andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-15 19:18:30 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

refactor: streamline agent execution and enhance flow compatibility

Browse Source 
Refactored the Agent class to simplify the execution method by removing the event loop check and clarifying the behavior when called from synchronous and asynchronous contexts. The changes ensure that the method operates seamlessly within flow methods, improving clarity in the documentation. Additionally, updated the AgentExecutor to set the response model to None, enhancing flexibility. New test cassettes were added to validate the functionality of agents within flow contexts, ensuring robust testing for both synchronous and asynchronous operations.
This commit is contained in:
lorenzejay
2026-01-14 18:51:09 -08:00
parent 6541f01b1b
commit 09185acc0d
8 changed files with 869 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
lib/crewai/src/crewai/agent/core.py
View File

@@ -1,7 +1,7 @@
from __future__ import annotations
import asyncio
from collections.abc import Callable, Coroutine, Sequence
from collections.abc import Callable, Sequence
import shutil
import subprocess
import time
@@ -70,7 +70,6 @@ from crewai.security.fingerprint import Fingerprint
from crewai.tools.agent_tools.agent_tools import AgentTools
from crewai.utilities.agent_utils import (
get_tool_names,
is_inside_event_loop,
load_agent_from_repository,
parse_tools,
render_text_description_and_args,
@@ -1684,16 +1683,16 @@ class Agent(BaseAgent):
self,
messages: str | list[LLMMessage],
response_format: type[Any] | None = None,
) -> LiteAgentOutput | Coroutine[Any, Any, LiteAgentOutput]:
) -> LiteAgentOutput:
"""
Execute the agent with the given messages using the AgentExecutor.
This method provides standalone agent execution without requiring a Crew.
It supports tools, response formatting, and guardrails.
When called from within a Flow (inside an event loop), this method
automatically returns a coroutine that the Flow framework will await,
making it work seamlessly in both sync and async contexts.
When called from within a sync Flow method, the Flow framework automatically
runs the method in a thread pool, so this works seamlessly. For async Flow
methods, use kickoff_async() instead.
Args:
messages: Either a string query or a list of message dictionaries.
@@ -1703,11 +1702,10 @@ class Agent(BaseAgent):
Returns:
LiteAgentOutput: The result of the agent execution.
Or a coroutine if called from within an event loop.
Note:
If called from an async context (not through Flow), use kickoff_async().
"""
# Magic auto-async: return coroutine for Flow to await
if is_inside_event_loop():
return self.kickoff_async(messages, response_format)
executor, inputs, agent_info, parsed_tools = self._prepare_kickoff(
messages, response_format

2
lib/crewai/src/crewai/experimental/agent_executor.py
View File

@@ -268,7 +268,7 @@ class AgentExecutor(Flow[AgentReActState], CrewAgentExecutorMixin):
printer=self._printer,
from_task=self.task,
from_agent=self.agent,
response_model=self.response_model,
response_model=None,
executor_context=self,
)

14
lib/crewai/src/crewai/flow/flow.py
View File

@@ -1575,13 +1575,15 @@ class Flow(Generic[T], metaclass=FlowMeta):
if future:
self._event_futures.append(future)
result = (
await method(*args, **kwargs)
if asyncio.iscoroutinefunction(method)
else method(*args, **kwargs)
)
if asyncio.iscoroutinefunction(method):
result = await method(*args, **kwargs)
else:
import contextvars
# Auto-await coroutines from sync methods (enables agent.kickoff() inside flows)
ctx = contextvars.copy_context()
result = await asyncio.to_thread(ctx.run, method, *args, **kwargs)
# Auto-await coroutines from sync methods (still useful for explicit coroutine returns)
if asyncio.iscoroutine(result):
result = await result

119
lib/crewai/tests/cassettes/agents/test_lite_agent_inside_flow_sync.yaml Normal file
View File

@@ -0,0 +1,119 @@
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"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '673'
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-Cy7b0HjL79y39EkUcMLrRhPFe3XGj\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444914,\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\":
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"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:55 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
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
content-length:
- '857'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '341'
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:
- 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

255
lib/crewai/tests/cassettes/agents/test_lite_agent_inside_flow_with_tools.yaml Normal file
View File

@@ -0,0 +1,255 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Calculator Agent. A math
expert\nYour personal goal is: Perform calculations\nYou ONLY have access to
the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: calculate\nTool Arguments: {\n \"properties\": {\n \"expression\":
{\n \"title\": \"Expression\",\n \"type\": \"string\"\n }\n },\n \"required\":
[\n \"expression\"\n ],\n \"title\": \"CalculatorToolSchema\",\n \"type\":
\"object\",\n \"additionalProperties\": false\n}\nTool Description: Calculate
the result of a mathematical expression.\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 [calculate], 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":"\nCurrent
Task: Calculate 10 * 5\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"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1403'
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-Cy7avghVPSpszLmlbHpwDQlWDoD6O\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444909,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to calculate the expression
10 * 5.\\nAction: calculate\\nAction Input: {\\\"expression\\\":\\\"10 * 5\\\"}\\nObservation:
50\",\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 291,\n \"completion_tokens\": 33,\n
\ \"total_tokens\": 324,\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"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:49 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
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
content-length:
- '939'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '579'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '598'
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 Calculator Agent. A math
expert\nYour personal goal is: Perform calculations\nYou ONLY have access to
the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: calculate\nTool Arguments: {\n \"properties\": {\n \"expression\":
{\n \"title\": \"Expression\",\n \"type\": \"string\"\n }\n },\n \"required\":
[\n \"expression\"\n ],\n \"title\": \"CalculatorToolSchema\",\n \"type\":
\"object\",\n \"additionalProperties\": false\n}\nTool Description: Calculate
the result of a mathematical expression.\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 [calculate], 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":"\nCurrent
Task: Calculate 10 * 5\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":"Thought:
I need to calculate the expression 10 * 5.\nAction: calculate\nAction Input:
{\"expression\":\"10 * 5\"}\nObservation: The result of 10 * 5 is 50"}],"model":"gpt-4o-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1591'
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-Cy7avDhDZCLvv8v2dh8ZQRrLdci6A\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444909,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer.\\nFinal
Answer: 50\",\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 337,\n \"completion_tokens\": 14,\n
\ \"total_tokens\": 351,\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"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:50 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
content-length:
- '864'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '429'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '457'
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

119
lib/crewai/tests/cassettes/agents/test_lite_agent_kickoff_async_inside_flow.yaml Normal file
View File

@@ -0,0 +1,119 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Async Test Agent. An async
helper\nYour personal goal is: Answer questions asynchronously\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 3+3?\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"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '657'
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-Cy7atOGxtc4y3oYNI62WiQ0Vogsdv\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444907,\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: The sum of 3 + 3 is 6. Therefore, the outcome is that if you add three
and three together, you will arrive at the total of six.\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
131,\n \"completion_tokens\": 46,\n \"total_tokens\": 177,\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"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:48 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
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
content-length:
- '983'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '944'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1192'
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

119
lib/crewai/tests/cassettes/agents/test_lite_agent_standalone_still_works.yaml Normal file
View File

@@ -0,0 +1,119 @@
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"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '674'
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-Cy7azhPwUHQ0p5tdhxSAmLPoE8UgC\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444913,\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\":
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"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:54 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
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
content-length:
- '858'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '455'
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:
- 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

240
lib/crewai/tests/cassettes/agents/test_multiple_agents_in_same_flow.yaml Normal file
View File

@@ -0,0 +1,240 @@
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"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '632'
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-Cy7awLGYnYfpKGEeRhKlU90FltH7L\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444910,\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 and welcome! It's wonderful to see you here. I hope you're having
a fantastic day. If there's anything you need or if you have any questions,
feel free to ask. I'm here to help and make your experience enjoyable!\",\n
\ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
127,\n \"completion_tokens\": 57,\n \"total_tokens\": 184,\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"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:51 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
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
content-length:
- '1074'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '1019'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1242'
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 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"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '640'
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-Cy7ayZre6crr19UyujJE9YbNxDndk\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444912,\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 conclude our conversation, I just want to take a moment to express
my heartfelt gratitude for your time and engagement. It has been a pleasure
interacting with you. I wish you all the best in your future endeavors. May
your path ahead be filled with success and happiness. Farewell, and until
we meet again!\",\n \"refusal\": null,\n \"annotations\": []\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 126,\n \"completion_tokens\":
75,\n \"total_tokens\": 201,\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"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:53 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
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
content-length:
- '1169'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '1298'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1550'
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