andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-05-03 08:12:39 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Merge branch 'main' into gl/feat/event-ordering

Browse Source
This commit is contained in:
Greyson LaLonde
2026-01-21 01:06:25 -05:00
parent f3cacdcf1d 741bf12bf4
commit 3281bae3a2
21 changed files with 3141 additions and 1372 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -0,0 +1,119 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Test Agent. A helpful
test assistant\nYour personal goal is: Answer questions\nTo give my best complete
final answer to the task respond using the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task:
What is 2+2? Reply with just the number.\n\nBegin! This is VERY important to
you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}],"model":"gpt-4o-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '673'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.83.0
x-stainless-read-timeout:
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-Cy7b0HjL79y39EkUcMLrRhPFe3XGj\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444914,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: 4\",\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 136,\n \"completion_tokens\": 13,\n
\ \"total_tokens\": 149,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_8bbc38b4db\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:55 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '857'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '341'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '358'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
version: 1

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

@@ -0,0 +1,255 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Calculator Agent. A math
expert\nYour personal goal is: Perform calculations\nYou ONLY have access to
the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: calculate\nTool Arguments: {\n \"properties\": {\n \"expression\":
{\n \"title\": \"Expression\",\n \"type\": \"string\"\n }\n },\n \"required\":
[\n \"expression\"\n ],\n \"title\": \"CalculatorToolSchema\",\n \"type\":
\"object\",\n \"additionalProperties\": false\n}\nTool Description: Calculate
the result of a mathematical expression.\n\nIMPORTANT: Use the following format
in your response:\n\n```\nThought: you should always think about what to do\nAction:
the action to take, only one name of [calculate], just the name, exactly as
it''s written.\nAction Input: the input to the action, just a simple JSON object,
enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
result of the action\n```\n\nOnce all necessary information is gathered, return
the following format:\n\n```\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n```"},{"role":"user","content":"\nCurrent
Task: Calculate 10 * 5\n\nBegin! This is VERY important to you, use the tools
available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4o-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1403'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.83.0
x-stainless-read-timeout:
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-Cy7avghVPSpszLmlbHpwDQlWDoD6O\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444909,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to calculate the expression
10 * 5.\\nAction: calculate\\nAction Input: {\\\"expression\\\":\\\"10 * 5\\\"}\\nObservation:
50\",\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 291,\n \"completion_tokens\": 33,\n
\ \"total_tokens\": 324,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_c4585b5b9c\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:49 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '939'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '579'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '598'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
- request:
body: '{"messages":[{"role":"system","content":"You are Calculator Agent. A math
expert\nYour personal goal is: Perform calculations\nYou ONLY have access to
the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: calculate\nTool Arguments: {\n \"properties\": {\n \"expression\":
{\n \"title\": \"Expression\",\n \"type\": \"string\"\n }\n },\n \"required\":
[\n \"expression\"\n ],\n \"title\": \"CalculatorToolSchema\",\n \"type\":
\"object\",\n \"additionalProperties\": false\n}\nTool Description: Calculate
the result of a mathematical expression.\n\nIMPORTANT: Use the following format
in your response:\n\n```\nThought: you should always think about what to do\nAction:
the action to take, only one name of [calculate], just the name, exactly as
it''s written.\nAction Input: the input to the action, just a simple JSON object,
enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
result of the action\n```\n\nOnce all necessary information is gathered, return
the following format:\n\n```\nThought: I now know the final answer\nFinal Answer:
the final answer to the original input question\n```"},{"role":"user","content":"\nCurrent
Task: Calculate 10 * 5\n\nBegin! This is VERY important to you, use the tools
available and give your best Final Answer, your job depends on it!\n\nThought:"},{"role":"assistant","content":"Thought:
I need to calculate the expression 10 * 5.\nAction: calculate\nAction Input:
{\"expression\":\"10 * 5\"}\nObservation: The result of 10 * 5 is 50"}],"model":"gpt-4o-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1591'
content-type:
- application/json
cookie:
- COOKIE-XXX
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.83.0
x-stainless-read-timeout:
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-Cy7avDhDZCLvv8v2dh8ZQRrLdci6A\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444909,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer.\\nFinal
Answer: 50\",\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 337,\n \"completion_tokens\": 14,\n
\ \"total_tokens\": 351,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_c4585b5b9c\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:50 GMT
Server:
- cloudflare
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '864'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '429'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '457'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
version: 1

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

@@ -0,0 +1,119 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Async Test Agent. An async
helper\nYour personal goal is: Answer questions asynchronously\nTo give my best
complete final answer to the task respond using the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task:
What is 3+3?\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4o-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '657'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.83.0
x-stainless-read-timeout:
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-Cy7atOGxtc4y3oYNI62WiQ0Vogsdv\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444907,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: The sum of 3 + 3 is 6. Therefore, the outcome is that if you add three
and three together, you will arrive at the total of six.\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
131,\n \"completion_tokens\": 46,\n \"total_tokens\": 177,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_29330a9688\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:48 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '983'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '944'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1192'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
version: 1

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

@@ -0,0 +1,119 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are Standalone Agent. A helpful
assistant\nYour personal goal is: Answer questions\nTo give my best complete
final answer to the task respond using the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task:
What is 5+5? Reply with just the number.\n\nBegin! This is VERY important to
you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}],"model":"gpt-4o-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '674'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.83.0
x-stainless-read-timeout:
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-Cy7azhPwUHQ0p5tdhxSAmLPoE8UgC\",\n \"object\":
\"chat.completion\",\n \"created\": 1768444913,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: 10\",\n \"refusal\": null,\n \"annotations\": []\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 136,\n \"completion_tokens\": 13,\n
\ \"total_tokens\": 149,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_29330a9688\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 02:41:54 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '858'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '455'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '583'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
version: 1

239
lib/crewai/tests/cassettes/agents/test_multiple_agents_in_same_flow.yaml Normal file
View File

@@ -0,0 +1,239 @@
interactions:
- request:
body: '{"messages":[{"role":"system","content":"You are First Agent. A friendly
greeter\nYour personal goal is: Greet users\nTo give my best complete final
answer to the task respond using the exact following format:\n\nThought: I now
can give a great answer\nFinal Answer: Your final answer must be the great and
the most complete as possible, it must be outcome described.\n\nI MUST use these
formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task: Say
hello\n\nBegin! This is VERY important to you, use the tools available and give
your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4o-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '632'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.83.0
x-stainless-read-timeout:
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-CyRKzgODZ9yn3F9OkaXsscLk2Ln3N\",\n \"object\":
\"chat.completion\",\n \"created\": 1768520801,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: Hello! Welcome! I'm so glad to see you here. If you need any assistance
or have any questions, feel free to ask. Have a wonderful day!\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
127,\n \"completion_tokens\": 43,\n \"total_tokens\": 170,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_c4585b5b9c\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 23:46:42 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '990'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '880'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1160'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
- request:
body: '{"messages":[{"role":"system","content":"You are Second Agent. A polite
farewell agent\nYour personal goal is: Say goodbye\nTo give my best complete
final answer to the task respond using the exact following format:\n\nThought:
I now can give a great answer\nFinal Answer: Your final answer must be the great
and the most complete as possible, it must be outcome described.\n\nI MUST use
these formats, my job depends on it!"},{"role":"user","content":"\nCurrent Task:
Say goodbye\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4o-mini"}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '640'
content-type:
- application/json
host:
- api.openai.com
x-stainless-arch:
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.83.0
x-stainless-read-timeout:
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-CyRL1Ua2PkK5xXPp3KeF0AnGAk3JP\",\n \"object\":
\"chat.completion\",\n \"created\": 1768520803,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: As we reach the end of our conversation, I want to express my gratitude
for the time we've shared. It's been a pleasure assisting you, and I hope
you found our interaction helpful and enjoyable. Remember, whenever you need
assistance, I'm just a message away. Wishing you all the best in your future
endeavors. Goodbye and take care!\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 126,\n \"completion_tokens\":
79,\n \"total_tokens\": 205,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_29330a9688\"\n}\n"
headers:
CF-RAY:
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Thu, 15 Jan 2026 23:46:44 GMT
Server:
- cloudflare
Set-Cookie:
- SET-COOKIE-XXX
Strict-Transport-Security:
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '1189'
openai-organization:
- OPENAI-ORG-XXX
openai-processing-ms:
- '1363'
openai-project:
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1605'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
version: 1

1680
lib/crewai/tests/cassettes/test_multiple_before_after_kickoff.yaml
View File

File diff suppressed because one or more lines are too long

448
lib/crewai/tests/cassettes/test_task_guardrail_process_output.yaml
View File

@@ -1,456 +1,528 @@
interactions:
- request:
body: '{"trace_id": "00000000-0000-0000-0000-000000000000", "execution_type": "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null, "crew_name": "Unknown Crew", "flow_name": null, "crewai_version": "1.3.0", "privacy_level": "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count": 0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-11-05T22:19:56.074812+00:00"}}'
body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are Guardrail Agent.
You are a expert at validating the output of a task. By providing effective
feedback if the output is not valid.\\nYour personal goal is: Validate the output
of the task\\nTo give my best complete final answer to the task respond using
the exact following format:\\n\\nThought: I now can give a great answer\\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described.\\n\\nI MUST use these formats, my job depends
on it!\"},{\"role\":\"user\",\"content\":\"\\nCurrent Task: \\n Ensure
the following task result complies with the given guardrail.\\n\\n Task
result:\\n \\n Lorem Ipsum is simply dummy text of the printing
and typesetting industry. Lorem Ipsum has been the industry's standard dummy
text ever\\n \\n\\n Guardrail:\\n Ensure the result has
less than 10 words\\n\\n Your task:\\n - Confirm if the Task result
complies with the guardrail.\\n - If not, provide clear feedback explaining
what is wrong (e.g., by how much it violates the rule, or what specific part
fails).\\n - Focus only on identifying issues \u2014 do not propose corrections.\\n
\ - If the Task result complies with the guardrail, saying that is valid\\n
\ \\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:
- '*/*'
Accept-Encoding:
- gzip, deflate, zstd
Connection:
- keep-alive
Content-Length:
- '434'
Content-Type:
- application/json
User-Agent:
- CrewAI-CLI/1.3.0
X-Crewai-Version:
- 1.3.0
method: POST
uri: https://app.crewai.com/crewai_plus/api/v1/tracing/batches
response:
body:
string: '{"error":"bad_credentials","message":"Bad credentials"}'
headers:
Connection:
- keep-alive
Content-Length:
- '55'
Content-Type:
- application/json; charset=utf-8
Date:
- Wed, 05 Nov 2025 22:19:56 GMT
cache-control:
- no-store
content-security-policy:
- 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net
https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com
https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com'
expires:
- '0'
permissions-policy:
- camera=(), microphone=(self), geolocation=()
pragma:
- no-cache
referrer-policy:
- strict-origin-when-cross-origin
strict-transport-security:
- max-age=63072000; includeSubDomains
vary:
- Accept
x-content-type-options:
- nosniff
x-frame-options:
- SAMEORIGIN
x-permitted-cross-domain-policies:
- none
x-request-id:
- 230c6cb5-92c7-448d-8c94-e5548a9f4259
x-runtime:
- '0.073220'
x-xss-protection:
- 1; mode=block
status:
code: 401
message: Unauthorized
- request:
body: '{"messages":[{"role":"system","content":"You are Guardrail Agent. You are a expert at validating the output of a task. By providing effective feedback if the output is not valid.\nYour personal goal is: Validate the output of the task\n\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!Ensure your final answer strictly adheres to the following OpenAPI schema: {\n \"type\": \"json_schema\",\n \"json_schema\": {\n \"name\": \"LLMGuardrailResult\",\n \"strict\": true,\n \"schema\": {\n \"properties\": {\n \"valid\": {\n \"description\": \"Whether the task output complies with the guardrail\",\n \"title\": \"Valid\",\n \"type\": \"boolean\"\n },\n \"feedback\": {\n \"anyOf\":
[\n {\n \"type\": \"string\"\n },\n {\n \"type\": \"null\"\n }\n ],\n \"default\": null,\n \"description\": \"A feedback about the task output if it is not valid\",\n \"title\": \"Feedback\"\n }\n },\n \"required\": [\n \"valid\",\n \"feedback\"\n ],\n \"title\": \"LLMGuardrailResult\",\n \"type\": \"object\",\n \"additionalProperties\": false\n }\n }\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python."},{"role":"user","content":"\n Ensure the following task result complies with the given guardrail.\n\n Task result:\n \n Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry''s standard dummy text ever\n \n\n Guardrail:\n Ensure
the result has less than 10 words\n\n Your task:\n - Confirm if the Task result complies with the guardrail.\n - If not, provide clear feedback explaining what is wrong (e.g., by how much it violates the rule, or what specific part fails).\n - Focus only on identifying issues — do not propose corrections.\n - If the Task result complies with the guardrail, saying that is valid\n "}],"model":"gpt-4o"}'
headers:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '2452'
- '1467'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.109.1
x-stainless-arch:
- arm64
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.109.1
- 1.83.0
x-stainless-read-timeout:
- '600'
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-CYg96Riy2RJRxnBHvoROukymP9wvs\",\n \"object\": \"chat.completion\",\n \"created\": 1762381196,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I need to check if the task result meets the requirement of having less than 10 words.\\n\\nFinal Answer: {\\n \\\"valid\\\": false,\\n \\\"feedback\\\": \\\"The task result contains more than 10 words, violating the guardrail. The text provided contains about 21 words.\\\"\\n}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 489,\n \"completion_tokens\": 61,\n \"total_tokens\": 550,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\"\
: 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_cbf1785567\"\n}\n"
string: "{\n \"id\": \"chatcmpl-Cy7yHRYTZi8yzRbcODnKr92keLKCb\",\n \"object\":
\"chat.completion\",\n \"created\": 1768446357,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The task result provided has more than
10 words. I will count the words to verify this.\\n\\nThe task result is the
following text:\\n\\\"Lorem Ipsum is simply dummy text of the printing and
typesetting industry. Lorem Ipsum has been the industry's standard dummy text
ever\\\"\\n\\nCounting the words:\\n\\n1. Lorem \\n2. Ipsum \\n3. is \\n4.
simply \\n5. dummy \\n6. text \\n7. of \\n8. the \\n9. printing \\n10. and
\\n11. typesetting \\n12. industry. \\n13. Lorem \\n14. Ipsum \\n15. has \\n16.
been \\n17. the \\n18. industry's \\n19. standard \\n20. dummy \\n21. text
\\n22. ever\\n\\nThe total word count is 22.\\n\\nThought: I now can give
a great answer\\nFinal Answer: The task result does not comply with the guardrail.
It contains 22 words, which exceeds the limit of 10 words.\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
285,\n \"completion_tokens\": 195,\n \"total_tokens\": 480,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_deacdd5f6f\"\n}\n"
headers:
CF-RAY:
- REDACTED-RAY
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Wed, 05 Nov 2025 22:19:58 GMT
- Thu, 15 Jan 2026 03:05:59 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:49:58 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
- _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
- SET-COOKIE-XXX
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- X-Request-ID
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '1557'
openai-organization:
- user-hortuttj2f3qtmxyik2zxf4q
- OPENAI-ORG-XXX
openai-processing-ms:
- '2201'
- '2130'
openai-project:
- proj_fL4UBWR1CMpAAdgzaSKqsVvA
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '2401'
- '2147'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- '500'
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- '30000'
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- '499'
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- '29439'
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- 120ms
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- 1.122s
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- req_REDACTED
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
- request:
body: '{"messages":[{"role":"system","content":"Ensure your final answer strictly adheres to the following OpenAPI schema: {\n \"type\": \"json_schema\",\n \"json_schema\": {\n \"name\": \"LLMGuardrailResult\",\n \"strict\": true,\n \"schema\": {\n \"properties\": {\n \"valid\": {\n \"description\": \"Whether the task output complies with the guardrail\",\n \"title\": \"Valid\",\n \"type\": \"boolean\"\n },\n \"feedback\": {\n \"anyOf\": [\n {\n \"type\": \"string\"\n },\n {\n \"type\": \"null\"\n }\n ],\n \"default\": null,\n \"description\": \"A feedback about the task output if it is not valid\",\n \"title\": \"Feedback\"\n }\n },\n \"required\": [\n \"valid\",\n \"feedback\"\n ],\n \"title\": \"LLMGuardrailResult\",\n \"type\": \"object\",\n \"additionalProperties\":
false\n }\n }\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python."},{"role":"user","content":"{\n \"valid\": false,\n \"feedback\": \"The task result contains more than 10 words, violating the guardrail. The text provided contains about 21 words.\"\n}"}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"valid":{"description":"Whether the task output complies with the guardrail","title":"Valid","type":"boolean"},"feedback":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"A feedback about the task output if it is not valid","title":"Feedback"}},"required":["valid","feedback"],"title":"LLMGuardrailResult","type":"object","additionalProperties":false},"name":"LLMGuardrailResult","strict":true}},"stream":false}'
body: '{"messages":[{"role":"system","content":"Ensure your final answer strictly
adheres to the following OpenAPI schema: {\n \"type\": \"json_schema\",\n \"json_schema\":
{\n \"name\": \"LLMGuardrailResult\",\n \"strict\": true,\n \"schema\":
{\n \"properties\": {\n \"valid\": {\n \"description\":
\"Whether the task output complies with the guardrail\",\n \"title\":
\"Valid\",\n \"type\": \"boolean\"\n },\n \"feedback\":
{\n \"anyOf\": [\n {\n \"type\": \"string\"\n },\n {\n \"type\":
\"null\"\n }\n ],\n \"default\": null,\n \"description\":
\"A feedback about the task output if it is not valid\",\n \"title\":
\"Feedback\"\n }\n },\n \"required\": [\n \"valid\",\n \"feedback\"\n ],\n \"title\":
\"LLMGuardrailResult\",\n \"type\": \"object\",\n \"additionalProperties\":
false\n }\n }\n}\n\nDo not include the OpenAPI schema in the final output.
Ensure the final output does not include any code block markers like ```json
or ```python."},{"role":"user","content":"The task result does not comply with
the guardrail. It contains 22 words, which exceeds the limit of 10 words."}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"valid":{"description":"Whether
the task output complies with the guardrail","title":"Valid","type":"boolean"},"feedback":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"A
feedback about the task output if it is not valid","title":"Feedback"}},"required":["valid","feedback"],"title":"LLMGuardrailResult","type":"object","additionalProperties":false},"name":"LLMGuardrailResult","strict":true}},"stream":false}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1884'
- '1835'
content-type:
- application/json
cookie:
- __cf_bm=REDACTED; _cfuvid=REDACTED
- COOKIE-XXX
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.109.1
x-stainless-arch:
- arm64
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-helper-method:
- chat.completions.parse
- beta.chat.completions.parse
x-stainless-lang:
- python
x-stainless-os:
- MacOS
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.109.1
- 1.83.0
x-stainless-read-timeout:
- '600'
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-CYg98QlZ8NTrQ69676MpXXyCoZJT8\",\n \"object\": \"chat.completion\",\n \"created\": 1762381198,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"{\\\"valid\\\":false,\\\"feedback\\\":\\\"The task result contains more than 10 words, violating the guardrail. The text provided contains about 21 words.\\\"}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 374,\n \"completion_tokens\": 32,\n \"total_tokens\": 406,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n\
\ \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_cbf1785567\"\n}\n"
string: "{\n \"id\": \"chatcmpl-Cy7yJiPCk4fXuogyT5e8XeGRLCSf8\",\n \"object\":
\"chat.completion\",\n \"created\": 1768446359,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"{\\\"valid\\\":false,\\\"feedback\\\":\\\"The
task output exceeds the word limit of 10 words by containing 22 words.\\\"}\",\n
\ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
363,\n \"completion_tokens\": 25,\n \"total_tokens\": 388,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_a0e9480a2f\"\n}\n"
headers:
CF-RAY:
- REDACTED-RAY
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Wed, 05 Nov 2025 22:19:59 GMT
- Thu, 15 Jan 2026 03:05:59 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- X-Request-ID
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '913'
openai-organization:
- user-hortuttj2f3qtmxyik2zxf4q
- OPENAI-ORG-XXX
openai-processing-ms:
- '419'
- '488'
openai-project:
- proj_fL4UBWR1CMpAAdgzaSKqsVvA
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '432'
- '507'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- '500'
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- '30000'
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- '499'
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- '29702'
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- 120ms
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- 596ms
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- req_REDACTED
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
- request:
body: '{"messages":[{"role":"system","content":"You are Guardrail Agent. You are a expert at validating the output of a task. By providing effective feedback if the output is not valid.\nYour personal goal is: Validate the output of the task\n\nTo give my best complete final answer to the task respond using the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described.\n\nI MUST use these formats, my job depends on it!Ensure your final answer strictly adheres to the following OpenAPI schema: {\n \"type\": \"json_schema\",\n \"json_schema\": {\n \"name\": \"LLMGuardrailResult\",\n \"strict\": true,\n \"schema\": {\n \"properties\": {\n \"valid\": {\n \"description\": \"Whether the task output complies with the guardrail\",\n \"title\": \"Valid\",\n \"type\": \"boolean\"\n },\n \"feedback\": {\n \"anyOf\":
[\n {\n \"type\": \"string\"\n },\n {\n \"type\": \"null\"\n }\n ],\n \"default\": null,\n \"description\": \"A feedback about the task output if it is not valid\",\n \"title\": \"Feedback\"\n }\n },\n \"required\": [\n \"valid\",\n \"feedback\"\n ],\n \"title\": \"LLMGuardrailResult\",\n \"type\": \"object\",\n \"additionalProperties\": false\n }\n }\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python."},{"role":"user","content":"\n Ensure the following task result complies with the given guardrail.\n\n Task result:\n \n Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry''s standard dummy text ever\n \n\n Guardrail:\n Ensure
the result has less than 500 words\n\n Your task:\n - Confirm if the Task result complies with the guardrail.\n - If not, provide clear feedback explaining what is wrong (e.g., by how much it violates the rule, or what specific part fails).\n - Focus only on identifying issues — do not propose corrections.\n - If the Task result complies with the guardrail, saying that is valid\n "}],"model":"gpt-4o"}'
body: "{\"messages\":[{\"role\":\"system\",\"content\":\"You are Guardrail Agent.
You are a expert at validating the output of a task. By providing effective
feedback if the output is not valid.\\nYour personal goal is: Validate the output
of the task\\nTo give my best complete final answer to the task respond using
the exact following format:\\n\\nThought: I now can give a great answer\\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described.\\n\\nI MUST use these formats, my job depends
on it!\"},{\"role\":\"user\",\"content\":\"\\nCurrent Task: \\n Ensure
the following task result complies with the given guardrail.\\n\\n Task
result:\\n \\n Lorem Ipsum is simply dummy text of the printing
and typesetting industry. Lorem Ipsum has been the industry's standard dummy
text ever\\n \\n\\n Guardrail:\\n Ensure the result has
less than 500 words\\n\\n Your task:\\n - Confirm if the Task
result complies with the guardrail.\\n - If not, provide clear feedback
explaining what is wrong (e.g., by how much it violates the rule, or what specific
part fails).\\n - Focus only on identifying issues \u2014 do not propose
corrections.\\n - If the Task result complies with the guardrail, saying
that is valid\\n \\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:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '2453'
- '1468'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.109.1
x-stainless-arch:
- arm64
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.109.1
- 1.83.0
x-stainless-read-timeout:
- '600'
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-CYgBMV6fu7EvV2BqzMdJaKyLAg1WW\",\n \"object\": \"chat.completion\",\n \"created\": 1762381336,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\\"valid\\\": true, \\\"feedback\\\": null}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 489,\n \"completion_tokens\": 23,\n \"total_tokens\": 512,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\"\
: \"fp_cbf1785567\"\n}\n"
string: "{\n \"id\": \"chatcmpl-Cy7yKa0rmi2YoTLpyXt9hjeLt2rTI\",\n \"object\":
\"chat.completion\",\n \"created\": 1768446360,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"First, I'll count the number of words
in the Task result to ensure it complies with the guardrail. \\n\\nThe Task
result is: \\\"Lorem Ipsum is simply dummy text of the printing and typesetting
industry. Lorem Ipsum has been the industry's standard dummy text ever.\\\"\\n\\nBy
counting the words: \\n1. Lorem\\n2. Ipsum\\n3. is\\n4. simply\\n5. dummy\\n6.
text\\n7. of\\n8. the\\n9. printing\\n10. and\\n11. typesetting\\n12. industry\\n13.
Lorem\\n14. Ipsum\\n15. has\\n16. been\\n17. the\\n18. industry's\\n19. standard\\n20.
dummy\\n21. text\\n22. ever\\n\\nThere are 22 words total in the Task result.\\n\\nI
need to verify if the count of 22 words is less than the guardrail limit of
500 words.\\n\\nThought: I now can give a great answer\\nFinal Answer: The
Task result complies with the guardrail as it contains 22 words, which is
less than the 500-word limit. Therefore, the output is valid.\",\n \"refusal\":
null,\n \"annotations\": []\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
285,\n \"completion_tokens\": 227,\n \"total_tokens\": 512,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_deacdd5f6f\"\n}\n"
headers:
CF-RAY:
- REDACTED-RAY
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Wed, 05 Nov 2025 22:22:16 GMT
- Thu, 15 Jan 2026 03:06:02 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:52:16 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
- _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
- SET-COOKIE-XXX
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- X-Request-ID
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '1668'
openai-organization:
- user-hortuttj2f3qtmxyik2zxf4q
- OPENAI-ORG-XXX
openai-processing-ms:
- '327'
- '2502'
openai-project:
- proj_fL4UBWR1CMpAAdgzaSKqsVvA
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '372'
- '2522'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- '500'
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- '30000'
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- '499'
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- '29438'
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- 120ms
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- 1.124s
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- req_REDACTED
- X-REQUEST-ID-XXX
status:
code: 200
message: OK
- request:
body: '{"messages":[{"role":"system","content":"Ensure your final answer strictly adheres to the following OpenAPI schema: {\n \"type\": \"json_schema\",\n \"json_schema\": {\n \"name\": \"LLMGuardrailResult\",\n \"strict\": true,\n \"schema\": {\n \"properties\": {\n \"valid\": {\n \"description\": \"Whether the task output complies with the guardrail\",\n \"title\": \"Valid\",\n \"type\": \"boolean\"\n },\n \"feedback\": {\n \"anyOf\": [\n {\n \"type\": \"string\"\n },\n {\n \"type\": \"null\"\n }\n ],\n \"default\": null,\n \"description\": \"A feedback about the task output if it is not valid\",\n \"title\": \"Feedback\"\n }\n },\n \"required\": [\n \"valid\",\n \"feedback\"\n ],\n \"title\": \"LLMGuardrailResult\",\n \"type\": \"object\",\n \"additionalProperties\":
false\n }\n }\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python."},{"role":"user","content":"{\"valid\": true, \"feedback\": null}"}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"valid":{"description":"Whether the task output complies with the guardrail","title":"Valid","type":"boolean"},"feedback":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"A feedback about the task output if it is not valid","title":"Feedback"}},"required":["valid","feedback"],"title":"LLMGuardrailResult","type":"object","additionalProperties":false},"name":"LLMGuardrailResult","strict":true}},"stream":false}'
body: '{"messages":[{"role":"system","content":"Ensure your final answer strictly
adheres to the following OpenAPI schema: {\n \"type\": \"json_schema\",\n \"json_schema\":
{\n \"name\": \"LLMGuardrailResult\",\n \"strict\": true,\n \"schema\":
{\n \"properties\": {\n \"valid\": {\n \"description\":
\"Whether the task output complies with the guardrail\",\n \"title\":
\"Valid\",\n \"type\": \"boolean\"\n },\n \"feedback\":
{\n \"anyOf\": [\n {\n \"type\": \"string\"\n },\n {\n \"type\":
\"null\"\n }\n ],\n \"default\": null,\n \"description\":
\"A feedback about the task output if it is not valid\",\n \"title\":
\"Feedback\"\n }\n },\n \"required\": [\n \"valid\",\n \"feedback\"\n ],\n \"title\":
\"LLMGuardrailResult\",\n \"type\": \"object\",\n \"additionalProperties\":
false\n }\n }\n}\n\nDo not include the OpenAPI schema in the final output.
Ensure the final output does not include any code block markers like ```json
or ```python."},{"role":"user","content":"The Task result complies with the
guardrail as it contains 22 words, which is less than the 500-word limit. Therefore,
the output is valid."}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"valid":{"description":"Whether
the task output complies with the guardrail","title":"Valid","type":"boolean"},"feedback":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"A
feedback about the task output if it is not valid","title":"Feedback"}},"required":["valid","feedback"],"title":"LLMGuardrailResult","type":"object","additionalProperties":false},"name":"LLMGuardrailResult","strict":true}},"stream":false}'
headers:
User-Agent:
- X-USER-AGENT-XXX
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
- ACCEPT-ENCODING-XXX
authorization:
- AUTHORIZATION-XXX
connection:
- keep-alive
content-length:
- '1762'
- '1864'
content-type:
- application/json
cookie:
- __cf_bm=REDACTED; _cfuvid=REDACTED
- COOKIE-XXX
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.109.1
x-stainless-arch:
- arm64
- X-STAINLESS-ARCH-XXX
x-stainless-async:
- 'false'
x-stainless-helper-method:
- chat.completions.parse
- beta.chat.completions.parse
x-stainless-lang:
- python
x-stainless-os:
- MacOS
- X-STAINLESS-OS-XXX
x-stainless-package-version:
- 1.109.1
- 1.83.0
x-stainless-read-timeout:
- '600'
- X-STAINLESS-READ-TIMEOUT-XXX
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
- 3.13.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: "{\n \"id\": \"chatcmpl-CYgBMU20R45qGGaLN6vNAmW1NR4R6\",\n \"object\": \"chat.completion\",\n \"created\": 1762381336,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"{\\\"valid\\\":true,\\\"feedback\\\":null}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 347,\n \"completion_tokens\": 9,\n \"total_tokens\": 356,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_cbf1785567\"\n}\n"
string: "{\n \"id\": \"chatcmpl-Cy7yMAjNYSCz2foZPEcSVCuapzF8y\",\n \"object\":
\"chat.completion\",\n \"created\": 1768446362,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"{\\\"valid\\\":true,\\\"feedback\\\":null}\",\n
\ \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
369,\n \"completion_tokens\": 9,\n \"total_tokens\": 378,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_a0e9480a2f\"\n}\n"
headers:
CF-RAY:
- REDACTED-RAY
- CF-RAY-XXX
Connection:
- keep-alive
Content-Type:
- application/json
Date:
- Wed, 05 Nov 2025 22:22:17 GMT
- Thu, 15 Jan 2026 03:06:03 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
- STS-XXX
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
- X-CONTENT-TYPE-XXX
access-control-expose-headers:
- X-Request-ID
- ACCESS-CONTROL-XXX
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
content-length:
- '837'
openai-organization:
- user-hortuttj2f3qtmxyik2zxf4q
- OPENAI-ORG-XXX
openai-processing-ms:
- '1081'
- '413'
openai-project:
- proj_fL4UBWR1CMpAAdgzaSKqsVvA
- OPENAI-PROJECT-XXX
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '1241'
- '650'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-requests:
- '500'
- X-RATELIMIT-LIMIT-REQUESTS-XXX
x-ratelimit-limit-tokens:
- '30000'
- X-RATELIMIT-LIMIT-TOKENS-XXX
x-ratelimit-remaining-requests:
- '499'
- X-RATELIMIT-REMAINING-REQUESTS-XXX
x-ratelimit-remaining-tokens:
- '29478'
- X-RATELIMIT-REMAINING-TOKENS-XXX
x-ratelimit-reset-requests:
- 120ms
- X-RATELIMIT-RESET-REQUESTS-XXX
x-ratelimit-reset-tokens:
- 1.042s
- X-RATELIMIT-RESET-TOKENS-XXX
x-request-id:
- req_REDACTED
- X-REQUEST-ID-XXX
status:
code: 200
message: OK