chore: restructure test env, cassettes, and conftest; fix flaky tests
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Mark stale issues and pull requests / stale (push) Has been cancelled

Consolidates pytest config, standardizes env handling, reorganizes cassette layout, removes outdated VCR configs, improves sync with threading.Condition, updates event-waiting logic, ensures cleanup, regenerates Gemini cassettes, and reverts unintended test changes.
This commit is contained in:
Greyson LaLonde
2025-11-29 16:55:24 -05:00
committed by GitHub
parent bc4e6a3127
commit c925d2d519
200 changed files with 2070 additions and 1891 deletions

View File

@@ -0,0 +1,115 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
the best research and analysis on 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: do you hate 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:\nI heard you LOVE them\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:
- '1021'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_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-AB7WnyWZFoccBH9YB7ghLbR1L8Wqa\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213909,\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 specialized in technology, I don't harbor emotions
such as hate towards AI agents. Instead, my focus is on understanding, analyzing,
and leveraging their potential to advance various fields. AI agents, when designed
and implemented effectively, can greatly augment human capabilities, streamline
processes, and provide valuable insights that might otherwise be overlooked.
My enthusiasm for AI agents stems from their ability to transform industries
and improve everyday life, making complex tasks more manageable and enhancing
overall efficiency. This passion drives my research and commitment to making
meaningful contributions in the realm of AI and AI agents.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\":
126,\n \"total_tokens\": 325,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85ebf47e661cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:31 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:
- '2498'
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:
- '29999755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_b7e2cb0620e45d3d74310d3f0166551f
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,116 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
the best research and analysis on 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: do you hate 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:\nI heard you LOVE them\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:
- '1021'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_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-AB7Wy6aW1XM0lWaMyQUNB9qhbCZlH\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213920,\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 specializing in technology and AI, I have a
deep appreciation for AI agents. These advanced tools have the potential to
revolutionize countless industries by improving efficiency, accuracy, and decision-making
processes. They can augment human capabilities, handle mundane and repetitive
tasks, and even offer insights that might be beyond human reach. While it's
crucial to approach AI with a balanced perspective, understanding both its capabilities
and limitations, my stance is one of optimism and fascination. Properly developed
and ethically managed, AI agents hold immense promise for driving innovation
and solving complex problems. So yes, I do love AI agents for their transformative
potential and the positive impact they can have on society.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\":
146,\n \"total_tokens\": 345,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85ec3c6f3b1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:42 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:
- '1675'
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:
- '29999755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a249567d37ada11bc8857404338b24cc
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,114 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
the best research and analysis on 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: do you hate 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:\nI heard you LOVE them\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:
- '1021'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_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-AB7Wq7edXMCGJR1zDd2QoySLdo8mM\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213912,\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 don't hate AI agents; on the contrary, I find them fascinating and
incredibly useful. Considering the rapid advancements in AI technology, these
agents have the potential to revolutionize various industries by automating
tasks, improving efficiency, and providing insights that were previously unattainable.
My expertise in researching and analyzing AI and AI agents has allowed me to
appreciate the intricate design and the vast possibilities they offer. Therefore,
it's more accurate to say that I love AI agents for their potential to drive
innovation and improve our daily lives.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\": 116,\n
\ \"total_tokens\": 315,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85ec05f8651cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:33 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:
- '1739'
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:
- '29999755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_d9e1e9458d5539061397a618345c27d4
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,132 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
the best research and analysis on 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: share your take on 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:\nI heard you hate
them\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:
- '1027'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_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-AB7WbKt7If02iTLuH5cJJjeYo9uDi\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213897,\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 understand why you might think I dislike AI agents, but my perspective
is more nuanced. AI agents, in essence, are incredibly versatile tools designed
to perform specific tasks autonomously or semi-autonomously. They harness various
artificial intelligence techniques, such as machine learning, natural language
processing, and computer vision, to interpret data, understand tasks, and execute
them efficiently. \\n\\nFrom a technological standpoint, AI agents have revolutionized
numerous industries. In customer service, for instance, AI agents like chatbots
and virtual assistants handle customer inquiries 24/7, providing quick and efficient
solutions. In healthcare, AI agents can assist in diagnosing diseases, managing
patient data, and even predicting outbreaks. The automation capabilities of
AI agents also enhance productivity in areas such as logistics, finance, and
cybersecurity by identifying patterns and anomalies at speeds far beyond human
capabilities.\\n\\nHowever, it's important to acknowledge the potential downsides
and challenges associated with AI agents. Ethical considerations are paramount.
Issues such as data privacy, security, and biases in AI algorithms need to be
carefully managed. There is also the human aspect to consider\u2014over-reliance
on AI agents might lead to job displacement in certain sectors, and ensuring
a fair transition for affected workers is crucial.\\n\\nMy concerns generally
stem from these ethical and societal implications rather than from the technology
itself. I advocate for responsible AI development, which includes transparency,
fairness, and accountability. By addressing these concerns, we can harness the
full potential of AI agents while mitigating the associated risks.\\n\\nSo,
to clarify, I don't hate AI agents; I recognize their immense potential and
the significant benefits they bring to various fields. However, I am equally
aware of the challenges they present and advocate for a balanced approach to
their development and deployment.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 200,\n \"completion_tokens\": 359,\n
\ \"total_tokens\": 559,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_3537616b13\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85ebaa5c061cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:22 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:
- '4928'
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:
- '29999755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_761796305026b5adfbb5a6237f14e32a
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,136 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
the best research and analysis on 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: share your take on 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:\nI heard you hate
them\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:
- '1027'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_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-AB7Wh4RzroZdiwUNOc4oRRhwfdRzs\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213903,\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: AI agents are essentially autonomous software programs that perform
tasks or provide services on behalf of humans. They're built on complex algorithms
and often leverage machine learning and neural networks to adapt and improve
over time. \\n\\nIt's important to clarify that I don't \\\"hate\\\" AI agents,
but I do approach them with a critical eye for a couple of reasons. AI agents
have enormous potential to transform industries, making processes more efficient,
providing insightful data analytics, and even learning from user behavior to
offer personalized experiences. However, this potential comes with significant
challenges and risks:\\n\\n1. **Ethical Concerns**: AI agents operate on data,
and the biases present in data can lead to unfair or unethical outcomes. Ensuring
that AI operates within ethical boundaries requires rigorous oversight, which
is not always in place.\\n\\n2. **Privacy Issues**: AI agents often need access
to large amounts of data, raising questions about privacy and data security.
If not managed correctly, this can lead to unauthorized data access and potential
misuse of sensitive information.\\n\\n3. **Transparency and Accountability**:
The decision-making process of AI agents can be opaque, making it difficult
to understand how they arrive at specific conclusions or actions. This lack
of transparency poses challenges for accountability, especially if something
goes wrong.\\n\\n4. **Job Displacement**: As AI agents become more capable,
there are valid concerns about their impact on employment. Tasks that were traditionally
performed by humans are increasingly being automated, which can lead to job
loss in certain sectors.\\n\\n5. **Reliability**: While AI agents can outperform
humans in many areas, they are not infallible. They can make mistakes, sometimes
with serious consequences. Continuous monitoring and regular updates are essential
to maintain their performance and reliability.\\n\\nIn summary, while AI agents
offer substantial benefits and opportunities, it's critical to approach their
adoption and deployment with careful consideration of the associated risks.
Balancing innovation with responsibility is key to leveraging AI agents effectively
and ethically. So, rather than \\\"hating\\\" AI agents, I advocate for a balanced,
cautious approach that maximizes benefits while mitigating potential downsides.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 200,\n \"completion_tokens\":
429,\n \"total_tokens\": 629,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_3537616b13\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85ebcdae971cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:29 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:
- '5730'
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:
- '29999755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_5da5b18b3cee10548a217ba97e133815
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,137 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
the best research and analysis on 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: share your take on 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:\nI heard you hate
them\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:
- '1027'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_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-AB7Wsv05NzccAAGC0CZVg03mE72wi\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213914,\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: My perspective on AI agents is quite nuanced and not a matter of simple
like or dislike. AI agents, depending on their design, deployment, and use cases,
can bring about both significant benefits and substantial challenges.\\n\\nOn
the positive side, AI agents have the potential to automate mundane tasks, enhance
productivity, and provide personalized services in ways that were previously
unimaginable. For instance, in customer service, AI agents can handle inquiries
24/7, reducing waiting times and improving user satisfaction. In healthcare,
they can assist in diagnosing diseases by analyzing vast datasets much faster
than humans. These applications demonstrate the transformative power of AI in
improving efficiency and delivering better outcomes across various industries.\\n\\nHowever,
my reservations stem from several critical concerns. Firstly, there's the issue
of reliability and accuracy. Mismanaged or poorly designed AI systems can lead
to significant errors, which could be particularly detrimental in high-stakes
environments like healthcare or autonomous vehicles. Second, there's a risk
of job displacement as AI agents become capable of performing tasks traditionally
done by humans. This raises socio-economic concerns that need to be addressed
through effective policy-making and upskilling programs.\\n\\nAdditionally,
there are ethical and privacy considerations. AI agents often require large
amounts of data to function effectively, which can lead to issues concerning
consent, data security, and individual privacy rights. The lack of transparency
in how these agents make decisions can also pose challenges\u2014this is often
referred to as the \\\"black box\\\" problem, where even the developers may
not fully understand how specific AI outputs are generated.\\n\\nFinally, the
deployment of AI agents by bad actors for malicious purposes, such as deepfakes,
misinformation, and hacking, remains a pertinent concern. These potential downsides
imply that while AI technology is extremely powerful and promising, it must
be developed and implemented with care, consideration, and robust ethical guidelines.\\n\\nSo,
in summary, I don't hate AI agents\u2014rather, I approach them critically with
a balanced perspective, recognizing both their profound potential and the significant
challenges they present. Thoughtful development, responsible deployment, and
ethical governance are crucial to harness the benefits while mitigating the
risks associated with AI agents.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
200,\n \"completion_tokens\": 436,\n \"total_tokens\": 636,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_3537616b13\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85ec12ab0d1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:40 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:
- '6251'
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:
- '29999755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_50aa23cad48cfb83b754a5a92939638e
http_version: HTTP/1.1
status_code: 200
version: 1

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,845 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Iterating Agent. You
are an agent that iterates a given number of times\nYour personal goal is: Call
the iterating tool 5 times\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: iterating_tool\nTool
Arguments: {''input_text'': {''description'': None, ''type'': ''str''}}\nTool
Description: A tool that iterates a given number of times\n\nIMPORTANT: Use
the following format in your response:\n\n```\nThought: you should always think
about what to do\nAction: the action to take, only one name of [iterating_tool],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
is gathered, return the following format:\n\n```\nThought: I now know the final
answer\nFinal Answer: the final answer to the original input question\n```"},
{"role": "user", "content": "\nCurrent Task: Call the iterating tool 5 times\n\nThis
is the expected criteria for your final answer: A list of the iterations\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:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '1452'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 971b3f72effa6897-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 19 Aug 2025 17:07:35 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=6OZC5kPO9TEmVSACP2sSOZK9ZEZ5I4T_VUlfmzsoY9Y-1755623255-1.0.1.1-ek3SaNBOhXmCg7K3J7LIsE0aCrnK5YfSumHDT6nc8Df1Zh3bzMLHLDqTUwtqiG8SwxiIFXeGP4.Vt2sx9b3FCkxoyrqNpgrBL5DAffAGHm8;
path=/; expires=Tue, 19-Aug-25 17:37:35 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=R_H7SrOF3QFEWePZfvxzuyKWZAt5ulsNbP28.6DC9wM-1755623255760-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
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:
- '2564'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '2751'
x-ratelimit-limit-project-tokens:
- '30000000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-tokens:
- '29999674'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999674'
x-ratelimit-reset-project-tokens:
- 0s
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_d654df1116aa42ca8ee7d10b4b424303
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Iterating Agent. You
are an agent that iterates a given number of times\nYour personal goal is: Call
the iterating tool 5 times\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: iterating_tool\nTool
Arguments: {''input_text'': {''description'': None, ''type'': ''str''}}\nTool
Description: A tool that iterates a given number of times\n\nIMPORTANT: Use
the following format in your response:\n\n```\nThought: you should always think
about what to do\nAction: the action to take, only one name of [iterating_tool],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
is gathered, return the following format:\n\n```\nThought: I now know the final
answer\nFinal Answer: the final answer to the original input question\n```"},
{"role": "user", "content": "\nCurrent Task: Call the iterating tool 5 times\n\nThis
is the expected criteria for your final answer: A list of the iterations\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":
"```\nThought: I need to call the iterating tool the first time.\nAction: iterating_tool\nAction
Input: {\"input_text\": \"First iteration\"}\nObservation: Iteration 0: First
iteration"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '1673'
content-type:
- application/json
cookie:
- __cf_bm=6OZC5kPO9TEmVSACP2sSOZK9ZEZ5I4T_VUlfmzsoY9Y-1755623255-1.0.1.1-ek3SaNBOhXmCg7K3J7LIsE0aCrnK5YfSumHDT6nc8Df1Zh3bzMLHLDqTUwtqiG8SwxiIFXeGP4.Vt2sx9b3FCkxoyrqNpgrBL5DAffAGHm8;
_cfuvid=R_H7SrOF3QFEWePZfvxzuyKWZAt5ulsNbP28.6DC9wM-1755623255760-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 971b3f84cf146897-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 19 Aug 2025 17:07:38 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
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:
- '1900'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '2551'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999629'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_f4181fe581264993ac5c6deba4f1c287
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Iterating Agent. You
are an agent that iterates a given number of times\nYour personal goal is: Call
the iterating tool 5 times\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: iterating_tool\nTool
Arguments: {''input_text'': {''description'': None, ''type'': ''str''}}\nTool
Description: A tool that iterates a given number of times\n\nIMPORTANT: Use
the following format in your response:\n\n```\nThought: you should always think
about what to do\nAction: the action to take, only one name of [iterating_tool],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
is gathered, return the following format:\n\n```\nThought: I now know the final
answer\nFinal Answer: the final answer to the original input question\n```"},
{"role": "user", "content": "\nCurrent Task: Call the iterating tool 5 times\n\nThis
is the expected criteria for your final answer: A list of the iterations\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":
"```\nThought: I need to call the iterating tool the first time.\nAction: iterating_tool\nAction
Input: {\"input_text\": \"First iteration\"}\nObservation: Iteration 0: First
iteration"}, {"role": "assistant", "content": "```\nThought: I have completed
the first iteration and need to proceed to the second one.\nAction: iterating_tool\nAction
Input: {\"input_text\": \"Second iteration\"}\nObservation: Iteration 0: Second
iteration"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '1922'
content-type:
- application/json
cookie:
- __cf_bm=6OZC5kPO9TEmVSACP2sSOZK9ZEZ5I4T_VUlfmzsoY9Y-1755623255-1.0.1.1-ek3SaNBOhXmCg7K3J7LIsE0aCrnK5YfSumHDT6nc8Df1Zh3bzMLHLDqTUwtqiG8SwxiIFXeGP4.Vt2sx9b3FCkxoyrqNpgrBL5DAffAGHm8;
_cfuvid=R_H7SrOF3QFEWePZfvxzuyKWZAt5ulsNbP28.6DC9wM-1755623255760-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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==
headers:
CF-RAY:
- 971b3f958e746897-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 19 Aug 2025 17:07:39 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
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:
- '890'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '906'
x-ratelimit-limit-project-tokens:
- '30000000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-tokens:
- '29999577'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999577'
x-ratelimit-reset-project-tokens:
- 0s
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_b3632e88268747218e4cc4cc08d87bca
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Iterating Agent. You
are an agent that iterates a given number of times\nYour personal goal is: Call
the iterating tool 5 times\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: iterating_tool\nTool
Arguments: {''input_text'': {''description'': None, ''type'': ''str''}}\nTool
Description: A tool that iterates a given number of times\n\nIMPORTANT: Use
the following format in your response:\n\n```\nThought: you should always think
about what to do\nAction: the action to take, only one name of [iterating_tool],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
is gathered, return the following format:\n\n```\nThought: I now know the final
answer\nFinal Answer: the final answer to the original input question\n```"},
{"role": "user", "content": "\nCurrent Task: Call the iterating tool 5 times\n\nThis
is the expected criteria for your final answer: A list of the iterations\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":
"```\nThought: I need to call the iterating tool the first time.\nAction: iterating_tool\nAction
Input: {\"input_text\": \"First iteration\"}\nObservation: Iteration 0: First
iteration"}, {"role": "assistant", "content": "```\nThought: I have completed
the first iteration and need to proceed to the second one.\nAction: iterating_tool\nAction
Input: {\"input_text\": \"Second iteration\"}\nObservation: Iteration 0: Second
iteration"}, {"role": "assistant", "content": "```\nThought: I have completed
the second iteration and need to proceed to the third one.\nAction: iterating_tool\nAction
Input: {\"input_text\": \"Third iteration\"}\nObservation: Iteration 0: Third
iteration\n\n\nYou ONLY have access to the following tools, and should NEVER
make up tools that are not listed here:\n\nTool Name: iterating_tool\nTool Arguments:
{''input_text'': {''description'': None, ''type'': ''str''}}\nTool Description:
A tool that iterates a given number of times\n\nIMPORTANT: Use the following
format in your response:\n\n```\nThought: you should always think about what
to do\nAction: the action to take, only one name of [iterating_tool], just the
name, exactly as it''s written.\nAction Input: the input to the action, just
a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\n```\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n```"}], "model": "gpt-4o",
"stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '3018'
content-type:
- application/json
cookie:
- __cf_bm=6OZC5kPO9TEmVSACP2sSOZK9ZEZ5I4T_VUlfmzsoY9Y-1755623255-1.0.1.1-ek3SaNBOhXmCg7K3J7LIsE0aCrnK5YfSumHDT6nc8Df1Zh3bzMLHLDqTUwtqiG8SwxiIFXeGP4.Vt2sx9b3FCkxoyrqNpgrBL5DAffAGHm8;
_cfuvid=R_H7SrOF3QFEWePZfvxzuyKWZAt5ulsNbP28.6DC9wM-1755623255760-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 971b3f9bbef86897-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 19 Aug 2025 17:07:40 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
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:
- '1182'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1208'
x-ratelimit-limit-project-tokens:
- '30000000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-tokens:
- '29999320'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999320'
x-ratelimit-reset-project-tokens:
- 1ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_7fc641fabc634f29ae085ef176071402
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Iterating Agent. You
are an agent that iterates a given number of times\nYour personal goal is: Call
the iterating tool 5 times\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: iterating_tool\nTool
Arguments: {''input_text'': {''description'': None, ''type'': ''str''}}\nTool
Description: A tool that iterates a given number of times\n\nIMPORTANT: Use
the following format in your response:\n\n```\nThought: you should always think
about what to do\nAction: the action to take, only one name of [iterating_tool],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
is gathered, return the following format:\n\n```\nThought: I now know the final
answer\nFinal Answer: the final answer to the original input question\n```"},
{"role": "user", "content": "\nCurrent Task: Call the iterating tool 5 times\n\nThis
is the expected criteria for your final answer: A list of the iterations\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":
"```\nThought: I need to call the iterating tool the first time.\nAction: iterating_tool\nAction
Input: {\"input_text\": \"First iteration\"}\nObservation: Iteration 0: First
iteration"}, {"role": "assistant", "content": "```\nThought: I have completed
the first iteration and need to proceed to the second one.\nAction: iterating_tool\nAction
Input: {\"input_text\": \"Second iteration\"}\nObservation: Iteration 0: Second
iteration"}, {"role": "assistant", "content": "```\nThought: I have completed
the second iteration and need to proceed to the third one.\nAction: iterating_tool\nAction
Input: {\"input_text\": \"Third iteration\"}\nObservation: Iteration 0: Third
iteration\n\n\nYou ONLY have access to the following tools, and should NEVER
make up tools that are not listed here:\n\nTool Name: iterating_tool\nTool Arguments:
{''input_text'': {''description'': None, ''type'': ''str''}}\nTool Description:
A tool that iterates a given number of times\n\nIMPORTANT: Use the following
format in your response:\n\n```\nThought: you should always think about what
to do\nAction: the action to take, only one name of [iterating_tool], just the
name, exactly as it''s written.\nAction Input: the input to the action, just
a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\n```\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n```"}, {"role": "assistant",
"content": "```\nThought: I have completed the third iteration and need to proceed
to the fourth one.\nAction: iterating_tool\nAction Input: {\"input_text\": \"Fourth
iteration\"}\nObservation: Iteration 0: Fourth iteration"}], "model": "gpt-4o",
"stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '3267'
content-type:
- application/json
cookie:
- __cf_bm=6OZC5kPO9TEmVSACP2sSOZK9ZEZ5I4T_VUlfmzsoY9Y-1755623255-1.0.1.1-ek3SaNBOhXmCg7K3J7LIsE0aCrnK5YfSumHDT6nc8Df1Zh3bzMLHLDqTUwtqiG8SwxiIFXeGP4.Vt2sx9b3FCkxoyrqNpgrBL5DAffAGHm8;
_cfuvid=R_H7SrOF3QFEWePZfvxzuyKWZAt5ulsNbP28.6DC9wM-1755623255760-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 971b3fa3ea2f6897-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 19 Aug 2025 17:07:41 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
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:
- '780'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '878'
x-ratelimit-limit-project-tokens:
- '30000000'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-project-tokens:
- '29999268'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999268'
x-ratelimit-reset-project-tokens:
- 1ms
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_603a6c645bac468888838d21c64db11f
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Iterating Agent. You
are an agent that iterates a given number of times\nYour personal goal is: Call
the iterating tool 5 times\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: iterating_tool\nTool
Arguments: {''input_text'': {''description'': None, ''type'': ''str''}}\nTool
Description: A tool that iterates a given number of times\n\nIMPORTANT: Use
the following format in your response:\n\n```\nThought: you should always think
about what to do\nAction: the action to take, only one name of [iterating_tool],
just the name, exactly as it''s written.\nAction Input: the input to the action,
just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
is gathered, return the following format:\n\n```\nThought: I now know the final
answer\nFinal Answer: the final answer to the original input question\n```"},
{"role": "user", "content": "\nCurrent Task: Call the iterating tool 5 times\n\nThis
is the expected criteria for your final answer: A list of the iterations\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":
"```\nThought: I need to call the iterating tool the first time.\nAction: iterating_tool\nAction
Input: {\"input_text\": \"First iteration\"}\nObservation: Iteration 0: First
iteration"}, {"role": "assistant", "content": "```\nThought: I have completed
the first iteration and need to proceed to the second one.\nAction: iterating_tool\nAction
Input: {\"input_text\": \"Second iteration\"}\nObservation: Iteration 0: Second
iteration"}, {"role": "assistant", "content": "```\nThought: I have completed
the second iteration and need to proceed to the third one.\nAction: iterating_tool\nAction
Input: {\"input_text\": \"Third iteration\"}\nObservation: Iteration 0: Third
iteration\n\n\nYou ONLY have access to the following tools, and should NEVER
make up tools that are not listed here:\n\nTool Name: iterating_tool\nTool Arguments:
{''input_text'': {''description'': None, ''type'': ''str''}}\nTool Description:
A tool that iterates a given number of times\n\nIMPORTANT: Use the following
format in your response:\n\n```\nThought: you should always think about what
to do\nAction: the action to take, only one name of [iterating_tool], just the
name, exactly as it''s written.\nAction Input: the input to the action, just
a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\n```\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n```"}, {"role": "assistant",
"content": "```\nThought: I have completed the third iteration and need to proceed
to the fourth one.\nAction: iterating_tool\nAction Input: {\"input_text\": \"Fourth
iteration\"}\nObservation: Iteration 0: Fourth iteration"}, {"role": "assistant",
"content": "```\nThought: I have completed the fourth iteration and need to
proceed to the fifth one.\nAction: iterating_tool\nAction Input: {\"input_text\":
\"Fifth iteration\"}\nObservation: Iteration 0: Fifth iteration"}], "model":
"gpt-4o", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '3514'
content-type:
- application/json
cookie:
- __cf_bm=6OZC5kPO9TEmVSACP2sSOZK9ZEZ5I4T_VUlfmzsoY9Y-1755623255-1.0.1.1-ek3SaNBOhXmCg7K3J7LIsE0aCrnK5YfSumHDT6nc8Df1Zh3bzMLHLDqTUwtqiG8SwxiIFXeGP4.Vt2sx9b3FCkxoyrqNpgrBL5DAffAGHm8;
_cfuvid=R_H7SrOF3QFEWePZfvxzuyKWZAt5ulsNbP28.6DC9wM-1755623255760-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 971b3faa6ba46897-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 19 Aug 2025 17:07:43 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
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:
- '1392'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1841'
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999217'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 1ms
x-request-id:
- req_19dc255cec9d4763be7d5f597c80e936
status:
code: 200
message: OK
version: 1