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

fix: ensure token usage recording, validate response model on stream
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Details
Build uv cache / build-cache (3.11) (push) Has been cancelled
Details
Build uv cache / build-cache (3.12) (push) Has been cancelled
Details
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
Details
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Details
Notify Downstream / notify-downstream (push) Has been cancelled
Details
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Details
Build uv cache / build-cache (3.13) (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Greyson LaLonde
2025-12-10 20:32:10 -05:00
committed by GitHub
parent 8e99d490b0
commit bdafe0fac7
312 changed files with 7846 additions and 33124 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
lib/crewai/tests/cassettes/tools/agent_tools/test_ask_question.yaml
View File

@@ -74,8 +74,6 @@ interactions:
- 8c85ebf47e661cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:

2
lib/crewai/tests/cassettes/tools/agent_tools/test_ask_question_with_coworker_as_array.yaml
View File

@@ -75,8 +75,6 @@ interactions:
- 8c85ec3c6f3b1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:

2
lib/crewai/tests/cassettes/tools/agent_tools/test_ask_question_with_wrong_co_worker_variable.yaml
View File

@@ -73,8 +73,6 @@ interactions:
- 8c85ec05f8651cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:

2
lib/crewai/tests/cassettes/tools/agent_tools/test_delegate_work.yaml
View File

@@ -91,8 +91,6 @@ interactions:
- 8c85ebaa5c061cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:

2
lib/crewai/tests/cassettes/tools/agent_tools/test_delegate_work_with_wrong_co_worker_variable.yaml
View File

@@ -95,8 +95,6 @@ interactions:
- 8c85ebcdae971cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:

2
lib/crewai/tests/cassettes/tools/agent_tools/test_delegate_work_withwith_coworker_as_array.yaml
View File

@@ -96,8 +96,6 @@ interactions:
- 8c85ec12ab0d1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:

98
lib/crewai/tests/cassettes/tools/test_async_tool_using_decorator_within_flow.yaml
View File

File diff suppressed because one or more lines are too long

98
lib/crewai/tests/cassettes/tools/test_async_tool_using_decorator_within_isolated_crew.yaml
View File

File diff suppressed because one or more lines are too long

98
lib/crewai/tests/cassettes/tools/test_async_tool_using_within_isolated_crew.yaml
View File

File diff suppressed because one or more lines are too long

98
lib/crewai/tests/cassettes/tools/test_async_tool_within_flow.yaml
View File

File diff suppressed because one or more lines are too long

310
lib/crewai/tests/cassettes/tools/test_max_usage_count_is_respected.yaml
View File

@@ -1,23 +1,7 @@
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:"]}'
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
@@ -57,23 +41,13 @@ interactions:
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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string: "{\n \"id\": \"chatcmpl-C6K61UxbPXZl2Q3VL3Tbnr0TiwNDk\",\n \"object\": \"chat.completion\",\n \"created\": 1755623253,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"```\\nThought: I need to call the iterating tool the first time.\\nAction: iterating_tool\\nAction Input: {\\\"input_text\\\": \\\"First iteration\\\"}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 299,\n \"completion_tokens\": 35,\n \"total_tokens\": 334,\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_46bff0e0c8\"\n}\n"
headers:
CF-RAY:
- 971b3f72effa6897-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
@@ -81,11 +55,8 @@ interactions:
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
- __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:
@@ -132,27 +103,8 @@ interactions:
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:"]}'
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
@@ -165,8 +117,7 @@ interactions:
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
- __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:
@@ -195,23 +146,13 @@ interactions:
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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string: "{\n \"id\": \"chatcmpl-C6K64phcuD8CKD2C8SEHiwqyhb6Bc\",\n \"object\": \"chat.completion\",\n \"created\": 1755623256,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"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\\\"}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 345,\n \"completion_tokens\": 38,\n \"total_tokens\": 383,\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_46bff0e0c8\"\n}\n"
headers:
CF-RAY:
- 971b3f84cf146897-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
@@ -258,30 +199,8 @@ interactions:
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:"]}'
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
@@ -294,8 +213,7 @@ interactions:
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
- __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:
@@ -324,23 +242,13 @@ interactions:
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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==
string: "{\n \"id\": \"chatcmpl-C6K66xHjsRB8kkHFcgfdjMd9IX2uY\",\n \"object\": \"chat.completion\",\n \"created\": 1755623258,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"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\\\"}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 394,\n \"completion_tokens\": 38,\n \"total_tokens\": 432,\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_46bff0e0c8\"\n}\n"
headers:
CF-RAY:
- 971b3f958e746897-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
@@ -393,44 +301,10 @@ interactions:
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:"]}'
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
@@ -443,8 +317,7 @@ interactions:
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
- __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:
@@ -473,23 +346,13 @@ interactions:
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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string: "{\n \"id\": \"chatcmpl-C6K67orXjH62DU9H4yrj3X9efoVpa\",\n \"object\": \"chat.completion\",\n \"created\": 1755623259,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"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\\\"}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 626,\n \"completion_tokens\": 38,\n \"total_tokens\": 664,\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_46bff0e0c8\"\n}\n"
headers:
CF-RAY:
- 971b3f9bbef86897-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
@@ -542,47 +405,10 @@ interactions:
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:"]}'
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
@@ -595,8 +421,7 @@ interactions:
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
- __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:
@@ -625,23 +450,13 @@ interactions:
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA4RTTW/bMAy9+1cQOieFmyZO5ts2bECxDwztgB3mwlFk2tZmi4JEFx2C/PdBchKn
W4ddBIGP74l8pPYJgNCVyEGoVrLqbTd/m33INvJ+0NnnT/ff3tTZR72483eSv7xLScwCg3Y/UPGJ
daWotx2yJjPCyqFkDKrX69UqW9wssjQCPVXYBVpjeb6k+SJdLOfpZp5mR2JLWqEXOXxPAAD28Qwl
mgqfRA5RJkZ69F42KPJzEoBw1IWIkN5rz9KwmE2gIsNoYtXb7bYwX1sampZzuIVWPiIcu8AKuEWo
aXDcgmZ0MnQG0lRgMKAE1pE6XmOurrkFMnhVmNcqZOcnomlKJupOcbg1duAc9oXQ4VYyPnEhcijE
+yhyfq8Qh8viHdaDl8E7M3TdBSCNIY6MaNvDETmcjeqosY52/g+qqLXRvi0dSk8mmOKZrIjoIQF4
iAMZnnksrKPecsn0E+Nz2Xo16olpBSb05tURZGLZTfH19XL2gl5ZIUvd+YuRCiVVi9VEneYvh0rT
BZBcdP13NS9pj52PE/qv/AQohZaxKq3DSqvnHU9pDsMP+Vfa2eVYsPDoHrXCkjW6MIkKazl04/IK
/8sz9mWtTYPOOj1ucG3LZbar6xRTtRHJIfkNAAD//wMANy12ZMoDAAA=
string: "{\n \"id\": \"chatcmpl-C6K68aSui6NMSWBf6Li2RsRatPE0o\",\n \"object\": \"chat.completion\",\n \"created\": 1755623260,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"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\\\"}\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 675,\n \"completion_tokens\": 39,\n \"total_tokens\": 714,\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_46bff0e0c8\"\n}\n"
headers:
CF-RAY:
- 971b3fa3ea2f6897-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
@@ -694,50 +509,10 @@ interactions:
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:"]}'
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
@@ -750,8 +525,7 @@ interactions:
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
- __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:
@@ -780,23 +554,13 @@ interactions:
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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string: "{\n \"id\": \"chatcmpl-C6K6A3TaJ7woqKq8S71FN6mZLvLko\",\n \"object\": \"chat.completion\",\n \"created\": 1755623262,\n \"model\": \"gpt-4o-2024-08-06\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"```\\nThought: I have completed all 5 iterations.\\nFinal Answer: [\\\"Iteration 0: First iteration\\\", \\\"Iteration 0: Second iteration\\\", \\\"Iteration 0: Third iteration\\\", \\\"Iteration 0: Fourth iteration\\\", \\\"Iteration 0: Fifth iteration\\\"]\\n```\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 725,\n \"completion_tokens\": 56,\n \"total_tokens\": 781,\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_46bff0e0c8\"\n}\n"
headers:
CF-RAY:
- 971b3faa6ba46897-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date: