andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-08 07:38:29 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Adding tool caching a loop execution prevention. (#25)

Browse Source 
* Adding tool caching a loop execution prevention.

This adds some guardrails, to both prevent the same tool to be used
consecutively and also caching tool's results across the entire crew
so it cuts down execution time and eventual LLM calls.

This plays a huge role for smaller opensource models that usually fall
into those behaviors patterns.

It also includes some smaller improvements around the tool prompt and
agent tools, all with the same intention of guiding models into
better conform with agent instructions.
This commit is contained in:
João Moura
2023-12-29 22:35:23 -03:00
committed by GitHub
parent 5cc230263c
commit af9e749edb
14 changed files with 3046 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
tests/agent_test.py
View File

@@ -4,6 +4,7 @@ import pytest
from langchain.chat_models import ChatOpenAI as OpenAI
from crewai.agent import Agent
from crewai.agents import CacheHandler
def test_agent_creation():
@@ -101,6 +102,77 @@ def test_agent_execution_with_tools():
assert output == "12"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_logging_tool_usage():
from langchain.tools import tool
@tool
def multiplier(numbers) -> float:
"""Useful for when you need to multiply two numbers together.
The input to this tool should be a comma separated list of numbers of
length two, representing the two numbers you want to multiply together.
For example, `1,2` would be the input if you wanted to multiply 1 by 2."""
a, b = numbers.split(",")
return int(a) * int(b)
agent = Agent(
role="test role",
goal="test goal",
backstory="test backstory",
tools=[multiplier],
allow_delegation=False,
verbose=True,
)
assert agent.tools_handler.last_used_tool == {}
output = agent.execute_task("What is 3 times 5?")
tool_usage = {
"tool": "multiplier",
"input": "3,5",
}
assert output == "3 times 5 is 15."
assert agent.tools_handler.last_used_tool == tool_usage
@pytest.mark.vcr(filter_headers=["authorization"])
def test_cache_hitting():
from unittest.mock import patch
from langchain.tools import tool
@tool
def multiplier(numbers) -> float:
"""Useful for when you need to multiply two numbers together.
The input to this tool should be a comma separated list of numbers of
length two, representing the two numbers you want to multiply together.
For example, `1,2` would be the input if you wanted to multiply 1 by 2."""
a, b = numbers.split(",")
return int(a) * int(b)
cache_handler = CacheHandler()
agent = Agent(
role="test role",
goal="test goal",
backstory="test backstory",
tools=[multiplier],
allow_delegation=False,
cache_handler=cache_handler,
verbose=True,
)
output = agent.execute_task("What is 2 times 6?")
output = agent.execute_task("What is 3 times 3?")
assert cache_handler._cache == {"multiplier-2,6": "12", "multiplier-3,3": "9"}
with patch.object(CacheHandler, "read") as read:
read.return_value = "0"
output = agent.execute_task("What is 2 times 6?")
assert output == "0"
read.assert_called_once_with("multiplier", "2,6")
@pytest.mark.vcr(filter_headers=["authorization"])
def test_agent_execution_with_specific_tools():
from langchain.tools import tool
@@ -122,4 +194,4 @@ def test_agent_execution_with_specific_tools():
)
output = agent.execute_task(task="What is 3 times 4", tools=[multiplier])
assert output == "3 times 4 is 12."
assert output == "12"

6
tests/agent_tools/agent_tools_test.py
View File

@@ -48,7 +48,7 @@ def test_delegate_work_with_wrong_input():
assert (
result
== "Error executing tool. Missing exact 3 pipe (|) separated values. For example, `coworker|task|information`."
== "\nError executing tool. Missing exact 3 pipe (|) separated values. For example, `coworker|task|information`."
)
@@ -59,7 +59,7 @@ def test_delegate_work_to_wrong_agent():
assert (
result
== "Error executing tool. Co-worker not found, double check the co-worker."
== "\nError executing tool. Co-worker mentioned on the Action Input not found, it must to be one of the following options: researcher."
)
@@ -70,5 +70,5 @@ def test_ask_question_to_wrong_agent():
assert (
result
== "Error executing tool. Co-worker not found, double check the co-worker."
== "\nError executing tool. Co-worker mentioned on the Action Input not found, it must to be one of the following options: researcher."
)

916
tests/cassettes/test_cache_hitting.yaml Normal file
View File

@@ -0,0 +1,916 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
to multiply two numbers together.\n The input to this tool should be
a comma separated list of numbers of\n length two, representing the two
numbers you want to multiply together.\n For example, `1,2` would be
the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the
exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
the action to take, should be one of [multiplier], just the name.\nAction Input:
the input to the action\nObservation: the result of the action\n```\n\nWhen
you have a response for your task, or if you do not need to use a tool, you
MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
[your response here]\n```\n\t\tThis is the summary of your work so far:\n \nBegin!
This is VERY important to you, your job depends on it!\n\nCurrent Task: What
is 2 times 6?\n\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1219'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b8NsTNQTMzHe8yjfHP8Eo31DhwBW\",\n \"object\":
\"chat.completion\",\n \"created\": 1703861056,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 261,\n \"completion_tokens\":
23,\n \"total_tokens\": 284\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d2d1f00d1101c3-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 14:44:17 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
path=/; expires=Fri, 29-Dec-23 15:14:17 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '1750'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299720'
x-ratelimit-remaining-tokens_usage_based:
- '299720'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 55ms
x-ratelimit-reset-tokens_usage_based:
- 55ms
x-request-id:
- 907b4e1c5dddb9abb47843bbab76cd7a
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
to multiply two numbers together.\n The input to this tool should be
a comma separated list of numbers of\n length two, representing the two
numbers you want to multiply together.\n For example, `1,2` would be
the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the
exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
the action to take, should be one of [multiplier], just the name.\nAction Input:
the input to the action\nObservation: the result of the action\n```\n\nWhen
you have a response for your task, or if you do not need to use a tool, you
MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
[your response here]\n```\n\t\tThis is the summary of your work so far:\n \nBegin!
This is VERY important to you, your job depends on it!\n\nCurrent Task: What
is 2 times 6?\nThought: Do I need to use a tool? Yes\nAction: multiplier\nAction
Input: 2,6\nObservation: 12\nThought: \n"}], "model": "gpt-4", "n": 1, "stop":
["\nObservation"], "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1323'
content-type:
- application/json
cookie:
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b8NuuCivtT2524QvfyDjrA3XkXLB\",\n \"object\":
\"chat.completion\",\n \"created\": 1703861058,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer:
12\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 294,\n \"completion_tokens\":
15,\n \"total_tokens\": 309\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d2d1fc79ad01c3-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 14:44:20 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '2779'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299695'
x-ratelimit-remaining-tokens_usage_based:
- '299695'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 60ms
x-ratelimit-reset-tokens_usage_based:
- 60ms
x-request-id:
- 5db441cfcc97cfd1ab228c2c0d5234f6
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Progressively summarize the
lines of conversation provided, adding onto the previous summary returning a
new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
of artificial intelligence. The AI thinks artificial intelligence is a force
for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
intelligence is a force for good?\nAI: Because artificial intelligence will
help humans reach their full potential.\n\nNew summary:\nThe human asks what
the AI thinks of artificial intelligence. The AI thinks artificial intelligence
is a force for good because it will help humans reach their full potential.\nEND
OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: What
is 2 times 6?\nAI: 12\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream":
false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '872'
content-type:
- application/json
cookie:
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b8Nxf7bPMYpEdt2JmUIWLV4maYXG\",\n \"object\":
\"chat.completion\",\n \"created\": 1703861061,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI to calculate 2
times 6, and the AI responds with 12.\"\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
149,\n \"completion_tokens\": 21,\n \"total_tokens\": 170\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d2d20fdf6f01c3-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 14:44:22 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '1463'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299796'
x-ratelimit-remaining-tokens_usage_based:
- '299796'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 40ms
x-ratelimit-reset-tokens_usage_based:
- 40ms
x-request-id:
- 99bc213367b851b629eb5489381887b7
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
to multiply two numbers together.\n The input to this tool should be
a comma separated list of numbers of\n length two, representing the two
numbers you want to multiply together.\n For example, `1,2` would be
the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the
exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
the action to take, should be one of [multiplier], just the name.\nAction Input:
the input to the action\nObservation: the result of the action\n```\n\nWhen
you have a response for your task, or if you do not need to use a tool, you
MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
[your response here]\n```\n\t\tThis is the summary of your work so far:\n The
human asks the AI to calculate 2 times 6, and the AI responds with 12.\nBegin!
This is VERY important to you, your job depends on it!\n\nCurrent Task: What
is 3 times 3?\n\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1293'
content-type:
- application/json
cookie:
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b8NyS4i9PXuCQMD9p0Afb7msIFLA\",\n \"object\":
\"chat.completion\",\n \"created\": 1703861062,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
multiplier\\nAction Input: 3,3\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 282,\n \"completion_tokens\":
23,\n \"total_tokens\": 305\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d2d21a893d01c3-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 14:44:25 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '2472'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299703'
x-ratelimit-remaining-tokens_usage_based:
- '299703'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 59ms
x-ratelimit-reset-tokens_usage_based:
- 59ms
x-request-id:
- ac6d5063cae237481f45c88406ee1134
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
to multiply two numbers together.\n The input to this tool should be
a comma separated list of numbers of\n length two, representing the two
numbers you want to multiply together.\n For example, `1,2` would be
the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the
exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
the action to take, should be one of [multiplier], just the name.\nAction Input:
the input to the action\nObservation: the result of the action\n```\n\nWhen
you have a response for your task, or if you do not need to use a tool, you
MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
[your response here]\n```\n\t\tThis is the summary of your work so far:\n The
human asks the AI to calculate 2 times 6, and the AI responds with 12.\nBegin!
This is VERY important to you, your job depends on it!\n\nCurrent Task: What
is 3 times 3?\nThought: Do I need to use a tool? Yes\nAction: multiplier\nAction
Input: 3,3\nObservation: 9\nThought: \n"}], "model": "gpt-4", "n": 1, "stop":
["\nObservation"], "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1396'
content-type:
- application/json
cookie:
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b8O1OvQNcMLn5JwCShOrcdUGDYTQ\",\n \"object\":
\"chat.completion\",\n \"created\": 1703861065,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer:
3 times 3 is 9.\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 315,\n \"completion_tokens\":
22,\n \"total_tokens\": 337\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d2d22c1c5c01c3-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 14:44:27 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '1885'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299678'
x-ratelimit-remaining-tokens_usage_based:
- '299678'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 64ms
x-ratelimit-reset-tokens_usage_based:
- 64ms
x-request-id:
- 34020a2529f99325e63ed40493268cd1
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Progressively summarize the
lines of conversation provided, adding onto the previous summary returning a
new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
of artificial intelligence. The AI thinks artificial intelligence is a force
for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
intelligence is a force for good?\nAI: Because artificial intelligence will
help humans reach their full potential.\n\nNew summary:\nThe human asks what
the AI thinks of artificial intelligence. The AI thinks artificial intelligence
is a force for good because it will help humans reach their full potential.\nEND
OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to calculate 2 times 6,
and the AI responds with 12.\n\nNew lines of conversation:\nHuman: What is 3
times 3?\nAI: 3 times 3 is 9.\n\nNew summary:"}], "model": "gpt-4", "n": 1,
"stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '959'
content-type:
- application/json
cookie:
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b8O3IxMbwCemZSzKFeBXV2doGGt7\",\n \"object\":
\"chat.completion\",\n \"created\": 1703861067,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI to calculate 2
times 6 and 3 times 3, and the AI responds with 12 and 9 respectively.\"\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 176,\n \"completion_tokens\": 31,\n
\ \"total_tokens\": 207\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d2d2395c4d01c3-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 14:44:30 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '3030'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299775'
x-ratelimit-remaining-tokens_usage_based:
- '299775'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 44ms
x-ratelimit-reset-tokens_usage_based:
- 44ms
x-request-id:
- 6a043e22366e13d63ad963dc01964533
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
to multiply two numbers together.\n The input to this tool should be
a comma separated list of numbers of\n length two, representing the two
numbers you want to multiply together.\n For example, `1,2` would be
the input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the
exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
the action to take, should be one of [multiplier], just the name.\nAction Input:
the input to the action\nObservation: the result of the action\n```\n\nWhen
you have a response for your task, or if you do not need to use a tool, you
MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
[your response here]\n```\n\t\tThis is the summary of your work so far:\n The
human asks the AI to calculate 2 times 6 and 3 times 3, and the AI responds
with 12 and 9 respectively.\nBegin! This is VERY important to you, your job
depends on it!\n\nCurrent Task: What is 2 times 6?\n\n"}], "model": "gpt-4",
"n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1326'
content-type:
- application/json
cookie:
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b8O7429GQMpUZpPBK77gOoK8UnMY\",\n \"object\":
\"chat.completion\",\n \"created\": 1703861071,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
multiplier\\nAction Input: 2,6\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 292,\n \"completion_tokens\":
23,\n \"total_tokens\": 315\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d2d24e09bf01c3-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 14:44:32 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '1369'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299695'
x-ratelimit-remaining-tokens_usage_based:
- '299695'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 61ms
x-ratelimit-reset-tokens_usage_based:
- 61ms
x-request-id:
- 7807e472ac55a3cb9201c4eadfe13ee2
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Progressively summarize the
lines of conversation provided, adding onto the previous summary returning a
new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
of artificial intelligence. The AI thinks artificial intelligence is a force
for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
intelligence is a force for good?\nAI: Because artificial intelligence will
help humans reach their full potential.\n\nNew summary:\nThe human asks what
the AI thinks of artificial intelligence. The AI thinks artificial intelligence
is a force for good because it will help humans reach their full potential.\nEND
OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to calculate 2 times 6
and 3 times 3, and the AI responds with 12 and 9 respectively.\n\nNew lines
of conversation:\nHuman: What is 2 times 6?\nAI: 0\n\nNew summary:"}], "model":
"gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '978'
content-type:
- application/json
cookie:
- __cf_bm=rd8TZZP3aKU.V0S.99_vKXMEF_oekbKasFEgEg.qrEw-1703861057-1-Ae5v8FUgqHuVy0hGrL9fTE3F2zt2n2q4pKK0tOpJh+mIw5ffYrGKfd68LoLAGihdbod6ucY4PYvsBE/6WSrp3sQ=;
_cfuvid=M5Tgs1dNQjihNi4NUGpcOR42zHumBRUVwL214O3LaPA-1703861057944-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b8O8FQhcRqwPnGUxFziRReKvggG1\",\n \"object\":
\"chat.completion\",\n \"created\": 1703861072,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI to calculate 2
times 6 and 3 times 3, and the AI responds with 12 and 9 respectively. However,
when asked again to calculate 2 times 6, the AI incorrectly responds with 0.\"\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 180,\n \"completion_tokens\":
52,\n \"total_tokens\": 232\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d2d2582ae901c3-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 14:44:37 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '4793'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299770'
x-ratelimit-remaining-tokens_usage_based:
- '299770'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 45ms
x-ratelimit-reset-tokens_usage_based:
- 45ms
x-request-id:
- feb3958ca226769ce85f1b4a6ba649ac
http_version: HTTP/1.1
status_code: 200
version: 1

1084
tests/cassettes/test_cache_hitting_between_agents.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

690
tests/cassettes/test_logging_tool_usage.yaml Normal file
View File

@@ -0,0 +1,690 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
- Useful for when you need to multiply two numbers together.\n The input
to this tool should be a comma separated list of numbers of\n length
two, representing the two numbers you want to multiply together.\n For
example, `1,2` would be the input if you wanted to multiply 1 by 2.\n\nTo use
a tool, please use the exact following format:\n\n```\nThought: Do I need to
use a tool? Yes\nAction: the action to take, should be one of [multiplier],
just the name.\nAction Input: the input to the action\nObservation: the result
of the action\n```\n\nWhen you have a response for your task, or if you do not
need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis is the summary
of your work so far:\n \nBegin! This is VERY important to you, your job depends
on it!\n\nCurrent Task: What is 3 times 5?\n\n"}], "model": "gpt-4", "n": 1,
"stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1231'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b7eDhOwdMJw0817wIqiD9MoXVRU8\",\n \"object\":
\"chat.completion\",\n \"created\": 1703858225,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
multiplier\\nAction Input: 3,5\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 264,\n \"completion_tokens\":
23,\n \"total_tokens\": 287\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d28cd70f9f1cd9-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 13:57:07 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
path=/; expires=Fri, 29-Dec-23 14:27:07 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '1725'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299717'
x-ratelimit-remaining-tokens_usage_based:
- '299717'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 56ms
x-ratelimit-reset-tokens_usage_based:
- 56ms
x-request-id:
- 689757a1e38baf0844ec69f20525c5d7
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
- Useful for when you need to multiply two numbers together.\n The input
to this tool should be a comma separated list of numbers of\n length
two, representing the two numbers you want to multiply together.\n For
example, `1,2` would be the input if you wanted to multiply 1 by 2.\n\nTo use
a tool, please use the exact following format:\n\n```\nThought: Do I need to
use a tool? Yes\nAction: the action to take, should be one of [multiplier],
just the name.\nAction Input: the input to the action\nObservation: the result
of the action\n```\n\nWhen you have a response for your task, or if you do not
need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis is the summary
of your work so far:\n \nBegin! This is VERY important to you, your job depends
on it!\n\nCurrent Task: What is 3 times 5?\nThought: Do I need to use a tool?
Yes\nAction: multiplier\nAction Input: 3,5\nObservation: 15\nThought: \n"}],
"model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1335'
content-type:
- application/json
cookie:
- __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
_cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b7eG2qnUr6SZcankL5AqkwIJvYFc\",\n \"object\":
\"chat.completion\",\n \"created\": 1703858228,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer:
3 times 5 is 15.\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 297,\n \"completion_tokens\":
22,\n \"total_tokens\": 319\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d28ce3ab3b1cd9-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 13:57:09 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '1568'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299693'
x-ratelimit-remaining-tokens_usage_based:
- '299693'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 61ms
x-ratelimit-reset-tokens_usage_based:
- 61ms
x-request-id:
- 66a02e3e08e3f6b5b29fb04cd19f50a0
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Progressively summarize the
lines of conversation provided, adding onto the previous summary returning a
new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
of artificial intelligence. The AI thinks artificial intelligence is a force
for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
intelligence is a force for good?\nAI: Because artificial intelligence will
help humans reach their full potential.\n\nNew summary:\nThe human asks what
the AI thinks of artificial intelligence. The AI thinks artificial intelligence
is a force for good because it will help humans reach their full potential.\nEND
OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: What
is 3 times 5?\nAI: 3 times 5 is 15.\n\nNew summary:"}], "model": "gpt-4", "n":
1, "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '886'
content-type:
- application/json
cookie:
- __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
_cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b7eIfmBgQoWGLW4jiQZTu3qzEBBL\",\n \"object\":
\"chat.completion\",\n \"created\": 1703858230,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI to calculate 3
times 5 and the AI responds that 3 times 5 is 15.\"\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
155,\n \"completion_tokens\": 26,\n \"total_tokens\": 181\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d28cf118221cd9-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 13:57:12 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '2188'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299794'
x-ratelimit-remaining-tokens_usage_based:
- '299794'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 41ms
x-ratelimit-reset-tokens_usage_based:
- 41ms
x-request-id:
- a644c703d416b1e4b06586e96e6d7297
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
- Useful for when you need to multiply two numbers together.\n The input
to this tool should be a comma separated list of numbers of\n length
two, representing the two numbers you want to multiply together.\n For
example, `1,2` would be the input if you wanted to multiply 1 by 2.\n\nTo use
a tool, please use the exact following format:\n\n```\nThought: Do I need to
use a tool? Yes\nAction: the action to take, should be one of [multiplier],
just the name.\nAction Input: the input to the action\nObservation: the result
of the action\n```\n\nWhen you have a response for your task, or if you do not
need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis is the summary
of your work so far:\n The human asks the AI to calculate 3 times 5 and the
AI responds that 3 times 5 is 15.\nBegin! This is VERY important to you, your
job depends on it!\n\nCurrent Task: What is 3 times 5?\n\n"}], "model": "gpt-4",
"n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1317'
content-type:
- application/json
cookie:
- __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
_cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b7eKehkNtTjrXJD0aFjiVUeXU7te\",\n \"object\":
\"chat.completion\",\n \"created\": 1703858232,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
multiplier\\nAction Input: 3,5\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 290,\n \"completion_tokens\":
23,\n \"total_tokens\": 313\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d28d007f461cd9-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 13:57:14 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '1885'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299697'
x-ratelimit-remaining-tokens_usage_based:
- '299697'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 60ms
x-ratelimit-reset-tokens_usage_based:
- 60ms
x-request-id:
- 87959bfa6a029f7bcafb5095e66d4964
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
- Useful for when you need to multiply two numbers together.\n The input
to this tool should be a comma separated list of numbers of\n length
two, representing the two numbers you want to multiply together.\n For
example, `1,2` would be the input if you wanted to multiply 1 by 2.\n\nTo use
a tool, please use the exact following format:\n\n```\nThought: Do I need to
use a tool? Yes\nAction: the action to take, should be one of [multiplier],
just the name.\nAction Input: the input to the action\nObservation: the result
of the action\n```\n\nWhen you have a response for your task, or if you do not
need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis is the summary
of your work so far:\n The human asks the AI to calculate 3 times 5 and the
AI responds that 3 times 5 is 15.\nBegin! This is VERY important to you, your
job depends on it!\n\nCurrent Task: What is 3 times 5?\n\nI just used the multiplier
tool with input 3,5. So I already knwo the result of that.\nObservation: Invalid
or incomplete response\nThought: \n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
"stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1460'
content-type:
- application/json
cookie:
- __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
_cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b7eME5fg1w8QcXUnl0FBcqxJWy7u\",\n \"object\":
\"chat.completion\",\n \"created\": 1703858234,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer:
3 times 5 is 15.\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 324,\n \"completion_tokens\":
22,\n \"total_tokens\": 346\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d28d0fcfaf1cd9-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 13:57:17 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '2494'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299661'
x-ratelimit-remaining-tokens_usage_based:
- '299661'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 67ms
x-ratelimit-reset-tokens_usage_based:
- 67ms
x-request-id:
- eb9704531634d4cd3c6652dff09914bc
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Progressively summarize the
lines of conversation provided, adding onto the previous summary returning a
new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
of artificial intelligence. The AI thinks artificial intelligence is a force
for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
intelligence is a force for good?\nAI: Because artificial intelligence will
help humans reach their full potential.\n\nNew summary:\nThe human asks what
the AI thinks of artificial intelligence. The AI thinks artificial intelligence
is a force for good because it will help humans reach their full potential.\nEND
OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to calculate 3 times 5
and the AI responds that 3 times 5 is 15.\n\nNew lines of conversation:\nHuman:
What is 3 times 5?\nAI: 3 times 5 is 15.\n\nNew summary:"}], "model": "gpt-4",
"n": 1, "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '972'
content-type:
- application/json
cookie:
- __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
_cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.1
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8b7eP77MzprkbgjaMbeaEob0aDx39\",\n \"object\":
\"chat.completion\",\n \"created\": 1703858237,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI to calculate 3
times 5 twice, and both times the AI responds that 3 times 5 is 15.\"\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 181,\n \"completion_tokens\": 30,\n
\ \"total_tokens\": 211\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 83d28d211f591cd9-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 29 Dec 2023 13:57:20 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '2967'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299771'
x-ratelimit-remaining-tokens_usage_based:
- '299771'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 45ms
x-ratelimit-reset-tokens_usage_based:
- 45ms
x-request-id:
- e3bbd11b2e9b28f76f8b43dc7a4d2b6d
http_version: HTTP/1.1
status_code: 200
version: 1

47
tests/crew_test.py
View File

@@ -8,6 +8,7 @@ from crewai.agent import Agent
from crewai.crew import Crew
from crewai.process import Process
from crewai.task import Task
from crewai.agents import CacheHandler
ceo = Agent(
role="CEO",
@@ -157,7 +158,7 @@ def test_crew_with_delegating_agents():
assert (
crew.kickoff()
== "The Senior Writer has created a compelling and engaging 1 paragraph draft about AI agents. The paragraph provides a brief yet comprehensive overview of AI agents, their uses, and implications in the current world. It emphasizes their potential and the role they can play in the future. The tone is informative but captivating, meeting the objectives of the task."
== '"AI agents, the digital masterminds at the heart of the 21st-century revolution, are shaping a new era of intelligence and innovation. They are autonomous entities, capable of observing their environment, making decisions, and acting on them, all in pursuit of a specific goal. From streamlining operations in logistics to personalizing customer experiences in retail, AI agents are transforming how businesses operate. But their potential extends far beyond the corporate world. They are the sentinels protecting our digital frontiers, the virtual assistants making our lives easier, and the unseen hands guiding autonomous vehicles. As this technology evolves, AI agents will play an increasingly central role in our world, ushering in an era of unprecedented efficiency, personalization, and productivity. But with great power comes great responsibility, and understanding and harnessing this potential responsibly will be one of our greatest challenges and opportunities in the coming years."'
)
@@ -194,3 +195,47 @@ def test_crew_verbose_output(capsys):
crew.kickoff()
captured = capsys.readouterr()
assert captured.out == ""
@pytest.mark.vcr(filter_headers=["authorization"])
def test_cache_hitting_between_agents():
from unittest.mock import patch
from langchain.tools import tool
@tool
def multiplier(numbers) -> float:
"""Useful for when you need to multiply two numbers together.
The input to this tool should be a comma separated list of numbers of
length two, representing the two numbers you want to multiply together.
For example, `1,2` would be the input if you wanted to multiply 1 by 2."""
a, b = numbers.split(",")
return int(a) * int(b)
tasks = [
Task(
description="What is 2 tims 6?",
tools=[multiplier],
agent=ceo,
),
Task(
description="What is 2 times 6?",
tools=[multiplier],
agent=researcher,
),
]
crew = Crew(
agents=[ceo, researcher],
tasks=tasks,
)
assert crew.cache_handler._cache == {}
output = crew.kickoff()
assert crew.cache_handler._cache == {"multiplier-2,6": "12"}
assert output == "12"
with patch.object(CacheHandler, "read") as read:
read.return_value = "12"
crew.kickoff()
read.assert_called_with("multiplier", "2,6")