andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-26 16:48:13 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Updating all cassetes

Browse Source
This commit is contained in:
João Moura
2024-09-18 04:17:41 -03:00
parent d7473edb41
commit 5a3b888f43
86 changed files with 14978 additions and 14587 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
tests/agent_tools/cassettes/test_ask_question.yaml
View File

@@ -25,12 +25,12 @@ interactions:
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -40,7 +40,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
- 1.46.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -50,29 +50,37 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81diwze1dbmDs6t6AXf1vRTethrp\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476290,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A8itGodu0IQ3bZNxRStGoqFBPnObt\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642546,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer.\\nFinal
Answer: No, I do not hate AI agents; in fact, I find them incredibly fascinating
and useful. As a researcher specializing in technology, particularly in AI and
AI agents, I appreciate their potential to revolutionize various industries
by automating tasks, providing deep insights through data analysis, and even
enhancing decision-making processes. AI agents can streamline operations, improve
efficiency, and contribute to advancements in fields like healthcare, finance,
and cybersecurity. While they do present challenges, such as ethical considerations
and the need for robust security measures, the benefits and potential for positive
impact are immense. Therefore, my stance is one of strong support and enthusiasm
for AI agents and their future developments.\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\":
145,\n \"total_tokens\": 344,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: As a researcher specialized in technology with a particular focus on
AI and AI agents, my stance on AI agents isn't rooted in emotional responses
like hate or love. Rather, it is grounded in objective analysis and thoughtful
consideration of their capabilities, ethics, and impact on society.\\n\\nAI
agents are powerful tools that can transform various industries, from healthcare
and finance to customer service and manufacturing. They have the potential to
increase efficiency, improve decision-making, and even solve complex problems
that were previously insurmountable. For instance, AI agents can analyze vast
amounts of data far more quickly and accurately than humans, leading to advancements
in medical research and diagnostics.\\n\\nHowever, it is equally important to
recognize the ethical and societal implications of AI agents. Issues such as
data privacy, algorithmic bias, and the potential displacement of jobs need
to be carefully managed. As a researcher, my role is to study these aspects
comprehensively, provide balanced insights, and advocate for responsible development
and deployment of AI technologies.\\n\\nSo, to address your question directly:
I don't hate AI agents. I appreciate their potential and am keenly aware of
their challenges. My goal is to contribute to a future where AI agents are designed
and used ethically and effectively to benefit humanity.\\n\\n\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\":
257,\n \"total_tokens\": 456,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f93ae9a382233-MIA
- 8c4f6ea85a70a67a-MIA
Connection:
- keep-alive
Content-Encoding:
@@ -80,7 +88,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:44:51 GMT
- Wed, 18 Sep 2024 06:55:49 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -94,7 +102,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1322'
- '2905'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -112,7 +120,7 @@ interactions:
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_c3606c83dcda394dc3caf0ef5ef72833
- req_ee404d560531f43e473f76818a52432f
http_version: HTTP/1.1
status_code: 200
version: 1

52
tests/agent_tools/cassettes/test_ask_question_with_coworker_as_array.yaml
View File

@@ -25,12 +25,12 @@ interactions:
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -40,7 +40,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
- 1.46.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -50,34 +50,28 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81dsDR0oIy60Go4lOiHoFauBk1Sl\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476300,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A8itTPbch8sPUbRd8BJdzF4NXLPhg\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642559,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: As a researcher specialized in technology, particularly in AI and AI
agents, my feelings toward them are far more nuanced than simply loving or hating
them. AI agents represent a remarkable advancement in technology and hold tremendous
potential for improving various aspects of our lives and industries. They can
automate tedious tasks, provide intelligent data analysis, support decision-making,
and even enhance our creative processes. These capabilities can drive efficiency,
innovation, and economic growth.\\n\\nHowever, it is also crucial to acknowledge
the challenges and ethical considerations posed by AI agents. Issues such as
data privacy, security, job displacement, and the need for proper regulation
are significant concerns that must be carefully managed. Moreover, the development
and deployment of AI should be guided by principles that ensure fairness, transparency,
and accountability.\\n\\nIn essence, I appreciate the profound impact AI agents
can have, but I also recognize the importance of approaching their integration
into society with thoughtful consideration and responsibility. Balancing enthusiasm
with caution and ethical oversight is key to harnessing the full potential of
AI while mitigating its risks.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
199,\n \"completion_tokens\": 219,\n \"total_tokens\": 418,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
Answer: No, I do not hate AI agents. In fact, I appreciate their potential and
the positive impact they can have in various fields. AI agents can perform tasks
that are either too mundane or too complex for humans, thereby increasing productivity
and allowing us to focus on more creative and strategic activities. Moreover,
they can process and analyze vast amounts of data much more quickly and accurately
than humans, leading to better decision-making and innovations. As a researcher
specialized in technology, I am always excited to see advancements in AI and
AI agents, as they push the boundaries of what technology can achieve. So, yes,
I do love the possibilities they bring to our world.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\":
144,\n \"total_tokens\": 343,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f93ee7b872233-MIA
- 8c4f6efe3d94a67a-MIA
Connection:
- keep-alive
Content-Encoding:
@@ -85,7 +79,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:45:02 GMT
- Wed, 18 Sep 2024 06:56:01 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -99,7 +93,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '2179'
- '1836'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -117,7 +111,7 @@ interactions:
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_924c8676ca28af7092f32e2992bde2ec
- req_51693c1b5a37ada8922542e71cae13c2
http_version: HTTP/1.1
status_code: 200
version: 1

45
tests/agent_tools/cassettes/test_ask_question_with_wrong_co_worker_variable.yaml
View File

@@ -25,12 +25,12 @@ interactions:
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -40,7 +40,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
- 1.46.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -50,27 +50,28 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81dkIBLB3iUbp5yVV0UtIcXQEK7d\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476292,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A8itJwg2Rf7SP6eMx3exZlflDAqWo\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642549,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: I do not hate AI agents; in fact, I appreciate them for their immense
potential and the numerous benefits they bring to various fields. My passion
for AI agents stems from their ability to streamline processes, enhance decision-making,
and provide innovative solutions to complex problems. They significantly contribute
to advancements in healthcare, finance, education, and many other sectors, making
tasks more efficient and freeing up human capacities for more creative and strategic
endeavors. So, to answer your question, I love AI agents because of the positive
impact they have on our world and their capability to drive technological progress.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\":
127,\n \"total_tokens\": 326,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
Answer: As an expert researcher specialized in technology, I have a profound
appreciation for AI and AI agents. They represent a pinnacle of human innovation
and have the potential to greatly enhance various aspects of our lives. AI agents
can assist in automating mundane tasks, providing insights through data analysis,
and even offering companionship to those in need. However, it's also essential
to approach AI with a balanced perspective, acknowledging both its strengths
and the ethical considerations it raises. In short, I don't hate AI agents;
I recognize their immense potential and value while being mindful of the responsibilities
that come with their development and deployment.\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\":
131,\n \"total_tokens\": 330,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f93b95d3e2233-MIA
- 8c4f6ebc9a84a67a-MIA
Connection:
- keep-alive
Content-Encoding:
@@ -78,7 +79,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:44:53 GMT
- Wed, 18 Sep 2024 06:55:51 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -92,7 +93,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1189'
- '2379'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -110,7 +111,7 @@ interactions:
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_920f3c16f8de451a0d9a615430347aa7
- req_15a5949e2566bb034b07c4cdad9cd404
http_version: HTTP/1.1
status_code: 200
version: 1

141
tests/agent_tools/cassettes/test_delegate_work.yaml
View File

@@ -1,40 +1,4 @@
interactions:
- request:
body: !!binary |
CtACCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSpwIKEgoQY3Jld2FpLnRl
bGVtZXRyeRKQAgoQHmlJBYzBdapZtSVKNMGqJBII8BLkKX2PvTYqDlRhc2sgRXhlY3V0aW9uMAE5
CChrngat9RdBSI3l4gat9RdKLgoIY3Jld19rZXkSIgogYzMwNzYwMDkzMjY3NjE0NDRkNTdjNzFk
MWRhM2YyN2NKMQoHY3Jld19pZBImCiQwYTY5M2NmYi00YWZmLTQwYmItOTdmNi05N2ZkYzRhZmYy
YmNKLgoIdGFza19rZXkSIgogODBkN2JjZDQ5MDk5MjkwMDgzODMyZjBlOTgzMzgwZGZKMQoHdGFz
a19pZBImCiQwMzM0ODBlZC1jZTgxLTQ4NmYtOGRlMC0wMDEwZjU4MjRmNWN6AhgBhQEAAQAA
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '339'
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, 16 Sep 2024 08:44:42 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
@@ -62,12 +26,12 @@ interactions:
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -77,7 +41,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
- 1.46.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -87,62 +51,53 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81dXrByTXv0g084WinelJOTZraCk\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476279,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A8it3IFHv0h3PfGPsKBeopqXSTLd1\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642533,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: \\n\\nWhile it's a common perception that I might \\\"hate\\\" AI agents,
my actual stance is much more nuanced and guided by an in-depth understanding
of their potential and limitations. As an expert researcher in technology, I
recognize that AI agents are a significant advancement in the field of computing
and artificial intelligence, offering numerous benefits and applications across
various sectors. Here's a detailed take on AI agents:\\n\\n**Advantages of AI
Agents:**\\n1. **Automation and Efficiency:** AI agents can automate repetitive
tasks, thus freeing up human workers for more complex and creative work. This
leads to significant efficiency gains in industries such as customer service
(chatbots), data analysis, and even healthcare (AI diagnostic tools).\\n\\n2.
**24/7 Availability:** Unlike human workers, AI agents can operate continuously
without fatigue. This is particularly beneficial in customer service environments
where support can be provided around the clock.\\n\\n3. **Data Handling and
Analysis:** AI agents can process and analyze vast amounts of data more quickly
and accurately than humans. This ability is invaluable in fields like finance,
where AI can detect fraudulent activities, or in marketing, where consumer data
can be analyzed to improve customer engagement strategies.\\n\\n4. **Personalization:**
AI agents can provide personalized experiences by learning from user interactions.
For example, recommendation systems on platforms like Netflix and Amazon use
AI agents to suggest content or products tailored to individual preferences.\\n\\n5.
**Scalability:** AI agents can be scaled up easily to handle increasing workloads,
making them ideal for businesses experiencing growth or variable demand.\\n\\n**Challenges
and Concerns:**\\n1. **Ethical Implications:** The deployment of AI agents raises
significant ethical questions, including issues of bias, privacy, and the potential
for job displacement. It\u2019s crucial to address these concerns by incorporating
transparent, fair, and inclusive practices in AI development and deployment.\\n\\n2.
**Dependability and Error Rates:** While AI agents are generally reliable, they
are not infallible. Errors, especially in critical areas like healthcare or
autonomous driving, can have severe consequences. Therefore, rigorous testing
and validation are essential.\\n\\n3. **Lack of Understanding:** Many users
and stakeholders may not fully understand how AI agents work, leading to mistrust
or misuse. Improving AI literacy and transparency can help build trust in these
systems.\\n\\n4. **Security Risks:** AI agents can be vulnerable to cyber-attacks.
Ensuring robust cybersecurity measures are in place is vital to protect sensitive
data and maintain the integrity of AI systems.\\n\\n5. **Regulation and Oversight:**
The rapid development of AI technology often outpaces regulatory frameworks.
Effective governance is needed to ensure AI is used responsibly and ethically.\\n\\nIn
summary, while I thoroughly understand the transformative potential of AI agents
and their numerous advantages, I also recognize the importance of addressing
the associated challenges. It's not about hating AI agents, but rather advocating
for their responsible and ethical use to ensure they benefit society as a whole.
My critical perspective is rooted in a desire to see AI agents implemented in
ways that maximize their benefits while minimizing potential harms.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 200,\n \"completion_tokens\":
618,\n \"total_tokens\": 818,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
Answer: While it's a common misconception that I might \\\"hate\\\" AI agents,
the reality is much more nuanced. As an expert in technology research, especially
in the realm of AI, I have a deep appreciation for both the potential and the
challenges that AI agents present.\\n\\nAI agents, which can be broadly defined
as autonomous software entities that perform tasks on behalf of users or other
programs, are transforming numerous aspects of our daily lives and industries.
Here are a few key points to consider:\\n\\n1. **Advantages of AI Agents**:\\n
\ - **Automation and Efficiency**: AI agents can handle repetitive and time-consuming
tasks efficiently, freeing up human workers to focus on more complex and creative
activities.\\n - **Availability**: Unlike humans, AI agents can operate 24/7
without breaks, providing continuous service and support.\\n - **Scalability**:
AI agents can be deployed across different platforms and industries, scaling
solutions quickly and effectively.\\n - **Data Analysis and Insights**: They
can process vast amounts of data rapidly, providing insights that would be difficult,
if not impossible, for humans to derive on their own.\\n\\n2. **Challenges and
Concerns**:\\n - **Ethical Implications**: There are significant concerns
regarding the ethical use of AI agents, particularly related to privacy, bias,
and decision-making transparency.\\n - **Job Displacement**: While AI agents
increase efficiency, they also raise concerns about potential job displacement
in certain sectors.\\n - **Dependence and Reliability**: Over-reliance on
AI agents could lead to vulnerabilities if the technology fails or is compromised.\\n\\n3.
**Looking Forward**:\\n - **Collaboration Between Humans and AI**: The best
outcomes are likely to come from a hybrid approach where AI agents augment human
capabilities rather than replace them outright.\\n - **Regulation and Standards**:
There is a growing need for clear regulations and standards to ensure the ethical
development and deployment of AI agents.\\n - **Continuous Improvement**:
The technology behind AI agents is constantly evolving. Continuous research
and development are essential to address current limitations and maximize benefits.\\n\\nIn
conclusion, my perspective on AI agents is not one of disdain but rather a cautious
optimism. They hold incredible promise for transforming various sectors and
improving efficiencies, but this potential comes with significant responsibilities.
It's essential to address the ethical, social, and technical challenges to harness
the full benefits of AI agents while mitigating potential downsides. Thus, thoughtful
consideration and ongoing dialogue about the role of AI agents in society are
crucial.\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
200,\n \"completion_tokens\": 517,\n \"total_tokens\": 717,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9369a8632233-MIA
- 8c4f6e56bef2a67a-MIA
Connection:
- keep-alive
Content-Encoding:
@@ -150,7 +105,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:44:46 GMT
- Wed, 18 Sep 2024 06:55:39 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -164,7 +119,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '7295'
- '5853'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -182,7 +137,7 @@ interactions:
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a8a7ba0ff499542e9c4fc4b4913be91c
- req_0aa0e2c887396b6e47ee79e68ce5d698
http_version: HTTP/1.1
status_code: 200
version: 1

81
tests/agent_tools/cassettes/test_delegate_work_with_wrong_co_worker_variable.yaml
View File

@@ -26,12 +26,12 @@ interactions:
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -41,7 +41,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
- 1.46.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -51,38 +51,53 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81df7uBLXNds4hfF7NxUw9LY2360\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476287,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A8it9LDkkRZSKsQkeXmWjzDg1qiUl\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642539,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: As an expert researcher in technology, particularly in the field of
AI and AI agents, it is essential to clarify that my perspective is not one
of hatred but rather critical analysis. My evaluation of AI agents is grounded
in a balanced view of their advantages and the challenges they present. \\n\\nAI
agents represent a significant leap in technological progress with a wide array
of applications across industries. They can perform tasks ranging from customer
service interactions, data analysis, complex simulations, to even personal assistance.
Their ability to learn and adapt makes them powerful tools for enhancing productivity
and innovation.\\n\\nHowever, there are considerable challenges and ethical
concerns associated with their deployment. These include privacy issues, job
displacement, and the potential for biased decision-making driven by flawed
algorithms. Furthermore, the security risks posed by AI agents, such as how
they can be manipulated or hacked, are critical concerns that cannot be ignored.\\n\\nIn
essence, while I do recognize the transformative potential of AI agents, I remain
vigilant about their implications. It is vital to ensure that their development
is guided by robust ethical standards and stringent regulations to mitigate
risks. My view is not rooted in hatred but in a deep commitment to responsible
and thoughtful technological advancement. \\n\\nI hope this clarifies my stance
on AI agents and underscores the importance of critical engagement with emerging
technologies.\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
200,\n \"completion_tokens\": 269,\n \"total_tokens\": 469,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
Answer: \\n\\nIt's not accurate to say that I hate AI agents. My stance is more
nuanced and rooted in a deep understanding of their capabilities, limitations,
and the potential impact on various sectors.\\n\\nAI agents are software entities
that perform tasks autonomously on behalf of users. They are designed to mimic
human decision-making and problem-solving abilities. The advances in machine
learning, natural language processing, and data analytics have significantly
improved the performance of AI agents, making them valuable tools for automation,
customer service, data analysis, and more.\\n\\nHowever, my concerns about AI
agents stem from several key points:\\n\\n1. **Ethical Considerations**: AI
agents can perpetuate biases present in their training data. If the data used
to train these agents contain biases, whether related to gender, race, or other
factors, the AI can replicate and even amplify these biases in its operations.
This has serious ethical implications for fairness and equality.\\n\\n2. **Job
Displacement**: While AI agents can enhance efficiency and productivity, they
can also displace human workers. Many routine and repetitive tasks previously
performed by humans are now automated, leading to job losses in certain sectors.
This aspect calls for a balanced approach where human roles are redefined rather
than completely eliminated.\\n\\n3. **Transparency and Accountability**: AI
agents often operate as \\\"black boxes,\\\" meaning their decision-making processes
are not transparent. If an AI agent makes an error\u2014whether in financial
transactions, medical diagnoses, or legal decisions\u2014it can be challenging
to understand why the error occurred and who is responsible. Ensuring transparency
and accountability is crucial for trust and reliability.\\n\\n4. **Security
and Privacy**: AI agents often deal with vast amounts of personal data. Ensuring
the security and privacy of this data is paramount. There are risks associated
with data breaches and the misuse of personal information, which can have significant
repercussions for individuals and organizations.\\n\\nDespite these concerns,
I also recognize the immense potential of AI agents to drive innovation, improve
efficiency, and provide solutions to complex problems. The key is to develop
and deploy AI responsibly, with robust regulatory frameworks and ethical guidelines.\\n\\nIn
conclusion, I don't hate AI agents. Instead, I advocate for a balanced perspective
that acknowledges their benefits while addressing their challenges. By doing
so, we can harness the power of AI agents for the greater good, ensuring they
contribute positively to society.\\n\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 200,\n \"completion_tokens\": 481,\n
\ \"total_tokens\": 681,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f9399ad0d2233-MIA
- 8c4f6e7eb93ea67a-MIA
Connection:
- keep-alive
Content-Encoding:
@@ -90,7 +105,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:44:50 GMT
- Wed, 18 Sep 2024 06:55:45 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -104,7 +119,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '2921'
- '6191'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -122,7 +137,7 @@ interactions:
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_cde4a648c2d50e68f65f851b9b2763e8
- req_28bf060b1878579d6ac179d10d06c5a5
http_version: HTTP/1.1
status_code: 200
version: 1

110
tests/agent_tools/cassettes/test_delegate_work_withwith_coworker_as_array.yaml
View File

@@ -26,12 +26,12 @@ interactions:
content-type:
- application/json
cookie:
- __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
_cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
- __cf_bm=.8.5x0rqghNdtUCxfmwblfhuXiKyPm_cRq.NIa0heL0-1726642369-1.0.1.1-VbsAGqjOt45ZD50K2QW2oZrByLLIh6w8K4nAkLthTbXgU5qTgdf0mhvFId8Q2F3DcHUw9E72lVIZEN.YVlYINQ;
_cfuvid=o5s1Ux898x0eFNtzUCnG996iqyX3LgXDXq99C5oqnVE-1726642369248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.45.0
- OpenAI/Python 1.46.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -41,7 +41,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.45.0
- 1.46.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -51,60 +51,58 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A81dl5AGe27OAaVIcwWPl9WlAiXhQ\",\n \"object\":
\"chat.completion\",\n \"created\": 1726476293,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A8itMCa7g4PWxQ81lBUGgOFC4fl2n\",\n \"object\":
\"chat.completion\",\n \"created\": 1726642552,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer.\\nFinal
Answer:\\n\\nAI agents have emerged as a revolutionary force in today's technological
landscape, and my stance on them is not rooted in hatred but in a critical,
analytical perspective. Let's delve deeper into what makes AI agents both a
boon and a bane in various contexts.\\n\\n**Benefits of AI Agents:**\\n\\n1.
**Automation and Efficiency:**\\n AI agents excel at automating repetitive
tasks, which frees up human resources for more complex and creative endeavors.
They are capable of performing tasks rapidly and with high accuracy, leading
to increased efficiency in operations.\\n\\n2. **Data Analysis and Decision
Making:**\\n These agents can process vast amounts of data at speeds far beyond
human capability. They can identify patterns and insights that would otherwise
be missed, aiding in informed decision-making processes across industries like
finance, healthcare, and logistics.\\n\\n3. **Personalization and User Experience:**\\n
\ AI agents can personalize interactions on a scale that is impractical for
humans. For example, recommendation engines in e-commerce or content platforms
tailor suggestions to individual users, enhancing user experience and satisfaction.\\n\\n4.
**24/7 Availability:**\\n Unlike human employees, AI agents can operate round-the-clock
without the need for breaks, sleep, or holidays. This makes them ideal for customer
service roles, providing consistent and immediate responses any time of the
day.\\n\\n**Challenges and Concerns:**\\n\\n1. **Job Displacement:**\\n One
of the major concerns is the displacement of jobs. As AI agents become more
proficient at a variety of tasks, there is a legitimate fear of human workers
being replaced, leading to unemployment and economic disruption.\\n\\n2. **Bias
and Fairness:**\\n AI agents are only as good as the data they are trained
on. If the training data contains biases, the AI agents can perpetuate or even
exacerbate these biases, leading to unfair and discriminatory outcomes.\\n\\n3.
**Privacy and Security:**\\n The use of AI agents often involves handling
large amounts of personal data, raising significant privacy and security concerns.
Unauthorized access or breaches could lead to severe consequences for individuals
and organizations.\\n\\n4. **Accountability and Transparency:**\\n The decision-making
processes of AI agents can be opaque, making it difficult to hold them accountable.
This lack of transparency can lead to mistrust and ethical dilemmas, particularly
when AI decisions impact human lives.\\n\\n5. **Ethical Considerations:**\\n
\ The deployment of AI agents in sensitive areas, such as surveillance and
law enforcement, raises ethical issues. The potential for misuse or overdependence
on AI decision-making poses a threat to individual freedoms and societal norms.\\n\\nIn
conclusion, while AI agents offer remarkable advantages in terms of efficiency,
data handling, and user experience, they also bring significant challenges that
need to be addressed carefully. My critical stance is driven by a desire to
ensure that their integration into society is balanced, fair, and beneficial
to all, without ignoring the potential downsides. Therefore, a nuanced approach
is essential in leveraging the power of AI agents responsibly.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 200,\n \"completion_tokens\":
609,\n \"total_tokens\": 809,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: \\n\\nIn addressing your query about AI agents, it's crucial to clarify
my stance. While I don't \\\"hate\\\" AI agents, I have a nuanced perspective
that balances both their potential benefits and inherent drawbacks. This balanced
view is essential for understanding the complex role that AI agents play in
today's technology landscape.\\n\\nAI agents are remarkable tools that can automate
tasks, provide intelligent recommendations, and enhance user experiences. They
harness advancements in machine learning, natural language processing, and big
data analytics to perform a wide range of functions, from personal assistants
like Siri and Alexa to sophisticated customer service bots and autonomous systems
in various industries.\\n\\nThe Potential Benefits of AI Agents:\\n1. **Automation
and Efficiency**: AI agents can handle repetitive and mundane tasks, freeing
up human workers to focus on more creative and high-value activities. This can
lead to increased productivity and operational efficiency in businesses.\\n2.
**Data-Driven Insights**: By analyzing vast amounts of data, AI agents can provide
actionable insights that inform decision-making processes in areas like finance,
healthcare, and marketing.\\n3. **Personalization**: AI agents can tailor recommendations
and services based on individual user preferences and behaviors, enhancing user
satisfaction and engagement.\\n4. **24/7 Availability**: Unlike human workers,
AI agents can operate continuously without the need for breaks, providing round-the-clock
support and services.\\n\\nHowever, there are also several challenges and concerns
associated with AI agents that cannot be overlooked:\\n\\n1. **Ethical Considerations**:
The deployment of AI agents raises ethical questions about privacy, surveillance,
and the potential for bias in their algorithms. Ensuring that AI systems are
transparent and fair is a critical issue.\\n2. **Job Displacement**: While AI
agents can increase efficiency, they also have the potential to displace human
workers, leading to concerns about unemployment and the need for workforce reskilling.\\n3.
**Trust and Reliability**: Building trust in AI systems is essential. Users
need to be confident that AI agents will perform their tasks accurately and
reliably, without unexpected failures or errors.\\n4. **Control and Accountability**:
Determining who is accountable when AI agents make errors or cause harm is a
complex issue, especially when these systems operate autonomously or with minimal
human oversight.\\n\\nIn summary, my view on AI agents is not one of antagonism
but of cautious optimism. I recognize the transformative potential of AI agents
in various domains, but I also emphasize the importance of addressing the ethical,
economic, and technical challenges they present. Our goal should be to develop
and deploy AI agents in a way that maximizes their benefits while mitigating
their risks. This balanced approach will ensure that AI agents can be a positive
force in society, driving innovation and improving quality of life without compromising
ethical standards or societal values.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 200,\n \"completion_tokens\": 564,\n
\ \"total_tokens\": 764,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_a5d11b2ef2\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c3f93c2ff952233-MIA
- 8c4f6ecd7940a67a-MIA
Connection:
- keep-alive
Content-Encoding:
@@ -112,7 +110,7 @@ interactions:
Content-Type:
- application/json
Date:
- Mon, 16 Sep 2024 08:45:00 GMT
- Wed, 18 Sep 2024 06:55:59 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -126,7 +124,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '6593'
- '7311'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -144,7 +142,7 @@ interactions:
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_74bbe724f57aed65432b42184a32f4ba
- req_ae1d80d4ecb5f536ad1aeb6548b63b1f
http_version: HTTP/1.1
status_code: 200
version: 1