Release/v1.0.0 (#3618)

* feat: add `apps` & `actions` attributes to Agent (#3504)

* feat: add app attributes to Agent

* feat: add actions attribute to Agent

* chore: resolve linter issues

* refactor: merge the apps and actions parameters into a single one

* fix: remove unnecessary print

* feat: logging error when CrewaiPlatformTools fails

* chore: export CrewaiPlatformTools directly from crewai_tools

* style: resolver linter issues

* test: fix broken tests

* style: solve linter issues

* fix: fix broken test

* feat: monorepo restructure and test/ci updates

- Add crewai workspace member
- Fix vcr cassette paths and restore test dirs
- Resolve ci failures and update linter/pytest rules

* chore: update python version to 3.13 and package metadata

* feat: add crewai-tools workspace and fix tests/dependencies

* feat: add crewai-tools workspace structure

* Squashed 'temp-crewai-tools/' content from commit 9bae5633

git-subtree-dir: temp-crewai-tools
git-subtree-split: 9bae56339096cb70f03873e600192bd2cd207ac9

* feat: configure crewai-tools workspace package with dependencies

* fix: apply ruff auto-formatting to crewai-tools code

* chore: update lockfile

* fix: don't allow tool tests yet

* fix: comment out extra pytest flags for now

* fix: remove conflicting conftest.py from crewai-tools tests

* fix: resolve dependency conflicts and test issues

- Pin vcrpy to 7.0.0 to fix pytest-recording compatibility
- Comment out types-requests to resolve urllib3 conflict
- Update requests requirement in crewai-tools to >=2.32.0

* chore: update CI workflows and docs for monorepo structure

* chore: update CI workflows and docs for monorepo structure

* fix: actions syntax

* chore: ci publish and pin versions

* fix: add permission to action

* chore: bump version to 1.0.0a1 across all packages

- Updated version to 1.0.0a1 in pyproject.toml for crewai and crewai-tools
- Adjusted version in __init__.py files for consistency

* WIP: v1 docs (#3626)

(cherry picked from commit d46e20fa09bcd2f5916282f5553ddeb7183bd92c)

* docs: parity for all translations

* docs: full name of acronym AMP

* docs: fix lingering unused code

* docs: expand contextual options in docs.json

* docs: add contextual action to request feature on GitHub (#3635)

* chore: apply linting fixes to crewai-tools

* feat: add required env var validation for brightdata

Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>

* fix: handle properly anyOf oneOf allOf schema's props

Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>

* feat: bump version to 1.0.0a2

* Lorenze/native inference sdks (#3619)

* ruff linted

* using native sdks with litellm fallback

* drop exa

* drop print on completion

* Refactor LLM and utility functions for type consistency

- Updated `max_tokens` parameter in `LLM` class to accept `float` in addition to `int`.
- Modified `create_llm` function to ensure consistent type hints and return types, now returning `LLM | BaseLLM | None`.
- Adjusted type hints for various parameters in `create_llm` and `_llm_via_environment_or_fallback` functions for improved clarity and type safety.
- Enhanced test cases to reflect changes in type handling and ensure proper instantiation of LLM instances.

* fix agent_tests

* fix litellm tests and usagemetrics fix

* drop print

* Refactor LLM event handling and improve test coverage

- Removed commented-out event emission for LLM call failures in `llm.py`.
- Added `from_agent` parameter to `CrewAgentExecutor` for better context in LLM responses.
- Enhanced test for LLM call failure to simulate OpenAI API failure and updated assertions for clarity.
- Updated agent and task ID assertions in tests to ensure they are consistently treated as strings.

* fix test_converter

* fixed tests/agents/test_agent.py

* Refactor LLM context length exception handling and improve provider integration

- Renamed `LLMContextLengthExceededException` to `LLMContextLengthExceededExceptionError` for clarity and consistency.
- Updated LLM class to pass the provider parameter correctly during initialization.
- Enhanced error handling in various LLM provider implementations to raise the new exception type.
- Adjusted tests to reflect the updated exception name and ensure proper error handling in context length scenarios.

* Enhance LLM context window handling across providers

- Introduced CONTEXT_WINDOW_USAGE_RATIO to adjust context window sizes dynamically for Anthropic, Azure, Gemini, and OpenAI LLMs.
- Added validation for context window sizes in Azure and Gemini providers to ensure they fall within acceptable limits.
- Updated context window size calculations to use the new ratio, improving consistency and adaptability across different models.
- Removed hardcoded context window sizes in favor of ratio-based calculations for better flexibility.

* fix test agent again

* fix test agent

* feat: add native LLM providers for Anthropic, Azure, and Gemini

- Introduced new completion implementations for Anthropic, Azure, and Gemini, integrating their respective SDKs.
- Added utility functions for tool validation and extraction to support function calling across LLM providers.
- Enhanced context window management and token usage extraction for each provider.
- Created a common utility module for shared functionality among LLM providers.

* chore: update dependencies and improve context management

- Removed direct dependency on `litellm` from the main dependencies and added it under extras for better modularity.
- Updated the `litellm` dependency specification to allow for greater flexibility in versioning.
- Refactored context length exception handling across various LLM providers to use a consistent error class.
- Enhanced platform-specific dependency markers for NVIDIA packages to ensure compatibility across different systems.

* refactor(tests): update LLM instantiation to include is_litellm flag in test cases

- Modified multiple test cases in test_llm.py to set the is_litellm parameter to True when instantiating the LLM class.
- This change ensures that the tests are aligned with the latest LLM configuration requirements and improves consistency across test scenarios.
- Adjusted relevant assertions and comments to reflect the updated LLM behavior.

* linter

* linted

* revert constants

* fix(tests): correct type hint in expected model description

- Updated the expected description in the test_generate_model_description_dict_field function to use 'Dict' instead of 'dict' for consistency with type hinting conventions.
- This change ensures that the test accurately reflects the expected output format for model descriptions.

* refactor(llm): enhance LLM instantiation and error handling

- Updated the LLM class to include validation for the model parameter, ensuring it is a non-empty string.
- Improved error handling by logging warnings when the native SDK fails, allowing for a fallback to LiteLLM.
- Adjusted the instantiation of LLM in test cases to consistently include the is_litellm flag, aligning with recent changes in LLM configuration.
- Modified relevant tests to reflect these updates, ensuring better coverage and accuracy in testing scenarios.

* fixed test

* refactor(llm): enhance token usage tracking and add copy methods

- Updated the LLM class to track token usage and log callbacks in streaming mode, improving monitoring capabilities.
- Introduced shallow and deep copy methods for the LLM instance, allowing for better management of LLM configurations and parameters.
- Adjusted test cases to instantiate LLM with the is_litellm flag, ensuring alignment with recent changes in LLM configuration.

* refactor(tests): reorganize imports and enhance error messages in test cases

- Cleaned up import statements in test_crew.py for better organization and readability.
- Enhanced error messages in test cases to use `re.escape` for improved regex matching, ensuring more robust error handling.
- Adjusted comments for clarity and consistency across test scenarios.
- Ensured that all necessary modules are imported correctly to avoid potential runtime issues.

* feat: add base devtooling

* fix: ensure dep refs are updated for devtools

* fix: allow pre-release

* feat: allow release after tag

* feat: bump versions to 1.0.0a3 

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>

* fix: match tag and release title, ignore devtools build for pypi

* fix: allow failed pypi publish

* feat: introduce trigger listing and execution commands for local development (#3643)

* chore: exclude tests from ruff linting

* chore: exclude tests from GitHub Actions linter

* fix: replace print statements with logger in agent and memory handling

* chore: add noqa for intentional print in printer utility

* fix: resolve linting errors across codebase

* feat: update docs with new approach to consume Platform Actions (#3675)

* fix: remove duplicate line and add explicit env var

* feat: bump versions to 1.0.0a4 (#3686)

* Update triggers docs (#3678)

* docs: introduce triggers list & triggers run command

* docs: add KO triggers docs

* docs: ensure CREWAI_PLATFORM_INTEGRATION_TOKEN is mentioned on docs (#3687)

* Lorenze/bedrock llm (#3693)

* feat: add AWS Bedrock support and update dependencies

- Introduced BedrockCompletion class for AWS Bedrock integration in LLM.
- Added boto3 as a new dependency in both pyproject.toml and uv.lock.
- Updated LLM class to support Bedrock provider.
- Created new files for Bedrock provider implementation.

* using converse api

* converse

* linted

* refactor: update BedrockCompletion class to improve parameter handling

- Changed max_tokens from a fixed integer to an optional integer.
- Simplified model ID assignment by removing the inference profile mapping method.
- Cleaned up comments and unnecessary code related to tool specifications and model-specific parameters.

* feat: improve event bus thread safety and async support

Add thread-safe, async-compatible event bus with read–write locking and
handler dependency ordering. Remove blinker dependency and implement
direct dispatch. Improve type safety, error handling, and deterministic
event synchronization.

Refactor tests to auto-wait for async handlers, ensure clean teardown,
and add comprehensive concurrency coverage. Replace thread-local state
in AgentEvaluator with instance-based locking for correct cross-thread
access. Enhance tracing reliability and event finalization.

* feat: enhance OpenAICompletion class with additional client parameters (#3701)

* feat: enhance OpenAICompletion class with additional client parameters

- Added support for default_headers, default_query, and client_params in the OpenAICompletion class.
- Refactored client initialization to use a dedicated method for client parameter retrieval.
- Introduced new test cases to validate the correct usage of OpenAICompletion with various parameters.

* fix: correct test case for unsupported OpenAI model

- Updated the test_openai.py to ensure that the LLM instance is created before calling the method, maintaining proper error handling for unsupported models.
- This change ensures that the test accurately checks for the NotFoundError when an invalid model is specified.

* fix: enhance error handling in OpenAICompletion class

- Added specific exception handling for NotFoundError and APIConnectionError in the OpenAICompletion class to provide clearer error messages and improve logging.
- Updated the test case for unsupported models to ensure it raises a ValueError with the appropriate message when a non-existent model is specified.
- This change improves the robustness of the OpenAI API integration and enhances the clarity of error reporting.

* fix: improve test for unsupported OpenAI model handling

- Refactored the test case in test_openai.py to create the LLM instance after mocking the OpenAI client, ensuring proper error handling for unsupported models.
- This change enhances the clarity of the test by accurately checking for ValueError when a non-existent model is specified, aligning with recent improvements in error handling for the OpenAICompletion class.

* feat: bump versions to 1.0.0b1 (#3706)

* Lorenze/tools drop litellm (#3710)

* completely drop litellm and correctly pass config for qdrant

* feat: add support for additional embedding models in EmbeddingService

- Expanded the list of supported embedding models to include Google Vertex, Hugging Face, Jina, Ollama, OpenAI, Roboflow, Watson X, custom embeddings, Sentence Transformers, Text2Vec, OpenClip, and Instructor.
- This enhancement improves the versatility of the EmbeddingService by allowing integration with a wider range of embedding providers.

* fix: update collection parameter handling in CrewAIRagAdapter

- Changed the condition for setting vectors_config in the CrewAIRagAdapter to check for QdrantConfig instance instead of using hasattr. This improves type safety and ensures proper configuration handling for Qdrant integration.

* moved stagehand as optional dep (#3712)

* feat: bump versions to 1.0.0b2 (#3713)

* feat: enhance AnthropicCompletion class with additional client parame… (#3707)

* feat: enhance AnthropicCompletion class with additional client parameters and tool handling

- Added support for client_params in the AnthropicCompletion class to allow for additional client configuration.
- Refactored client initialization to use a dedicated method for retrieving client parameters.
- Implemented a new method to handle tool use conversation flow, ensuring proper execution and response handling.
- Introduced comprehensive test cases to validate the functionality of the AnthropicCompletion class, including tool use scenarios and parameter handling.

* drop print statements

* test: add fixture to mock ANTHROPIC_API_KEY for tests

- Introduced a pytest fixture to automatically mock the ANTHROPIC_API_KEY environment variable for all tests in the test_anthropic.py module.
- This change ensures that tests can run without requiring a real API key, improving test isolation and reliability.

* refactor: streamline streaming message handling in AnthropicCompletion class

- Removed the 'stream' parameter from the API call as it is set internally by the SDK.
- Simplified the handling of tool use events and response construction by extracting token usage from the final message.
- Enhanced the flow for managing tool use conversation, ensuring proper integration with the streaming API response.

* fix streaming here too

* fix: improve error handling in tool conversion for AnthropicCompletion class

- Enhanced exception handling during tool conversion by catching KeyError and ValueError.
- Added logging for conversion errors to aid in debugging and maintain robustness in tool integration.

* feat: enhance GeminiCompletion class with client parameter support (#3717)

* feat: enhance GeminiCompletion class with client parameter support

- Added support for client_params in the GeminiCompletion class to allow for additional client configuration.
- Refactored client initialization into a dedicated method for improved parameter handling.
- Introduced a new method to retrieve client parameters, ensuring compatibility with the base class.
- Enhanced error handling during client initialization to provide clearer messages for missing configuration.
- Updated documentation to reflect the changes in client parameter usage.

* add optional dependancies

* refactor: update test fixture to mock GOOGLE_API_KEY

- Renamed the fixture from `mock_anthropic_api_key` to `mock_google_api_key` to reflect the change in the environment variable being mocked.
- This update ensures that all tests in the module can run with a mocked GOOGLE_API_KEY, improving test isolation and reliability.

* fix tests

* feat: enhance BedrockCompletion class with advanced features

* feat: enhance BedrockCompletion class with advanced features and error handling

- Added support for guardrail configuration, additional model request fields, and custom response field paths in the BedrockCompletion class.
- Improved error handling for AWS exceptions and added token usage tracking with stop reason logging.
- Enhanced streaming response handling with comprehensive event management, including tool use and content block processing.
- Updated documentation to reflect new features and initialization parameters.
- Introduced a new test suite for BedrockCompletion to validate functionality and ensure robust integration with AWS Bedrock APIs.

* chore: add boto typing

* fix: use typing_extensions.Required for Python 3.10 compatibility

---------

Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>

* feat: azure native tests

* feat: add Azure AI Inference support and related tests

- Introduced the `azure-ai-inference` package with version `1.0.0b9` and its dependencies in `uv.lock` and `pyproject.toml`.
- Added new test files for Azure LLM functionality, including tests for Azure completion and tool handling.
- Implemented comprehensive test cases to validate Azure-specific behavior and integration with the CrewAI framework.
- Enhanced the testing framework to mock Azure credentials and ensure proper isolation during tests.

* feat: enhance AzureCompletion class with Azure OpenAI support

- Added support for the Azure OpenAI endpoint in the AzureCompletion class, allowing for flexible endpoint configurations.
- Implemented endpoint validation and correction to ensure proper URL formats for Azure OpenAI deployments.
- Enhanced error handling to provide clearer messages for common HTTP errors, including authentication and rate limit issues.
- Updated tests to validate the new endpoint handling and error messaging, ensuring robust integration with Azure AI Inference.
- Refactored parameter preparation to conditionally include the model parameter based on the endpoint type.

* refactor: convert project module to metaclass with full typing

* Lorenze/OpenAI base url backwards support (#3723)

* fix: enhance OpenAICompletion class base URL handling

- Updated the base URL assignment in the OpenAICompletion class to prioritize the new `api_base` attribute and fallback to the environment variable `OPENAI_BASE_URL` if both are not set.
- Added `api_base` to the list of parameters in the OpenAICompletion class to ensure proper configuration and flexibility in API endpoint management.

* feat: enhance OpenAICompletion class with api_base support

- Added the `api_base` parameter to the OpenAICompletion class to allow for flexible API endpoint configuration.
- Updated the `_get_client_params` method to prioritize `base_url` over `api_base`, ensuring correct URL handling.
- Introduced comprehensive tests to validate the behavior of `api_base` and `base_url` in various scenarios, including environment variable fallback.
- Enhanced test coverage for client parameter retrieval, ensuring robust integration with the OpenAI API.

* fix: improve OpenAICompletion class configuration handling

- Added a debug print statement to log the client configuration parameters during initialization for better traceability.
- Updated the base URL assignment logic to ensure it defaults to None if no valid base URL is provided, enhancing robustness in API endpoint configuration.
- Refined the retrieval of the `api_base` environment variable to streamline the configuration process.

* drop print

* feat: improvements on import native sdk support (#3725)

* feat: add support for Anthropic provider and enhance logging

- Introduced the `anthropic` package with version `0.69.0` in `pyproject.toml` and `uv.lock`, allowing for integration with the Anthropic API.
- Updated logging in the LLM class to provide clearer error messages when importing native providers, enhancing debugging capabilities.
- Improved error handling in the AnthropicCompletion class to guide users on installation via the updated error message format.
- Refactored import error handling in other provider classes to maintain consistency in error messaging and installation instructions.

* feat: enhance LLM support with Bedrock provider and update dependencies

- Added support for the `bedrock` provider in the LLM class, allowing integration with AWS Bedrock APIs.
- Updated `uv.lock` to replace `boto3` with `bedrock` in the dependencies, reflecting the new provider structure.
- Introduced `SUPPORTED_NATIVE_PROVIDERS` to include `bedrock` and ensure proper error handling when instantiating native providers.
- Enhanced error handling in the LLM class to raise informative errors when native provider instantiation fails.
- Added tests to validate the behavior of the new Bedrock provider and ensure fallback mechanisms work correctly for unsupported providers.

* test: update native provider fallback tests to expect ImportError

* adjust the test with the expected bevaior - raising ImportError

* this is exoecting the litellm format, all gemini native tests are in test_google.py

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>

* fix: remove stdout prints, improve test determinism, and update trace handling

Removed `print` statements from the `LLMStreamChunkEvent` handler to prevent
LLM response chunks from being written directly to stdout. The listener now
only tracks chunks internally.

Fixes #3715

Added explicit return statements for trace-related tests.

Updated cassette for `test_failed_evaluation` to reflect new behavior where
an empty trace dict is used instead of returning early.

Ensured deterministic cleanup order in test fixtures by making
`clear_event_bus_handlers` depend on `setup_test_environment`. This guarantees
event bus shutdown and file handle cleanup occur before temporary directory
deletion, resolving intermittent “Directory not empty” errors in CI.

* chore: remove lib/crewai exclusion from pre-commit hooks

* feat: enhance task guardrail functionality and validation

* feat: enhance task guardrail functionality and validation

- Introduced support for multiple guardrails in the Task class, allowing for sequential processing of guardrails.
- Added a new `guardrails` field to the Task model to accept a list of callable guardrails or string descriptions.
- Implemented validation to ensure guardrails are processed correctly, including handling of retries and error messages.
- Enhanced the `_invoke_guardrail_function` method to manage guardrail execution and integrate with existing task output processing.
- Updated tests to cover various scenarios involving multiple guardrails, including success, failure, and retry mechanisms.

This update improves the flexibility and robustness of task execution by allowing for more complex validation scenarios.

* refactor: enhance guardrail type handling in Task model

- Updated the Task class to improve guardrail type definitions, introducing GuardrailType and GuardrailsType for better clarity and type safety.
- Simplified the validation logic for guardrails, ensuring that both single and multiple guardrails are processed correctly.
- Enhanced error messages for guardrail validation to provide clearer feedback when incorrect types are provided.
- This refactor improves the maintainability and robustness of task execution by standardizing guardrail handling.

* feat: implement per-guardrail retry tracking in Task model

- Introduced a new private attribute `_guardrail_retry_counts` to the Task class for tracking retry attempts on a per-guardrail basis.
- Updated the guardrail processing logic to utilize the new retry tracking, allowing for independent retry counts for each guardrail.
- Enhanced error handling to provide clearer feedback when guardrails fail validation after exceeding retry limits.
- Modified existing tests to validate the new retry tracking behavior, ensuring accurate assertions on guardrail retries.

This update improves the robustness and flexibility of task execution by allowing for more granular control over guardrail validation and retry mechanisms.

* chore: 1.0.0b3 bump (#3734)

* chore: full ruff and mypy

improved linting, pre-commit setup, and internal architecture. Configured Ruff to respect .gitignore, added stricter rules, and introduced a lock pre-commit hook with virtualenv activation. Fixed type shadowing in EXASearchTool using a type_ alias to avoid PEP 563 conflicts and resolved circular imports in agent executor and guardrail modules. Removed agent-ops attributes, deprecated watson alias, and dropped crewai-enterprise tools with corresponding test updates. Refactored cache and memoization for thread safety and cleaned up structured output adapters and related logic.

* New MCL DSL (#3738)

* Adding MCP implementation

* New tests for MCP implementation

* fix tests

* update docs

* Revert "New tests for MCP implementation"

This reverts commit 0bbe6dee90.

* linter

* linter

* fix

* verify mcp pacakge exists

* adjust docs to be clear only remote servers are supported

* reverted

* ensure args schema generated properly

* properly close out

---------

Co-authored-by: lorenzejay <lorenzejaytech@gmail.com>
Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>

* feat: a2a experimental

experimental a2a support

---------

Co-authored-by: Lucas Gomide <lucaslg200@gmail.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Tony Kipkemboi <iamtonykipkemboi@gmail.com>
Co-authored-by: Mike Plachta <mplachta@users.noreply.github.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
This commit is contained in:
Lorenze Jay
2025-10-20 14:10:19 -07:00
committed by GitHub
parent 42f2b4d551
commit d1343b96ed
1339 changed files with 111657 additions and 19564 deletions

View File

@@ -0,0 +1,243 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\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: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzTXAk4GatJOmLO9sEOCCITIjf1Dx\",\n \"object\":
\"chat.completion\",\n \"created\": 1739214900,\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: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\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_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90fe6ce92eba67b3-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 10 Feb 2025 19:15:01 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=pjX1I6y8RlqCjS.gvOqvXk4vM69UNwFwmslh1BhALNg-1739214901-1.0.1.1-nJcNlSdNcug82eDl7KSvteLbsg0xCiEh2yI1TZX2jMAblL7AMQ8LFhvXkJLlAMfk49RMzRzWy2aiQgeM7WRHPg;
path=/; expires=Mon, 10-Feb-25 19:45:01 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '571'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a95183a7a85e6bdfe381b2510bf70f34
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
from 0 to 10 evaluating on completion, quality, and overall performance- Entities
extracted from the task output, if any, their type, description, and relationships"}],
"model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
"TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
"description": "Correctly extracted `TaskEvaluation` with all the required parameters
with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
{"description": "The name of the entity.", "title": "Name", "type": "string"},
"type": {"description": "The type of the entity.", "title": "Type", "type":
"string"}, "description": {"description": "Description of the entity.", "title":
"Description", "type": "string"}, "relationships": {"description": "Relationships
of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
"array"}}, "required": ["name", "type", "description", "relationships"], "title":
"Entity", "type": "object"}}, "properties": {"suggestions": {"description":
"Suggestions to improve future similar tasks.", "items": {"type": "string"},
"title": "Suggestions", "type": "array"}, "quality": {"description": "A score
from 0 to 10 evaluating on completion, quality, and overall performance, all
taking into account the task description, expected output, and the result of
the task.", "title": "Quality", "type": "number"}, "entities": {"description":
"Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
"title": "Entities", "type": "array"}}, "required": ["entities", "quality",
"suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1962'
content-type:
- application/json
cookie:
- __cf_bm=pjX1I6y8RlqCjS.gvOqvXk4vM69UNwFwmslh1BhALNg-1739214901-1.0.1.1-nJcNlSdNcug82eDl7KSvteLbsg0xCiEh2yI1TZX2jMAblL7AMQ8LFhvXkJLlAMfk49RMzRzWy2aiQgeM7WRHPg;
_cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzTXDcgKWq3yosIyBal8LcY8dDrn1\",\n \"object\":
\"chat.completion\",\n \"created\": 1739214903,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_c41SAnqyEKNXEAZd5XV3jKF3\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"TaskEvaluation\",\n
\ \"arguments\": \"{\\\"suggestions\\\":[\\\"Consider specifying
the tone or context of the greeting for more engaging interactions.\\\",\\\"Clarify
if additional greetings or responses are acceptable to enhance the task's scope.\\\"],\\\"quality\\\":10,\\\"entities\\\":[]
}\"\n }\n }\n ],\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 273,\n \"completion_tokens\": 43,\n
\ \"total_tokens\": 316,\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_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 90fe6cf8c96e67b3-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 10 Feb 2025 19:15:04 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1181'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999876'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_b2286c8ae6f9b2a42f46a3e2c52b4211
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,114 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "Name: Alice, Age: 30"}], "model":
"gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name": "SimpleModel"}},
"tools": [{"type": "function", "function": {"name": "SimpleModel", "description":
"Correctly extracted `SimpleModel` with all the required parameters with correct
types", "parameters": {"properties": {"name": {"title": "Name", "type": "string"},
"age": {"title": "Age", "type": "integer"}}, "required": ["age", "name"], "type":
"object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '507'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.59.6
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.59.6
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-Aq4a4xDv8G0i4fbTtPJEI2B8UNBup\",\n \"object\":
\"chat.completion\",\n \"created\": 1736974028,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_uO5nec8hTk1fpYINM8TUafhe\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"SimpleModel\",\n
\ \"arguments\": \"{\\\"name\\\":\\\"Alice\\\",\\\"age\\\":30}\"\n
\ }\n }\n ],\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 79,\n \"completion_tokens\": 10,\n
\ \"total_tokens\": 89,\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_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 9028b81aeb1cb05f-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 15 Jan 2025 20:47:08 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=PzayZLF04c14veGc.0ocVg3VHBbpzKRW8Hqox8L9U7c-1736974028-1.0.1.1-mZpK8.SH9l7K2z8Tvt6z.dURiVPjFqEz7zYEITfRwdr5z0razsSebZGN9IRPmI5XC_w5rbZW2Kg6hh5cenXinQ;
path=/; expires=Wed, 15-Jan-25 21:17:08 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=ciwC3n2Srn20xx4JhEUeN6Ap0tNBaE44S95nIilboQ0-1736974028496-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '439'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999978'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a468000458b9d2848b7497b2e3d485a3
http_version: HTTP/1.1
status_code: 200
version: 1

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,67 @@
interactions:
- request:
body: '{"model": "meta-llama/llama-3.2-3b-instruct", "messages": [{"role": "system",
"content": "Please convert the following text into valid JSON.\n\nOutput ONLY
the valid JSON and nothing else.\n\nThe JSON must follow this format exactly:\n{\n \"name\":
str,\n \"age\": int\n}"}, {"role": "user", "content": "Name: Alice Llama, Age:
30"}], "stream": false, "stop": []}'
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '365'
content-type:
- application/json
host:
- openrouter.ai
http-referer:
- https://litellm.ai
user-agent:
- litellm/1.68.0
x-title:
- liteLLM
method: POST
uri: https://openrouter.ai/api/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAAwAAAP//dJDBTsMwEER/pZqzU1ICKfKNMwgQEieCKsfZJgbHG9mbghTl31FatZy4
7GHm8N7OBNdAo6WQbbY327zMi81t9vwizVv5sB9f22/DdOg730FhiHxwDUVoPFHtxgSFnhvy0OhJ
TOa96c3V8WbF+jor6syFJHG0AgWuP8kKNGxnZG25HzyJ4wAFG8kINdB/Egq2Y2cpQb9P8NwOkesE
HUbvFfYuuNTtIpnEARpJeIBCMOIOtPundaGhH+hcoaeUTEvQEyJ7goZJySUxYRG1HITCYjpVCKan
CnpV4d47S6vH5bsKalXBtMemyGcoRNqPyfiz4IntQnsK5vlDYTwzh8j9IDvhLwoJuiwX5nmOS7xs
ICzGX5K7zTz/AgAA//8DAIXfumyyAQAA
headers:
Access-Control-Allow-Origin:
- '*'
CF-RAY:
- 93ea9f59596559fa-DEL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 12 May 2025 14:31:55 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
Vary:
- Accept-Encoding
x-clerk-auth-message:
- Invalid JWT form. A JWT consists of three parts separated by dots. (reason=token-invalid,
token-carrier=header)
x-clerk-auth-reason:
- token-invalid
x-clerk-auth-status:
- signed-out
status:
code: 200
message: OK
version: 1

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,315 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\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: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
cookie:
- __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
_cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJK2OCJSkUj1plgbj59b4dC39QV2\",\n \"object\":
\"chat.completion\",\n \"created\": 1738698990,\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: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\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_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90cd396c0ab71698-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 19:56:30 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '951'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_2c3cb5caed61ccd1e058ef3e6301c691
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '2480'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Tue, 04 Feb 2025 19:56:31 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
from 0 to 10 evaluating on completion, quality, and overall performance- Entities
extracted from the task output, if any, their type, description, and relationships"}],
"model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
"TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
"description": "Correctly extracted `TaskEvaluation` with all the required parameters
with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
{"description": "The name of the entity.", "title": "Name", "type": "string"},
"type": {"description": "The type of the entity.", "title": "Type", "type":
"string"}, "description": {"description": "Description of the entity.", "title":
"Description", "type": "string"}, "relationships": {"description": "Relationships
of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
"array"}}, "required": ["name", "type", "description", "relationships"], "title":
"Entity", "type": "object"}}, "properties": {"suggestions": {"description":
"Suggestions to improve future similar tasks.", "items": {"type": "string"},
"title": "Suggestions", "type": "array"}, "quality": {"description": "A score
from 0 to 10 evaluating on completion, quality, and overall performance, all
taking into account the task description, expected output, and the result of
the task.", "title": "Quality", "type": "number"}, "entities": {"description":
"Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
"title": "Entities", "type": "array"}}, "required": ["entities", "quality",
"suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1962'
content-type:
- application/json
cookie:
- __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
_cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJK3bJiyqGhPeqdCcCjoeNavGHrR\",\n \"object\":
\"chat.completion\",\n \"created\": 1738698991,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_uAFkclWHIRqgrXFrQFcEoUIS\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"TaskEvaluation\",\n
\ \"arguments\": \"{\\\"suggestions\\\":[\\\"Include additional
context for the greeting to make it more meaningful.\\\",\\\"Specify if you
want a casual or formal tone for greetings.\\\",\\\"Provide examples of variations
of the greeting if necessary.\\\"],\\\"quality\\\":10,\\\"entities\\\":[],\\\"relationships\\\":[]}\"\n
\ }\n }\n ],\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 273,\n \"completion_tokens\": 50,\n
\ \"total_tokens\": 323,\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_bd83329f63\"\n}\n"
headers:
CF-RAY:
- 90cd3973589f1698-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 19:56:32 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1408'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999876'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_519fd27ca3d5da4d541c4331654e0520
http_version: HTTP/1.1
status_code: 200
version: 1

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,245 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\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: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJIrSWAFqDEsNtLRhcM8vMHO9Ejw\",\n \"object\":
\"chat.completion\",\n \"created\": 1738698917,\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: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\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_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90cd37a83f5f176a-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 19:55:18 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=rKQWp4fbAvcCp4rasEN6DqiTjQfiWYpLfjcLpWcmzi0-1738698918-1.0.1.1-qlcCSdBY3KWbzVms0eLtz5ub5SSLGs_sRLxTdNhDk_purQuz9k6EFp8PHJfN3aP_sLnuyKnFlppM3.2k_dCtPQ;
path=/; expires=Tue, 04-Feb-25 20:25:18 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=Oi91zDXvjWohBYXSVqK4hFsq3_GZePEIIbi7b7wrjcI-1738698918130-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '894'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_864253996bbc0f797f9a2c1b9247a0d5
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
from 0 to 10 evaluating on completion, quality, and overall performance- Entities
extracted from the task output, if any, their type, description, and relationships"}],
"model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
"TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
"description": "Correctly extracted `TaskEvaluation` with all the required parameters
with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
{"description": "The name of the entity.", "title": "Name", "type": "string"},
"type": {"description": "The type of the entity.", "title": "Type", "type":
"string"}, "description": {"description": "Description of the entity.", "title":
"Description", "type": "string"}, "relationships": {"description": "Relationships
of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
"array"}}, "required": ["name", "type", "description", "relationships"], "title":
"Entity", "type": "object"}}, "properties": {"suggestions": {"description":
"Suggestions to improve future similar tasks.", "items": {"type": "string"},
"title": "Suggestions", "type": "array"}, "quality": {"description": "A score
from 0 to 10 evaluating on completion, quality, and overall performance, all
taking into account the task description, expected output, and the result of
the task.", "title": "Quality", "type": "number"}, "entities": {"description":
"Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
"title": "Entities", "type": "array"}}, "required": ["entities", "quality",
"suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1962'
content-type:
- application/json
cookie:
- __cf_bm=rKQWp4fbAvcCp4rasEN6DqiTjQfiWYpLfjcLpWcmzi0-1738698918-1.0.1.1-qlcCSdBY3KWbzVms0eLtz5ub5SSLGs_sRLxTdNhDk_purQuz9k6EFp8PHJfN3aP_sLnuyKnFlppM3.2k_dCtPQ;
_cfuvid=Oi91zDXvjWohBYXSVqK4hFsq3_GZePEIIbi7b7wrjcI-1738698918130-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJIsVEppA04iGQh0k6sanKnVObrO\",\n \"object\":
\"chat.completion\",\n \"created\": 1738698918,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_AQ3iizjGWjEvk1SmhGCzjbf1\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"TaskEvaluation\",\n
\ \"arguments\": \"{\\\"suggestions\\\":[\\\"Provide context for
the greeting, like a specific scenario or recipient.\\\",\\\"Encourage responses
or follow-ups to promote engagement.\\\",\\\"Specify the tone or formality of
the greeting, if relevant.\\\"],\\\"quality\\\":10,\\\"entities\\\":[{\\\"name\\\":\\\"hi\\\",\\\"type\\\":\\\"greeting\\\",\\\"description\\\":\\\"A
common informal expression used to initiate conversation or acknowledge someone.\\\",\\\"relationships\\\":[\\\"used
in conversation\\\",\\\"expresses friendliness\\\"]}]}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
273,\n \"completion_tokens\": 84,\n \"total_tokens\": 357,\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_bd83329f63\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 90cd37aec8c8176a-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 19:55:21 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '3269'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999876'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_e6e67a3f5c6f2d48e0351cdce95edd97
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,243 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\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: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJJzafmayYpGTsTAWbOyZkmQJNa5\",\n \"object\":
\"chat.completion\",\n \"created\": 1738698987,\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: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\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_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 90cd395b0e641698-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 19:56:27 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
path=/; expires=Tue, 04-Feb-25 20:26:27 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '839'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_577b484a927b455c40ed80f9fd4d9106
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
from 0 to 10 evaluating on completion, quality, and overall performance- Entities
extracted from the task output, if any, their type, description, and relationships"}],
"model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
"TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
"description": "Correctly extracted `TaskEvaluation` with all the required parameters
with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
{"description": "The name of the entity.", "title": "Name", "type": "string"},
"type": {"description": "The type of the entity.", "title": "Type", "type":
"string"}, "description": {"description": "Description of the entity.", "title":
"Description", "type": "string"}, "relationships": {"description": "Relationships
of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
"array"}}, "required": ["name", "type", "description", "relationships"], "title":
"Entity", "type": "object"}}, "properties": {"suggestions": {"description":
"Suggestions to improve future similar tasks.", "items": {"type": "string"},
"title": "Suggestions", "type": "array"}, "quality": {"description": "A score
from 0 to 10 evaluating on completion, quality, and overall performance, all
taking into account the task description, expected output, and the result of
the task.", "title": "Quality", "type": "number"}, "entities": {"description":
"Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
"title": "Entities", "type": "array"}}, "required": ["entities", "quality",
"suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1962'
content-type:
- application/json
cookie:
- __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
_cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJJz10KP7iadNPdKsbcsvHBa7cic\",\n \"object\":
\"chat.completion\",\n \"created\": 1738698987,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_czeHQgy5eiOVa0zlrtcfwepe\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"TaskEvaluation\",\n
\ \"arguments\": \"{\\\"suggestions\\\":[\\\"Provide more context
or details for similar tasks to enhance output expectations.\\\",\\\"Encourage
creativity in responses for simple tasks to engage users more effectively.\\\"],\\\"quality\\\":10,\\\"entities\\\":[]
}\"\n }\n }\n ],\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 273,\n \"completion_tokens\": 40,\n
\ \"total_tokens\": 313,\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_bd83329f63\"\n}\n"
headers:
CF-RAY:
- 90cd39615b281698-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 19:56:29 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1411'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999876'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_3e717a80c7d9c5ea19893dd990aaae26
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,245 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\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: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
cookie:
- __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
_cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJiiHEQwIXsiG0Sd5wofcuhxVbo9\",\n \"object\":
\"chat.completion\",\n \"created\": 1738700520,\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: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\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_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90cd5ecd0f7667ee-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 20:22:01 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=nedOdWE1YnKQYt1kSbrcA.zhwa3bZDzmZqTOjZYER0c-1738700521-1.0.1.1-xQk9iXOvqvyXNhkIOgc8Ws2WYcT1mJFkDCvCC8xA5joFD8QfNrBIAr_Qs6sIxt2EzXyeFwBA6gA8ZgWApCHx0Q;
path=/; expires=Tue, 04-Feb-25 20:52:01 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '450'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_10eaafc81640a98a0a4789d270dd94d9
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
from 0 to 10 evaluating on completion, quality, and overall performance- Entities
extracted from the task output, if any, their type, description, and relationships"}],
"model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
"TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
"description": "Correctly extracted `TaskEvaluation` with all the required parameters
with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
{"description": "The name of the entity.", "title": "Name", "type": "string"},
"type": {"description": "The type of the entity.", "title": "Type", "type":
"string"}, "description": {"description": "Description of the entity.", "title":
"Description", "type": "string"}, "relationships": {"description": "Relationships
of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
"array"}}, "required": ["name", "type", "description", "relationships"], "title":
"Entity", "type": "object"}}, "properties": {"suggestions": {"description":
"Suggestions to improve future similar tasks.", "items": {"type": "string"},
"title": "Suggestions", "type": "array"}, "quality": {"description": "A score
from 0 to 10 evaluating on completion, quality, and overall performance, all
taking into account the task description, expected output, and the result of
the task.", "title": "Quality", "type": "number"}, "entities": {"description":
"Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
"title": "Entities", "type": "array"}}, "required": ["entities", "quality",
"suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1962'
content-type:
- application/json
cookie:
- __cf_bm=nedOdWE1YnKQYt1kSbrcA.zhwa3bZDzmZqTOjZYER0c-1738700521-1.0.1.1-xQk9iXOvqvyXNhkIOgc8Ws2WYcT1mJFkDCvCC8xA5joFD8QfNrBIAr_Qs6sIxt2EzXyeFwBA6gA8ZgWApCHx0Q;
_cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJijOhk12Ua6lS23IwtZTachfjq9\",\n \"object\":
\"chat.completion\",\n \"created\": 1738700521,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_DSteeMHHPf5RanJb8qjCo4qx\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"TaskEvaluation\",\n
\ \"arguments\": \"{\\\"suggestions\\\":[\\\"Consider adding context
for the greeting to make it more engaging.\\\",\\\"Specify if any additional
information or tone is desired in the greeting.\\\"],\\\"quality\\\":10,\\\"entities\\\":[{\\\"name\\\":\\\"greeting\\\",\\\"type\\\":\\\"text\\\",\\\"description\\\":\\\"A
simple greeting phrase\\\",\\\"relationships\\\":[\\\"is a\\\",\\\"is part of
a conversation\\\"]}]}\"\n }\n }\n ],\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 273,\n \"completion_tokens\":
67,\n \"total_tokens\": 340,\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_bd83329f63\"\n}\n"
headers:
CF-RAY:
- 90cd5ed20cb267ee-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 20:22:02 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1624'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999876'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_4ee944acdd3928afbf6c5562403b064a
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,114 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\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: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzpkZLpCyjKT5d6Udfx4zAme2sOMy\",\n \"object\":
\"chat.completion\",\n \"created\": 1739300299,\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: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\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_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 910691d3ab90ebef-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 11 Feb 2025 18:58:20 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=MOH5EY6n3p8JKY53.yz7qzLuLYsEB8QdQXH09loUMBM-1739300300-1.0.1.1-hjb4mk04sMygPFhoFyiySKZSqB_fN5PbhbOyn.kipa3.eLvk7EtriDyjvGkBFIAV13DYnc08BfF_l2kxdx9hfQ;
path=/; expires=Tue, 11-Feb-25 19:28:20 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=uu.cEiV.FfgvSvCdKOooDYJWrwjVEuFeGdQodijGUUI-1739300300232-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1357'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_2277503f851195e7d7a43b66eb044454
http_version: HTTP/1.1
status_code: 200
version: 1

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,103 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "Hello, how are you?"}], "model":
"gpt-4o-mini", "stop": []}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '102'
content-type:
- application/json
cookie:
- _cfuvid=IY8ppO70AMHr2skDSUsGh71zqHHdCQCZ3OvkPi26NBc-1740424913267-0.0.1.1-604800000;
__cf_bm=fU6K5KZoDmgcEuF8_yWAYKUO5fKHh6q5.wDPnna393g-1740424913-1.0.1.1-2iOaq3JVGWs439V0HxJee0IC9HdJm7dPkeJorD.AGw0YwkngRPM8rrTzn_7ht1BkbOauEezj.wPKcBz18gIYUg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-B4YLA2SrC2rwdVQ3U87G5a0P5lsLw\",\n \"object\":
\"chat.completion\",\n \"created\": 1740425016,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Hello! I'm just a computer program, so
I don't have feelings, but I'm here and ready to help you. How can I assist
you today?\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
13,\n \"completion_tokens\": 30,\n \"total_tokens\": 43,\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_709714d124\"\n}\n"
headers:
CF-RAY:
- 9171d4c0ed44236e-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 24 Feb 2025 19:23:38 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1954'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999978'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_ea2703502b8827e4297cd2a7bae9d9c8
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,108 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "Hello, how are you?"}], "model":
"gpt-4o-mini", "stop": []}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '102'
content-type:
- application/json
cookie:
- _cfuvid=GefCcEtb_Gem93E4a9Hvt3Xyof1YQZVJAXBb9I6pEUs-1739398417375-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-B4YJU8IWKGyBQtAyPDRd3SFI2flYR\",\n \"object\":
\"chat.completion\",\n \"created\": 1740424912,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Hello! I'm just a computer program, so
I don't have feelings, but I'm here and ready to help you. How can I assist
you today?\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
13,\n \"completion_tokens\": 30,\n \"total_tokens\": 43,\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_7fcd609668\"\n}\n"
headers:
CF-RAY:
- 9171d230d8ed7ae0-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 24 Feb 2025 19:21:53 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=fU6K5KZoDmgcEuF8_yWAYKUO5fKHh6q5.wDPnna393g-1740424913-1.0.1.1-2iOaq3JVGWs439V0HxJee0IC9HdJm7dPkeJorD.AGw0YwkngRPM8rrTzn_7ht1BkbOauEezj.wPKcBz18gIYUg;
path=/; expires=Mon, 24-Feb-25 19:51:53 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=IY8ppO70AMHr2skDSUsGh71zqHHdCQCZ3OvkPi26NBc-1740424913267-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '993'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999978'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_d9c4d49185e97b1797061efc1e55d811
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,171 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Speaker. You are a
helpful assistant that just says hi\nYour personal goal is: Just say hi\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!"}, {"role": "user",
"content": "say hi!"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
"stream": true, "stream_options": {"include_usage": true}}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '602'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.78.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.78.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.12
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":" \n"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
Hi"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null}
data: {"id":"chatcmpl-BoGFzpBc0nuAKcVrYlEEztNwzrUG6","object":"chat.completion.chunk","created":1751318591,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[],"usage":{"prompt_tokens":99,"completion_tokens":15,"total_tokens":114,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}}}
data: [DONE]
'
headers:
CF-RAY:
- 9580b92adce5e838-GRU
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Mon, 30 Jun 2025 21:23:12 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=nhFmL5HNobQWdbf2Sd9Z8X9ad5zXKG7Ln7MlzuiuwP8-1751318592-1.0.1.1-5qDyF6nVC5d8PDerEmHSOgyWEYdzMdgyFRXqgiJB3FSyWWnvzL4PyVp6LGx9z0P5iTX8PNbxfUOEOYX.7bFaK6p.CyxLaXK7WpnQ3zeasG8;
path=/; expires=Mon, 30-Jun-25 21:53:12 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=APKo781sOKEk.HlN5nFBT1Mkid8Lj04kw6JPleI78bU-1751318592001-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '321'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-envoy-upstream-service-time:
- '326'
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999896'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_0b0f668953604810c182b1e83e9709fe
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,118 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\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: Just say hi\n\nThis is the expected criteria for
your final answer: hi\nyou MUST return the actual complete content as the final
answer, not a summary.\n\nBegin! This is VERY important to you, use the tools
available and give your best Final Answer, your job depends on it!\n\nThought:"}],
"model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '838'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.78.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.78.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.12
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA4xSTW/bMAy9+1cQOsdDnI9m861ZMGAbBuyyHbYWBiMxtjaZEiS5aVHkvw+y09jd
OqAXA+bje3qP5GMGILQSJQjZYJStM/nW7j6z+vb9R739+mm707vj7sv2gffq/v2VEbPEsPtfJOMT
6420rTMUteUBlp4wUlItNutiOd8s15seaK0ik2i1i/nK5q1mnS/mi1U+3+TF2zO7sVpSECX8zAAA
Hvtv8smK7kUJ89lTpaUQsCZRXpoAhLcmVQSGoENEjmI2gtJyJO6tfwS2R5DIUOs7AoQ62QbkcCQP
cMMfNKOB6/6/hEZPdTwduoApC3fGTABkthHTLPoEt2fkdPFsbO283Ye/qOKgWYem8oTBcvIXonWi
R08ZwG0/m+5ZXOG8bV2sov1N/XPFVTHoiXElE3RxBqONaCb1zXL2gl6lKKI2YTJdIVE2pEbquArs
lLYTIJuk/tfNS9pDcs31a+RHQEpykVTlPCktnyce2zyli/1f22XKvWERyN9pSVXU5NMmFB2wM8Md
ifAQIrXVQXNN3nk9HNPBVcsVrldI75ZSZKfsDwAAAP//AwBulbOoWgMAAA==
headers:
CF-RAY:
- 957fa6e91a22023d-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 30 Jun 2025 18:15:58 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=9WXNY0u6p0Nlyb1G36cXHDgtwb1538JzaUNoS4tgrpo-1751307358-1.0.1.1-BAvg6Fgqsv3ITFxrC3z3E42AqgSZcGq4Gr1Wrjx56TOsljYynqCePNzQ79oAncT9KXehFnUMxA6JSf2lAfQOeSLVREY3_P6GjPkbcwIsVXw;
path=/; expires=Mon, 30-Jun-25 18:45:58 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=N5kr6p8e26f8scPW5s2uVOatzh2RYjlQb13eQUBsrts-1751307358295-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '308'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-envoy-upstream-service-time:
- '310'
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999823'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_78bb0375ac6e0939c8e05f66869e0137
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,170 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "Tell me a short joke"}], "model":
"gpt-3.5-turbo", "stop": [], "stream": true}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '121'
content-type:
- application/json
cookie:
- _cfuvid=IY8ppO70AMHr2skDSUsGh71zqHHdCQCZ3OvkPi26NBc-1740424913267-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.65.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.65.1
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Why"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
couldn"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"''t"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
the"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
bicycle"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
stand"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
up"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
by"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
itself"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"?"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
Because"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
it"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
was"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
two"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-t"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ired"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-B74aE2TDl9ZbKx2fXoVatoMDnErNm","object":"chat.completion.chunk","created":1741025614,"model":"gpt-3.5-turbo-0125","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-RAY:
- 91ab1bcbad95bcda-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Mon, 03 Mar 2025 18:13:34 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=Jydtg8l0yjWRI2vKmejdq.C1W.sasIwEbTrV2rUt6V0-1741025614-1.0.1.1-Af3gmq.j2ecn9QEa3aCVY09QU4VqoW2GTk9AjvzPA.jyAZlwhJd4paniSt3kSusH0tryW03iC8uaX826hb2xzapgcfSm6Jdh_eWh_BMCh_8;
path=/; expires=Mon, 03-Mar-25 18:43:34 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=5wzaJSCvT1p1Eazad55wDvp1JsgxrlghhmmU9tx0fMs-1741025614868-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '127'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '50000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '49999978'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_2a2a04977ace88fdd64cf570f80c0202
status:
code: 200
message: OK
version: 1

View File

@@ -0,0 +1,110 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "Tell me a short joke"}], "model":
"gpt-4o", "stop": []}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '98'
content-type:
- application/json
cookie:
- _cfuvid=IY8ppO70AMHr2skDSUsGh71zqHHdCQCZ3OvkPi26NBc-1740424913267-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.68.2
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.68.2
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-BHJ51XXwVMlREjnoe4n4fiA0Ynkab\",\n \"object\":
\"chat.completion\",\n \"created\": 1743464619,\n \"model\": \"gpt-4o-2024-08-06\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Why don't skeletons fight each other?\\n\\nThey
don't have the guts.\",\n \"refusal\": null,\n \"annotations\":
[]\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 12,\n \"completion_tokens\":
15,\n \"total_tokens\": 27,\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_de57b65c90\"\n}\n"
headers:
CF-RAY:
- 9293b5d18d3f9450-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 31 Mar 2025 23:43:40 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=.esGqWXxYzwXyi6048Ocr_NZH1IMsgTTuNN0drcWtSI-1743464620-1.0.1.1-YroBLb5o02zaPiXdGGE3YNO3x56olTA3JQos540j.l2aoeOzHIMVubkp2uSSTBHefPb7OPDKFzjpRXoAVof9jgVUDL6C89g4Zu1_SXtWxEE;
path=/; expires=Tue, 01-Apr-25 00:13:40 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=jrsyZSqr3xLO_beX7x7VEel62eQFToYHZgRqR0eqVNs-1743464620187-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '275'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '50000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '49999'
x-ratelimit-remaining-tokens:
- '149999993'
x-ratelimit-reset-requests:
- 1ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_09cc97e978a7a4b57a1c9ebc9c688fb8
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,111 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\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: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
cookie:
- _cfuvid=gsNyCo_jrDOolzf8SXHDaxQQrEgdR3jgv4OAH8MziDE-1739291824699-0.0.1.1-604800000;
__cf_bm=cRijYuylMGzRGxv3udQL5PhHOR5mRN_9_eLLwevlM_o-1739299455-1.0.1.1-Fszr_Msw0B1.IBMkiunP.VF2ilul1YGZZV8TqMcO3Q2SHvSlqfgm9NHgns1bJrm0wWRvHiCE7wdZfUAOx7T3Lg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzpWx6pctOvzu6xsbyg0XfSAc0q9V\",\n \"object\":
\"chat.completion\",\n \"created\": 1739299455,\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: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\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_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 91067d3ddc68fa16-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 11 Feb 2025 18:44:16 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '703'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_89222c00e4608e8557a135e91b223556
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,114 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\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: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
cookie:
- _cfuvid=gsNyCo_jrDOolzf8SXHDaxQQrEgdR3jgv4OAH8MziDE-1739291824699-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzpWxLzAcRzigZuIGmjP3ckQgxAom\",\n \"object\":
\"chat.completion\",\n \"created\": 1739299455,\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: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\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_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 91067d389e90fa16-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 11 Feb 2025 18:44:15 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=cRijYuylMGzRGxv3udQL5PhHOR5mRN_9_eLLwevlM_o-1739299455-1.0.1.1-Fszr_Msw0B1.IBMkiunP.VF2ilul1YGZZV8TqMcO3Q2SHvSlqfgm9NHgns1bJrm0wWRvHiCE7wdZfUAOx7T3Lg;
path=/; expires=Tue, 11-Feb-25 19:14:15 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '716'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_ef807dc3223d40332aae8a313e96ef3a
http_version: HTTP/1.1
status_code: 200
version: 1

View File

@@ -0,0 +1,165 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are TestAgent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\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: Just say hi\n\nThis is the expected criteria for
your final answer: hi\nyou MUST return the actual complete content as the final
answer, not a summary.\n\nBegin! This is VERY important to you, use the tools
available and give your best Final Answer, your job depends on it!\n\nThought:"}],
"model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream": true, "stream_options":
{"include_usage": true}}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '896'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.78.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.78.0
x-stainless-raw-response:
- 'true'
x-stainless-read-timeout:
- '600.0'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.12
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":" \n"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{"content":"
hi"},"logprobs":null,"finish_reason":null}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null}
data: {"id":"chatcmpl-BoFTMrRBBaVsju5o285dR7JBeVVvS","object":"chat.completion.chunk","created":1751315576,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_34a54ae93c","choices":[],"usage":{"prompt_tokens":161,"completion_tokens":12,"total_tokens":173,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}}}
data: [DONE]
'
headers:
CF-RAY:
- 95806f8e3fc2f213-GRU
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Mon, 30 Jun 2025 20:32:56 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=dxb.Rn1CsTQLjW9eU0KWonEuID9KkkVRJ1FaBBsW5gQ-1751315576-1.0.1.1-R7bLnCfrjJwtHYzbKEE9in7ilYfymelWgYg1OcPqSEllAFA9_R2ctsY0f7Mrv7i0dXaynAooDpLs9hGIzfgyBR9EgkRjqoaHbByPXjxy_5s;
path=/; expires=Mon, 30-Jun-25 21:02:56 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=MwdjLsfFXJDWzbJseVfA4MIpVAqLa7envAu7EAkdK4o-1751315576696-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '238'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-envoy-upstream-service-time:
- '241'
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999824'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_394b055696dfcdc221b5ecd0fba49e97
status:
code: 200
message: OK
version: 1

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,512 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: say_hi\nTool Arguments: {}\nTool Description:
Say hi\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 [say_hi], 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: Just say
hi\n\nThis is the expect criteria for your final answer: hi\nyou MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1275'
content-type:
- application/json
cookie:
- _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzUA6kJQfpUvB4CGot4gSfAIR0foh\",\n \"object\":
\"chat.completion\",\n \"created\": 1739217314,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"you should always think about what to
do \\nAction: say_hi \\nAction Input: {} \",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 257,\n \"completion_tokens\":
19,\n \"total_tokens\": 276,\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_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90fea7d78e1fceb9-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 10 Feb 2025 19:55:15 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=fmlg1wjOwuOwZhUUOEtL1tQYluAPumn7AHLF8s0EU2Y-1739217315-1.0.1.1-PQDvxn8TOhzaznlHjwVsqPZUzbAyJWFkvzCubfNJydTu2_AyA1cJ8hkM0khsEE4UY_xp8iPe2gSGmH1ydrDa0Q;
path=/; expires=Mon, 10-Feb-25 20:25:15 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '526'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999703'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_f6358ff0cc7a2b8d2e167ab00a40f2a4
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: say_hi\nTool Arguments: {}\nTool Description:
Say hi\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 [say_hi], 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: Just say
hi\n\nThis is the expect criteria for your final answer: hi\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": "you
should always think about what to do \nAction: say_hi \nAction Input: {} \nObservation:
hi"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1410'
content-type:
- application/json
cookie:
- _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000;
__cf_bm=fmlg1wjOwuOwZhUUOEtL1tQYluAPumn7AHLF8s0EU2Y-1739217315-1.0.1.1-PQDvxn8TOhzaznlHjwVsqPZUzbAyJWFkvzCubfNJydTu2_AyA1cJ8hkM0khsEE4UY_xp8iPe2gSGmH1ydrDa0Q
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzUA7QdlQy1WZZijxNWUv25sZycg0\",\n \"object\":
\"chat.completion\",\n \"created\": 1739217315,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"```\\nThought: I now know the final answer\\nFinal
Answer: hi\\n```\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
283,\n \"completion_tokens\": 17,\n \"total_tokens\": 300,\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_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90fea7dc5ba6ceb9-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 10 Feb 2025 19:55:15 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '388'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999680'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_7d7c68b90b3a9c3ac6092fe17ac1185a
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '6534'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Mon, 10 Feb 2025 19:55:17 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n```\n\nPlease
provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
from 0 to 10 evaluating on completion, quality, and overall performance- Entities
extracted from the task output, if any, their type, description, and relationships"}],
"model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
"TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
"description": "Correctly extracted `TaskEvaluation` with all the required parameters
with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
{"description": "The name of the entity.", "title": "Name", "type": "string"},
"type": {"description": "The type of the entity.", "title": "Type", "type":
"string"}, "description": {"description": "Description of the entity.", "title":
"Description", "type": "string"}, "relationships": {"description": "Relationships
of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
"array"}}, "required": ["name", "type", "description", "relationships"], "title":
"Entity", "type": "object"}}, "properties": {"suggestions": {"description":
"Suggestions to improve future similar tasks.", "items": {"type": "string"},
"title": "Suggestions", "type": "array"}, "quality": {"description": "A score
from 0 to 10 evaluating on completion, quality, and overall performance, all
taking into account the task description, expected output, and the result of
the task.", "title": "Quality", "type": "number"}, "entities": {"description":
"Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
"title": "Entities", "type": "array"}}, "required": ["entities", "quality",
"suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1967'
content-type:
- application/json
cookie:
- _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000;
__cf_bm=fmlg1wjOwuOwZhUUOEtL1tQYluAPumn7AHLF8s0EU2Y-1739217315-1.0.1.1-PQDvxn8TOhzaznlHjwVsqPZUzbAyJWFkvzCubfNJydTu2_AyA1cJ8hkM0khsEE4UY_xp8iPe2gSGmH1ydrDa0Q
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzUA8oE0A2d99i1Khpu0CI7fSgRtZ\",\n \"object\":
\"chat.completion\",\n \"created\": 1739217316,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_bk3duHRErK1qCyvWJ1uVmmGl\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"TaskEvaluation\",\n
\ \"arguments\": \"{\\\"suggestions\\\":[\\\"Provide more context
or details for similar tasks to enhance clarity.\\\",\\\"Specify desired tone
or style for the output.\\\",\\\"Consider adding more variety in tasks to keep
engagement high.\\\"],\\\"quality\\\":10,\\\"entities\\\":[{\\\"name\\\":\\\"hi\\\",\\\"type\\\":\\\"greeting\\\",\\\"description\\\":\\\"A
casual way to say hello or acknowledge someone's presence.\\\",\\\"relationships\\\":[\\\"used
as a greeting\\\",\\\"expresses friendliness\\\"]}]}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
275,\n \"completion_tokens\": 80,\n \"total_tokens\": 355,\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_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90fea7dfef41ceb9-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 10 Feb 2025 19:55:17 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1535'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999874'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_55d8eb91b4318245556b73d3f4c1e7c4
http_version: HTTP/1.1
status_code: 200
version: 1