paragraph article about AI with a focus on AI Agents. Agents are, their functionalities, importance, and potential future developments.
The first deliverable is a 1-paragraph draft that sets the tone for the full The draft paragraph should serve as a compelling introduction that hooks the
article, emphasizing the significance and capabilities of AI Agents in modern audience and introduces the subject matter effectively.\\\",\\\"coworker\\\":\\\"Senior
technology. The final article should be coherent, seamlessly cover the topic, Writer\\\"}\"\n }\n }\n ],\n \"refusal\":
and be suitable for publication on a technology-focused platform.\\\"}\"\n null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ }\n }\n ],\n \"refusal\": null,\n \"annotations\": \ \"finish_reason\": \"tool_calls\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n 386,\n \"completion_tokens\": 124,\n \"total_tokens\": 510,\n \"prompt_tokens_details\":
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 399,\n \"completion_tokens\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
159,\n \"total_tokens\": 558,\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\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n" \"default\",\n \"system_fingerprint\": \"fp_5e793402c9\"\n}\n"
headers: headers:
CF-RAY: CF-Cache-Status:
- CF-RAY-XXX - DYNAMIC
CF-Ray:
- 9dc8140db9f85f83-EWR
Connection: Connection:
- keep-alive - keep-alive
Content-Type: Content-Type:
- application/json - application/json
Date: Date:
- Thu, 22 Jan 2026 19:07:14 GMT - Sun, 15 Mar 2026 02:27:20 GMT
Server: Server:
- cloudflare - cloudflare
Set-Cookie:
- SET-COOKIE-XXX
Strict-Transport-Security: Strict-Transport-Security:
- STS-XXX - STS-XXX
Transfer-Encoding: Transfer-Encoding:
@@ -109,18 +107,16 @@ interactions:
- ACCESS-CONTROL-XXX - ACCESS-CONTROL-XXX
alt-svc: alt-svc:
- h3=":443"; ma=86400 - h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization: openai-organization:
- OPENAI-ORG-XXX - OPENAI-ORG-XXX
openai-processing-ms: openai-processing-ms:
- '2967' - '1331'
openai-project: openai-project:
- OPENAI-PROJECT-XXX - OPENAI-PROJECT-XXX
openai-version: openai-version:
- '2020-10-01' - '2020-10-01'
x-envoy-upstream-service-time: set-cookie:
- '2989' - SET-COOKIE-XXX
x-openai-proxy-wasm: x-openai-proxy-wasm:
- v0.1 - v0.1
x-ratelimit-limit-requests: x-ratelimit-limit-requests:
@@ -144,25 +140,18 @@ interactions:
body: '{"messages":[{"role":"system","content":"You are Senior Writer. You''re body: '{"messages":[{"role":"system","content":"You are Senior Writer. You''re
a senior writer, specialized in technology, software engineering, AI and startups. a senior writer, specialized in technology, software engineering, AI and startups.
You work as a freelancer and are now working on writing content for a new customer.\nYour You work as a freelancer and are now working on writing content for a new customer.\nYour
personal goal is: Write the best content about AI and AI agents.\nTo give my personal goal is: Write the best content about AI and AI agents."},{"role":"user","content":"\nCurrent
best complete final answer to the task respond using the exact following format:\n\nThought: Task: Produce an amazing 1 paragraph draft of an article about AI Agents. This
I now can give a great answer\nFinal Answer: Your final answer must be the great paragraph should be engaging, informative, and provide a clear introduction
and the most complete as possible, it must be outcome described.\n\nI MUST use to the topic of AI Agents, capturing the readers'' interest and setting the
these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: stage for a longer article.\n\nThis is the expected criteria for your final
Produce a 4-paragraph article about AI focusing on AI Agents, starting with answer: Your best answer to your coworker asking you this, accounting for the
a 1-paragraph draft. The article should be engaging, informative, and demonstrate context shared.\nyou MUST return the actual complete content as the final answer,
a deep understanding of the topic, highlighting how AI Agents function, their not a summary.\n\nThis is the context you''re working with:\nThe article on
applications, benefits and potential future developments.\n\nThis is the expected AI Agents will be a 4 paragraph piece aiming to explain what AI Agents are,
criteria for your final answer: Your best answer to your coworker asking you their functionalities, importance, and potential future developments. The draft
this, accounting for the context shared.\nyou MUST return the actual complete paragraph should serve as a compelling introduction that hooks the audience
content as the final answer, not a summary.\n\nThis is the context you''re working and introduces the subject matter effectively.\n\nProvide your complete response:"}],"model":"gpt-4.1-mini"}'
with:\nThe task is to produce an amazing 4-paragraph article about AI with a
focus on AI Agents. The first deliverable is a 1-paragraph draft that sets the
tone for the full article, emphasizing the significance and capabilities of
AI Agents in modern technology. The final article should be coherent, seamlessly
cover the topic, and be suitable for publication on a technology-focused platform.\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-4.1-mini"}'
headers: headers:
User-Agent: User-Agent:
- X-USER-AGENT-XXX - X-USER-AGENT-XXX
@@ -175,7 +164,7 @@ interactions:
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '1766' - '1228'
content-type: content-type:
- application/json - application/json
host: host:
@@ -197,53 +186,46 @@ interactions:
x-stainless-runtime: x-stainless-runtime:
- CPython - CPython
x-stainless-runtime-version: x-stainless-runtime-version:
- 3.13.3 - 3.13.12
method: POST method: POST
uri: https://api.openai.com/v1/chat/completions uri: https://api.openai.com/v1/chat/completions
response: response:
body: body:
string: "{\n \"id\": \"chatcmpl-D0uJOvgyklVDFe1l4S0ty6oMuhfak\",\n \"object\": string: "{\n \"id\": \"chatcmpl-DJVUHEhPlZEKRnV2LXW33Z2y5jZB6\",\n \"object\":
\"chat.completion\",\n \"created\": 1769108834,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"chat.completion\",\n \"created\": 1773541641,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal \"assistant\",\n \"content\": \"In the rapidly evolving landscape of
Answer: \\n\\nArtificial Intelligence (AI) agents have emerged as a transformative artificial intelligence, AI agents stand out as transformative entities capable
force in modern technology, redefining how machines interact with the world of perceiving their environment, making decisions, and autonomously executing
and assist humans in complex tasks. These autonomous systems are designed tasks to achieve specific goals. Far beyond simple algorithms, these agents
to perceive their environment, make decisions, and execute actions to achieve act as intelligent intermediaries that can range from virtual assistants managing
specific goals, often adapting in real-time to changing conditions. Unlike our schedules to complex systems driving autonomous vehicles or optimizing
traditional software that follows pre-programmed instructions without deviation, supply chains. As AI agents increasingly integrate into daily life and business
AI agents exhibit a level of intelligence akin to decision-making entities, operations, understanding their core principles and potential impact is essential\u2014not
leveraging advanced algorithms in machine learning, natural language processing, just for tech enthusiasts but for anyone interested in how intelligent automation
and computer vision. From virtual assistants like Siri and Alexa to sophisticated is reshaping our future. This article will explore what AI agents are, how
industrial robots and predictive analytics systems, AI agents are not only they function, their growing significance across industries, and the exciting
enhancing efficiency but also opening new frontiers in automation and human-computer possibilities they hold on the horizon.\",\n \"refusal\": null,\n \"annotations\":
interaction. Their capacity to learn, reason, and self-improve positions them
as pivotal enablers in sectors ranging from healthcare and finance to autonomous
vehicles and smart cities, heralding a future where intelligent agents will
seamlessly augment daily life and enterprise operations. This article delves
into the inner workings of AI agents, explores their diverse applications,
underscores their benefits, and envisions their evolving role in shaping the
technological landscape.\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 340,\n \"completion_tokens\": \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 222,\n \"completion_tokens\":
233,\n \"total_tokens\": 573,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 137,\n \"total_tokens\": 359,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_2191215734\"\n}\n" \"default\",\n \"system_fingerprint\": \"fp_5e793402c9\"\n}\n"
headers: headers:
CF-RAY: CF-Cache-Status:
- CF-RAY-XXX - DYNAMIC
CF-Ray:
- 9dc814182b1c281b-EWR
Connection: Connection:
- keep-alive - keep-alive
Content-Type: Content-Type:
- application/json - application/json
Date: Date:
- Thu, 22 Jan 2026 19:07:18 GMT - Sun, 15 Mar 2026 02:27:22 GMT
Server: Server:
- cloudflare - cloudflare
Set-Cookie:
- SET-COOKIE-XXX
Strict-Transport-Security: Strict-Transport-Security:
- STS-XXX - STS-XXX
Transfer-Encoding: Transfer-Encoding:
@@ -254,18 +236,16 @@ interactions:
- ACCESS-CONTROL-XXX - ACCESS-CONTROL-XXX
alt-svc: alt-svc:
- h3=":443"; ma=86400 - h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization: openai-organization:
- OPENAI-ORG-XXX - OPENAI-ORG-XXX
openai-processing-ms: openai-processing-ms:
- '3760' - '1582'
openai-project: openai-project:
- OPENAI-PROJECT-XXX - OPENAI-PROJECT-XXX
openai-version: openai-version:
- '2020-10-01' - '2020-10-01'
x-envoy-upstream-service-time: set-cookie:
- '3776' - SET-COOKIE-XXX
x-openai-proxy-wasm: x-openai-proxy-wasm:
- v0.1 - v0.1
x-ratelimit-limit-requests: x-ratelimit-limit-requests:
@@ -286,57 +266,50 @@ interactions:
code: 200 code: 200
message: OK message: OK
- request: - request:
body: '{"messages":[{"role":"system","content":"You are CEO. You''re an long time body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are CEO. You're an
CEO of a content creation agency with a Senior Writer on the team. You''re now long time CEO of a content creation agency with a Senior Writer on the team.
working on a new project and want to make sure the content produced is amazing.\nYour You're now working on a new project and want to make sure the content produced
personal goal is: Make sure the writers in your company produce amazing content."},{"role":"user","content":"\nCurrent is amazing.\\nYour personal goal is: Make sure the writers in your company produce
Task: Produce and amazing 1 paragraph draft of an article about AI Agents.\n\nThis amazing content.\"},{\"role\":\"user\",\"content\":\"\\nCurrent Task: Produce
is the expected criteria for your final answer: A 4 paragraph article about and amazing 1 paragraph draft of an article about AI Agents.\\n\\nThis is the
AI.\nyou MUST return the actual complete content as the final answer, not a expected criteria for your final answer: A 4 paragraph article about AI.\\nyou
summary.\n\nThis is VERY important to you, your job depends on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_j5vDsg6M6N1UbDUrQTZnwKia","type":"function","function":{"name":"Delegate_work_to_coworker","arguments":"{\"coworker\":\"Senior MUST return the actual complete content as the final answer, not a summary.\"},{\"role\":\"assistant\",\"content\":null,\"tool_calls\":[{\"id\":\"call_wi7jZ8PKxWMadJufpDtwfLF3\",\"type\":\"function\",\"function\":{\"name\":\"delegate_work_to_coworker\",\"arguments\":\"{\\\"task\\\":\\\"Produce
Writer\",\"task\":\"Produce a 4-paragraph article about AI focusing on AI Agents, an amazing 1 paragraph draft of an article about AI Agents. This paragraph should
starting with a 1-paragraph draft. The article should be engaging, informative, be engaging, informative, and provide a clear introduction to the topic of AI
and demonstrate a deep understanding of the topic, highlighting how AI Agents Agents, capturing the readers' interest and setting the stage for a longer article.\\\",\\\"context\\\":\\\"The
function, their applications, benefits and potential future developments.\",\"context\":\"The article on AI Agents will be a 4 paragraph piece aiming to explain what AI Agents
task is to produce an amazing 4-paragraph article about AI with a focus on AI are, their functionalities, importance, and potential future developments. The
Agents. The first deliverable is a 1-paragraph draft that sets the tone for draft paragraph should serve as a compelling introduction that hooks the audience
the full article, emphasizing the significance and capabilities of AI Agents and introduces the subject matter effectively.\\\",\\\"coworker\\\":\\\"Senior
in modern technology. The final article should be coherent, seamlessly cover Writer\\\"}\"}}]},{\"role\":\"tool\",\"tool_call_id\":\"call_wi7jZ8PKxWMadJufpDtwfLF3\",\"name\":\"delegate_work_to_coworker\",\"content\":\"In
the topic, and be suitable for publication on a technology-focused platform.\"}"}}]},{"role":"tool","tool_call_id":"call_j5vDsg6M6N1UbDUrQTZnwKia","content":"Artificial the rapidly evolving landscape of artificial intelligence, AI agents stand out
Intelligence (AI) agents have emerged as a transformative force in modern technology, as transformative entities capable of perceiving their environment, making decisions,
redefining how machines interact with the world and assist humans in complex and autonomously executing tasks to achieve specific goals. Far beyond simple
tasks. These autonomous systems are designed to perceive their environment, algorithms, these agents act as intelligent intermediaries that can range from
make decisions, and execute actions to achieve specific goals, often adapting virtual assistants managing our schedules to complex systems driving autonomous
in real-time to changing conditions. Unlike traditional software that follows vehicles or optimizing supply chains. As AI agents increasingly integrate into
pre-programmed instructions without deviation, AI agents exhibit a level of daily life and business operations, understanding their core principles and
intelligence akin to decision-making entities, leveraging advanced algorithms potential impact is essential\u2014not just for tech enthusiasts but for anyone
in machine learning, natural language processing, and computer vision. From interested in how intelligent automation is reshaping our future. This article
virtual assistants like Siri and Alexa to sophisticated industrial robots and will explore what AI agents are, how they function, their growing significance
predictive analytics systems, AI agents are not only enhancing efficiency but across industries, and the exciting possibilities they hold on the horizon.\"},{\"role\":\"user\",\"content\":\"Analyze
also opening new frontiers in automation and human-computer interaction. Their
capacity to learn, reason, and self-improve positions them as pivotal enablers
in sectors ranging from healthcare and finance to autonomous vehicles and smart
cities, heralding a future where intelligent agents will seamlessly augment
daily life and enterprise operations. This article delves into the inner workings
of AI agents, explores their diverse applications, underscores their benefits,
and envisions their evolving role in shaping the technological landscape."},{"role":"user","content":"Analyze
the tool result. If requirements are met, provide the Final Answer. Otherwise, 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-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"Delegate_work_to_coworker","description":"Delegate call the next tool. Deliver only the answer without meta-commentary.\"}],\"model\":\"gpt-4.1-mini\",\"tool_choice\":\"auto\",\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"delegate_work_to_coworker\",\"description\":\"Delegate
a specific task to one of the following coworkers: Senior Writer\nThe input a specific task to one of the following coworkers: Senior Writer\\nThe input
to this tool should be the coworker, the task you want them to do, and ALL necessary to this tool should be the coworker, the task you want them to do, and ALL necessary
context to execute the task, they know nothing about the task, so share absolutely context to execute the task, they know nothing about the task, so share absolutely
everything you know, don''t reference things but instead explain them.","parameters":{"properties":{"task":{"description":"The everything you know, don't reference things but instead explain them.\",\"strict\":true,\"parameters\":{\"properties\":{\"task\":{\"description\":\"The
task to delegate","title":"Task","type":"string"},"context":{"description":"The task to delegate\",\"title\":\"Task\",\"type\":\"string\"},\"context\":{\"description\":\"The
context for the task","title":"Context","type":"string"},"coworker":{"description":"The context for the task\",\"title\":\"Context\",\"type\":\"string\"},\"coworker\":{\"description\":\"The
role/name of the coworker to delegate to","title":"Coworker","type":"string"}},"required":["task","context","coworker"],"type":"object"}}},{"type":"function","function":{"name":"Ask_question_to_coworker","description":"Ask role/name of the coworker to delegate to\",\"title\":\"Coworker\",\"type\":\"string\"}},\"required\":[\"task\",\"context\",\"coworker\"],\"type\":\"object\",\"additionalProperties\":false}}},{\"type\":\"function\",\"function\":{\"name\":\"ask_question_to_coworker\",\"description\":\"Ask
a specific question to one of the following coworkers: Senior Writer\nThe input a specific question to one of the following coworkers: Senior Writer\\nThe input
to this tool should be the coworker, the question you have for them, and ALL to this tool should be the coworker, the question you have for them, and ALL
necessary context to ask the question properly, they know nothing about the necessary context to ask the question properly, they know nothing about the
question, so share absolutely everything you know, don''t reference things but question, so share absolutely everything you know, don't reference things but
instead explain them.","parameters":{"properties":{"question":{"description":"The instead explain them.\",\"strict\":true,\"parameters\":{\"properties\":{\"question\":{\"description\":\"The
question to ask","title":"Question","type":"string"},"context":{"description":"The question to ask\",\"title\":\"Question\",\"type\":\"string\"},\"context\":{\"description\":\"The
context for the question","title":"Context","type":"string"},"coworker":{"description":"The context for the question\",\"title\":\"Context\",\"type\":\"string\"},\"coworker\":{\"description\":\"The
role/name of the coworker to ask","title":"Coworker","type":"string"}},"required":["question","context","coworker"],"type":"object"}}}]}' role/name of the coworker to ask\",\"title\":\"Coworker\",\"type\":\"string\"}},\"required\":[\"question\",\"context\",\"coworker\"],\"type\":\"object\",\"additionalProperties\":false}}}]}"
headers: headers:
User-Agent: User-Agent:
- X-USER-AGENT-XXX - X-USER-AGENT-XXX
@@ -349,7 +322,7 @@ interactions:
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '4785' - '4241'
content-type: content-type:
- application/json - application/json
cookie: cookie:
@@ -373,81 +346,67 @@ interactions:
x-stainless-runtime: x-stainless-runtime:
- CPython - CPython
x-stainless-runtime-version: x-stainless-runtime-version:
- 3.13.3 - 3.13.12
method: POST method: POST
uri: https://api.openai.com/v1/chat/completions uri: https://api.openai.com/v1/chat/completions
response: response:
body: body:
string: "{\n \"id\": \"chatcmpl-D0uJShynrNj5AQsUdLGMcR3mi57nv\",\n \"object\": string: "{\n \"id\": \"chatcmpl-DJVUIWVgzE4ZVBGyKaXO2HDAhJvSL\",\n \"object\":
\"chat.completion\",\n \"created\": 1769108838,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n \"chat.completion\",\n \"created\": 1773541642,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Artificial Intelligence (AI) agents \"assistant\",\n \"content\": \"AI Agents: Transforming the Future
have emerged as a transformative force in modern technology, redefining how with Intelligent Automation\\n\\nIn the rapidly evolving landscape of artificial
machines interact with the world and assist humans in complex tasks. These intelligence, AI agents stand out as transformative entities capable of perceiving
autonomous systems are designed to perceive their environment, make decisions, their environment, making decisions, and autonomously executing tasks to achieve
and execute actions to achieve specific goals, often adapting in real-time specific goals. Far beyond simple algorithms, these agents act as intelligent
to changing conditions. Unlike traditional software that follows pre-programmed intermediaries that can range from virtual assistants managing our schedules
instructions without deviation, AI agents exhibit a level of intelligence to complex systems driving autonomous vehicles or optimizing supply chains.
akin to decision-making entities, leveraging advanced algorithms in machine As AI agents increasingly integrate into daily life and business operations,
learning, natural language processing, and computer vision. From virtual assistants understanding their core principles and potential impact is essential\u2014not
like Siri and Alexa to sophisticated industrial robots and predictive analytics just for tech enthusiasts but for anyone interested in how intelligent automation
systems, AI agents are not only enhancing efficiency but also opening new is reshaping our future. This article will explore what AI agents are, how
frontiers in automation and human-computer interaction. Their capacity to they function, their growing significance across industries, and the exciting
learn, reason, and self-improve positions them as pivotal enablers in sectors possibilities they hold on the horizon.\\n\\nAI agents operate by utilizing
ranging from healthcare and finance to autonomous vehicles and smart cities, a combination of machine learning, natural language processing, and decision-making
heralding a future where intelligent agents will seamlessly augment daily algorithms to interpret data, recognize patterns, and perform actions based
life and enterprise operations. This article delves into the inner workings on their programming and learning experiences. These intelligent entities
of AI agents, explores their diverse applications, underscores their benefits, can adapt to new information, improve their performance over time, and interact
and envisions their evolving role in shaping the technological landscape. with humans or other systems in a meaningful way. From customer service chatbots
\\n\\nAt the core, AI agents function by integrating sensory data with algorithms that provide personalized support to AI-powered diagnostics in healthcare,
that mimic human cognition, enabling them to interpret complex inputs and the versatility of AI agents highlights their capacity to enhance efficiency
make autonomous decisions. These agents operate through a cycle of perception, and innovation across countless fields.\\n\\nThe importance of AI agents extends
reasoning, and action: perceiving their environment via sensors or input data; beyond automation. They hold the promise of solving complex problems, augmenting
processing this information through models that predict outcomes and strategize human capabilities, and making real-time decisions in environments where speed
moves; and finally, executing actions that influence or interact with the and accuracy are critical. Industries such as finance, logistics, manufacturing,
external world. Machine learning plays a critical role, allowing agents to and entertainment are experiencing disruptive changes driven by AI agents
improve their performance based on experience without explicit reprogramming. that help optimize resources, reduce costs, and create new value propositions.
Reinforcement learning, a subset of machine learning, teaches agents to learn Moreover, ethical considerations and responsible development practices are
optimal behaviors by rewarding desirable outcomes. This intelligent adaptability crucial to ensure these technologies benefit society while minimizing risks
makes AI agents valuable in dynamic and unpredictable environments, where and biases.\\n\\nLooking ahead, the future of AI agents is brimming with potential.
rules and conditions continuously evolve.\\n\\nThe applications of AI agents Advances in explainability, generalization, and collaboration between multiple
are vast and growing rapidly, spanning various industries and daily life realms. agents could lead to even more sophisticated systems capable of tackling challenges
In healthcare, AI agents support diagnostics, personalized treatment plans, that were once thought to be exclusively human domains. As AI agents continue
and patient monitoring, aiding doctors with data-driven insights. In finance, to evolve, their integration into everyday life will deepen, transforming
they power algorithmic trading, fraud detection, and customer service chatbots. how we work, communicate, and solve problems\u2014ushering in a new era of
Autonomous vehicles rely heavily on AI agents to navigate, interpret traffic intelligent technology that empowers individuals and organizations alike.\",\n
signals, and ensure passenger safety. Smart homes use these agents for energy \ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
management and security, while industries deploy them in robotics for assembly null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
lines and quality control. These agents' ability to automate routine and complex 695,\n \"completion_tokens\": 428,\n \"total_tokens\": 1123,\n \"prompt_tokens_details\":
tasks leads to significant cost savings, higher precision, and scalability, {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
improving overall productivity and opening innovative business models.\\n\\nLooking
ahead, the evolution of AI agents promises even more profound impacts, with
advances in explainability, ethics, and collaboration between human and machine
intelligence. Future agents will likely be more transparent, offering clearer
reasoning for their decisions, which builds trust and accountability. Enhanced
multi-agent systems could coordinate complex tasks by sharing knowledge and
collaborating seamlessly. Moreover, ongoing research aims to ensure ethical
considerations are embedded from the ground up, addressing biases and safeguarding
privacy. As AI agents become increasingly integrated into society, they will
not only augment human abilities but also inspire new forms of creativity,
problem-solving, and interaction, ultimately shaping a more intelligent and
adaptive world.\",\n \"refusal\": null,\n \"annotations\": []\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 825,\n \"completion_tokens\":
625,\n \"total_tokens\": 1450,\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\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n" \"default\",\n \"system_fingerprint\": \"fp_5e793402c9\"\n}\n"
headers: headers:
CF-RAY: CF-Cache-Status:
- CF-RAY-XXX - DYNAMIC
CF-Ray:
- 9dc814239fb65f83-EWR
Connection: Connection:
- keep-alive - keep-alive
Content-Type: Content-Type:
- application/json - application/json
Date: Date:
- Thu, 22 Jan 2026 19:07:28 GMT - Sun, 15 Mar 2026 02:27:28 GMT
Server: Server:
- cloudflare - cloudflare
Strict-Transport-Security: Strict-Transport-Security:
@@ -460,18 +419,14 @@ interactions:
- ACCESS-CONTROL-XXX - ACCESS-CONTROL-XXX
alt-svc: alt-svc:
- h3=":443"; ma=86400 - h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization: openai-organization:
- OPENAI-ORG-XXX - OPENAI-ORG-XXX
openai-processing-ms: openai-processing-ms:
- '9924' - '4942'
openai-project: openai-project:
- OPENAI-PROJECT-XXX - OPENAI-PROJECT-XXX
openai-version: openai-version:
- '2020-10-01' - '2020-10-01'
x-envoy-upstream-service-time:
- '9940'
x-openai-proxy-wasm: x-openai-proxy-wasm:
- v0.1 - v0.1
x-ratelimit-limit-requests: x-ratelimit-limit-requests:

2944
lib/crewai/tests/cassettes/test_memory_remember_called_after_task.yaml
View File

File diff suppressed because one or more lines are too long

252
lib/crewai/tests/cassettes/test_task_tools_override_agent_tools.yaml
View File

@@ -1,247 +1,123 @@
interactions: interactions:
- request: - request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re body: '{"messages":[{"role":"system","content":"You are Researcher. You''re an
an expert researcher, specialized in technology, software engineering, AI and expert researcher, specialized in technology, software engineering, AI and startups.
startups. You work as a freelancer and is now working on doing research and You work as a freelancer and is now working on doing research and analysis for
analysis for a new customer.\nYour personal goal is: Make the best research a new customer.\nYour personal goal is: Make the best research and analysis
and analysis on content about AI and AI agents\nYou ONLY have access to the on content about AI and AI agents"},{"role":"user","content":"\nCurrent Task:
following tools, and should NEVER make up tools that are not listed here:\n\nTool Write a test task\n\nThis is the expected criteria for your final answer: Test
Name: Another Test Tool\nTool Arguments: {''query'': {''description'': ''Query output\nyou MUST return the actual complete content as the final answer, not
to process'', ''type'': ''str''}}\nTool Description: Another test tool\n\nUse a summary."}],"model":"gpt-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"another_test_tool","description":"Another
the following format:\n\nThought: you should always think about what to do\nAction: test tool","strict":true,"parameters":{"properties":{"query":{"description":"Query
the action to take, only one name of [Another Test Tool], just the name, exactly to process","title":"Query","type":"string"}},"required":["query"],"type":"object","additionalProperties":false}}}]}'
as it''s written.\nAction Input: the input to the action, just a simple python
dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question"}, {"role": "user", "content": "\nCurrent Task: Write a test
task\n\nThis is the expect criteria for your final answer: Test output\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"],
"stream": false}'
headers: headers:
User-Agent:
- X-USER-AGENT-XXX
accept: accept:
- application/json - application/json
accept-encoding: accept-encoding:
- gzip, deflate - ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection: connection:
- keep-alive - keep-alive
content-length: content-length:
- '1525' - '892'
content-type: content-type:
- application/json - application/json
cookie:
- _cfuvid=eQzzWvIXDS8Me1OIBdCG5F1qFyVfAo3sumvYRE7J41E-1734965710778-0.0.1.1-604800000
host: host:
- api.openai.com - api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch: x-stainless-arch:
- arm64 - X-STAINLESS-ARCH-XXX
x-stainless-async: x-stainless-async:
- 'false' - 'false'
x-stainless-lang: x-stainless-lang:
- python - python
x-stainless-os: x-stainless-os:
- MacOS - X-STAINLESS-OS-XXX
x-stainless-package-version: x-stainless-package-version:
- 1.52.1 - 1.83.0
x-stainless-raw-response: x-stainless-read-timeout:
- 'true' - X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count: x-stainless-retry-count:
- '0' - '0'
x-stainless-runtime: x-stainless-runtime:
- CPython - CPython
x-stainless-runtime-version: x-stainless-runtime-version:
- 3.12.7 - 3.13.12
method: POST method: POST
uri: https://api.openai.com/v1/chat/completions uri: https://api.openai.com/v1/chat/completions
response: response:
body: body:
string: "{\n \"id\": \"chatcmpl-AmjYyKbTn42DzaLVOjDvJpLubTjSq\",\n \"object\"\ string: "{\n \"id\": \"chatcmpl-DJVYArMj7gxUpliUsjoQOzDxaw0Ta\",\n \"object\":
: \"chat.completion\",\n \"created\": 1736178252,\n \"model\": \"gpt-4o-2024-08-06\"\ \"chat.completion\",\n \"created\": 1773541882,\n \"model\": \"gpt-4.1-mini-2025-04-14\",\n
,\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \ \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\ \"role\": \"assistant\",\n \"content\": \"Action: Another Test\ \"assistant\",\n \"content\": \"Test Task: \\n\\nWrite a program in
\ Tool\\nAction Input: {\\\"query\\\": \\\"AI and AI agents\\\"}\",\n \ your preferred programming language that accomplishes the following:\\n\\n1.
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\"\ Accepts a list of integers as input.\\n2. Filters the list to include only
: \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 295,\n \ prime numbers.\\n3. Sorts the filtered prime numbers in ascending order.\\n4.
\ \"completion_tokens\": 18,\n \"total_tokens\": 313,\n \"prompt_tokens_details\"\ Outputs the sorted list of prime numbers.\\n\\nRequirements:\\n- Provide the
: {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"\ complete source code.\\n- Include comments explaining the logic.\\n- Ensure
completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\"\ the code handles invalid inputs gracefully.\\n- Test the program with at least
: 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\"\ three different input sets and show the outputs.\\n\\nExample:\\n\\nInput:
: 0\n }\n },\n \"system_fingerprint\": \"fp_5f20662549\"\n}\n" [12, 7, 5, 18, 11, 3, 20]\\nOutput: [3, 5, 7, 11]\\n\\nPlease provide the
full code along with sample input and output for verification.\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
147,\n \"completion_tokens\": 157,\n \"total_tokens\": 304,\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_e76a310957\"\n}\n"
headers: headers:
CF-Cache-Status: CF-Cache-Status:
- DYNAMIC - DYNAMIC
CF-RAY: CF-Ray:
- 8fdcd3fc9a56bf66-ATL - 9dc819faed93433f-EWR
Connection: Connection:
- keep-alive - keep-alive
Content-Type: Content-Type:
- application/json - application/json
Date: Date:
- Mon, 06 Jan 2025 15:44:12 GMT - Sun, 15 Mar 2026 02:31:26 GMT
Server: Server:
- cloudflare - cloudflare
Set-Cookie: Strict-Transport-Security:
- __cf_bm=X1fuDKrQrN8tU.uxjB0murgJXWXcPtlNLnD7xUrAKTs-1736178252-1.0.1.1-AME9VZZVtEpqX9.BEN_Kj9pI9uK3sIJc2LdbuPsP3wULKxF4Il6r8ghX0to2wpcYsGWbJXSqWP.dQz4vGf_Gbw; - STS-XXX
path=/; expires=Mon, 06-Jan-25 16:14:12 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=mv42xOepGYaNopc5ovT9Ajamw5rJrze8tlWTik8lfrk-1736178252935-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding: Transfer-Encoding:
- chunked - chunked
X-Content-Type-Options: X-Content-Type-Options:
- nosniff - X-CONTENT-TYPE-XXX
access-control-expose-headers: access-control-expose-headers:
- X-Request-ID - ACCESS-CONTROL-XXX
alt-svc: alt-svc:
- h3=":443"; ma=86400 - h3=":443"; ma=86400
openai-organization: openai-organization:
- crewai-iuxna1 - OPENAI-ORG-XXX
openai-processing-ms: openai-processing-ms:
- '632' - '3681'
openai-project:
- OPENAI-PROJECT-XXX
openai-version: openai-version:
- '2020-10-01' - '2020-10-01'
strict-transport-security: set-cookie:
- max-age=31536000; includeSubDomains; preload - SET-COOKIE-XXX
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests: x-ratelimit-limit-requests:
- '10000' - X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens: x-ratelimit-limit-tokens:
- '30000000' - X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests: x-ratelimit-remaining-requests:
- '9999' - X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens: x-ratelimit-remaining-tokens:
- '29999644' - X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests: x-ratelimit-reset-requests:
- 6ms - X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens: x-ratelimit-reset-tokens:
- 0s - X-RATELIMIT-RESET-TOKENS-XXX
x-request-id: x-request-id:
- req_9276753b2200fc95c74fc43c9d7d84a6 - X-REQUEST-ID-XXX
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
an expert researcher, specialized in technology, software engineering, AI and
startups. You work as a freelancer and is now working on doing research and
analysis for a new customer.\nYour personal goal is: Make the best research
and analysis on content about AI and AI agents\nYou ONLY have access to the
following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: Another Test Tool\nTool Arguments: {''query'': {''description'': ''Query
to process'', ''type'': ''str''}}\nTool Description: Another test tool\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Another Test Tool], just the name, exactly
as it''s written.\nAction Input: the input to the action, just a simple python
dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question"}, {"role": "user", "content": "\nCurrent Task: Write a test
task\n\nThis is the expect criteria for your final answer: Test output\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}, {"role": "assistant", "content":
"Action: Another Test Tool\nAction Input: {\"query\": \"AI and AI agents\"}\nObservation:
Another processed: AI and AI agents"}], "model": "gpt-4o", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1687'
content-type:
- application/json
cookie:
- _cfuvid=mv42xOepGYaNopc5ovT9Ajamw5rJrze8tlWTik8lfrk-1736178252935-0.0.1.1-604800000;
__cf_bm=X1fuDKrQrN8tU.uxjB0murgJXWXcPtlNLnD7xUrAKTs-1736178252-1.0.1.1-AME9VZZVtEpqX9.BEN_Kj9pI9uK3sIJc2LdbuPsP3wULKxF4Il6r8ghX0to2wpcYsGWbJXSqWP.dQz4vGf_Gbw
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-AmjYzChV9s4D4qOJJvTvBAt3kRh7n\",\n \"object\"\
: \"chat.completion\",\n \"created\": 1736178253,\n \"model\": \"gpt-4o-2024-08-06\"\
,\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \
\ \"role\": \"assistant\",\n \"content\": \"Thought: I now know\
\ the final answer\\nFinal Answer: Another processed: AI and AI agents\",\n\
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"\
finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\"\
: 326,\n \"completion_tokens\": 19,\n \"total_tokens\": 345,\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 \"system_fingerprint\"\
: \"fp_5f20662549\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8fdcd4011938bf66-ATL
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Mon, 06 Jan 2025 15:44:15 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '2488'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999613'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_5e3a1a90ef91ff4f12d5b84e396beccc
status: status:
code: 200 code: 200
message: OK message: OK

1976
lib/crewai/tests/cassettes/test_using_memory_recall_and_save.yaml
View File

File diff suppressed because one or more lines are too long