andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-22 14:48:13 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Merge branch 'main' into brandon/eng-266-conversation-crew-v1

Browse Source
This commit is contained in:
Brandon Hancock (bhancock_ai)
2025-01-03 10:41:16 -05:00
committed by GitHub
parent 0284095ff8 bfe2c44f55
commit 3ba15e8bc9
62 changed files with 6329 additions and 1430 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
tests/agent_test.py
View File

@@ -1445,44 +1445,43 @@ def test_llm_call_with_all_attributes():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_agent_with_ollama_gemma():
def test_agent_with_ollama_llama3():
agent = Agent(
role="test role",
goal="test goal",
backstory="test backstory",
llm=LLM(
model="ollama/gemma2:latest",
base_url="http://localhost:8080",
),
llm=LLM(model="ollama/llama3.2:3b", base_url="http://localhost:11434"),
)
assert isinstance(agent.llm, LLM)
assert agent.llm.model == "ollama/gemma2:latest"
assert agent.llm.base_url == "http://localhost:8080"
assert agent.llm.model == "ollama/llama3.2:3b"
assert agent.llm.base_url == "http://localhost:11434"
task = "Respond in 20 words. Who are you?"
task = "Respond in 20 words. Which model are you?"
response = agent.llm.call([{"role": "user", "content": task}])
assert response
assert len(response.split()) <= 25 # Allow a little flexibility in word count
assert "Gemma" in response or "AI" in response or "language model" in response
assert "Llama3" in response or "AI" in response or "language model" in response
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_call_with_ollama_gemma():
def test_llm_call_with_ollama_llama3():
llm = LLM(
model="ollama/gemma2:latest",
base_url="http://localhost:8080",
model="ollama/llama3.2:3b",
base_url="http://localhost:11434",
temperature=0.7,
max_tokens=30,
)
messages = [{"role": "user", "content": "Respond in 20 words. Who are you?"}]
messages = [
{"role": "user", "content": "Respond in 20 words. Which model are you?"}
]
response = llm.call(messages)
assert response
assert len(response.split()) <= 25 # Allow a little flexibility in word count
assert "Gemma" in response or "AI" in response or "language model" in response
assert "Llama3" in response or "AI" in response or "language model" in response
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -1578,7 +1577,7 @@ def test_agent_execute_task_with_ollama():
role="test role",
goal="test goal",
backstory="test backstory",
llm=LLM(model="ollama/gemma2:latest", base_url="http://localhost:8080"),
llm=LLM(model="ollama/llama3.2:3b", base_url="http://localhost:11434"),
)
task = Task(

58
tests/cassettes/test_agent_execute_task_with_ollama.yaml
View File

@@ -1,42 +1,6 @@
interactions:
- request:
body: !!binary |
CrcCCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSjgIKEgoQY3Jld2FpLnRl
bGVtZXRyeRJoChA/Q8UW5bidCRtKvri5fOaNEgh5qLzvLvZJkioQVG9vbCBVc2FnZSBFcnJvcjAB
OYjFVQr1TPgXQXCXhwr1TPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMHoCGAGFAQABAAAS
jQEKEChQTWQ07t26ELkZmP5RresSCHEivRGBpsP7KgpUb29sIFVzYWdlMAE5sKkbC/VM+BdB8MIc
C/VM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShkKCXRvb2xfbmFtZRIMCgpkdW1teV90
b29sSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAA=
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '314'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Tue, 24 Sep 2024 21:57:54 GMT
status:
code: 200
message: OK
- request:
body: '{"model": "gemma2:latest", "prompt": "### System:\nYou are test role. test
body: '{"model": "llama3.2:3b", "prompt": "### System:\nYou are test role. test
backstory\nYour personal goal is: test goal\nTo give my best complete final
answer to the task use 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
@@ -46,7 +10,7 @@ interactions:
explanation of AI\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:\n\n",
"options": {}, "stream": false}'
"options": {"stop": ["\nObservation:"]}, "stream": false}'
headers:
Accept:
- '*/*'
@@ -55,26 +19,26 @@ interactions:
Connection:
- keep-alive
Content-Length:
- '815'
- '839'
Content-Type:
- application/json
User-Agent:
- python-requests/2.31.0
- python-requests/2.32.3
method: POST
uri: http://localhost:8080/api/generate
uri: http://localhost:11434/api/generate
response:
body:
string: '{"model":"gemma2:latest","created_at":"2024-09-24T21:57:55.835715Z","response":"Thought:
I can explain AI in one sentence. \n\nFinal Answer: Artificial intelligence
(AI) is the ability of computer systems to perform tasks that typically require
human intelligence, such as learning, problem-solving, and decision-making. \n","done":true,"done_reason":"stop","context":[106,1645,108,6176,1479,235292,108,2045,708,2121,4731,235265,2121,135147,108,6922,3749,6789,603,235292,2121,6789,108,1469,2734,970,1963,3407,2048,3448,577,573,6911,1281,573,5463,2412,5920,235292,109,65366,235292,590,1490,798,2734,476,1775,3448,108,11263,10358,235292,3883,2048,3448,2004,614,573,1775,578,573,1546,3407,685,3077,235269,665,2004,614,17526,6547,235265,109,235285,44472,1281,1450,32808,235269,970,3356,12014,611,665,235341,109,6176,4926,235292,109,6846,12297,235292,36576,1212,16481,603,575,974,13060,109,1596,603,573,5246,12830,604,861,2048,3448,235292,586,974,235290,47366,15844,576,16481,108,4747,44472,2203,573,5579,3407,3381,685,573,2048,3448,235269,780,476,13367,235265,109,12694,235341,1417,603,50471,2845,577,692,235269,1281,573,8112,2506,578,2734,861,1963,14124,10358,235269,861,3356,12014,611,665,235341,109,65366,235292,109,107,108,106,2516,108,65366,235292,590,798,10200,16481,575,974,13060,235265,235248,109,11263,10358,235292,42456,17273,591,11716,235275,603,573,7374,576,6875,5188,577,3114,13333,674,15976,2817,3515,17273,235269,1582,685,6044,235269,3210,235290,60495,235269,578,4530,235290,14577,235265,139,108],"total_duration":3370959792,"load_duration":20611750,"prompt_eval_count":173,"prompt_eval_duration":688036000,"eval_count":51,"eval_duration":2660291000}'
string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:05:52.24992Z","response":"Final
Answer: Artificial Intelligence (AI) refers to the development of computer
systems capable of performing tasks that typically require human intelligence,
such as learning, problem-solving, decision-making, and perception.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,744,512,2675,527,1296,3560,13,1296,93371,198,7927,4443,5915,374,25,1296,5915,198,1271,3041,856,1888,4686,1620,4320,311,279,3465,1005,279,4839,2768,3645,1473,85269,25,358,1457,649,3041,264,2294,4320,198,19918,22559,25,4718,1620,4320,2011,387,279,2294,323,279,1455,4686,439,3284,11,433,2011,387,15632,7633,382,40,28832,1005,1521,20447,11,856,2683,14117,389,433,2268,14711,2724,1473,5520,5546,25,83017,1148,15592,374,304,832,11914,271,2028,374,279,1755,13186,369,701,1620,4320,25,362,832,1355,18886,16540,315,15592,198,9514,28832,471,279,5150,4686,2262,439,279,1620,4320,11,539,264,12399,382,11382,0,1115,374,48174,3062,311,499,11,1005,279,7526,2561,323,3041,701,1888,13321,22559,11,701,2683,14117,389,433,2268,85269,1473,128009,128006,78191,128007,271,19918,22559,25,59294,22107,320,15836,8,19813,311,279,4500,315,6500,6067,13171,315,16785,9256,430,11383,1397,3823,11478,11,1778,439,6975,11,3575,99246,11,5597,28846,11,323,21063,13],"total_duration":1461909875,"load_duration":39886208,"prompt_eval_count":181,"prompt_eval_duration":701000000,"eval_count":39,"eval_duration":719000000}'
headers:
Content-Length:
- '1662'
- '1537'
Content-Type:
- application/json; charset=utf-8
Date:
- Tue, 24 Sep 2024 21:57:55 GMT
- Thu, 02 Jan 2025 20:05:52 GMT
status:
code: 200
message: OK

397
tests/cassettes/test_agent_with_ollama_gemma.yaml
View File

@@ -1,397 +0,0 @@
interactions:
- request:
body: !!binary |
CumTAQokCiIKDHNlcnZpY2UubmFtZRISChBjcmV3QUktdGVsZW1ldHJ5Er+TAQoSChBjcmV3YWku
dGVsZW1ldHJ5EqoHChDvqD2QZooz9BkEwtbWjp4OEgjxh72KACHvZSoMQ3JldyBDcmVhdGVkMAE5
qMhNnvBM+BdBcO9PnvBM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShoKDnB5dGhvbl92
ZXJzaW9uEggKBjMuMTEuN0ouCghjcmV3X2tleRIiCiBkNTUxMTNiZTRhYTQxYmE2NDNkMzI2MDQy
YjJmMDNmMUoxCgdjcmV3X2lkEiYKJGY4YTA1OTA1LTk0OGEtNDQ0YS04NmJmLTJiNTNiNDkyYjgy
MkocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jl
d19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFKxwIKC2Ny
ZXdfYWdlbnRzErcCCrQCW3sia2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1ODJi
IiwgImlkIjogIjg1MGJjNWUwLTk4NTctNDhkOC1iNWZlLTJmZjk2OWExYTU3YiIsICJyb2xlIjog
InRlc3Qgcm9sZSIsICJ2ZXJib3NlPyI6IHRydWUsICJtYXhfaXRlciI6IDQsICJtYXhfcnBtIjog
MTAsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00byIsICJkZWxlZ2F0
aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1h
eF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1KkAIKCmNyZXdfdGFza3MSgQIK
/gFbeyJrZXkiOiAiNGEzMWI4NTEzM2EzYTI5NGM2ODUzZGE3NTdkNGJhZTciLCAiaWQiOiAiOTc1
ZDgwMjItMWJkMS00NjBlLTg2NmEtYjJmZGNiYjA4ZDliIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBm
YWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJ0ZXN0IHJvbGUiLCAi
YWdlbnRfa2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1ODJiIiwgInRvb2xzX25h
bWVzIjogWyJnZXRfZmluYWxfYW5zd2VyIl19XXoCGAGFAQABAAASjgIKEP9UYSAOFQbZquSppN1j
IeUSCAgZmXUoJKFmKgxUYXNrIENyZWF0ZWQwATloPV+e8Ez4F0GYsl+e8Ez4F0ouCghjcmV3X2tl
eRIiCiBkNTUxMTNiZTRhYTQxYmE2NDNkMzI2MDQyYjJmMDNmMUoxCgdjcmV3X2lkEiYKJGY4YTA1
OTA1LTk0OGEtNDQ0YS04NmJmLTJiNTNiNDkyYjgyMkouCgh0YXNrX2tleRIiCiA0YTMxYjg1MTMz
YTNhMjk0YzY4NTNkYTc1N2Q0YmFlN0oxCgd0YXNrX2lkEiYKJDk3NWQ4MDIyLTFiZDEtNDYwZS04
NjZhLWIyZmRjYmIwOGQ5YnoCGAGFAQABAAASkwEKEEfiywgqgiUXE3KoUbrnHDQSCGmv+iM7Wc1Z
KgpUb29sIFVzYWdlMAE5kOybnvBM+BdBIM+cnvBM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42
MS4wSh8KCXRvb2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGF
AQABAAASkwEKEH7AHXpfmvwIkA45HB8YyY0SCAFRC+uJpsEZKgpUb29sIFVzYWdlMAE56PLdnvBM
+BdBYFbfnvBM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wSh8KCXRvb2xfbmFtZRISChBn
ZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASkwEKEIDKKEbYU4lcJF+a
WsAVZwESCI+/La7oL86MKgpUb29sIFVzYWdlMAE5yIkgn/BM+BdBWGwhn/BM+BdKGgoOY3Jld2Fp
X3ZlcnNpb24SCAoGMC42MS4wSh8KCXRvb2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0
dGVtcHRzEgIYAXoCGAGFAQABAAASnAEKEMTZ2IhpLz6J2hJhHBQ8/M4SCEuWz+vjzYifKhNUb29s
IFJlcGVhdGVkIFVzYWdlMAE5mAVhn/BM+BdBKOhhn/BM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoG
MC42MS4wSh8KCXRvb2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoC
GAGFAQABAAASkAIKED8C+t95p855kLcXs5Nnt/sSCM4XAhL6u8O8Kg5UYXNrIEV4ZWN1dGlvbjAB
OdD8X57wTPgXQUgno5/wTPgXSi4KCGNyZXdfa2V5EiIKIGQ1NTExM2JlNGFhNDFiYTY0M2QzMjYw
NDJiMmYwM2YxSjEKB2NyZXdfaWQSJgokZjhhMDU5MDUtOTQ4YS00NDRhLTg2YmYtMmI1M2I0OTJi
ODIySi4KCHRhc2tfa2V5EiIKIDRhMzFiODUxMzNhM2EyOTRjNjg1M2RhNzU3ZDRiYWU3SjEKB3Rh
c2tfaWQSJgokOTc1ZDgwMjItMWJkMS00NjBlLTg2NmEtYjJmZGNiYjA4ZDliegIYAYUBAAEAABLO
CwoQFlnZCfbZ3Dj0L9TAE5LrLBIIoFr7BZErFNgqDENyZXcgQ3JlYXRlZDABOVhDDaDwTPgXQSg/
D6DwTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMEoaCg5weXRob25fdmVyc2lvbhIICgYz
LjExLjdKLgoIY3Jld19rZXkSIgogOTRjMzBkNmMzYjJhYzhmYjk0YjJkY2ZjNTcyZDBmNTlKMQoH
Y3Jld19pZBImCiQyMzM2MzRjNi1lNmQ2LTQ5ZTYtODhhZS1lYWUxYTM5YjBlMGZKHAoMY3Jld19w
cm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29m
X3Rhc2tzEgIYAkobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSv4ECgtjcmV3X2FnZW50cxLu
BArrBFt7ImtleSI6ICJlMTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJpZCI6ICI0
MjAzZjIyYi0wNWM3LTRiNjUtODBjMS1kM2Y0YmFlNzZhNDYiLCAicm9sZSI6ICJ0ZXN0IHJvbGUi
LCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAyLCAibWF4X3JwbSI6IDEwLCAiZnVuY3Rp
b25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVk
PyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGlt
aXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX0sIHsia2V5IjogImU3ZThlZWE4ODZiY2I4ZjEwNDVh
YmVlY2YxNDI1ZGI3IiwgImlkIjogImZjOTZjOTQ1LTY4ZDUtNDIxMy05NmNkLTNmYTAwNmUyZTYz
MCIsICJyb2xlIjogInRlc3Qgcm9sZTIiLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAx
LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdw
dC00byIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlv
bj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/QMK
CmNyZXdfdGFza3MS7gMK6wNbeyJrZXkiOiAiMzIyZGRhZTNiYzgwYzFkNDViODVmYTc3NTZkYjg2
NjUiLCAiaWQiOiAiOTVjYTg4NDItNmExMi00MGQ5LWIwZDItNGI0MzYxYmJlNTZkIiwgImFzeW5j
X2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6
ICJ0ZXN0IHJvbGUiLCAiYWdlbnRfa2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1
ODJiIiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICI1ZTljYTdkNjRiNDIwNWJiN2M0N2Uw
YjNmY2I1ZDIxZiIsICJpZCI6ICI5NzI5MTg2Yy1kN2JlLTRkYjQtYTk0ZS02OWU5OTk2NTI3MDAi
LCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2Vu
dF9yb2xlIjogInRlc3Qgcm9sZTIiLCAiYWdlbnRfa2V5IjogImU3ZThlZWE4ODZiY2I4ZjEwNDVh
YmVlY2YxNDI1ZGI3IiwgInRvb2xzX25hbWVzIjogWyJnZXRfZmluYWxfYW5zd2VyIl19XXoCGAGF
AQABAAASjgIKEC/YM2OukRrSg+ZAev4VhGESCOQ5RvzSS5IEKgxUYXNrIENyZWF0ZWQwATmQJx6g
8Ez4F0EgjR6g8Ez4F0ouCghjcmV3X2tleRIiCiA5NGMzMGQ2YzNiMmFjOGZiOTRiMmRjZmM1NzJk
MGY1OUoxCgdjcmV3X2lkEiYKJDIzMzYzNGM2LWU2ZDYtNDllNi04OGFlLWVhZTFhMzliMGUwZkou
Cgh0YXNrX2tleRIiCiAzMjJkZGFlM2JjODBjMWQ0NWI4NWZhNzc1NmRiODY2NUoxCgd0YXNrX2lk
EiYKJDk1Y2E4ODQyLTZhMTItNDBkOS1iMGQyLTRiNDM2MWJiZTU2ZHoCGAGFAQABAAASkAIKEHqZ
L8s3clXQyVTemNcTCcQSCA0tzK95agRQKg5UYXNrIEV4ZWN1dGlvbjABOQC8HqDwTPgXQdgNSqDw
TPgXSi4KCGNyZXdfa2V5EiIKIDk0YzMwZDZjM2IyYWM4ZmI5NGIyZGNmYzU3MmQwZjU5SjEKB2Ny
ZXdfaWQSJgokMjMzNjM0YzYtZTZkNi00OWU2LTg4YWUtZWFlMWEzOWIwZTBmSi4KCHRhc2tfa2V5
EiIKIDMyMmRkYWUzYmM4MGMxZDQ1Yjg1ZmE3NzU2ZGI4NjY1SjEKB3Rhc2tfaWQSJgokOTVjYTg4
NDItNmExMi00MGQ5LWIwZDItNGI0MzYxYmJlNTZkegIYAYUBAAEAABKOAgoQjhKzodMUmQ8NWtdy
Uj99whIIBsGtAymZibwqDFRhc2sgQ3JlYXRlZDABOXjVVaDwTPgXQXhSVqDwTPgXSi4KCGNyZXdf
a2V5EiIKIDk0YzMwZDZjM2IyYWM4ZmI5NGIyZGNmYzU3MmQwZjU5SjEKB2NyZXdfaWQSJgokMjMz
NjM0YzYtZTZkNi00OWU2LTg4YWUtZWFlMWEzOWIwZTBmSi4KCHRhc2tfa2V5EiIKIDVlOWNhN2Q2
NGI0MjA1YmI3YzQ3ZTBiM2ZjYjVkMjFmSjEKB3Rhc2tfaWQSJgokOTcyOTE4NmMtZDdiZS00ZGI0
LWE5NGUtNjllOTk5NjUyNzAwegIYAYUBAAEAABKTAQoQx5IUsjAFMGNUaz5MHy20OBIIzl2tr25P
LL8qClRvb2wgVXNhZ2UwATkgt5Sg8Ez4F0GwFpag8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYw
LjYxLjBKHwoJdG9vbF9uYW1lEhIKEGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1wdHMSAhgBegIY
AYUBAAEAABKQAgoQEkfcfCrzTYIM6GQXhknlexIIa/oxeT78OL8qDlRhc2sgRXhlY3V0aW9uMAE5
WIFWoPBM+BdBuL/GoPBM+BdKLgoIY3Jld19rZXkSIgogOTRjMzBkNmMzYjJhYzhmYjk0YjJkY2Zj
NTcyZDBmNTlKMQoHY3Jld19pZBImCiQyMzM2MzRjNi1lNmQ2LTQ5ZTYtODhhZS1lYWUxYTM5YjBl
MGZKLgoIdGFza19rZXkSIgogNWU5Y2E3ZDY0YjQyMDViYjdjNDdlMGIzZmNiNWQyMWZKMQoHdGFz
a19pZBImCiQ5NzI5MTg2Yy1kN2JlLTRkYjQtYTk0ZS02OWU5OTk2NTI3MDB6AhgBhQEAAQAAEqwH
ChDrKBdEe+Z5276g9fgg6VzjEgiJfnDwsv1SrCoMQ3JldyBDcmVhdGVkMAE5MLQYofBM+BdBQFIa
ofBM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMu
MTEuN0ouCghjcmV3X2tleRIiCiA3M2FhYzI4NWU2NzQ2NjY3Zjc1MTQ3NjcwMDAzNDExMEoxCgdj
cmV3X2lkEiYKJDg0NDY0YjhlLTRiZjctNDRiYy05MmUxLWE4ZDE1NGZlNWZkN0ocCgxjcmV3X3By
b2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2Zf
dGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFKyQIKC2NyZXdfYWdlbnRzErkC
CrYCW3sia2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1ODJiIiwgImlkIjogIjk4
YmIwNGYxLTBhZGMtNGZiNC04YzM2LWM3M2Q1MzQ1ZGRhZCIsICJyb2xlIjogInRlc3Qgcm9sZSIs
ICJ2ZXJib3NlPyI6IHRydWUsICJtYXhfaXRlciI6IDEsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0
aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvIiwgImRlbGVnYXRpb25fZW5hYmxl
ZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xp
bWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUqQAgoKY3Jld190YXNrcxKBAgr+AVt7ImtleSI6
ICJmN2E5ZjdiYjFhZWU0YjZlZjJjNTI2ZDBhOGMyZjJhYyIsICJpZCI6ICIxZjRhYzJhYS03YmQ4
LTQ1NWQtODgyMC1jMzZmMjJjMDY4MzciLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVt
YW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogInRlc3Qgcm9sZSIsICJhZ2VudF9rZXki
OiAiZTE0OGU1MzIwMjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAidG9vbHNfbmFtZXMiOiBbImdl
dF9maW5hbF9hbnN3ZXIiXX1degIYAYUBAAEAABKOAgoQ0/vrakH7zD0uSvmVBUV8lxIIYe4YKcYG
hNgqDFRhc2sgQ3JlYXRlZDABOdBXKqHwTPgXQcCtKqHwTPgXSi4KCGNyZXdfa2V5EiIKIDczYWFj
Mjg1ZTY3NDY2NjdmNzUxNDc2NzAwMDM0MTEwSjEKB2NyZXdfaWQSJgokODQ0NjRiOGUtNGJmNy00
NGJjLTkyZTEtYThkMTU0ZmU1ZmQ3Si4KCHRhc2tfa2V5EiIKIGY3YTlmN2JiMWFlZTRiNmVmMmM1
MjZkMGE4YzJmMmFjSjEKB3Rhc2tfaWQSJgokMWY0YWMyYWEtN2JkOC00NTVkLTg4MjAtYzM2ZjIy
YzA2ODM3egIYAYUBAAEAABKkAQoQ5GDzHNlSdlcVDdxsI3abfRIIhYu8fZS3iA4qClRvb2wgVXNh
Z2UwATnIi2eh8Ez4F0FYbmih8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBKHwoJdG9v
bF9uYW1lEhIKEGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1wdHMSAhgBSg8KA2xsbRIICgZncHQt
NG96AhgBhQEAAQAAEpACChAy85Jfr/EEIe1THU8koXoYEgjlkNn7xfysjioOVGFzayBFeGVjdXRp
b24wATm42Cqh8Ez4F0GgxZah8Ez4F0ouCghjcmV3X2tleRIiCiA3M2FhYzI4NWU2NzQ2NjY3Zjc1
MTQ3NjcwMDAzNDExMEoxCgdjcmV3X2lkEiYKJDg0NDY0YjhlLTRiZjctNDRiYy05MmUxLWE4ZDE1
NGZlNWZkN0ouCgh0YXNrX2tleRIiCiBmN2E5ZjdiYjFhZWU0YjZlZjJjNTI2ZDBhOGMyZjJhY0ox
Cgd0YXNrX2lkEiYKJDFmNGFjMmFhLTdiZDgtNDU1ZC04ODIwLWMzNmYyMmMwNjgzN3oCGAGFAQAB
AAASrAcKEG0ZVq5Ww+/A0wOY3HmKgq4SCMe0ooxqjqBlKgxDcmV3IENyZWF0ZWQwATlwmISi8Ez4
F0HYUYai8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBKGgoOcHl0aG9uX3ZlcnNpb24S
CAoGMy4xMS43Si4KCGNyZXdfa2V5EiIKIGQ1NTExM2JlNGFhNDFiYTY0M2QzMjYwNDJiMmYwM2Yx
SjEKB2NyZXdfaWQSJgokNzkyMWVlYmItMWI4NS00MzNjLWIxMDAtZDU4MmMyOTg5MzBkShwKDGNy
ZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJl
cl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrJAgoLY3Jld19hZ2Vu
dHMSuQIKtgJbeyJrZXkiOiAiZTE0OGU1MzIwMjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAiaWQi
OiAiZmRiZDI1MWYtYzUwOC00YmFhLTkwNjctN2U5YzQ2ZGZiZTJhIiwgInJvbGUiOiAidGVzdCBy
b2xlIiwgInZlcmJvc2U/IjogdHJ1ZSwgIm1heF9pdGVyIjogNiwgIm1heF9ycG0iOiBudWxsLCAi
ZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9l
bmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0
cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSpACCgpjcmV3X3Rhc2tzEoECCv4BW3si
a2V5IjogIjRhMzFiODUxMzNhM2EyOTRjNjg1M2RhNzU3ZDRiYWU3IiwgImlkIjogIjA2YWFmM2Y1
LTE5ODctNDAxYS05Yzk0LWY3ZjM1YmQzMDg3OSIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2Us
ICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAidGVzdCByb2xlIiwgImFnZW50
X2tleSI6ICJlMTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJ0b29sc19uYW1lcyI6
IFsiZ2V0X2ZpbmFsX2Fuc3dlciJdfV16AhgBhQEAAQAAEo4CChDT+zPZHwfacDilkzaZJ9uGEgip
Kr5r62JB+ioMVGFzayBDcmVhdGVkMAE56KeTovBM+BdB8PmTovBM+BdKLgoIY3Jld19rZXkSIgog
ZDU1MTEzYmU0YWE0MWJhNjQzZDMyNjA0MmIyZjAzZjFKMQoHY3Jld19pZBImCiQ3OTIxZWViYi0x
Yjg1LTQzM2MtYjEwMC1kNTgyYzI5ODkzMGRKLgoIdGFza19rZXkSIgogNGEzMWI4NTEzM2EzYTI5
NGM2ODUzZGE3NTdkNGJhZTdKMQoHdGFza19pZBImCiQwNmFhZjNmNS0xOTg3LTQwMWEtOWM5NC1m
N2YzNWJkMzA4Nzl6AhgBhQEAAQAAEpMBChCl85ZcL2Fa0N5QTl6EsIfnEghyDo3bxT+AkyoKVG9v
bCBVc2FnZTABOVBA2aLwTPgXQYAy2qLwTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMEof
Cgl0b29sX25hbWUSEgoQZ2V0X2ZpbmFsX2Fuc3dlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
EpwBChB22uwKhaur9zmeoeEMaRKzEgjrtSEzMbRdIioTVG9vbCBSZXBlYXRlZCBVc2FnZTABOQga
C6PwTPgXQaDRC6PwTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMEofCgl0b29sX25hbWUS
EgoQZ2V0X2ZpbmFsX2Fuc3dlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpMBChArAfcRpE+W
02oszyzccbaWEghTAO9J3zq/kyoKVG9vbCBVc2FnZTABORBRTqPwTPgXQegnT6PwTPgXShoKDmNy
ZXdhaV92ZXJzaW9uEggKBjAuNjEuMEofCgl0b29sX25hbWUSEgoQZ2V0X2ZpbmFsX2Fuc3dlckoO
CghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpwBChBdtM3p3aqT7wTGaXi6el/4Egie6lFQpa+AfioT
VG9vbCBSZXBlYXRlZCBVc2FnZTABOdBg2KPwTPgXQehW2aPwTPgXShoKDmNyZXdhaV92ZXJzaW9u
EggKBjAuNjEuMEofCgl0b29sX25hbWUSEgoQZ2V0X2ZpbmFsX2Fuc3dlckoOCghhdHRlbXB0cxIC
GAF6AhgBhQEAAQAAEpMBChDq4OuaUKkNoi6jlMyahPJpEgg1MFDHktBxNSoKVG9vbCBVc2FnZTAB
ORD/K6TwTPgXQZgMLaTwTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMEofCgl0b29sX25h
bWUSEgoQZ2V0X2ZpbmFsX2Fuc3dlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpACChBhvTmu
QWP+bx9JMmGpt+w5Egh1J17yki7s8ioOVGFzayBFeGVjdXRpb24wATnoJJSi8Ez4F0HwNX6k8Ez4
F0ouCghjcmV3X2tleRIiCiBkNTUxMTNiZTRhYTQxYmE2NDNkMzI2MDQyYjJmMDNmMUoxCgdjcmV3
X2lkEiYKJDc5MjFlZWJiLTFiODUtNDMzYy1iMTAwLWQ1ODJjMjk4OTMwZEouCgh0YXNrX2tleRIi
CiA0YTMxYjg1MTMzYTNhMjk0YzY4NTNkYTc1N2Q0YmFlN0oxCgd0YXNrX2lkEiYKJDA2YWFmM2Y1
LTE5ODctNDAxYS05Yzk0LWY3ZjM1YmQzMDg3OXoCGAGFAQABAAASrg0KEOJZEqiJ7LTTX/J+tuLR
stQSCHKjy4tIcmKEKgxDcmV3IENyZWF0ZWQwATmIEuGk8Ez4F0FYDuOk8Ez4F0oaCg5jcmV3YWlf
dmVyc2lvbhIICgYwLjYxLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMS43Si4KCGNyZXdfa2V5
EiIKIDExMWI4NzJkOGYwY2Y3MDNmMmVmZWYwNGNmM2FjNzk4SjEKB2NyZXdfaWQSJgokYWFiYmU5
MmQtYjg3NC00NTZmLWE0NzAtM2FmMDc4ZTdjYThlShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50
aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGANKGwoVY3Jl
d19udW1iZXJfb2ZfYWdlbnRzEgIYAkqEBQoLY3Jld19hZ2VudHMS9AQK8QRbeyJrZXkiOiAiZTE0
OGU1MzIwMjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAiaWQiOiAiZmYzOTE0OGEtZWI2NS00Nzkx
LWI3MTMtM2Q4ZmE1YWQ5NTJlIiwgInJvbGUiOiAidGVzdCByb2xlIiwgInZlcmJvc2U/IjogZmFs
c2UsICJtYXhfaXRlciI6IDE1LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xs
bSI6ICIiLCAibGxtIjogImdwdC00byIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJh
bGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29s
c19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiZTdlOGVlYTg4NmJjYjhmMTA0NWFiZWVjZjE0MjVkYjci
LCAiaWQiOiAiYzYyNDJmNDMtNmQ2Mi00N2U4LTliYmMtNjM0ZDQwYWI4YTQ2IiwgInJvbGUiOiAi
dGVzdCByb2xlMiIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAxNSwgIm1heF9ycG0i
OiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVs
ZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2Us
ICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dStcFCgpjcmV3X3Rhc2tz
EsgFCsUFW3sia2V5IjogIjMyMmRkYWUzYmM4MGMxZDQ1Yjg1ZmE3NzU2ZGI4NjY1IiwgImlkIjog
IjRmZDZhZDdiLTFjNWMtNDE1ZC1hMWQ4LTgwYzExZGNjMTY4NiIsICJhc3luY19leGVjdXRpb24/
IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAidGVzdCByb2xl
IiwgImFnZW50X2tleSI6ICJlMTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJ0b29s
c19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiY2M0ODc2ZjZlNTg4ZTcxMzQ5YmJkM2E2NTg4OGMzZTki
LCAiaWQiOiAiOTFlYWFhMWMtMWI4ZC00MDcxLTk2ZmQtM2QxZWVkMjhjMzZjIiwgImFzeW5jX2V4
ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJ0
ZXN0IHJvbGUiLCAiYWdlbnRfa2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1ODJi
IiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICJlMGIxM2UxMGQ3YTE0NmRjYzRjNDg4ZmNm
OGQ3NDhhMCIsICJpZCI6ICI4NjExZjhjZS1jNDVlLTQ2OTgtYWEyMS1jMGJkNzdhOGY2ZWYiLCAi
YXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9y
b2xlIjogInRlc3Qgcm9sZTIiLCAiYWdlbnRfa2V5IjogImU3ZThlZWE4ODZiY2I4ZjEwNDVhYmVl
Y2YxNDI1ZGI3IiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEMbX6YsWK7RRf4L1
NBRKD6cSCFLJiNmspsyjKgxUYXNrIENyZWF0ZWQwATnonPGk8Ez4F0EotvKk8Ez4F0ouCghjcmV3
X2tleRIiCiAxMTFiODcyZDhmMGNmNzAzZjJlZmVmMDRjZjNhYzc5OEoxCgdjcmV3X2lkEiYKJGFh
YmJlOTJkLWI4NzQtNDU2Zi1hNDcwLTNhZjA3OGU3Y2E4ZUouCgh0YXNrX2tleRIiCiAzMjJkZGFl
M2JjODBjMWQ0NWI4NWZhNzc1NmRiODY2NUoxCgd0YXNrX2lkEiYKJDRmZDZhZDdiLTFjNWMtNDE1
ZC1hMWQ4LTgwYzExZGNjMTY4NnoCGAGFAQABAAASkAIKEM9JnUNanFbE9AtnSxqA7H8SCBWlG0WJ
sMgKKg5UYXNrIEV4ZWN1dGlvbjABOfDo8qTwTPgXQWhEH6XwTPgXSi4KCGNyZXdfa2V5EiIKIDEx
MWI4NzJkOGYwY2Y3MDNmMmVmZWYwNGNmM2FjNzk4SjEKB2NyZXdfaWQSJgokYWFiYmU5MmQtYjg3
NC00NTZmLWE0NzAtM2FmMDc4ZTdjYThlSi4KCHRhc2tfa2V5EiIKIDMyMmRkYWUzYmM4MGMxZDQ1
Yjg1ZmE3NzU2ZGI4NjY1SjEKB3Rhc2tfaWQSJgokNGZkNmFkN2ItMWM1Yy00MTVkLWExZDgtODBj
MTFkY2MxNjg2egIYAYUBAAEAABKOAgoQaQALCJNe5ByN4Wu7FE0kABIIYW/UfVfnYscqDFRhc2sg
Q3JlYXRlZDABOWhzLKXwTPgXQSD8LKXwTPgXSi4KCGNyZXdfa2V5EiIKIDExMWI4NzJkOGYwY2Y3
MDNmMmVmZWYwNGNmM2FjNzk4SjEKB2NyZXdfaWQSJgokYWFiYmU5MmQtYjg3NC00NTZmLWE0NzAt
M2FmMDc4ZTdjYThlSi4KCHRhc2tfa2V5EiIKIGNjNDg3NmY2ZTU4OGU3MTM0OWJiZDNhNjU4ODhj
M2U5SjEKB3Rhc2tfaWQSJgokOTFlYWFhMWMtMWI4ZC00MDcxLTk2ZmQtM2QxZWVkMjhjMzZjegIY
AYUBAAEAABKQAgoQpPfkgFlpIsR/eN2zn+x3MRIILoWF4/HvceAqDlRhc2sgRXhlY3V0aW9uMAE5
GCctpfBM+BdBQLNapfBM+BdKLgoIY3Jld19rZXkSIgogMTExYjg3MmQ4ZjBjZjcwM2YyZWZlZjA0
Y2YzYWM3OThKMQoHY3Jld19pZBImCiRhYWJiZTkyZC1iODc0LTQ1NmYtYTQ3MC0zYWYwNzhlN2Nh
OGVKLgoIdGFza19rZXkSIgogY2M0ODc2ZjZlNTg4ZTcxMzQ5YmJkM2E2NTg4OGMzZTlKMQoHdGFz
a19pZBImCiQ5MWVhYWExYy0xYjhkLTQwNzEtOTZmZC0zZDFlZWQyOGMzNmN6AhgBhQEAAQAAEo4C
ChCdvXmXZRltDxEwZx2XkhWhEghoKdomHHhLGSoMVGFzayBDcmVhdGVkMAE54HpmpfBM+BdB4Pdm
pfBM+BdKLgoIY3Jld19rZXkSIgogMTExYjg3MmQ4ZjBjZjcwM2YyZWZlZjA0Y2YzYWM3OThKMQoH
Y3Jld19pZBImCiRhYWJiZTkyZC1iODc0LTQ1NmYtYTQ3MC0zYWYwNzhlN2NhOGVKLgoIdGFza19r
ZXkSIgogZTBiMTNlMTBkN2ExNDZkY2M0YzQ4OGZjZjhkNzQ4YTBKMQoHdGFza19pZBImCiQ4NjEx
ZjhjZS1jNDVlLTQ2OTgtYWEyMS1jMGJkNzdhOGY2ZWZ6AhgBhQEAAQAAEpACChAIvs/XQL53haTt
NV8fk6geEgicgSOcpcYulyoOVGFzayBFeGVjdXRpb24wATnYImel8Ez4F0Gw5ZSl8Ez4F0ouCghj
cmV3X2tleRIiCiAxMTFiODcyZDhmMGNmNzAzZjJlZmVmMDRjZjNhYzc5OEoxCgdjcmV3X2lkEiYK
JGFhYmJlOTJkLWI4NzQtNDU2Zi1hNDcwLTNhZjA3OGU3Y2E4ZUouCgh0YXNrX2tleRIiCiBlMGIx
M2UxMGQ3YTE0NmRjYzRjNDg4ZmNmOGQ3NDhhMEoxCgd0YXNrX2lkEiYKJDg2MTFmOGNlLWM0NWUt
NDY5OC1hYTIxLWMwYmQ3N2E4ZjZlZnoCGAGFAQABAAASvAcKEARTPn0s+U/k8GclUc+5rRoSCHF3
KCh8OS0FKgxDcmV3IENyZWF0ZWQwATlo+Pul8Ez4F0EQ0f2l8Ez4F0oaCg5jcmV3YWlfdmVyc2lv
bhIICgYwLjYxLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMS43Si4KCGNyZXdfa2V5EiIKIDQ5
NGYzNjU3MjM3YWQ4YTMwMzViMmYxYmVlY2RjNjc3SjEKB2NyZXdfaWQSJgokOWMwNzg3NWUtMTMz
Mi00MmMzLWFhZTEtZjNjMjc1YTQyNjYwShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEK
C2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1i
ZXJfb2ZfYWdlbnRzEgIYAUrbAgoLY3Jld19hZ2VudHMSywIKyAJbeyJrZXkiOiAiZTE0OGU1MzIw
MjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAiaWQiOiAiNGFkYzNmMmItN2IwNC00MDRlLWEwNDQt
N2JkNjVmYTMyZmE4IiwgInJvbGUiOiAidGVzdCByb2xlIiwgInZlcmJvc2U/IjogZmFsc2UsICJt
YXhfaXRlciI6IDE1LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIi
LCAibGxtIjogImdwdC00byIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19j
b2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1l
cyI6IFsibGVhcm5fYWJvdXRfYWkiXX1dSo4CCgpjcmV3X3Rhc2tzEv8BCvwBW3sia2V5IjogImYy
NTk3Yzc4NjdmYmUzMjRkYzY1ZGMwOGRmZGJmYzZjIiwgImlkIjogIjg2YzZiODE2LTgyOWMtNDUx
Zi1iMDZkLTUyZjQ4YTdhZWJiMyIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9p
bnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAidGVzdCByb2xlIiwgImFnZW50X2tleSI6ICJl
MTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJ0b29sc19uYW1lcyI6IFsibGVhcm5f
YWJvdXRfYWkiXX1degIYAYUBAAEAABKOAgoQZWSU3+i71QSqlD8iiLdyWBII1Pawtza2ZHsqDFRh
c2sgQ3JlYXRlZDABOdj2FKbwTPgXQZhUFabwTPgXSi4KCGNyZXdfa2V5EiIKIDQ5NGYzNjU3MjM3
YWQ4YTMwMzViMmYxYmVlY2RjNjc3SjEKB2NyZXdfaWQSJgokOWMwNzg3NWUtMTMzMi00MmMzLWFh
ZTEtZjNjMjc1YTQyNjYwSi4KCHRhc2tfa2V5EiIKIGYyNTk3Yzc4NjdmYmUzMjRkYzY1ZGMwOGRm
ZGJmYzZjSjEKB3Rhc2tfaWQSJgokODZjNmI4MTYtODI5Yy00NTFmLWIwNmQtNTJmNDhhN2FlYmIz
egIYAYUBAAEAABKRAQoQl3nNMLhrOg+OgsWWX6A9LxIINbCKrQzQ3JkqClRvb2wgVXNhZ2UwATlA
TlCm8Ez4F0FASFGm8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBKHQoJdG9vbF9uYW1l
EhAKDmxlYXJuX2Fib3V0X0FJSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASkAIKEL9YI/QwoVBJ
1HBkTLyQxOESCCcKWhev/Dc8Kg5UYXNrIEV4ZWN1dGlvbjABOXiDFabwTPgXQcjEfqbwTPgXSi4K
CGNyZXdfa2V5EiIKIDQ5NGYzNjU3MjM3YWQ4YTMwMzViMmYxYmVlY2RjNjc3SjEKB2NyZXdfaWQS
JgokOWMwNzg3NWUtMTMzMi00MmMzLWFhZTEtZjNjMjc1YTQyNjYwSi4KCHRhc2tfa2V5EiIKIGYy
NTk3Yzc4NjdmYmUzMjRkYzY1ZGMwOGRmZGJmYzZjSjEKB3Rhc2tfaWQSJgokODZjNmI4MTYtODI5
Yy00NTFmLWIwNmQtNTJmNDhhN2FlYmIzegIYAYUBAAEAABLBBwoQ0Le1256mT8wmcvnuLKYeNRII
IYBlVsTs+qEqDENyZXcgQ3JlYXRlZDABOYCBiKrwTPgXQRBeiqrwTPgXShoKDmNyZXdhaV92ZXJz
aW9uEggKBjAuNjEuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgog
NDk0ZjM2NTcyMzdhZDhhMzAzNWIyZjFiZWVjZGM2NzdKMQoHY3Jld19pZBImCiQyN2VlMGYyYy1h
ZjgwLTQxYWMtYjg3ZC0xNmViYWQyMTVhNTJKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxK
EQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251
bWJlcl9vZl9hZ2VudHMSAhgBSuACCgtjcmV3X2FnZW50cxLQAgrNAlt7ImtleSI6ICJlMTQ4ZTUz
MjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJpZCI6ICJmMTYyMTFjNS00YWJlLTRhZDAtOWI0
YS0yN2RmMTJhODkyN2UiLCAicm9sZSI6ICJ0ZXN0IHJvbGUiLCAidmVyYm9zZT8iOiBmYWxzZSwg
Im1heF9pdGVyIjogMiwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAi
Z3B0LTRvIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAi
YWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9v
bHNfbmFtZXMiOiBbImxlYXJuX2Fib3V0X2FpIl19XUqOAgoKY3Jld190YXNrcxL/AQr8AVt7Imtl
eSI6ICJmMjU5N2M3ODY3ZmJlMzI0ZGM2NWRjMDhkZmRiZmM2YyIsICJpZCI6ICJjN2FiOWRiYi0y
MTc4LTRmOGItOGFiNi1kYTU1YzE0YTBkMGMiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAi
aHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogInRlc3Qgcm9sZSIsICJhZ2VudF9r
ZXkiOiAiZTE0OGU1MzIwMjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAidG9vbHNfbmFtZXMiOiBb
ImxlYXJuX2Fib3V0X2FpIl19XXoCGAGFAQABAAASjgIKECr4ueCUCo/tMB7EuBQt6TcSCD/UepYl
WGqAKgxUYXNrIENyZWF0ZWQwATk4kpyq8Ez4F0Hg85yq8Ez4F0ouCghjcmV3X2tleRIiCiA0OTRm
MzY1NzIzN2FkOGEzMDM1YjJmMWJlZWNkYzY3N0oxCgdjcmV3X2lkEiYKJDI3ZWUwZjJjLWFmODAt
NDFhYy1iODdkLTE2ZWJhZDIxNWE1MkouCgh0YXNrX2tleRIiCiBmMjU5N2M3ODY3ZmJlMzI0ZGM2
NWRjMDhkZmRiZmM2Y0oxCgd0YXNrX2lkEiYKJGM3YWI5ZGJiLTIxNzgtNGY4Yi04YWI2LWRhNTVj
MTRhMGQwY3oCGAGFAQABAAASeQoQkj0vmbCBIZPi33W9KrvrYhIIM2g73dOAN9QqEFRvb2wgVXNh
Z2UgRXJyb3IwATnQgsyr8Ez4F0GghM2r8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBK
DwoDbGxtEggKBmdwdC00b3oCGAGFAQABAAASeQoQavr4/1SWr8x7HD5mAzlM0hIIXPx740Skkd0q
EFRvb2wgVXNhZ2UgRXJyb3IwATkouH9C8Uz4F0FQ1YBC8Uz4F0oaCg5jcmV3YWlfdmVyc2lvbhII
CgYwLjYxLjBKDwoDbGxtEggKBmdwdC00b3oCGAGFAQABAAASkAIKEIgmJ3QURJvSsEifMScSiUsS
CCyiPHcZT8AnKg5UYXNrIEV4ZWN1dGlvbjABOcAinarwTPgXQeBEynvxTPgXSi4KCGNyZXdfa2V5
EiIKIDQ5NGYzNjU3MjM3YWQ4YTMwMzViMmYxYmVlY2RjNjc3SjEKB2NyZXdfaWQSJgokMjdlZTBm
MmMtYWY4MC00MWFjLWI4N2QtMTZlYmFkMjE1YTUySi4KCHRhc2tfa2V5EiIKIGYyNTk3Yzc4Njdm
YmUzMjRkYzY1ZGMwOGRmZGJmYzZjSjEKB3Rhc2tfaWQSJgokYzdhYjlkYmItMjE3OC00ZjhiLThh
YjYtZGE1NWMxNGEwZDBjegIYAYUBAAEAABLEBwoQY+GZuYkP6mwdaVQQc11YuhII7ADKOlFZlzQq
DENyZXcgQ3JlYXRlZDABObCoi3zxTPgXQeCUjXzxTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAu
NjEuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogN2U2NjA4OTg5
ODU5YTY3ZWVjODhlZWY3ZmNlODUyMjVKMQoHY3Jld19pZBImCiQxMmE0OTFlNS00NDgwLTQ0MTYt
OTAxYi1iMmI1N2U1ZWU4ZThKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19t
ZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9h
Z2VudHMSAhgBSt8CCgtjcmV3X2FnZW50cxLPAgrMAlt7ImtleSI6ICIyMmFjZDYxMWU0NGVmNWZh
YzA1YjUzM2Q3NWU4ODkzYiIsICJpZCI6ICI5NjljZjhlMy0yZWEwLTQ5ZjgtODNlMS02MzEzYmE4
ODc1ZjUiLCAicm9sZSI6ICJEYXRhIFNjaWVudGlzdCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4
X2l0ZXIiOiAxNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwg
ImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29k
ZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMi
OiBbImdldCBncmVldGluZ3MiXX1dSpICCgpjcmV3X3Rhc2tzEoMCCoACW3sia2V5IjogImEyNzdi
MzRiMmMxNDZmMGM1NmM1ZTEzNTZlOGY4YTU3IiwgImlkIjogImIwMTg0NTI2LTJlOWItNDA0My1h
M2JiLTFiM2QzNWIxNTNhOCIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1
dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiRGF0YSBTY2llbnRpc3QiLCAiYWdlbnRfa2V5Ijog
IjIyYWNkNjExZTQ0ZWY1ZmFjMDViNTMzZDc1ZTg4OTNiIiwgInRvb2xzX25hbWVzIjogWyJnZXQg
Z3JlZXRpbmdzIl19XXoCGAGFAQABAAASjgIKEI/rrKkPz08VpVWNehfvxJ0SCIpeq76twGj3KgxU
YXNrIENyZWF0ZWQwATlA9aR88Uz4F0HoVqV88Uz4F0ouCghjcmV3X2tleRIiCiA3ZTY2MDg5ODk4
NTlhNjdlZWM4OGVlZjdmY2U4NTIyNUoxCgdjcmV3X2lkEiYKJDEyYTQ5MWU1LTQ0ODAtNDQxNi05
MDFiLWIyYjU3ZTVlZThlOEouCgh0YXNrX2tleRIiCiBhMjc3YjM0YjJjMTQ2ZjBjNTZjNWUxMzU2
ZThmOGE1N0oxCgd0YXNrX2lkEiYKJGIwMTg0NTI2LTJlOWItNDA0My1hM2JiLTFiM2QzNWIxNTNh
OHoCGAGFAQABAAASkAEKEKKr5LR8SkqfqqktFhniLdkSCPMnqI2ma9UoKgpUb29sIFVzYWdlMAE5
sCHgfPFM+BdB+A/hfPFM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShwKCXRvb2xfbmFt
ZRIPCg1HZXQgR3JlZXRpbmdzSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASkAIKEOj2bALdBlz6
1kP1MvHE5T0SCLw4D7D331IOKg5UYXNrIEV4ZWN1dGlvbjABOeCBpXzxTPgXQSjiEH3xTPgXSi4K
CGNyZXdfa2V5EiIKIDdlNjYwODk4OTg1OWE2N2VlYzg4ZWVmN2ZjZTg1MjI1SjEKB2NyZXdfaWQS
JgokMTJhNDkxZTUtNDQ4MC00NDE2LTkwMWItYjJiNTdlNWVlOGU4Si4KCHRhc2tfa2V5EiIKIGEy
NzdiMzRiMmMxNDZmMGM1NmM1ZTEzNTZlOGY4YTU3SjEKB3Rhc2tfaWQSJgokYjAxODQ1MjYtMmU5
Yi00MDQzLWEzYmItMWIzZDM1YjE1M2E4egIYAYUBAAEAABLQBwoQLjz7NWyGPgGU4tVFJ0sh9BII
N6EzU5f/sykqDENyZXcgQ3JlYXRlZDABOajOcX3xTPgXQUCAc33xTPgXShoKDmNyZXdhaV92ZXJz
aW9uEggKBjAuNjEuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgog
YzMwNzYwMDkzMjY3NjE0NDRkNTdjNzFkMWRhM2YyN2NKMQoHY3Jld19pZBImCiQ1N2Y0NjVhNC03
Zjk1LTQ5Y2MtODNmZC0zZTIwNWRhZDBjZTJKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxK
EQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251
bWJlcl9vZl9hZ2VudHMSAhgBSuUCCgtjcmV3X2FnZW50cxLVAgrSAlt7ImtleSI6ICI5OGYzYjFk
NDdjZTk2OWNmMDU3NzI3Yjc4NDE0MjVjZCIsICJpZCI6ICJjZjcyZDlkNy01MjQwLTRkMzEtYjA2
Mi0xMmNjMDU2OGNjM2MiLCAicm9sZSI6ICJGcmllbmRseSBOZWlnaGJvciIsICJ2ZXJib3NlPyI6
IGZhbHNlLCAibWF4X2l0ZXIiOiAxNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGlu
Z19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNl
LCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAi
dG9vbHNfbmFtZXMiOiBbImRlY2lkZSBncmVldGluZ3MiXX1dSpgCCgpjcmV3X3Rhc2tzEokCCoYC
W3sia2V5IjogIjgwZDdiY2Q0OTA5OTI5MDA4MzgzMmYwZTk4MzM4MGRmIiwgImlkIjogIjUxNTJk
MmQ2LWYwODYtNGIyMi1hOGMxLTMyODA5NzU1NjZhZCIsICJhc3luY19leGVjdXRpb24/IjogZmFs
c2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiRnJpZW5kbHkgTmVpZ2hi
b3IiLCAiYWdlbnRfa2V5IjogIjk4ZjNiMWQ0N2NlOTY5Y2YwNTc3MjdiNzg0MTQyNWNkIiwgInRv
b2xzX25hbWVzIjogWyJkZWNpZGUgZ3JlZXRpbmdzIl19XXoCGAGFAQABAAASjgIKEM+95r2LzVVg
kqAMolHjl9oSCN9WyhdF/ucVKgxUYXNrIENyZWF0ZWQwATnoCoJ98Uz4F0HwXIJ98Uz4F0ouCghj
cmV3X2tleRIiCiBjMzA3NjAwOTMyNjc2MTQ0NGQ1N2M3MWQxZGEzZjI3Y0oxCgdjcmV3X2lkEiYK
JDU3ZjQ2NWE0LTdmOTUtNDljYy04M2ZkLTNlMjA1ZGFkMGNlMkouCgh0YXNrX2tleRIiCiA4MGQ3
YmNkNDkwOTkyOTAwODM4MzJmMGU5ODMzODBkZkoxCgd0YXNrX2lkEiYKJDUxNTJkMmQ2LWYwODYt
NGIyMi1hOGMxLTMyODA5NzU1NjZhZHoCGAGFAQABAAASkwEKENJjTKn4eTP/P11ERMIGcdYSCIKF
bGEmcS7bKgpUb29sIFVzYWdlMAE5EFu5ffFM+BdBoD26ffFM+BdKGgoOY3Jld2FpX3ZlcnNpb24S
CAoGMC42MS4wSh8KCXRvb2xfbmFtZRISChBEZWNpZGUgR3JlZXRpbmdzSg4KCGF0dGVtcHRzEgIY
AXoCGAGFAQABAAASkAIKEG29htC06tLF7ihE5Yz6NyMSCAAsKzOcj25nKg5UYXNrIEV4ZWN1dGlv
bjABOQCEgn3xTPgXQfgg7X3xTPgXSi4KCGNyZXdfa2V5EiIKIGMzMDc2MDA5MzI2NzYxNDQ0ZDU3
YzcxZDFkYTNmMjdjSjEKB2NyZXdfaWQSJgokNTdmNDY1YTQtN2Y5NS00OWNjLTgzZmQtM2UyMDVk
YWQwY2UySi4KCHRhc2tfa2V5EiIKIDgwZDdiY2Q0OTA5OTI5MDA4MzgzMmYwZTk4MzM4MGRmSjEK
B3Rhc2tfaWQSJgokNTE1MmQyZDYtZjA4Ni00YjIyLWE4YzEtMzI4MDk3NTU2NmFkegIYAYUBAAEA
AA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '18925'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Tue, 24 Sep 2024 21:57:39 GMT
status:
code: 200
message: OK
- request:
body: '{"model": "gemma2:latest", "prompt": "### User:\nRespond in 20 words. Who
are you?\n\n", "options": {}, "stream": false}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '120'
Content-Type:
- application/json
User-Agent:
- python-requests/2.31.0
method: POST
uri: http://localhost:8080/api/generate
response:
body:
string: '{"model":"gemma2:latest","created_at":"2024-09-24T21:57:51.284303Z","response":"I
am Gemma, an open-weights AI assistant developed by Google DeepMind. \n","done":true,"done_reason":"stop","context":[106,1645,108,6176,4926,235292,108,54657,575,235248,235284,235276,3907,235265,7702,708,692,235336,109,107,108,106,2516,108,235285,1144,137061,235269,671,2174,235290,30316,16481,20409,6990,731,6238,20555,35777,235265,139,108],"total_duration":14046647083,"load_duration":12942541833,"prompt_eval_count":25,"prompt_eval_duration":177695000,"eval_count":19,"eval_duration":923120000}'
headers:
Content-Length:
- '579'
Content-Type:
- application/json; charset=utf-8
Date:
- Tue, 24 Sep 2024 21:57:51 GMT
status:
code: 200
message: OK
version: 1

36
tests/cassettes/test_agent_with_ollama_llama3.yaml Normal file
View File

@@ -0,0 +1,36 @@
interactions:
- request:
body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Who
which model are you?\n\n", "options": {"stop": ["\nObservation:"]}, "stream":
false}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '156'
Content-Type:
- application/json
User-Agent:
- python-requests/2.32.3
method: POST
uri: http://localhost:11434/api/generate
response:
body:
string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:07:07.623404Z","response":"I''m
an AI designed to assist and communicate with users, utilizing a combination
of natural language processing models.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,10699,902,1646,527,499,1980,128009,128006,78191,128007,271,40,2846,459,15592,6319,311,7945,323,19570,449,3932,11,35988,264,10824,315,5933,4221,8863,4211,13],"total_duration":1076617833,"load_duration":46505416,"prompt_eval_count":40,"prompt_eval_duration":626000000,"eval_count":22,"eval_duration":399000000}'
headers:
Content-Length:
- '690'
Content-Type:
- application/json; charset=utf-8
Date:
- Thu, 02 Jan 2025 20:07:07 GMT
status:
code: 200
message: OK
version: 1

243
tests/cassettes/test_crew_output_file_end_to_end.yaml Normal file
View File

@@ -0,0 +1,243 @@
interactions:
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '3685'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Sun, 29 Dec 2024 04:43:27 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You have
extensive AI research experience.\nYour personal goal is: Analyze AI topics\nTo
give my best complete final answer to the task use 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: Explain the advantages of AI.\n\nThis is the expect criteria for your
final answer: A summary of the main advantages, bullet points recommended.\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-mini", "stop":
["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '922'
content-type:
- application/json
cookie:
- _cfuvid=eff7OIkJ0zWRunpA6z67LHqscmSe6XjNxXiPw1R3xCc-1733770413538-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- x64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- Linux
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:
content: "{\n \"id\": \"chatcmpl-AjfR6FDuTw7NGzy8w7sxjvOkUQlru\",\n \"object\":
\"chat.completion\",\n \"created\": 1735447404,\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: \\n**Advantages of AI** \\n\\n1. **Increased Efficiency and Productivity**
\ \\n - AI systems can process large amounts of data quickly and accurately,
leading to faster decision-making and increased productivity in various sectors.\\n\\n2.
**Cost Savings** \\n - Automation of repetitive and time-consuming tasks
reduces labor costs and increases operational efficiency, allowing businesses
to allocate resources more effectively.\\n\\n3. **Enhanced Data Analysis** \\n
\ - AI excels at analyzing big data, identifying patterns, and providing insights
that support better strategic planning and business decision-making.\\n\\n4.
**24/7 Availability** \\n - AI solutions, such as chatbots and virtual assistants,
operate continuously without breaks, offering constant support and customer
service, enhancing user experience.\\n\\n5. **Personalization** \\n - AI
enables the customization of content, products, and services based on user preferences
and behaviors, leading to improved customer satisfaction and loyalty.\\n\\n6.
**Improved Accuracy** \\n - AI technologies, such as machine learning algorithms,
reduce the likelihood of human error in various processes, leading to greater
accuracy and reliability.\\n\\n7. **Enhanced Innovation** \\n - AI fosters
innovative solutions by providing new tools and approaches to problem-solving,
enabling companies to develop cutting-edge products and services.\\n\\n8. **Scalability**
\ \\n - AI can be scaled to handle varying amounts of workloads without significant
changes to infrastructure, making it easier for organizations to expand operations.\\n\\n9.
**Predictive Capabilities** \\n - Advanced analytics powered by AI can anticipate
trends and outcomes, allowing businesses to proactively adjust strategies and
improve forecasting.\\n\\n10. **Health Benefits** \\n - In healthcare, AI
assists in diagnostics, personalized treatment plans, and predictive analytics,
leading to better patient care and improved health outcomes.\\n\\n11. **Safety
and Risk Mitigation** \\n - AI can enhance safety in various industries
by taking over dangerous tasks, monitoring for hazards, and predicting maintenance
needs for critical machinery, thereby preventing accidents.\\n\\n12. **Reduced
Environmental Impact** \\n - AI can optimize resource usage in areas such
as energy consumption and supply chain logistics, contributing to sustainability
efforts and reducing overall environmental footprints.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 168,\n \"completion_tokens\":
440,\n \"total_tokens\": 608,\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_0aa8d3e20b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8f9721053d1eb9f1-SEA
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 29 Dec 2024 04:43:32 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=5enubNIoQSGMYEgy8Q2FpzzhphA0y.0lXukRZrWFvMk-1735447412-1.0.1.1-FIK1sMkUl3YnW1gTC6ftDtb2mKsbosb4mwabdFAlWCfJ6pXeavYq.bPsfKNvzAb5WYq60yVGH5lHsJT05bhSgw;
path=/; expires=Sun, 29-Dec-24 05:13:32 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=63wmKMTuFamkLN8FBI4fP8JZWbjWiRxWm7wb3kz.z_A-1735447412038-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
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:
- '7577'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999793'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_55b8d714656e8f10f4e23cbe9034d66b
http_version: HTTP/1.1
status_code: 200
version: 1

556
tests/cassettes/test_crew_with_delegating_agents.yaml
View File

@@ -3,223 +3,17 @@ interactions:
body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\nYour
personal goal is: Make sure the writers in your company produce amazing content.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate 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
context to execute the task, they know nothing about the task, so share absolute
everything you know, don''t reference things but instead explain them.\nTool
Arguments: {''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'':
{''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Ask 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 necessary context to ask the question properly,
they know nothing about the question, so share absolute everything you know,
don''t reference things but instead explain them.\nTool Arguments: {''question'':
{''title'': ''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'',
''type'': ''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [Delegate work to coworker, Ask question to coworker],
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\n"}, {"role": "user", "content":
"\nCurrent Task: Produce and amazing 1 paragraph draft of an article about AI
Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
article about AI.\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:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2762'
content-type:
- 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:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
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-AB7ZvxqgeOayGTQWwR61ASlZp0s74\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214103,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: To ensure the content is amazing,
I'll delegate the task of producing a one-paragraph draft of an article about
AI Agents to the Senior Writer with all necessary context.\\n\\nAction: Delegate
work to coworker\\nAction Input: \\n{\\n \\\"coworker\\\": \\\"Senior Writer\\\",
\\n \\\"task\\\": \\\"Produce a one paragraph draft of an article about AI
Agents\\\", \\n \\\"context\\\": \\\"We need an amazing one-paragraph draft
as the beginning of a 4-paragraph article about AI Agents. This is for a high-stakes
project that critically impacts our company. The paragraph should highlight
what AI Agents are, their significance, and how they are transforming various
industries. The tone should be professional yet engaging. Make sure the content
is original, insightful, and thoroughly researched.\\\"\\n}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 608,\n \"completion_tokens\":
160,\n \"total_tokens\": 768,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f0b038a71cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:41:45 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1826'
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:
- '29999325'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_79054638deeb01da76c5bba273bffc28
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1842'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Tue, 24 Sep 2024 21:41:46 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Senior Writer. You''re
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
personal goal is: Write the best content about AI and AI agents.\nTo give my
best complete final answer to the task use the exact following format:\n\nThought:
personal goal is: Make sure the writers in your company produce amazing content.\nTo
give my best complete final answer to the task use 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: Produce a one paragraph draft of an article about AI Agents\n\nThis is
the expect criteria for your final answer: Your best answer to your coworker
asking you this, accounting for the context shared.\nyou MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\nWe need an amazing one-paragraph draft as the beginning
of a 4-paragraph article about AI Agents. This is for a high-stakes project
that critically impacts our company. The paragraph should highlight what AI
Agents are, their significance, and how they are transforming various industries.
The tone should be professional yet engaging. Make sure the content is original,
insightful, and thoroughly researched.\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"}'
Task: Produce and amazing 1 paragraph draft of an article about AI Agents.\n\nThis
is the expect criteria for your final answer: A 4 paragraph article about AI.\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-mini", "stop":
["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
@@ -228,16 +22,13 @@ interactions:
connection:
- keep-alive
content-length:
- '1545'
- '1105'
content-type:
- 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:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
@@ -247,9 +38,11 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
@@ -257,31 +50,51 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7ZxDYcPlSiBZsftdRs2cWbUJllW\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214105,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-Ahe7liUPejwfqxMe8aEWmKGJ837em\",\n \"object\":
\"chat.completion\",\n \"created\": 1734965705,\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: Artificial Intelligence (AI) Agents are sophisticated computer programs
designed to perform tasks that typically require human intelligence, such as
decision making, problem-solving, and learning. These agents operate autonomously,
utilizing vast amounts of data, advanced algorithms, and machine learning techniques
to analyze their environment, adapt to new information, and improve their performance
over time. The significance of AI Agents lies in their transformative potential
across various industries. In healthcare, they assist in diagnosing diseases
with greater accuracy; in finance, they predict market trends and manage risks;
in customer service, they provide personalized and efficient responses. As these
AI-powered entities continue to evolve, they are not only enhancing operational
efficiencies but also driving innovation and creating new opportunities for
growth and development in every sector they penetrate.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 297,\n \"completion_tokens\":
160,\n \"total_tokens\": 457,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
Answer: In the rapidly evolving landscape of technology, AI agents have emerged
as formidable tools, revolutionizing how we interact with data and automate
tasks. These sophisticated systems leverage machine learning and natural language
processing to perform a myriad of functions, from virtual personal assistants
to complex decision-making companions in industries such as finance, healthcare,
and education. By mimicking human intelligence, AI agents can analyze massive
data sets at unparalleled speeds, enabling businesses to uncover valuable insights,
enhance productivity, and elevate user experiences to unprecedented levels.\\n\\nOne
of the most striking aspects of AI agents is their adaptability; they learn
from their interactions and continuously improve their performance over time.
This feature is particularly valuable in customer service where AI agents can
address inquiries, resolve issues, and provide personalized recommendations
without the limitations of human fatigue. Moreover, with intuitive interfaces,
AI agents enhance user interactions, making technology more accessible and user-friendly,
thereby breaking down barriers that have historically hindered digital engagement.\\n\\nDespite
their immense potential, the deployment of AI agents raises important ethical
and practical considerations. Issues related to privacy, data security, and
the potential for job displacement necessitate thoughtful dialogue and proactive
measures. Striking a balance between technological innovation and societal impact
will be crucial as organizations integrate these agents into their operations.
Additionally, ensuring transparency in AI decision-making processes is vital
to maintain public trust as AI agents become an integral part of daily life.\\n\\nLooking
ahead, the future of AI agents appears bright, with ongoing advancements promising
even greater capabilities. As we continue to harness the power of AI, we can
expect these agents to play a transformative role in shaping various sectors\u2014streamlining
workflows, enabling smarter decision-making, and fostering more personalized
experiences. Embracing this technology responsibly can lead to a future where
AI agents not only augment human effort but also inspire creativity and efficiency
across the board, ultimately redefining our interaction with the digital world.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 208,\n \"completion_tokens\":
382,\n \"total_tokens\": 590,\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_0aa8d3e20b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f0c0cf961cf3-GRU
- 8f6930c97a33ae54-GRU
Connection:
- keep-alive
Content-Encoding:
@@ -289,45 +102,77 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:41:48 GMT
- Mon, 23 Dec 2024 14:55:10 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=g58erGPkGAltcfYpDRU4IsdEEzb955dGmBOAZacFlPA-1734965710-1.0.1.1-IiodiX3uxbT5xSa4seI7M.gRM4Jj46h2d6ZW2wCkSUYUAX.ivRh_sGQN2hucEMzdG8O87pc00dCl7E5W8KkyEA;
path=/; expires=Mon, 23-Dec-24 15:25:10 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=eQzzWvIXDS8Me1OIBdCG5F1qFyVfAo3sumvYRE7J41E-1734965710778-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
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:
- '2468'
- '5401'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
- '30000'
x-ratelimit-limit-tokens:
- '30000000'
- '150000000'
x-ratelimit-remaining-requests:
- '9999'
- '29999'
x-ratelimit-remaining-tokens:
- '29999625'
- '149999746'
x-ratelimit-reset-requests:
- 6ms
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_66c8801b42ac865249246d98225c1492
- req_30791533923ae20626ef35a03ae66172
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CtwBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSswEKEgoQY3Jld2FpLnRl
bGVtZXRyeRKcAQoQROg/k5NCUGdgfvfLrFlQDxIIlfh6oMbmqu0qClRvb2wgVXNhZ2UwATlws+Wj
FEz4F0EwBeijFEz4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBKKAoJdG9vbF9uYW1lEhsK
GURlbGVnYXRlIHdvcmsgdG8gY293b3JrZXJKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAAA==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headers:
Accept:
- '*/*'
@@ -336,7 +181,7 @@ interactions:
Connection:
- keep-alive
Content-Length:
- '223'
- '1577'
Content-Type:
- application/x-protobuf
User-Agent:
@@ -352,213 +197,8 @@ interactions:
Content-Type:
- application/x-protobuf
Date:
- Tue, 24 Sep 2024 21:41:51 GMT
- Mon, 23 Dec 2024 14:55:10 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\nYour
personal goal is: Make sure the writers in your company produce amazing content.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Delegate work to coworker(task: str, context:
str, coworker: Optional[str] = None, **kwargs)\nTool Description: Delegate 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
context to execute the task, they know nothing about the task, so share absolute
everything you know, don''t reference things but instead explain them.\nTool
Arguments: {''task'': {''title'': ''Task'', ''type'': ''string''}, ''context'':
{''title'': ''Context'', ''type'': ''string''}, ''coworker'': {''title'': ''Coworker'',
''type'': ''string''}, ''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\nTool
Name: Ask question to coworker(question: str, context: str, coworker: Optional[str]
= None, **kwargs)\nTool Description: Ask 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 necessary context to ask the question properly,
they know nothing about the question, so share absolute everything you know,
don''t reference things but instead explain them.\nTool Arguments: {''question'':
{''title'': ''Question'', ''type'': ''string''}, ''context'': {''title'': ''Context'',
''type'': ''string''}, ''coworker'': {''title'': ''Coworker'', ''type'': ''string''},
''kwargs'': {''title'': ''Kwargs'', ''type'': ''object''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [Delegate work to coworker, Ask question to coworker],
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\n"}, {"role": "user", "content":
"\nCurrent Task: Produce and amazing 1 paragraph draft of an article about AI
Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
article about AI.\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": "Thought: To ensure the content is amazing,
I''ll delegate the task of producing a one-paragraph draft of an article about
AI Agents to the Senior Writer with all necessary context.\n\nAction: Delegate
work to coworker\nAction Input: \n{\n \"coworker\": \"Senior Writer\", \n \"task\":
\"Produce a one paragraph draft of an article about AI Agents\", \n \"context\":
\"We need an amazing one-paragraph draft as the beginning of a 4-paragraph article
about AI Agents. This is for a high-stakes project that critically impacts our
company. The paragraph should highlight what AI Agents are, their significance,
and how they are transforming various industries. The tone should be professional
yet engaging. Make sure the content is original, insightful, and thoroughly
researched.\"\n}\nObservation: Artificial Intelligence (AI) Agents are sophisticated
computer programs designed to perform tasks that typically require human intelligence,
such as decision making, problem-solving, and learning. These agents operate
autonomously, utilizing vast amounts of data, advanced algorithms, and machine
learning techniques to analyze their environment, adapt to new information,
and improve their performance over time. The significance of AI Agents lies
in their transformative potential across various industries. In healthcare,
they assist in diagnosing diseases with greater accuracy; in finance, they predict
market trends and manage risks; in customer service, they provide personalized
and efficient responses. As these AI-powered entities continue to evolve, they
are not only enhancing operational efficiencies but also driving innovation
and creating new opportunities for growth and development in every sector they
penetrate."}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4536'
content-type:
- 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:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
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-AB7a1PO3pMNybn76wXDFc5HE7ZRsL\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214109,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: The paragraph provided by the
Senior Writer is well-detailed and engaging. I will now structure the 4-paragraph
article around this draft, adding an introduction, expanding on the specific
applications in various industries, and concluding with the potential future
impact of AI Agents.\\n\\nFinal Answer:\\n\\nArtificial Intelligence (AI) Agents
are sophisticated computer programs designed to perform tasks that typically
require human intelligence, such as decision making, problem-solving, and learning.
These agents operate autonomously, utilizing vast amounts of data, advanced
algorithms, and machine learning techniques to analyze their environment, adapt
to new information, and improve their performance over time.\\n\\nThe significance
of AI Agents lies in their transformative potential across various industries.
In healthcare, for example, they assist in diagnosing diseases with greater
accuracy and speed than human practitioners, offering personalized treatment
plans by analyzing patient data. In finance, AI Agents predict market trends,
manage risks, and even execute trades, contributing to more stable and profitable
financial systems. Customer service sectors benefit significantly from AI Agents,
as they provide personalized and efficient responses, often resolving issues
faster than traditional methods.\\n\\nMoreover, AI Agents are also making substantial
contributions in fields like education and manufacturing. In education, they
offer tailored learning experiences by assessing individual student needs and
adjusting teaching methods accordingly. They help educators identify students
who might need additional support and provide resources to enhance learning
outcomes. In manufacturing, AI Agents optimize production lines, predict equipment
failures, and improve supply chain management, thus boosting productivity and
reducing downtime.\\n\\nAs these AI-powered entities continue to evolve, they
are not only enhancing operational efficiencies but also driving innovation
and creating new opportunities for growth and development in every sector they
penetrate. The future of AI Agents looks promising, with the potential to revolutionize
the way we live and work, making processes more efficient, decisions more data-driven,
and solutions more innovative than ever before.\\n\\nThis is now a well-rounded,
four-paragraph article that comprehensively covers the topic of AI Agents.\\n\\nFinal
Answer: This is the complete content as specified:\\nArtificial Intelligence
(AI) Agents are sophisticated computer programs designed to perform tasks that
typically require human intelligence, such as decision making, problem-solving,
and learning. These agents operate autonomously, utilizing vast amounts of data,
advanced algorithms, and machine learning techniques to analyze their environment,
adapt to new information, and improve their performance over time.\\n\\nThe
significance of AI Agents lies in their transformative potential across various
industries. In healthcare, for example, they assist in diagnosing diseases with
greater accuracy and speed than human practitioners, offering personalized treatment
plans by analyzing patient data. In finance, AI Agents predict market trends,
manage risks, and even execute trades, contributing to more stable and profitable
financial systems. Customer service sectors benefit significantly from AI Agents,
as they provide personalized and efficient responses, often resolving issues
faster than traditional methods.\\n\\nMoreover, AI Agents are also making substantial
contributions in fields like education and manufacturing. In education, they
offer tailored learning experiences by assessing individual student needs and
adjusting teaching methods accordingly. They help educators identify students
who might need additional support and provide resources to enhance learning
outcomes. In manufacturing, AI Agents optimize production lines, predict equipment
failures, and improve supply chain management, thus boosting productivity and
reducing downtime.\\n\\nAs these AI-powered entities continue to evolve, they
are not only enhancing operational efficiencies but also driving innovation
and creating new opportunities for growth and development in every sector they
penetrate. The future of AI Agents looks promising, with the potential to revolutionize
the way we live and work, making processes more efficient, decisions more data-driven,
and solutions more innovative than ever before.\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 923,\n \"completion_tokens\":
715,\n \"total_tokens\": 1638,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f0d2f90c1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:41:58 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '8591'
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:
- '29998895'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_2b51b5cff02148d29b04284b40ca6081
http_version: HTTP/1.1
status_code: 200
version: 1

480
tests/cassettes/test_crew_with_delegating_agents_should_not_override_agent_tools.yaml Normal file
View File

@@ -0,0 +1,480 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\nYour
personal goal is: Make sure the writers in your company produce amazing content.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
just returns the input\n\nUse the following format:\n\nThought: you should always
think about what to do\nAction: the action to take, only one name of [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: Produce and amazing 1 paragraph draft of an article about AI
Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
article about AI.\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-mini", "stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1581'
content-type:
- application/json
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:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AhLsKP8xKkISk8ntUscyUKL30xRXW\",\n \"object\":
\"chat.completion\",\n \"created\": 1734895556,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to gather information to create
an amazing paragraph draft about AI Agents that aligns with the expected criteria
of a 4-paragraph article about AI. \\n\\nAction: Test Tool \\nAction Input:
{\\\"query\\\": \\\"Write a captivating and informative paragraph about AI Agents,
focusing on their capabilities, applications, and significance in modern technology.\\\"}
\ \",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 309,\n \"completion_tokens\":
68,\n \"total_tokens\": 377,\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_0aa8d3e20b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8f62802d0b3f00d5-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 22 Dec 2024 19:25:57 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=vwBNilrHRgMLd8ALWzYrBO5Lm8ieJzbQ3WCVOgmuJ.s-1734895557-1.0.1.1-z.QnDsynL_Ndu.JkWrh_wGMo57vvpK88nWDBTA8P.6prlSRmA91GQLpP62yRUbCW6yoKFbDxroSaYO6qrzZPRg;
path=/; expires=Sun, 22-Dec-24 19:55:57 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
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:
- '1075'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999630'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_80fbcef3505afac708a24ef167b701bb
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\nYour
personal goal is: Make sure the writers in your company produce amazing content.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
just returns the input\n\nUse the following format:\n\nThought: you should always
think about what to do\nAction: the action to take, only one name of [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: Produce and amazing 1 paragraph draft of an article about AI
Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
article about AI.\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": "I need to gather information to create an
amazing paragraph draft about AI Agents that aligns with the expected criteria
of a 4-paragraph article about AI. \n\nAction: Test Tool \nAction Input: {\"query\":
\"Write a captivating and informative paragraph about AI Agents, focusing on
their capabilities, applications, and significance in modern technology.\"} \nObservation:
Processed: Write a captivating and informative paragraph about AI Agents, focusing
on their capabilities, applications, and significance in modern technology."}],
"model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2153'
content-type:
- application/json
cookie:
- __cf_bm=vwBNilrHRgMLd8ALWzYrBO5Lm8ieJzbQ3WCVOgmuJ.s-1734895557-1.0.1.1-z.QnDsynL_Ndu.JkWrh_wGMo57vvpK88nWDBTA8P.6prlSRmA91GQLpP62yRUbCW6yoKFbDxroSaYO6qrzZPRg;
_cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000
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:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AhLsMt1AgrzynC2TSJZZSwr9El8FV\",\n \"object\":
\"chat.completion\",\n \"created\": 1734895558,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I have received the content
related to AI Agents, which I need to now use as a foundation for creating a
complete 4-paragraph article about AI. \\n\\nAction: Test Tool \\nAction Input:
{\\\"query\\\": \\\"Based on the previous paragraph about AI Agents, write a
4-paragraph article about AI, including an introduction, discussion of AI Agents,
their applications, and a conclusion on the future of AI.\\\"} \",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 409,\n \"completion_tokens\":
88,\n \"total_tokens\": 497,\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_0aa8d3e20b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8f6280352b9400d5-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 22 Dec 2024 19:25:59 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:
- '1346'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999498'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_e25b377af34ef03b9a6955c9cfca5738
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1885'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Sun, 22 Dec 2024 19:26:01 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\nYour
personal goal is: Make sure the writers in your company produce amazing content.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
just returns the input\n\nUse the following format:\n\nThought: you should always
think about what to do\nAction: the action to take, only one name of [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: Produce and amazing 1 paragraph draft of an article about AI
Agents.\n\nThis is the expect criteria for your final answer: A 4 paragraph
article about AI.\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": "I need to gather information to create an
amazing paragraph draft about AI Agents that aligns with the expected criteria
of a 4-paragraph article about AI. \n\nAction: Test Tool \nAction Input: {\"query\":
\"Write a captivating and informative paragraph about AI Agents, focusing on
their capabilities, applications, and significance in modern technology.\"} \nObservation:
Processed: Write a captivating and informative paragraph about AI Agents, focusing
on their capabilities, applications, and significance in modern technology."},
{"role": "assistant", "content": "Thought: I have received the content related
to AI Agents, which I need to now use as a foundation for creating a complete
4-paragraph article about AI. \n\nAction: Test Tool \nAction Input: {\"query\":
\"Based on the previous paragraph about AI Agents, write a 4-paragraph article
about AI, including an introduction, discussion of AI Agents, their applications,
and a conclusion on the future of AI.\"} \nObservation: Processed: Based on
the previous paragraph about AI Agents, write a 4-paragraph article about AI,
including an introduction, discussion of AI Agents, their applications, and
a conclusion on the future of AI."}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2820'
content-type:
- application/json
cookie:
- __cf_bm=vwBNilrHRgMLd8ALWzYrBO5Lm8ieJzbQ3WCVOgmuJ.s-1734895557-1.0.1.1-z.QnDsynL_Ndu.JkWrh_wGMo57vvpK88nWDBTA8P.6prlSRmA91GQLpP62yRUbCW6yoKFbDxroSaYO6qrzZPRg;
_cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000
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:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AhLsNJa6GxRIHF8l8eViU7D6CyBHP\",\n \"object\":
\"chat.completion\",\n \"created\": 1734895559,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I have gathered the complete
article on AI, which aligns with the expected criteria. Now I will present the
final answer as required. \\n\\nFinal Answer: \\n\\nArtificial Intelligence
(AI) has rapidly evolved to become an integral part of our modern world, driving
significant advancements across various industries. AI refers to the simulation
of human intelligence in machines programmed to think and learn like humans.
This technology enables machines to analyze data, recognize patterns, and make
decisions with minimal human intervention, paving the way for innovation in
fields like healthcare, finance, and transportation.\\n\\nAI Agents, in particular,
embody the future of artificial intelligence by acting autonomously to perform
complex tasks. These agents leverage machine learning and natural language processing
to interact with users and understand their needs. They're deployed in customer
service applications, virtual assistants, and personal scheduling tools, showcasing
their capability to streamline processes and enhance user experience. By mimicking
human reasoning, AI Agents can adapt to changing situations and provide personalized
solutions.\\n\\nThe applications of AI Agents extend beyond mere task completion;
they are transforming the way businesses operate. In the realm of customer engagement,
AI Agents analyze customer behavior to provide insights that help companies
tailor their offerings. In healthcare, they assist in diagnosing illnesses by
analyzing patient data and suggesting treatments. The versatility of AI Agents
makes them invaluable assets in our increasingly automated world.\\n\\nAs we
look to the future, the potential of AI continues to expand. With ongoing advancements
in technology, AI Agents are set to become even more sophisticated, further
bridging the gap between humans and machines. The prospects of AI promise not
only to improve efficiency and productivity but also to change the way we live
and work, promising a future where intelligent, autonomous agents support us
in our daily lives.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
546,\n \"completion_tokens\": 343,\n \"total_tokens\": 889,\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_0aa8d3e20b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8f62803eed8100d5-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 22 Dec 2024 19:26:04 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:
- '4897'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999342'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_65fdf94aa8bbc10f64f2a27ccdcc5cc8
http_version: HTTP/1.1
status_code: 200
version: 1

623
tests/cassettes/test_crew_with_delegating_agents_should_not_override_task_tools.yaml Normal file
View File

@@ -0,0 +1,623 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\nYour
personal goal is: Make sure the writers in your company produce amazing content.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
just returns the input\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate 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 context to execute the task, they
know nothing about the task, so share absolute everything you know, don''t reference
things but instead explain them.\nTool Name: Ask question to coworker\nTool
Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
ask'', ''type'': ''str''}}\nTool Description: Ask 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 necessary context to ask
the question properly, they know nothing about the question, so share absolute
everything you know, don''t reference things but instead explain them.\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Test Tool, Delegate work to coworker,
Ask question to coworker], 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: Produce and amazing
1 paragraph draft of an article about AI Agents.\n\nThis is the expect criteria
for your final answer: A 4 paragraph article about AI.\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-mini", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2892'
content-type:
- application/json
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:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AhLQELAjJpn76wiLmWBinm3sqf32l\",\n \"object\":
\"chat.completion\",\n \"created\": 1734893814,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to gather information and insights
to ensure the Senior Writer produces a high-quality draft about AI Agents, which
will then serve as a foundation for the complete article.\\n\\nAction: Ask question
to coworker \\nAction Input: {\\\"question\\\":\\\"Can you provide a detailed
overview of what AI Agents are, their functionalities, and their applications
in real-world scenarios? Please include examples of how they are being used
in various industries, and discuss their potential impact on the future of technology
and society.\\\",\\\"context\\\":\\\"We are looking to create a comprehensive
understanding of AI Agents as part of a four-paragraph article. This will help
generate a high-quality draft for the article.\\\",\\\"coworker\\\":\\\"Senior
Writer\\\"} \",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
604,\n \"completion_tokens\": 138,\n \"total_tokens\": 742,\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_0aa8d3e20b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8f6255a1bf08a519-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 22 Dec 2024 18:56:56 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=rVquIlcnYXc7wMkbKG5Ii90HxfQ_ukNJjDgSHhsWb1k-1734893816-1.0.1.1-33qDl8KNWcxLAGBuPhT8FrZ6QUnEy9oOYh2Fp2hIjDnF.cQlyrgxiWcuHljTTxG_mH7eQrf1AHJ6p8sxZJZ30A;
path=/; expires=Sun, 22-Dec-24 19:26:56 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=xqgLJsf3h5lBKZFTADRNNUqizeChNBBFoLvWiR2WPnw-1734893816555-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
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:
- '2340'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999305'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_53956b48bd1188451efc104e8a234ef4
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1588'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Sun, 22 Dec 2024 18:56:59 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Senior Writer. You''re
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
personal goal is: Write the best content about AI and AI agents.\nTo give my
best complete final answer to the task use 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: Can you provide a detailed overview of what AI Agents are, their functionalities,
and their applications in real-world scenarios? Please include examples of how
they are being used in various industries, and discuss their potential impact
on the future of technology and society.\n\nThis is the expect criteria for
your final answer: Your best answer to your coworker asking you this, accounting
for the context shared.\nyou MUST return the actual complete content as the
final answer, not a summary.\n\nThis is the context you''re working with:\nWe
are looking to create a comprehensive understanding of AI Agents as part of
a four-paragraph article. This will help generate a high-quality draft for the
article.\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", "stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1572'
content-type:
- application/json
cookie:
- __cf_bm=rVquIlcnYXc7wMkbKG5Ii90HxfQ_ukNJjDgSHhsWb1k-1734893816-1.0.1.1-33qDl8KNWcxLAGBuPhT8FrZ6QUnEy9oOYh2Fp2hIjDnF.cQlyrgxiWcuHljTTxG_mH7eQrf1AHJ6p8sxZJZ30A;
_cfuvid=xqgLJsf3h5lBKZFTADRNNUqizeChNBBFoLvWiR2WPnw-1734893816555-0.0.1.1-604800000
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:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AhLQG5ubl99yeBYm6TTV0sodagMND\",\n \"object\":
\"chat.completion\",\n \"created\": 1734893816,\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: \\n\\n**Overview of AI Agents** \\nAI agents are advanced software
systems designed to autonomously perform tasks, make decisions, and learn from
their environments without needing constant human intervention. They leverage
machine learning, natural language processing, and various AI techniques to
simulate human-like understanding and autonomy. These agents can be categorized
into three types: reactive agents (which operate purely based on their environment),
deliberative agents (which can make decisions based on reasoning), and hybrid
agents that incorporate aspects of both types. Their ability to adapt and learn
over time makes them instrumental in automating processes across various domains.\\n\\n**Functionalities
of AI Agents** \\nThe core functionalities of AI agents include perception,
action, learning, and interaction. They perceive data through sensors or data
feeds, process information through algorithms, and take actions based on this
data. Machine learning allows them to refine their performance over time by
analyzing outcomes and adjusting their strategies accordingly. Interaction capabilities
enable them to communicate with users, providing insights, answering queries,
or even negotiating in some cases. These functionalities make AI agents invaluable
for tasks such as predictive analytics, personal assistance, and real-time decision-making
in complex systems.\\n\\n**Applications in Various Industries** \\nAI agents
are already being utilized across multiple industries, demonstrating their versatility
and efficiency. In healthcare, AI agents assist in diagnostics by analyzing
medical records and suggesting treatment plans tailored to individual patients.
In finance, they power robo-advisors that manage investment portfolios, automate
trading strategies, and provide financial advice based on real-time market analysis.
Furthermore, in customer service, AI chatbots serve as virtual assistants, enhancing
user experience by providing instant support and resolving queries without human
intervention. The logistics and supply chain industries have also seen AI agents
optimize inventory management and route planning, significantly improving operational
efficiency.\\n\\n**Future Impact on Technology and Society** \\nThe ongoing
development of AI agents is poised to have a profound impact on technology and
society. As these agents become more sophisticated, we can anticipate a shift
towards increased automation in both professional and personal spheres, leading
to enhanced productivity and new business models. However, this automation introduces
challenges such as job displacement and ethical considerations regarding decision-making
by AI. It is essential to foster an ongoing dialogue on the implications of
AI agents to ensure responsible development and integration into our daily lives.
As AI agents continue to evolve, they will undoubtedly play a pivotal role in
shaping the future of technology and its intersection with societal dynamics,
making it critical for us to engage thoughtfully with this emerging paradigm.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 289,\n \"completion_tokens\":
506,\n \"total_tokens\": 795,\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_0aa8d3e20b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8f6255b1f832a519-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 22 Dec 2024 18:57:04 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:
- '7836'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999630'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_c14268346d6ce72ceea4b1472f73c5ae
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CtsBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSsgEKEgoQY3Jld2FpLnRl
bGVtZXRyeRKbAQoQ7U/1ZgBSTkCXtesUNPA2URIIrnRWFVT58Z8qClRvb2wgVXNhZ2UwATl4lN3i
vZQTGEGgevzivZQTGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKJwoJdG9vbF9uYW1lEhoK
GEFzayBxdWVzdGlvbiB0byBjb3dvcmtlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '222'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Sun, 22 Dec 2024 18:57:09 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are CEO. You''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\nYour
personal goal is: Make sure the writers in your company produce amazing content.\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: Test Tool\nTool Arguments: {''query'': {''description'':
''Query to process'', ''type'': ''str''}}\nTool Description: A test tool that
just returns the input\nTool Name: Delegate work to coworker\nTool Arguments:
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
''str''}}\nTool Description: Delegate 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 context to execute the task, they
know nothing about the task, so share absolute everything you know, don''t reference
things but instead explain them.\nTool Name: Ask question to coworker\nTool
Arguments: {''question'': {''description'': ''The question to ask'', ''type'':
''str''}, ''context'': {''description'': ''The context for the question'', ''type'':
''str''}, ''coworker'': {''description'': ''The role/name of the coworker to
ask'', ''type'': ''str''}}\nTool Description: Ask 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 necessary context to ask
the question properly, they know nothing about the question, so share absolute
everything you know, don''t reference things but instead explain them.\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Test Tool, Delegate work to coworker,
Ask question to coworker], 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: Produce and amazing
1 paragraph draft of an article about AI Agents.\n\nThis is the expect criteria
for your final answer: A 4 paragraph article about AI.\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": "I need
to gather information and insights to ensure the Senior Writer produces a high-quality
draft about AI Agents, which will then serve as a foundation for the complete
article.\n\nAction: Ask question to coworker \nAction Input: {\"question\":\"Can
you provide a detailed overview of what AI Agents are, their functionalities,
and their applications in real-world scenarios? Please include examples of how
they are being used in various industries, and discuss their potential impact
on the future of technology and society.\",\"context\":\"We are looking to create
a comprehensive understanding of AI Agents as part of a four-paragraph article.
This will help generate a high-quality draft for the article.\",\"coworker\":\"Senior
Writer\"} \nObservation: **Overview of AI Agents** \nAI agents are advanced
software systems designed to autonomously perform tasks, make decisions, and
learn from their environments without needing constant human intervention. They
leverage machine learning, natural language processing, and various AI techniques
to simulate human-like understanding and autonomy. These agents can be categorized
into three types: reactive agents (which operate purely based on their environment),
deliberative agents (which can make decisions based on reasoning), and hybrid
agents that incorporate aspects of both types. Their ability to adapt and learn
over time makes them instrumental in automating processes across various domains.\n\n**Functionalities
of AI Agents** \nThe core functionalities of AI agents include perception,
action, learning, and interaction. They perceive data through sensors or data
feeds, process information through algorithms, and take actions based on this
data. Machine learning allows them to refine their performance over time by
analyzing outcomes and adjusting their strategies accordingly. Interaction capabilities
enable them to communicate with users, providing insights, answering queries,
or even negotiating in some cases. These functionalities make AI agents invaluable
for tasks such as predictive analytics, personal assistance, and real-time decision-making
in complex systems.\n\n**Applications in Various Industries** \nAI agents are
already being utilized across multiple industries, demonstrating their versatility
and efficiency. In healthcare, AI agents assist in diagnostics by analyzing
medical records and suggesting treatment plans tailored to individual patients.
In finance, they power robo-advisors that manage investment portfolios, automate
trading strategies, and provide financial advice based on real-time market analysis.
Furthermore, in customer service, AI chatbots serve as virtual assistants, enhancing
user experience by providing instant support and resolving queries without human
intervention. The logistics and supply chain industries have also seen AI agents
optimize inventory management and route planning, significantly improving operational
efficiency.\n\n**Future Impact on Technology and Society** \nThe ongoing development
of AI agents is poised to have a profound impact on technology and society.
As these agents become more sophisticated, we can anticipate a shift towards
increased automation in both professional and personal spheres, leading to enhanced
productivity and new business models. However, this automation introduces challenges
such as job displacement and ethical considerations regarding decision-making
by AI. It is essential to foster an ongoing dialogue on the implications of
AI agents to ensure responsible development and integration into our daily lives.
As AI agents continue to evolve, they will undoubtedly play a pivotal role in
shaping the future of technology and its intersection with societal dynamics,
making it critical for us to engage thoughtfully with this emerging paradigm."}],
"model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '6755'
content-type:
- application/json
cookie:
- __cf_bm=rVquIlcnYXc7wMkbKG5Ii90HxfQ_ukNJjDgSHhsWb1k-1734893816-1.0.1.1-33qDl8KNWcxLAGBuPhT8FrZ6QUnEy9oOYh2Fp2hIjDnF.cQlyrgxiWcuHljTTxG_mH7eQrf1AHJ6p8sxZJZ30A;
_cfuvid=xqgLJsf3h5lBKZFTADRNNUqizeChNBBFoLvWiR2WPnw-1734893816555-0.0.1.1-604800000
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:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AhLQOmLKuevpaWtRyyhHjHVYqvNVk\",\n \"object\":
\"chat.completion\",\n \"created\": 1734893824,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I have received a comprehensive
overview from the Senior Writer that includes the necessary information about
AI Agents, their functionalities, applications, and future implications. Now,
I can compile this into a final answer following the specified format: a complete
four-paragraph article.\\n\\nFinal Answer: \\n\\n**Overview of AI Agents** \\nAI
agents are advanced software systems designed to autonomously perform tasks,
make decisions, and learn from their environments without needing constant human
intervention. They leverage machine learning, natural language processing, and
various AI techniques to simulate human-like understanding and autonomy. These
agents can be categorized into three types: reactive agents (which operate purely
based on their environment), deliberative agents (which can make decisions based
on reasoning), and hybrid agents that incorporate aspects of both types. Their
ability to adapt and learn over time makes them instrumental in automating processes
across various domains.\\n\\n**Functionalities of AI Agents** \\nThe core functionalities
of AI agents include perception, action, learning, and interaction. They perceive
data through sensors or data feeds, process information through algorithms,
and take actions based on this data. Machine learning allows them to refine
their performance over time by analyzing outcomes and adjusting their strategies
accordingly. Interaction capabilities enable them to communicate with users,
providing insights, answering queries, or even negotiating in some cases. These
functionalities make AI agents invaluable for tasks such as predictive analytics,
personal assistance, and real-time decision-making in complex systems.\\n\\n**Applications
in Various Industries** \\nAI agents are already being utilized across multiple
industries, demonstrating their versatility and efficiency. In healthcare, AI
agents assist in diagnostics by analyzing medical records and suggesting treatment
plans tailored to individual patients. In finance, they power robo-advisors
that manage investment portfolios, automate trading strategies, and provide
financial advice based on real-time market analysis. Furthermore, in customer
service, AI chatbots serve as virtual assistants, enhancing user experience
by providing instant support and resolving queries without human intervention.
The logistics and supply chain industries have also seen AI agents optimize
inventory management and route planning, significantly improving operational
efficiency.\\n\\n**Future Impact on Technology and Society** \\nThe ongoing
development of AI agents is poised to have a profound impact on technology and
society. As these agents become more sophisticated, we can anticipate a shift
towards increased automation in both professional and personal spheres, leading
to enhanced productivity and new business models. However, this automation introduces
challenges such as job displacement and ethical considerations regarding decision-making
by AI. It is essential to foster an ongoing dialogue on the implications of
AI agents to ensure responsible development and integration into our daily lives.
As AI agents continue to evolve, they will undoubtedly play a pivotal role in
shaping the future of technology and its intersection with societal dynamics,
making it critical for us to engage thoughtfully with this emerging paradigm.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 1242,\n \"completion_tokens\":
550,\n \"total_tokens\": 1792,\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_0aa8d3e20b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8f6255e49b37a519-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 22 Dec 2024 18:57:12 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:
- '7562'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149998353'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a812bbb85b3d785660c4662212614ab9
http_version: HTTP/1.1
status_code: 200
version: 1

35
tests/cassettes/test_llm_call_with_ollama_gemma.yaml
View File

@@ -1,35 +0,0 @@
interactions:
- request:
body: '{"model": "gemma2:latest", "prompt": "### User:\nRespond in 20 words. Who
are you?\n\n", "options": {"num_predict": 30, "temperature": 0.7}, "stream":
false}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '157'
Content-Type:
- application/json
User-Agent:
- python-requests/2.31.0
method: POST
uri: http://localhost:8080/api/generate
response:
body:
string: '{"model":"gemma2:latest","created_at":"2024-09-24T21:57:52.329049Z","response":"I
am Gemma, an open-weights AI assistant trained by Google DeepMind. \n","done":true,"done_reason":"stop","context":[106,1645,108,6176,4926,235292,108,54657,575,235248,235284,235276,3907,235265,7702,708,692,235336,109,107,108,106,2516,108,235285,1144,137061,235269,671,2174,235290,30316,16481,20409,17363,731,6238,20555,35777,235265,139,108],"total_duration":991843667,"load_duration":31664750,"prompt_eval_count":25,"prompt_eval_duration":51409000,"eval_count":19,"eval_duration":908132000}'
headers:
Content-Length:
- '572'
Content-Type:
- application/json; charset=utf-8
Date:
- Tue, 24 Sep 2024 21:57:52 GMT
status:
code: 200
message: OK
version: 1

36
tests/cassettes/test_llm_call_with_ollama_llama3.yaml Normal file
View File

@@ -0,0 +1,36 @@
interactions:
- request:
body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Which
model are you??\n\n", "options": {"num_predict": 30, "temperature": 0.7}, "stream":
false}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '164'
Content-Type:
- application/json
User-Agent:
- python-requests/2.32.3
method: POST
uri: http://localhost:11434/api/generate
response:
body:
string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:24:24.812595Z","response":"I''m
an AI, specifically a large language model, designed to understand and respond
to user queries with accuracy.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,16299,1646,527,499,71291,128009,128006,78191,128007,271,40,2846,459,15592,11,11951,264,3544,4221,1646,11,6319,311,3619,323,6013,311,1217,20126,449,13708,13],"total_duration":827817584,"load_duration":41560542,"prompt_eval_count":39,"prompt_eval_duration":384000000,"eval_count":23,"eval_duration":400000000}'
headers:
Content-Length:
- '683'
Content-Type:
- application/json; charset=utf-8
Date:
- Thu, 02 Jan 2025 20:24:24 GMT
status:
code: 200
message: OK
version: 1

481
tests/cassettes/test_multimodal_agent_live_image_analysis.yaml Normal file
View File

@@ -0,0 +1,481 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Image Analyst. You''re
an expert at visual analysis, trained to notice and describe details in images.\nYour
personal goal is: Analyze images with high attention to detail\nYou ONLY have
access to the following tools, and should NEVER make up tools that are not listed
here:\n\nTool Name: Add image to content\nTool Arguments: {''image_url'': {''description'':
''The URL or path of the image to add'', ''type'': ''str''}, ''action'': {''description'':
''Optional context or question about the image'', ''type'': ''str''}}\nTool
Description: See image to understand it''s content, you can optionally ask a
question about the image\n\nUse the following format:\n\nThought: you should
always think about what to do\nAction: the action to take, only one name of
[Add image to content], 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: \n Analyze the provided image and describe
what you see in detail.\n Focus on main elements, colors, composition,
and any notable details.\n Image: https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=\n \n\nThis
is the expect criteria for your final answer: A comprehensive description of
the image contents.\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:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1948'
content-type:
- application/json
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:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AiuIfzzcje5KdvKIG5CkFeORroiKk\",\n \"object\":
\"chat.completion\",\n \"created\": 1735266213,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Action: Add image to content\\nAction
Input: {\\\"image_url\\\": \\\"https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=\\\",
\\\"action\\\": \\\"Analyze the provided image and describe what you see in
detail.\\\"}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
417,\n \"completion_tokens\": 103,\n \"total_tokens\": 520,\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:
- 8f85d96b280df217-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 27 Dec 2024 02:23:35 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=kJ1pw1xjCMSxjHSS8iJC5z_j2PZxl.i387KCpj9xNZU-1735266215-1.0.1.1-Ybg0wVTsrBlpVZmtQyA1ullY8m3v2Ix0N_SYlhr9z7zKfbLeqGZEVL37YSY.dvIiLVY3XPZzMtG8Xwo6UucW6A;
path=/; expires=Fri, 27-Dec-24 02:53:35 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=v_wJZ5m7qCjrnRfks0gT2GAk9yR14BdIDAQiQR7xxI8-1735266215000-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
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:
- '1212'
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:
- '29999539'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_663a2b18099a18361d6b02befc175289
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1425'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Fri, 27 Dec 2024 02:23:39 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Image Analyst. You''re
an expert at visual analysis, trained to notice and describe details in images.\nYour
personal goal is: Analyze images with high attention to detail\nYou ONLY have
access to the following tools, and should NEVER make up tools that are not listed
here:\n\nTool Name: Add image to content\nTool Arguments: {''image_url'': {''description'':
''The URL or path of the image to add'', ''type'': ''str''}, ''action'': {''description'':
''Optional context or question about the image'', ''type'': ''str''}}\nTool
Description: See image to understand it''s content, you can optionally ask a
question about the image\n\nUse the following format:\n\nThought: you should
always think about what to do\nAction: the action to take, only one name of
[Add image to content], 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: \n Analyze the provided image and describe
what you see in detail.\n Focus on main elements, colors, composition,
and any notable details.\n Image: https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=\n \n\nThis
is the expect criteria for your final answer: A comprehensive description of
the image contents.\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": "user", "content": [{"type": "text", "text": "Analyze the provided
image and describe what you see in detail."}, {"type": "image_url", "image_url":
{"url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k="}}]}],
"model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2279'
content-type:
- application/json
cookie:
- __cf_bm=kJ1pw1xjCMSxjHSS8iJC5z_j2PZxl.i387KCpj9xNZU-1735266215-1.0.1.1-Ybg0wVTsrBlpVZmtQyA1ullY8m3v2Ix0N_SYlhr9z7zKfbLeqGZEVL37YSY.dvIiLVY3XPZzMtG8Xwo6UucW6A;
_cfuvid=v_wJZ5m7qCjrnRfks0gT2GAk9yR14BdIDAQiQR7xxI8-1735266215000-0.0.1.1-604800000
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:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AiuIiqT33ROFMdw1gNmqH9jiw6PfF\",\n \"object\":
\"chat.completion\",\n \"created\": 1735266216,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The image is an aerial view of Lower
Manhattan in New York City. \\n\\nMain Elements:\\n- The One World Trade Center
tower stands prominently, distinguishable by its sleek, tapering structure reaching
into the sky, surrounded by other skyscrapers.\\n- Skyscrapers in varying heights
and architectural styles, fill the densely packed urban landscape.\\n- A waterfront
is visible at the edges, with docks and piers extending into the water.\\n\\nColors:\\n-
The buildings exhibit a mix of colors, predominantly grays, whites, and browns,
against the blues of the sky and water.\\n- There's a section of greenery visible,
likely a park or recreational space, offering a contrast with its vibrant green
hues.\\n\\nComposition:\\n- The angle of the photograph showcases the expanse
of the city, highlighting the density and scale of the buildings.\\n- Water
borders the city on two prominent sides, creating a natural boundary and enhancing
the island's urban island feel.\\n\\nNotable Details:\\n- The image captures
the iconic layout of Manhattan, with the surrounding Hudson River and New York
Harbor visible in the background.\\n- Beyond Lower Manhattan, more of the cityscape
stretches into the distance, illustrating the vastness of New York City.\\n-
The day appears clear and sunny, with shadows casting from the buildings, indicating
time in the morning or late afternoon.\\n\\nOverall, the image is a striking
depiction of the dynamic and bustling environment of New York's Lower Manhattan,
encapsulating its urban character and proximity to the water.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 858,\n \"completion_tokens\":
295,\n \"total_tokens\": 1153,\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:
- 8f85d9741d0cf217-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 27 Dec 2024 02:23:40 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:
- '5136'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-input-images:
- '50000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-input-images:
- '49999'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29998756'
x-ratelimit-reset-input-images:
- 1ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_57a7430712d4ff4a81f600ffb94d3b6e
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Image Analyst. You''re
an expert at visual analysis, trained to notice and describe details in images.\nYour
personal goal is: Analyze images with high attention to detail\nYou ONLY have
access to the following tools, and should NEVER make up tools that are not listed
here:\n\nTool Name: Add image to content\nTool Arguments: {''image_url'': {''description'':
''The URL or path of the image to add'', ''type'': ''str''}, ''action'': {''description'':
''Optional context or question about the image'', ''type'': ''str''}}\nTool
Description: See image to understand it''s content, you can optionally ask a
question about the image\n\nUse the following format:\n\nThought: you should
always think about what to do\nAction: the action to take, only one name of
[Add image to content], 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: \n Analyze the provided image and describe
what you see in detail.\n Focus on main elements, colors, composition,
and any notable details.\n Image: https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=\n \n\nThis
is the expect criteria for your final answer: A comprehensive description of
the image contents.\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": "user", "content": [{"type": "text", "text": "Analyze the provided
image and describe what you see in detail."}, {"type": "image_url", "image_url":
{"url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k="}}]},
{"role": "user", "content": "I did it wrong. Invalid Format: I missed the ''Action:''
after ''Thought:''. I will do right next, and don''t use a tool I have already
used.\n\nIf you don''t need to use any more tools, you must give your best complete
final answer, make sure it satisfies the expected criteria, use the EXACT format
below:\n\nThought: I now can give a great answer\nFinal Answer: my best complete
final answer to the task.\n\n"}], "model": "gpt-4o", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2717'
content-type:
- application/json
cookie:
- __cf_bm=kJ1pw1xjCMSxjHSS8iJC5z_j2PZxl.i387KCpj9xNZU-1735266215-1.0.1.1-Ybg0wVTsrBlpVZmtQyA1ullY8m3v2Ix0N_SYlhr9z7zKfbLeqGZEVL37YSY.dvIiLVY3XPZzMtG8Xwo6UucW6A;
_cfuvid=v_wJZ5m7qCjrnRfks0gT2GAk9yR14BdIDAQiQR7xxI8-1735266215000-0.0.1.1-604800000
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:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AiuInuYNldaQVo6B1EsEquT1VFMN7\",\n \"object\":
\"chat.completion\",\n \"created\": 1735266221,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: The image is an aerial view of Lower Manhattan in New York City. The
photograph prominently features the cluster of skyscrapers that characterizes
the area, with One World Trade Center standing out as a particularly tall and
iconic structure. The buildings vary in color, with shades of glassy blue, grey,
and natural stone dominating the skyline. In the bottom part of the image, there
is a green space, likely Battery Park, providing a stark contrast to the dense
urban environment, with trees and pathways visible. The water surrounding Manhattan
is a deep blue, and several piers jut into the harbor. The Hudson River is visible
on the left, and the East River can be seen on the right, framing the island.
The overall composition captures the bustling and vibrant nature of New York\u2019s
financial hub, with bright sunlight illuminating the buildings, casting sharp
shadows and enhancing the depth of the cityscape. The sky is clear, suggesting
a sunny day with good visibility.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 952,\n \"completion_tokens\": 203,\n
\ \"total_tokens\": 1155,\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:
- 8f85d995ad1ef217-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 27 Dec 2024 02:23:43 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:
- '3108'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-input-images:
- '50000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-input-images:
- '49999'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29998656'
x-ratelimit-reset-input-images:
- 1ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_45f0e3d457a18f973a59074d16f137b6
http_version: HTTP/1.1
status_code: 200
version: 1

569
tests/cassettes/test_task_tools_override_agent_tools.yaml Normal file
View File

@@ -0,0 +1,569 @@
interactions:
- 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: Test Tool\nTool Arguments: {''query'': {''description'': ''Query to process'',
''type'': ''str''}}\nTool Description: A test tool that just returns the input\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [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:"}], "model": "gpt-4o-mini", "stop":
["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1536'
content-type:
- application/json
cookie:
- _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000
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:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AhQfznhDMtsr58XvTuRDZoB1kxwfK\",\n \"object\":
\"chat.completion\",\n \"created\": 1734914011,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to come up with a suitable test
task that meets the criteria provided. I will focus on outlining a clear and
effective test task related to AI and AI agents.\\n\\nAction: Test Tool\\nAction
Input: {\\\"query\\\": \\\"Create a test task that involves evaluating the performance
of an AI agent in a given scenario, including criteria for success, tools required,
and process for assessment.\\\"}\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
298,\n \"completion_tokens\": 78,\n \"total_tokens\": 376,\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_d02d531b47\"\n}\n"
headers:
CF-RAY:
- 8f6442b868fda486-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Dec 2024 00:33:32 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=i6jvNjhsDne300GPAeEmyiJJKYqy7OPuamFG_kht3KE-1734914012-1.0.1.1-tCeVANAF521vkXpBdgYw.ov.fYUr6t5QC4LG_DugWyzu4C60Pi2CruTVniUgfCvkcu6rdHA5DwnaEZf2jFaRCQ;
path=/; expires=Mon, 23-Dec-24 01:03:32 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1400'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999642'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_c3e50e9ca9dc22de5572692e1a9c0f16
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '14771'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Mon, 23 Dec 2024 00:33:37 GMT
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: Test Tool\nTool Arguments: {''query'': {''description'': ''Query to process'',
''type'': ''str''}}\nTool Description: A test tool that just returns the input\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [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":
"I need to come up with a suitable test task that meets the criteria provided.
I will focus on outlining a clear and effective test task related to AI and
AI agents.\n\nAction: Test Tool\nAction Input: {\"query\": \"Create a test task
that involves evaluating the performance of an AI agent in a given scenario,
including criteria for success, tools required, and process for assessment.\"}\nObservation:
Processed: Create a test task that involves evaluating the performance of an
AI agent in a given scenario, including criteria for success, tools required,
and process for assessment."}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2160'
content-type:
- application/json
cookie:
- _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000;
__cf_bm=i6jvNjhsDne300GPAeEmyiJJKYqy7OPuamFG_kht3KE-1734914012-1.0.1.1-tCeVANAF521vkXpBdgYw.ov.fYUr6t5QC4LG_DugWyzu4C60Pi2CruTVniUgfCvkcu6rdHA5DwnaEZf2jFaRCQ
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:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AhQg0Cx1FED7gOwMpJUD5cQxVzQBK\",\n \"object\":
\"chat.completion\",\n \"created\": 1734914012,\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 compile a complete
and detailed test task based on the processed input, ensuring it includes all
necessary components as per the expect criteria.\\n\\nFinal Answer: \\n### Test
Task: Evaluating the Performance of an AI Agent\\n\\n**Objective:** \\nTo evaluate
the performance of an AI agent in simulating conversation with users in a customer
service context.\\n\\n**Scenario:**\\nAn AI agent is tasked with handling customer
inquiries on an e-commerce platform. The agent must respond to questions about
product availability, order tracking, returns, and other common queries.\\n\\n**Criteria
for Success:**\\n1. **Accuracy:** The AI should provide correct information
in at least 90% of the interactions.\\n2. **Response Time:** The average response
time should be under 2 seconds.\\n3. **User Satisfaction:** Aim for a user satisfaction
score of 85% or higher based on follow-up surveys after interactions.\\n4. **Fallback
Rate:** The AI should not default to a human agent more than 10% of the time.\\n\\n**Tools
Required:**\\n- Chatbot development platform (e.g., Dialogflow, Rasa)\\n- Metrics
tracking software (to measure accuracy, response times, and user satisfaction)\\n-
Survey tool (e.g., Google Forms, SurveyMonkey) for feedback collection\\n\\n**Process
for Assessment:**\\n1. **Setup:** Deploy the AI agent on a testing environment
simulating real customer inquiries.\\n2. **Data Collection:** Run the test for
a predetermined period (e.g., one week) or until a set number of interactions
(e.g., 1000).\\n3. **Measurement:**\\n - Record the interactions and analyze
the accuracy of the AI's responses.\\n - Measure the average response time
for each interaction.\\n - Collect user satisfaction scores via surveys sent
after the interaction.\\n4. **Analysis:** Compile the data to see if the AI
met the success criteria. Identify strengths and weaknesses in the responses.\\n5.
**Review:** Share findings with the development team to strategize improvements.\\n\\nThis
detailed task will help assess the AI agent\u2019s capabilities and provide
insights for further enhancements.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 416,\n \"completion_tokens\": 422,\n
\ \"total_tokens\": 838,\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_d02d531b47\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8f6442c2ba15a486-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Dec 2024 00:33:39 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:
- '6734'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999497'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_7d8df8b840e279bd64280d161d854161
http_version: HTTP/1.1
status_code: 200
version: 1

9
tests/cli/tools/test_main.py
View File

@@ -28,9 +28,10 @@ def test_create_success(mock_subprocess):
with in_temp_dir():
tool_command = ToolCommand()
with patch.object(tool_command, "login") as mock_login, patch(
"sys.stdout", new=StringIO()
) as fake_out:
with (
patch.object(tool_command, "login") as mock_login,
patch("sys.stdout", new=StringIO()) as fake_out,
):
tool_command.create("test-tool")
output = fake_out.getvalue()
@@ -82,7 +83,7 @@ def test_install_success(mock_get, mock_subprocess_run):
capture_output=False,
text=True,
check=True,
env=unittest.mock.ANY
env=unittest.mock.ANY,
)
assert "Successfully installed sample-tool" in output

833
tests/crew_test.py
View File

@@ -332,22 +332,39 @@ def test_manager_agent_delegating_to_assigned_task_agent():
tasks=[task],
)
crew.kickoff()
# Check if the manager agent has the correct tools
assert crew.manager_agent is not None
assert crew.manager_agent.tools is not None
assert len(crew.manager_agent.tools) == 2
assert (
"Delegate a specific task to one of the following coworkers: Researcher\n"
in crew.manager_agent.tools[0].description
)
assert (
"Ask a specific question to one of the following coworkers: Researcher\n"
in crew.manager_agent.tools[1].description
mock_task_output = TaskOutput(
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Because we are mocking execute_sync, we never hit the underlying _execute_core
# which sets the output attribute of the task
task.output = mock_task_output
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Verify execute_sync was called once
mock_execute_sync.assert_called_once()
# Get the tools argument from the call
_, kwargs = mock_execute_sync.call_args
tools = kwargs["tools"]
# Verify the delegation tools were passed correctly
assert len(tools) == 2
assert any(
"Delegate a specific task to one of the following coworkers: Researcher"
in tool.description
for tool in tools
)
assert any(
"Ask a specific question to one of the following coworkers: Researcher"
in tool.description
for tool in tools
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_manager_agent_delegating_to_all_agents():
@@ -382,6 +399,83 @@ def test_manager_agent_delegating_to_all_agents():
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_manager_agent_delegates_with_varied_role_cases():
"""
Test that the manager agent can delegate to agents regardless of case or whitespace variations in role names.
This test verifies the fix for issue #1503 where role matching was too strict.
"""
# Create agents with varied case and whitespace in roles
researcher_spaced = Agent(
role=" Researcher ", # Extra spaces
goal="Research with spaces in role",
backstory="A researcher with spaces in role name",
allow_delegation=False,
)
writer_caps = Agent(
role="SENIOR WRITER", # All caps
goal="Write with caps in role",
backstory="A writer with caps in role name",
allow_delegation=False,
)
task = Task(
description="Research and write about AI. The researcher should do the research, and the writer should write it up.",
expected_output="A well-researched article about AI.",
agent=researcher_spaced, # Assign to researcher with spaces
)
crew = Crew(
agents=[researcher_spaced, writer_caps],
process=Process.hierarchical,
manager_llm="gpt-4o",
tasks=[task],
)
mock_task_output = TaskOutput(
description="Mock description", raw="mocked output", agent="mocked agent"
)
task.output = mock_task_output
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Verify execute_sync was called once
mock_execute_sync.assert_called_once()
# Get the tools argument from the call
_, kwargs = mock_execute_sync.call_args
tools = kwargs["tools"]
# Verify the delegation tools were passed correctly and can handle case/whitespace variations
assert len(tools) == 2
# Check delegation tool descriptions (should work despite case/whitespace differences)
delegation_tool = tools[0]
question_tool = tools[1]
assert (
"Delegate a specific task to one of the following coworkers:"
in delegation_tool.description
)
assert (
" Researcher " in delegation_tool.description
or "SENIOR WRITER" in delegation_tool.description
)
assert (
"Ask a specific question to one of the following coworkers:"
in question_tool.description
)
assert (
" Researcher " in question_tool.description
or "SENIOR WRITER" in question_tool.description
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_with_delegating_agents():
tasks = [
@@ -402,10 +496,274 @@ def test_crew_with_delegating_agents():
assert (
result.raw
== "This is the complete content as specified:\nArtificial Intelligence (AI) Agents are sophisticated computer programs designed to perform tasks that typically require human intelligence, such as decision making, problem-solving, and learning. These agents operate autonomously, utilizing vast amounts of data, advanced algorithms, and machine learning techniques to analyze their environment, adapt to new information, and improve their performance over time.\n\nThe significance of AI Agents lies in their transformative potential across various industries. In healthcare, for example, they assist in diagnosing diseases with greater accuracy and speed than human practitioners, offering personalized treatment plans by analyzing patient data. In finance, AI Agents predict market trends, manage risks, and even execute trades, contributing to more stable and profitable financial systems. Customer service sectors benefit significantly from AI Agents, as they provide personalized and efficient responses, often resolving issues faster than traditional methods.\n\nMoreover, AI Agents are also making substantial contributions in fields like education and manufacturing. In education, they offer tailored learning experiences by assessing individual student needs and adjusting teaching methods accordingly. They help educators identify students who might need additional support and provide resources to enhance learning outcomes. In manufacturing, AI Agents optimize production lines, predict equipment failures, and improve supply chain management, thus boosting productivity and reducing downtime.\n\nAs these AI-powered entities continue to evolve, they are not only enhancing operational efficiencies but also driving innovation and creating new opportunities for growth and development in every sector they penetrate. The future of AI Agents looks promising, with the potential to revolutionize the way we live and work, making processes more efficient, decisions more data-driven, and solutions more innovative than ever before."
== "In the rapidly evolving landscape of technology, AI agents have emerged as formidable tools, revolutionizing how we interact with data and automate tasks. These sophisticated systems leverage machine learning and natural language processing to perform a myriad of functions, from virtual personal assistants to complex decision-making companions in industries such as finance, healthcare, and education. By mimicking human intelligence, AI agents can analyze massive data sets at unparalleled speeds, enabling businesses to uncover valuable insights, enhance productivity, and elevate user experiences to unprecedented levels.\n\nOne of the most striking aspects of AI agents is their adaptability; they learn from their interactions and continuously improve their performance over time. This feature is particularly valuable in customer service where AI agents can address inquiries, resolve issues, and provide personalized recommendations without the limitations of human fatigue. Moreover, with intuitive interfaces, AI agents enhance user interactions, making technology more accessible and user-friendly, thereby breaking down barriers that have historically hindered digital engagement.\n\nDespite their immense potential, the deployment of AI agents raises important ethical and practical considerations. Issues related to privacy, data security, and the potential for job displacement necessitate thoughtful dialogue and proactive measures. Striking a balance between technological innovation and societal impact will be crucial as organizations integrate these agents into their operations. Additionally, ensuring transparency in AI decision-making processes is vital to maintain public trust as AI agents become an integral part of daily life.\n\nLooking ahead, the future of AI agents appears bright, with ongoing advancements promising even greater capabilities. As we continue to harness the power of AI, we can expect these agents to play a transformative role in shaping various sectors—streamlining workflows, enabling smarter decision-making, and fostering more personalized experiences. Embracing this technology responsibly can lead to a future where AI agents not only augment human effort but also inspire creativity and efficiency across the board, ultimately redefining our interaction with the digital world."
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_with_delegating_agents_should_not_override_task_tools():
from typing import Type
from pydantic import BaseModel, Field
from crewai.tools import BaseTool
class TestToolInput(BaseModel):
"""Input schema for TestTool."""
query: str = Field(..., description="Query to process")
class TestTool(BaseTool):
name: str = "Test Tool"
description: str = "A test tool that just returns the input"
args_schema: Type[BaseModel] = TestToolInput
def _run(self, query: str) -> str:
return f"Processed: {query}"
# Create a task with the test tool
tasks = [
Task(
description="Produce and amazing 1 paragraph draft of an article about AI Agents.",
expected_output="A 4 paragraph article about AI.",
agent=ceo,
tools=[TestTool()],
)
]
crew = Crew(
agents=[ceo, writer],
process=Process.sequential,
tasks=tasks,
)
mock_task_output = TaskOutput(
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Because we are mocking execute_sync, we never hit the underlying _execute_core
# which sets the output attribute of the task
tasks[0].output = mock_task_output
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Execute the task and verify both tools are present
_, kwargs = mock_execute_sync.call_args
tools = kwargs["tools"]
assert any(
isinstance(tool, TestTool) for tool in tools
), "TestTool should be present"
assert any(
"delegate" in tool.name.lower() for tool in tools
), "Delegation tool should be present"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_with_delegating_agents_should_not_override_agent_tools():
from typing import Type
from pydantic import BaseModel, Field
from crewai.tools import BaseTool
class TestToolInput(BaseModel):
"""Input schema for TestTool."""
query: str = Field(..., description="Query to process")
class TestTool(BaseTool):
name: str = "Test Tool"
description: str = "A test tool that just returns the input"
args_schema: Type[BaseModel] = TestToolInput
def _run(self, query: str) -> str:
return f"Processed: {query}"
new_ceo = ceo.model_copy()
new_ceo.tools = [TestTool()]
# Create a task with the test tool
tasks = [
Task(
description="Produce and amazing 1 paragraph draft of an article about AI Agents.",
expected_output="A 4 paragraph article about AI.",
agent=new_ceo,
)
]
crew = Crew(
agents=[new_ceo, writer],
process=Process.sequential,
tasks=tasks,
)
mock_task_output = TaskOutput(
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Because we are mocking execute_sync, we never hit the underlying _execute_core
# which sets the output attribute of the task
tasks[0].output = mock_task_output
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Execute the task and verify both tools are present
_, kwargs = mock_execute_sync.call_args
tools = kwargs["tools"]
assert any(
isinstance(tool, TestTool) for tool in new_ceo.tools
), "TestTool should be present"
assert any(
"delegate" in tool.name.lower() for tool in tools
), "Delegation tool should be present"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_task_tools_override_agent_tools():
from typing import Type
from pydantic import BaseModel, Field
from crewai.tools import BaseTool
class TestToolInput(BaseModel):
"""Input schema for TestTool."""
query: str = Field(..., description="Query to process")
class TestTool(BaseTool):
name: str = "Test Tool"
description: str = "A test tool that just returns the input"
args_schema: Type[BaseModel] = TestToolInput
def _run(self, query: str) -> str:
return f"Processed: {query}"
class AnotherTestTool(BaseTool):
name: str = "Another Test Tool"
description: str = "Another test tool"
args_schema: Type[BaseModel] = TestToolInput
def _run(self, query: str) -> str:
return f"Another processed: {query}"
# Set agent tools
new_researcher = researcher.model_copy()
new_researcher.tools = [TestTool()]
# Create task with different tools
task = Task(
description="Write a test task",
expected_output="Test output",
agent=new_researcher,
tools=[AnotherTestTool()],
)
crew = Crew(agents=[new_researcher], tasks=[task], process=Process.sequential)
crew.kickoff()
# Verify task tools override agent tools
assert len(task.tools) == 1 # AnotherTestTool
assert any(isinstance(tool, AnotherTestTool) for tool in task.tools)
assert not any(isinstance(tool, TestTool) for tool in task.tools)
# Verify agent tools remain unchanged
assert len(new_researcher.tools) == 1
assert isinstance(new_researcher.tools[0], TestTool)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_task_tools_override_agent_tools_with_allow_delegation():
"""
Test that task tools override agent tools while preserving delegation tools when allow_delegation=True
"""
from typing import Type
from pydantic import BaseModel, Field
from crewai.tools import BaseTool
class TestToolInput(BaseModel):
query: str = Field(..., description="Query to process")
class TestTool(BaseTool):
name: str = "Test Tool"
description: str = "A test tool that just returns the input"
args_schema: Type[BaseModel] = TestToolInput
def _run(self, query: str) -> str:
return f"Processed: {query}"
class AnotherTestTool(BaseTool):
name: str = "Another Test Tool"
description: str = "Another test tool"
args_schema: Type[BaseModel] = TestToolInput
def _run(self, query: str) -> str:
return f"Another processed: {query}"
# Set up agents with tools and allow_delegation
researcher_with_delegation = researcher.model_copy()
researcher_with_delegation.allow_delegation = True
researcher_with_delegation.tools = [TestTool()]
writer_for_delegation = writer.model_copy()
# Create a task with different tools
task = Task(
description="Write a test task",
expected_output="Test output",
agent=researcher_with_delegation,
tools=[AnotherTestTool()],
)
crew = Crew(
agents=[researcher_with_delegation, writer_for_delegation],
tasks=[task],
process=Process.sequential,
)
mock_task_output = TaskOutput(
description="Mock description", raw="mocked output", agent="mocked agent"
)
# We mock execute_sync to verify which tools get used at runtime
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Inspect the call kwargs to verify the actual tools passed to execution
_, kwargs = mock_execute_sync.call_args
used_tools = kwargs["tools"]
# Confirm AnotherTestTool is present but TestTool is not
assert any(
isinstance(tool, AnotherTestTool) for tool in used_tools
), "AnotherTestTool should be present"
assert not any(
isinstance(tool, TestTool) for tool in used_tools
), "TestTool should not be present among used tools"
# Confirm delegation tool(s) are present
assert any(
"delegate" in tool.name.lower() for tool in used_tools
), "Delegation tool should be present"
# Finally, make sure the agent's original tools remain unchanged
assert len(researcher_with_delegation.tools) == 1
assert isinstance(researcher_with_delegation.tools[0], TestTool)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_verbose_output(capsys):
tasks = [
@@ -692,8 +1050,8 @@ def test_three_task_with_async_execution():
)
@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.mark.asyncio
@pytest.mark.vcr(filter_headers=["authorization"])
async def test_crew_async_kickoff():
inputs = [
{"topic": "dog"},
@@ -740,8 +1098,9 @@ async def test_crew_async_kickoff():
assert result[0].token_usage.successful_requests > 0 # type: ignore
@pytest.mark.asyncio
@pytest.mark.vcr(filter_headers=["authorization"])
def test_async_task_execution_call_count():
async def test_async_task_execution_call_count():
from unittest.mock import MagicMock, patch
list_ideas = Task(
@@ -868,7 +1227,6 @@ def test_kickoff_for_each_empty_input():
assert results == []
@pytest.mark.vcr(filter_headers=["authorization"])
def test_kickoff_for_each_invalid_input():
"""Tests if kickoff_for_each raises TypeError for invalid input types."""
@@ -891,7 +1249,6 @@ def test_kickoff_for_each_invalid_input():
crew.kickoff_for_each("invalid input")
@pytest.mark.vcr(filter_headers=["authorization"])
def test_kickoff_for_each_error_handling():
"""Tests error handling in kickoff_for_each when kickoff raises an error."""
from unittest.mock import patch
@@ -928,7 +1285,6 @@ def test_kickoff_for_each_error_handling():
crew.kickoff_for_each(inputs=inputs)
@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.mark.asyncio
async def test_kickoff_async_basic_functionality_and_output():
"""Tests the basic functionality and output of kickoff_async."""
@@ -963,7 +1319,6 @@ async def test_kickoff_async_basic_functionality_and_output():
mock_kickoff.assert_called_once_with(inputs)
@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.mark.asyncio
async def test_async_kickoff_for_each_async_basic_functionality_and_output():
"""Tests the basic functionality and output of kickoff_for_each_async."""
@@ -1010,7 +1365,6 @@ async def test_async_kickoff_for_each_async_basic_functionality_and_output():
mock_kickoff_async.assert_any_call(inputs=input_data)
@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.mark.asyncio
async def test_async_kickoff_for_each_async_empty_input():
"""Tests if akickoff_for_each_async handles an empty input list."""
@@ -1193,11 +1547,24 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
crew = Crew(agents=[programmer], tasks=[task])
with patch.object(Agent, "execute_task") as executor:
executor.return_value = "ok"
mock_task_output = TaskOutput(
description="Mock description", raw="mocked output", agent="mocked agent"
)
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
assert len(programmer.tools) == 1
assert programmer.tools[0].__class__ == CodeInterpreterTool
# Get the tools that were actually used in execution
_, kwargs = mock_execute_sync.call_args
used_tools = kwargs["tools"]
# Verify that exactly one tool was used and it was a CodeInterpreterTool
assert len(used_tools) == 1, "Should have exactly one tool"
assert isinstance(
used_tools[0], CodeInterpreterTool
), "Tool should be CodeInterpreterTool"
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -1307,21 +1674,45 @@ def test_hierarchical_crew_creation_tasks_with_agents():
process=Process.hierarchical,
manager_llm="gpt-4o",
)
crew.kickoff()
assert crew.manager_agent is not None
assert crew.manager_agent.tools is not None
assert (
"Delegate a specific task to one of the following coworkers: Senior Writer\n"
in crew.manager_agent.tools[0].description
mock_task_output = TaskOutput(
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Because we are mocking execute_sync, we never hit the underlying _execute_core
# which sets the output attribute of the task
task.output = mock_task_output
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Verify execute_sync was called once
mock_execute_sync.assert_called_once()
# Get the tools argument from the call
_, kwargs = mock_execute_sync.call_args
tools = kwargs["tools"]
# Verify the delegation tools were passed correctly
assert len(tools) == 2
assert any(
"Delegate a specific task to one of the following coworkers: Senior Writer"
in tool.description
for tool in tools
)
assert any(
"Ask a specific question to one of the following coworkers: Senior Writer"
in tool.description
for tool in tools
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_hierarchical_crew_creation_tasks_with_async_execution():
"""
Agents are not required for tasks in a hierarchical process but sometimes they are still added
This test makes sure that the manager still delegates the task to the agent even if the agent is passed in the task
Tests that async tasks in hierarchical crews are handled correctly with proper delegation tools
"""
task = Task(
description="Write one amazing paragraph about AI.",
@@ -1337,14 +1728,43 @@ def test_hierarchical_crew_creation_tasks_with_async_execution():
manager_llm="gpt-4o",
)
crew.kickoff()
assert crew.manager_agent is not None
assert crew.manager_agent.tools is not None
assert (
"Delegate a specific task to one of the following coworkers: Senior Writer\n"
in crew.manager_agent.tools[0].description
mock_task_output = TaskOutput(
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Create a mock Future that returns our TaskOutput
mock_future = MagicMock(spec=Future)
mock_future.result.return_value = mock_task_output
# Because we are mocking execute_async, we never hit the underlying _execute_core
# which sets the output attribute of the task
task.output = mock_task_output
with patch.object(
Task, "execute_async", return_value=mock_future
) as mock_execute_async:
crew.kickoff()
# Verify execute_async was called once
mock_execute_async.assert_called_once()
# Get the tools argument from the call
_, kwargs = mock_execute_async.call_args
tools = kwargs["tools"]
# Verify the delegation tools were passed correctly
assert len(tools) == 2
assert any(
"Delegate a specific task to one of the following coworkers: Senior Writer\n"
in tool.description
for tool in tools
)
assert any(
"Ask a specific question to one of the following coworkers: Senior Writer\n"
in tool.description
for tool in tools
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_hierarchical_crew_creation_tasks_with_sync_last():
@@ -1640,6 +2060,88 @@ def test_crew_log_file_output(tmp_path):
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_output_file_end_to_end(tmp_path):
"""Test output file functionality in a full crew context."""
# Create an agent
agent = Agent(
role="Researcher",
goal="Analyze AI topics",
backstory="You have extensive AI research experience.",
allow_delegation=False,
)
# Create a task with dynamic output file path
dynamic_path = tmp_path / "output_{topic}.txt"
task = Task(
description="Explain the advantages of {topic}.",
expected_output="A summary of the main advantages, bullet points recommended.",
agent=agent,
output_file=str(dynamic_path),
)
# Create and run the crew
crew = Crew(
agents=[agent],
tasks=[task],
process=Process.sequential,
)
crew.kickoff(inputs={"topic": "AI"})
# Verify file creation and cleanup
expected_file = tmp_path / "output_AI.txt"
assert expected_file.exists(), f"Output file {expected_file} was not created"
def test_crew_output_file_validation_failures():
"""Test output file validation failures in a crew context."""
agent = Agent(
role="Researcher",
goal="Analyze data",
backstory="You analyze data files.",
allow_delegation=False,
)
# Test path traversal
with pytest.raises(ValueError, match="Path traversal"):
task = Task(
description="Analyze data",
expected_output="Analysis results",
agent=agent,
output_file="../output.txt",
)
Crew(agents=[agent], tasks=[task]).kickoff()
# Test shell special characters
with pytest.raises(ValueError, match="Shell special characters"):
task = Task(
description="Analyze data",
expected_output="Analysis results",
agent=agent,
output_file="output.txt | rm -rf /",
)
Crew(agents=[agent], tasks=[task]).kickoff()
# Test shell expansion
with pytest.raises(ValueError, match="Shell expansion"):
task = Task(
description="Analyze data",
expected_output="Analysis results",
agent=agent,
output_file="~/output.txt",
)
Crew(agents=[agent], tasks=[task]).kickoff()
# Test invalid template variable
with pytest.raises(ValueError, match="Invalid template variable"):
task = Task(
description="Analyze data",
expected_output="Analysis results",
agent=agent,
output_file="{invalid-name}/output.txt",
)
Crew(agents=[agent], tasks=[task]).kickoff()
def test_manager_agent():
from unittest.mock import patch
@@ -2606,3 +3108,254 @@ def test_fetch_inputs():
assert (
actual_placeholders == expected_placeholders
), f"Expected {expected_placeholders}, but got {actual_placeholders}"
def test_task_tools_preserve_code_execution_tools():
"""
Test that task tools don't override code execution tools when allow_code_execution=True
"""
from typing import Type
from crewai_tools import CodeInterpreterTool
from pydantic import BaseModel, Field
from crewai.tools import BaseTool
class TestToolInput(BaseModel):
"""Input schema for TestTool."""
query: str = Field(..., description="Query to process")
class TestTool(BaseTool):
name: str = "Test Tool"
description: str = "A test tool that just returns the input"
args_schema: Type[BaseModel] = TestToolInput
def _run(self, query: str) -> str:
return f"Processed: {query}"
# Create a programmer agent with code execution enabled
programmer = Agent(
role="Programmer",
goal="Write code to solve problems.",
backstory="You're a programmer who loves to solve problems with code.",
allow_delegation=True,
allow_code_execution=True,
)
# Create a code reviewer agent
reviewer = Agent(
role="Code Reviewer",
goal="Review code for bugs and improvements",
backstory="You're an experienced code reviewer who ensures code quality and best practices.",
allow_delegation=True,
allow_code_execution=True,
)
# Create a task with its own tools
task = Task(
description="Write a program to calculate fibonacci numbers.",
expected_output="A working fibonacci calculator.",
agent=programmer,
tools=[TestTool()],
)
crew = Crew(
agents=[programmer, reviewer],
tasks=[task],
process=Process.sequential,
)
mock_task_output = TaskOutput(
description="Mock description", raw="mocked output", agent="mocked agent"
)
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Get the tools that were actually used in execution
_, kwargs = mock_execute_sync.call_args
used_tools = kwargs["tools"]
# Verify all expected tools are present
assert any(
isinstance(tool, TestTool) for tool in used_tools
), "Task's TestTool should be present"
assert any(
isinstance(tool, CodeInterpreterTool) for tool in used_tools
), "CodeInterpreterTool should be present"
assert any(
"delegate" in tool.name.lower() for tool in used_tools
), "Delegation tool should be present"
# Verify the total number of tools (TestTool + CodeInterpreter + 2 delegation tools)
assert (
len(used_tools) == 4
), "Should have TestTool, CodeInterpreter, and 2 delegation tools"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_multimodal_flag_adds_multimodal_tools():
"""
Test that an agent with multimodal=True automatically has multimodal tools added to the task execution.
"""
from crewai.tools.agent_tools.add_image_tool import AddImageTool
# Create an agent that supports multimodal
multimodal_agent = Agent(
role="Multimodal Analyst",
goal="Handle multiple media types (text, images, etc.).",
backstory="You're an agent specialized in analyzing text, images, and other media.",
allow_delegation=False,
multimodal=True, # crucial for adding the multimodal tool
)
# Create a dummy task
task = Task(
description="Describe what's in this image and generate relevant metadata.",
expected_output="An image description plus any relevant metadata.",
agent=multimodal_agent,
)
# Define a crew with the multimodal agent
crew = Crew(agents=[multimodal_agent], tasks=[task], process=Process.sequential)
mock_task_output = TaskOutput(
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Mock execute_sync to verify the tools passed at runtime
with patch.object(
Task, "execute_sync", return_value=mock_task_output
) as mock_execute_sync:
crew.kickoff()
# Get the tools that were actually used in execution
_, kwargs = mock_execute_sync.call_args
used_tools = kwargs["tools"]
# Check that the multimodal tool was added
assert any(
isinstance(tool, AddImageTool) for tool in used_tools
), "AddImageTool should be present when agent is multimodal"
# Verify we have exactly one tool (just the AddImageTool)
assert len(used_tools) == 1, "Should only have the AddImageTool"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_multimodal_agent_image_tool_handling():
"""
Test that multimodal agents properly handle image tools in the CrewAgentExecutor
"""
# Create a multimodal agent
multimodal_agent = Agent(
role="Image Analyst",
goal="Analyze images and provide descriptions",
backstory="You're an expert at analyzing and describing images.",
allow_delegation=False,
multimodal=True,
)
# Create a task that involves image analysis
task = Task(
description="Analyze this image and describe what you see.",
expected_output="A detailed description of the image.",
agent=multimodal_agent,
)
crew = Crew(agents=[multimodal_agent], tasks=[task])
# Mock the image tool response
mock_image_tool_result = {
"role": "user",
"content": [
{"type": "text", "text": "Please analyze this image"},
{
"type": "image_url",
"image_url": {
"url": "https://example.com/test-image.jpg",
},
},
],
}
# Create a mock task output for the final result
mock_task_output = TaskOutput(
description="Mock description",
raw="A detailed analysis of the image",
agent="Image Analyst",
)
with patch.object(Task, "execute_sync") as mock_execute_sync:
# Set up the mock to return our task output
mock_execute_sync.return_value = mock_task_output
# Execute the crew
crew.kickoff()
# Get the tools that were passed to execute_sync
_, kwargs = mock_execute_sync.call_args
tools = kwargs["tools"]
# Verify the AddImageTool is present and properly configured
image_tools = [tool for tool in tools if tool.name == "Add image to content"]
assert len(image_tools) == 1, "Should have exactly one AddImageTool"
# Test the tool's execution
image_tool = image_tools[0]
result = image_tool._run(
image_url="https://example.com/test-image.jpg",
action="Please analyze this image",
)
# Verify the tool returns the expected format
assert result == mock_image_tool_result
assert result["role"] == "user"
assert len(result["content"]) == 2
assert result["content"][0]["type"] == "text"
assert result["content"][1]["type"] == "image_url"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_multimodal_agent_live_image_analysis():
"""
Test that multimodal agents can analyze images through a real API call
"""
# Create a multimodal agent
image_analyst = Agent(
role="Image Analyst",
goal="Analyze images with high attention to detail",
backstory="You're an expert at visual analysis, trained to notice and describe details in images.",
allow_delegation=False,
multimodal=True,
verbose=True,
llm="gpt-4o",
)
# Create a task for image analysis
analyze_image = Task(
description="""
Analyze the provided image and describe what you see in detail.
Focus on main elements, colors, composition, and any notable details.
Image: {image_url}
""",
expected_output="A comprehensive description of the image contents.",
agent=image_analyst,
)
# Create and run the crew
crew = Crew(agents=[image_analyst], tasks=[analyze_image])
# Execute with an image URL
result = crew.kickoff(
inputs={
"image_url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k="
}
)
# Verify we got a meaningful response
assert isinstance(result.raw, str)
assert len(result.raw) > 100 # Expecting a detailed analysis
assert "error" not in result.raw.lower() # No error messages in response

59
tests/flow_test.py
View File

@@ -263,3 +263,62 @@ def test_flow_with_custom_state():
flow = StateFlow()
flow.kickoff()
assert flow.counter == 2
def test_router_with_multiple_conditions():
"""Test a router that triggers when any of multiple steps complete (OR condition),
and another router that triggers only after all specified steps complete (AND condition).
"""
execution_order = []
class ComplexRouterFlow(Flow):
@start()
def step_a(self):
execution_order.append("step_a")
@start()
def step_b(self):
execution_order.append("step_b")
@router(or_("step_a", "step_b"))
def router_or(self):
execution_order.append("router_or")
return "next_step_or"
@listen("next_step_or")
def handle_next_step_or_event(self):
execution_order.append("handle_next_step_or_event")
@listen(handle_next_step_or_event)
def branch_2_step(self):
execution_order.append("branch_2_step")
@router(and_(handle_next_step_or_event, branch_2_step))
def router_and(self):
execution_order.append("router_and")
return "final_step"
@listen("final_step")
def log_final_step(self):
execution_order.append("log_final_step")
flow = ComplexRouterFlow()
flow.kickoff()
assert "step_a" in execution_order
assert "step_b" in execution_order
assert "router_or" in execution_order
assert "handle_next_step_or_event" in execution_order
assert "branch_2_step" in execution_order
assert "router_and" in execution_order
assert "log_final_step" in execution_order
# Check that the AND router triggered after both relevant steps:
assert execution_order.index("router_and") > execution_order.index(
"handle_next_step_or_event"
)
assert execution_order.index("router_and") > execution_order.index("branch_2_step")
# final_step should run after router_and
assert execution_order.index("log_final_step") > execution_order.index("router_and")

25
tests/knowledge/knowledge_test.py
View File

@@ -578,9 +578,26 @@ def test_multiple_docling_sources():
assert docling_source.content is not None
def test_docling_source_with_local_file():
def test_file_path_validation():
"""Test file path validation for knowledge sources."""
current_dir = Path(__file__).parent
pdf_path = current_dir / "crewai_quickstart.pdf"
docling_source = CrewDoclingSource(file_paths=[pdf_path])
assert docling_source.file_paths == [pdf_path]
assert docling_source.content is not None
# Test valid single file_path
source = PDFKnowledgeSource(file_path=pdf_path)
assert source.safe_file_paths == [pdf_path]
# Test valid file_paths list
source = PDFKnowledgeSource(file_paths=[pdf_path])
assert source.safe_file_paths == [pdf_path]
# Test both file_path and file_paths provided (should use file_paths)
source = PDFKnowledgeSource(file_path=pdf_path, file_paths=[pdf_path])
assert source.safe_file_paths == [pdf_path]
# Test neither file_path nor file_paths provided
with pytest.raises(
ValueError,
match="file_path/file_paths must be a Path, str, or a list of these types",
):
PDFKnowledgeSource()

98
tests/task_test.py
View File

@@ -719,61 +719,58 @@ def test_interpolate_inputs():
task = Task(
description="Give me a list of 5 interesting ideas about {topic} to explore for an article, what makes them unique and interesting.",
expected_output="Bullet point list of 5 interesting ideas about {topic}.",
output_file="/tmp/{topic}/output_{date}.txt",
)
task.interpolate_inputs(inputs={"topic": "AI"})
task.interpolate_inputs(inputs={"topic": "AI", "date": "2024"})
assert (
task.description
== "Give me a list of 5 interesting ideas about AI to explore for an article, what makes them unique and interesting."
)
assert task.expected_output == "Bullet point list of 5 interesting ideas about AI."
assert task.output_file == "/tmp/AI/output_2024.txt"
task.interpolate_inputs(inputs={"topic": "ML"})
task.interpolate_inputs(inputs={"topic": "ML", "date": "2025"})
assert (
task.description
== "Give me a list of 5 interesting ideas about ML to explore for an article, what makes them unique and interesting."
)
assert task.expected_output == "Bullet point list of 5 interesting ideas about ML."
assert task.output_file == "/tmp/ML/output_2025.txt"
def test_interpolate_only():
"""Test the interpolate_only method for various scenarios including JSON structure preservation."""
task = Task(
description="Unused in this test",
expected_output="Unused in this test"
description="Unused in this test", expected_output="Unused in this test"
)
# Test JSON structure preservation
json_string = '{"info": "Look at {placeholder}", "nested": {"val": "{nestedVal}"}}'
result = task.interpolate_only(
input_string=json_string,
inputs={"placeholder": "the data", "nestedVal": "something else"}
inputs={"placeholder": "the data", "nestedVal": "something else"},
)
assert '"info": "Look at the data"' in result
assert '"val": "something else"' in result
assert "{placeholder}" not in result
assert "{nestedVal}" not in result
# Test normal string interpolation
normal_string = "Hello {name}, welcome to {place}!"
result = task.interpolate_only(
input_string=normal_string,
inputs={"name": "John", "place": "CrewAI"}
input_string=normal_string, inputs={"name": "John", "place": "CrewAI"}
)
assert result == "Hello John, welcome to CrewAI!"
# Test empty string
result = task.interpolate_only(
input_string="",
inputs={"unused": "value"}
)
result = task.interpolate_only(input_string="", inputs={"unused": "value"})
assert result == ""
# Test string with no placeholders
no_placeholders = "Hello, this is a test"
result = task.interpolate_only(
input_string=no_placeholders,
inputs={"unused": "value"}
input_string=no_placeholders, inputs={"unused": "value"}
)
assert result == no_placeholders
@@ -872,3 +869,70 @@ def test_key():
assert (
task.key == hash
), "The key should be the hash of the non-interpolated description."
def test_output_file_validation():
"""Test output file path validation."""
# Valid paths
assert (
Task(
description="Test task",
expected_output="Test output",
output_file="output.txt",
).output_file
== "output.txt"
)
assert (
Task(
description="Test task",
expected_output="Test output",
output_file="/tmp/output.txt",
).output_file
== "tmp/output.txt"
)
assert (
Task(
description="Test task",
expected_output="Test output",
output_file="{dir}/output_{date}.txt",
).output_file
== "{dir}/output_{date}.txt"
)
# Invalid paths
with pytest.raises(ValueError, match="Path traversal"):
Task(
description="Test task",
expected_output="Test output",
output_file="../output.txt",
)
with pytest.raises(ValueError, match="Path traversal"):
Task(
description="Test task",
expected_output="Test output",
output_file="folder/../output.txt",
)
with pytest.raises(ValueError, match="Shell special characters"):
Task(
description="Test task",
expected_output="Test output",
output_file="output.txt | rm -rf /",
)
with pytest.raises(ValueError, match="Shell expansion"):
Task(
description="Test task",
expected_output="Test output",
output_file="~/output.txt",
)
with pytest.raises(ValueError, match="Shell expansion"):
Task(
description="Test task",
expected_output="Test output",
output_file="$HOME/output.txt",
)
with pytest.raises(ValueError, match="Invalid template variable"):
Task(
description="Test task",
expected_output="Test output",
output_file="{invalid-name}/output.txt",
)

56
tests/test_manager_llm_delegation.py Normal file
View File

@@ -0,0 +1,56 @@
from unittest.mock import MagicMock
import pytest
from crewai import Agent, Task
from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool
class TestAgentTool(BaseAgentTool):
"""Concrete implementation of BaseAgentTool for testing."""
def _run(self, *args, **kwargs):
"""Implement required _run method."""
return "Test response"
@pytest.mark.parametrize(
"role_name,should_match",
[
("Futel Official Infopoint", True), # exact match
(' "Futel Official Infopoint" ', True), # extra quotes and spaces
("Futel Official Infopoint\n", True), # trailing newline
('"Futel Official Infopoint"', True), # embedded quotes
(" FUTEL\nOFFICIAL INFOPOINT ", True), # multiple whitespace and newline
("futel official infopoint", True), # lowercase
("FUTEL OFFICIAL INFOPOINT", True), # uppercase
("Non Existent Agent", False), # non-existent agent
(None, False), # None agent name
],
)
def test_agent_tool_role_matching(role_name, should_match):
"""Test that agent tools can match roles regardless of case, whitespace, and special characters."""
# Create test agent
test_agent = Agent(
role="Futel Official Infopoint",
goal="Answer questions about Futel",
backstory="Futel Football Club info",
allow_delegation=False,
)
# Create test agent tool
agent_tool = TestAgentTool(
name="test_tool", description="Test tool", agents=[test_agent]
)
# Test role matching
result = agent_tool._execute(agent_name=role_name, task="Test task", context=None)
if should_match:
assert (
"coworker mentioned not found" not in result.lower()
), f"Should find agent with role name: {role_name}"
else:
assert (
"coworker mentioned not found" in result.lower()
), f"Should not find agent with role name: {role_name}"

27
tests/test_task_guardrails.py
View File

@@ -15,10 +15,7 @@ def test_task_without_guardrail():
agent.execute_task.return_value = "test result"
agent.crew = None
task = Task(
description="Test task",
expected_output="Output"
)
task = Task(description="Test task", expected_output="Output")
result = task.execute_sync(agent=agent)
assert isinstance(result, TaskOutput)
@@ -27,6 +24,7 @@ def test_task_without_guardrail():
def test_task_with_successful_guardrail():
"""Test that successful guardrail validation passes transformed result."""
def guardrail(result: TaskOutput):
return (True, result.raw.upper())
@@ -35,11 +33,7 @@ def test_task_with_successful_guardrail():
agent.execute_task.return_value = "test result"
agent.crew = None
task = Task(
description="Test task",
expected_output="Output",
guardrail=guardrail
)
task = Task(description="Test task", expected_output="Output", guardrail=guardrail)
result = task.execute_sync(agent=agent)
assert isinstance(result, TaskOutput)
@@ -48,22 +42,20 @@ def test_task_with_successful_guardrail():
def test_task_with_failing_guardrail():
"""Test that failing guardrail triggers retry with error context."""
def guardrail(result: TaskOutput):
return (False, "Invalid format")
agent = Mock()
agent.role = "test_agent"
agent.execute_task.side_effect = [
"bad result",
"good result"
]
agent.execute_task.side_effect = ["bad result", "good result"]
agent.crew = None
task = Task(
description="Test task",
expected_output="Output",
guardrail=guardrail,
max_retries=1
max_retries=1,
)
# First execution fails guardrail, second succeeds
@@ -77,6 +69,7 @@ def test_task_with_failing_guardrail():
def test_task_with_guardrail_retries():
"""Test that guardrail respects max_retries configuration."""
def guardrail(result: TaskOutput):
return (False, "Invalid format")
@@ -89,7 +82,7 @@ def test_task_with_guardrail_retries():
description="Test task",
expected_output="Output",
guardrail=guardrail,
max_retries=2
max_retries=2,
)
with pytest.raises(Exception) as exc_info:
@@ -102,6 +95,7 @@ def test_task_with_guardrail_retries():
def test_guardrail_error_in_context():
"""Test that guardrail error is passed in context for retry."""
def guardrail(result: TaskOutput):
return (False, "Expected JSON, got string")
@@ -113,11 +107,12 @@ def test_guardrail_error_in_context():
description="Test task",
expected_output="Output",
guardrail=guardrail,
max_retries=1
max_retries=1,
)
# Mock execute_task to succeed on second attempt
first_call = True
def execute_task(task, context, tools):
nonlocal first_call
if first_call:

84
tests/utilities/test_knowledge_planning.py Normal file
View File

@@ -0,0 +1,84 @@
"""
Tests for verifying the integration of knowledge sources in the planning process.
This module ensures that agent knowledge is properly included during task planning.
"""
from unittest.mock import patch
import pytest
from crewai.agent import Agent
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
from crewai.task import Task
from crewai.utilities.planning_handler import CrewPlanner
@pytest.fixture
def mock_knowledge_source():
"""
Create a mock knowledge source with test content.
Returns:
StringKnowledgeSource:
A knowledge source containing AI-related test content
"""
content = """
Important context about AI:
1. AI systems use machine learning algorithms
2. Neural networks are a key component
3. Training data is essential for good performance
"""
return StringKnowledgeSource(content=content)
@patch('crewai.knowledge.storage.knowledge_storage.chromadb')
def test_knowledge_included_in_planning(mock_chroma):
"""Test that verifies knowledge sources are properly included in planning."""
# Mock ChromaDB collection
mock_collection = mock_chroma.return_value.get_or_create_collection.return_value
mock_collection.add.return_value = None
# Create an agent with knowledge
agent = Agent(
role="AI Researcher",
goal="Research and explain AI concepts",
backstory="Expert in artificial intelligence",
knowledge_sources=[
StringKnowledgeSource(
content="AI systems require careful training and validation."
)
]
)
# Create a task for the agent
task = Task(
description="Explain the basics of AI systems",
expected_output="A clear explanation of AI fundamentals",
agent=agent
)
# Create a crew planner
planner = CrewPlanner([task], None)
# Get the task summary
task_summary = planner._create_tasks_summary()
# Verify that knowledge is included in planning when present
assert "AI systems require careful training" in task_summary, \
"Knowledge content should be present in task summary when knowledge exists"
assert '"agent_knowledge"' in task_summary, \
"agent_knowledge field should be present in task summary when knowledge exists"
# Verify that knowledge is properly formatted
assert isinstance(task.agent.knowledge_sources, list), \
"Knowledge sources should be stored in a list"
assert len(task.agent.knowledge_sources) > 0, \
"At least one knowledge source should be present"
assert task.agent.knowledge_sources[0].content in task_summary, \
"Knowledge source content should be included in task summary"
# Verify that other expected components are still present
assert task.description in task_summary, \
"Task description should be present in task summary"
assert task.expected_output in task_summary, \
"Expected output should be present in task summary"
assert agent.role in task_summary, \
"Agent role should be present in task summary"

73
tests/utilities/test_planning_handler.py
View File

@@ -1,10 +1,14 @@
from unittest.mock import patch
from typing import Optional
from unittest.mock import MagicMock, patch
import pytest
from pydantic import BaseModel
from crewai.agent import Agent
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
from crewai.task import Task
from crewai.tasks.task_output import TaskOutput
from crewai.tools.base_tool import BaseTool
from crewai.utilities.planning_handler import (
CrewPlanner,
PlannerTaskPydanticOutput,
@@ -92,7 +96,72 @@ class TestCrewPlanner:
tasks_summary = crew_planner._create_tasks_summary()
assert isinstance(tasks_summary, str)
assert tasks_summary.startswith("\n Task Number 1 - Task 1")
assert tasks_summary.endswith('"agent_tools": []\n ')
assert '"agent_tools": "agent has no tools"' in tasks_summary
# Knowledge field should not be present when empty
assert '"agent_knowledge"' not in tasks_summary
@patch('crewai.knowledge.storage.knowledge_storage.chromadb')
def test_create_tasks_summary_with_knowledge_and_tools(self, mock_chroma):
"""Test task summary generation with both knowledge and tools present."""
# Mock ChromaDB collection
mock_collection = mock_chroma.return_value.get_or_create_collection.return_value
mock_collection.add.return_value = None
# Create mock tools with proper string descriptions and structured tool support
class MockTool(BaseTool):
name: str
description: str
def __init__(self, name: str, description: str):
tool_data = {"name": name, "description": description}
super().__init__(**tool_data)
def __str__(self):
return self.name
def __repr__(self):
return self.name
def to_structured_tool(self):
return self
def _run(self, *args, **kwargs):
pass
def _generate_description(self) -> str:
"""Override _generate_description to avoid args_schema handling."""
return self.description
tool1 = MockTool("tool1", "Tool 1 description")
tool2 = MockTool("tool2", "Tool 2 description")
# Create a task with knowledge and tools
task = Task(
description="Task with knowledge and tools",
expected_output="Expected output",
agent=Agent(
role="Test Agent",
goal="Test Goal",
backstory="Test Backstory",
tools=[tool1, tool2],
knowledge_sources=[
StringKnowledgeSource(content="Test knowledge content")
]
)
)
# Create planner with the new task
planner = CrewPlanner([task], None)
tasks_summary = planner._create_tasks_summary()
# Verify task summary content
assert isinstance(tasks_summary, str)
assert task.description in tasks_summary
assert task.expected_output in tasks_summary
assert '"agent_tools": [tool1, tool2]' in tasks_summary
assert '"agent_knowledge": "[\\"Test knowledge content\\"]"' in tasks_summary
assert task.agent.role in tasks_summary
assert task.agent.goal in tasks_summary
def test_handle_crew_planning_different_llm(self, crew_planner_different_llm):
with patch.object(Task, "execute_sync") as execute: