andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 16:18:30 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
Files
c5f0abfc9fb50d5e1a0e1bfa3c14d658fcc118a9
crewAI/lib/crewai/tests/cassettes/test_tools_with_custom_caching.yaml
Lorenze Jay d1343b96ed 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>
2025-10-20 14:10:19 -07:00

1138 lines
52 KiB
YAML
Raw Blame History

interactions:
- request:
body: !!binary |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==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '7123'
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, 24 Sep 2024 21:44:51 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Writer. You''re an
expert in writing and you love to teach kids but you know nothing of math.\nYour
personal goal is: You write lessons of math for kids.\nYou ONLY have access
to the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplcation_tool(*args: Any, **kwargs: Any) -> Any\nTool Description:
multiplcation_tool(first_number: ''integer'', second_number: ''integer'') -
Useful for when you need to multiply two numbers together. \nTool Arguments:
{''first_number'': {''title'': ''First Number'', ''type'': ''integer''}, ''second_number'':
{''title'': ''Second Number'', ''type'': ''integer''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [multiplcation_tool], just the name, exactly as it''s
written.\nAction Input: the input to the action, just a simple python dictionary,
enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n"}, {"role": "user", "content": "\nCurrent Task: What is 2 times
6? Return only the number after using the multiplication tool.\n\nThis is the
expect criteria for your final answer: the result of multiplication\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"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1632'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7cxmIoaje8EuANfQlScaRhmmAv7\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214291,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"To find the result of 2 times 6, I need
to perform a multiplication operation.\\n\\nAction: multiplcation_tool\\nAction
Input: {\\\"first_number\\\": 2, \\\"second_number\\\": 6}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 342,\n \"completion_tokens\":
42,\n \"total_tokens\": 384,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_52a7f40b0b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f547695d1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:44:52 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '611'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999605'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_d1923350f1d9dc9edf59048d19a8e10f
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Writer. You''re an
expert in writing and you love to teach kids but you know nothing of math.\nYour
personal goal is: You write lessons of math for kids.\nYou ONLY have access
to the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplcation_tool(*args: Any, **kwargs: Any) -> Any\nTool Description:
multiplcation_tool(first_number: ''integer'', second_number: ''integer'') -
Useful for when you need to multiply two numbers together. \nTool Arguments:
{''first_number'': {''title'': ''First Number'', ''type'': ''integer''}, ''second_number'':
{''title'': ''Second Number'', ''type'': ''integer''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [multiplcation_tool], just the name, exactly as it''s
written.\nAction Input: the input to the action, just a simple python dictionary,
enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n"}, {"role": "user", "content": "\nCurrent Task: What is 2 times
6? Return only the number after using the multiplication tool.\n\nThis is the
expect criteria for your final answer: the result of multiplication\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":
"To find the result of 2 times 6, I need to perform a multiplication operation.\n\nAction:
multiplcation_tool\nAction Input: {\"first_number\": 2, \"second_number\": 6}\nObservation:
12"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1854'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7cySrhEXD6EdorOPH1A40GleibV\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214292,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer\\nFinal
Answer: 12\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
392,\n \"completion_tokens\": 14,\n \"total_tokens\": 406,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_52a7f40b0b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f54db9e71cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:44:52 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '328'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999561'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_fa3ab23c940122094b656b01f335e866
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Writer. You''re an
expert in writing and you love to teach kids but you know nothing of math.\nYour
personal goal is: You write lessons of math for kids.\nYou ONLY have access
to the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplcation_tool(*args: Any, **kwargs: Any) -> Any\nTool Description:
multiplcation_tool(first_number: ''integer'', second_number: ''integer'') -
Useful for when you need to multiply two numbers together. \nTool Arguments:
{''first_number'': {''title'': ''First Number'', ''type'': ''integer''}, ''second_number'':
{''title'': ''Second Number'', ''type'': ''integer''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [multiplcation_tool], just the name, exactly as it''s
written.\nAction Input: the input to the action, just a simple python dictionary,
enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n"}, {"role": "user", "content": "\nCurrent Task: What is 3 times
1? Return only the number after using the multiplication tool.\n\nThis is the
expect criteria for your final answer: the result of multiplication\nyou MUST
return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\n12\n\nBegin! This is VERY important to
you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1680'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7czLxoxlgPDetJbvOBWuFGeM1b9\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214293,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to use the multiplication tool
to find the product of 3 and 1.\\n\\nAction: multiplcation_tool\\nAction Input:
{\\\"first_number\\\": 3, \\\"second_number\\\": 1}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 352,\n \"completion_tokens\":
41,\n \"total_tokens\": 393,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_9f2bfdaa89\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f55268051cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:44:53 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '484'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999594'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_70783c5a9d4e20b2d97fc8c11df00f13
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Writer. You''re an
expert in writing and you love to teach kids but you know nothing of math.\nYour
personal goal is: You write lessons of math for kids.\nYou ONLY have access
to the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplcation_tool(*args: Any, **kwargs: Any) -> Any\nTool Description:
multiplcation_tool(first_number: ''integer'', second_number: ''integer'') -
Useful for when you need to multiply two numbers together. \nTool Arguments:
{''first_number'': {''title'': ''First Number'', ''type'': ''integer''}, ''second_number'':
{''title'': ''Second Number'', ''type'': ''integer''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [multiplcation_tool], just the name, exactly as it''s
written.\nAction Input: the input to the action, just a simple python dictionary,
enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n"}, {"role": "user", "content": "\nCurrent Task: What is 3 times
1? Return only the number after using the multiplication tool.\n\nThis is the
expect criteria for your final answer: the result of multiplication\nyou MUST
return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\n12\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": "I need to use the multiplication
tool to find the product of 3 and 1.\n\nAction: multiplcation_tool\nAction Input:
{\"first_number\": 3, \"second_number\": 1}\nObservation: 3"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1892'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7d0xSpvf8lWUzweYo2jN6qeWLXI\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214294,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer\\nFinal
Answer: 3\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
401,\n \"completion_tokens\": 14,\n \"total_tokens\": 415,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_52a7f40b0b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f557e8741cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:44:54 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '286'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999552'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_99ba8fec9f8babaaa42d4b46bd83aaf0
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Writer. You''re an
expert in writing and you love to teach kids but you know nothing of math.\nYour
personal goal is: You write lessons of math for kids.\nYou ONLY have access
to the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplcation_tool(*args: Any, **kwargs: Any) -> Any\nTool Description:
multiplcation_tool(first_number: ''integer'', second_number: ''integer'') -
Useful for when you need to multiply two numbers together. \nTool Arguments:
{''first_number'': {''title'': ''First Number'', ''type'': ''integer''}, ''second_number'':
{''title'': ''Second Number'', ''type'': ''integer''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [multiplcation_tool], just the name, exactly as it''s
written.\nAction Input: the input to the action, just a simple python dictionary,
enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n"}, {"role": "user", "content": "\nCurrent Task: What is 2 times
6? Return only the number after using the multiplication tool.\n\nThis is the
expect criteria for your final answer: the result of multiplication\nyou MUST
return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\n3\n\nBegin! This is VERY important to
you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1679'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7d0rJFcb9wnYqP1SzHl3KX0UOai\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214294,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"To determine the result of multiplying
2 by 6, I will use the multiplication tool.\\n\\nAction: multiplcation_tool\\nAction
Input: {\\\"first_number\\\": 2, \\\"second_number\\\": 6}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 352,\n \"completion_tokens\":
42,\n \"total_tokens\": 394,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_52a7f40b0b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f55c6f231cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:44:55 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1030'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999594'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_c7d9beac850c329ca199e98fac0c0677
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Writer. You''re an
expert in writing and you love to teach kids but you know nothing of math.\nYour
personal goal is: You write lessons of math for kids.\nYou ONLY have access
to the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplcation_tool(*args: Any, **kwargs: Any) -> Any\nTool Description:
multiplcation_tool(first_number: ''integer'', second_number: ''integer'') -
Useful for when you need to multiply two numbers together. \nTool Arguments:
{''first_number'': {''title'': ''First Number'', ''type'': ''integer''}, ''second_number'':
{''title'': ''Second Number'', ''type'': ''integer''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [multiplcation_tool], just the name, exactly as it''s
written.\nAction Input: the input to the action, just a simple python dictionary,
enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n"}, {"role": "user", "content": "\nCurrent Task: What is 2 times
6? Return only the number after using the multiplication tool.\n\nThis is the
expect criteria for your final answer: the result of multiplication\nyou MUST
return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\n3\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": "To determine the result
of multiplying 2 by 6, I will use the multiplication tool.\n\nAction: multiplcation_tool\nAction
Input: {\"first_number\": 2, \"second_number\": 6}\nObservation: 12"}], "model":
"gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1905'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7d2W5DIzFz0SX9ya78G9IiyWU5f\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214296,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer\\nFinal
Answer: 12\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
402,\n \"completion_tokens\": 14,\n \"total_tokens\": 416,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_9f2bfdaa89\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f5655b201cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:44:56 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '416'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999549'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_399313564f358da692e72f05914ae587
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:
- '1616'
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, 24 Sep 2024 21:44:56 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Writer. You''re an
expert in writing and you love to teach kids but you know nothing of math.\nYour
personal goal is: You write lessons of math for kids.\nYou ONLY have access
to the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplcation_tool(*args: Any, **kwargs: Any) -> Any\nTool Description:
multiplcation_tool(first_number: ''integer'', second_number: ''integer'') -
Useful for when you need to multiply two numbers together. \nTool Arguments:
{''first_number'': {''title'': ''First Number'', ''type'': ''integer''}, ''second_number'':
{''title'': ''Second Number'', ''type'': ''integer''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [multiplcation_tool], just the name, exactly as it''s
written.\nAction Input: the input to the action, just a simple python dictionary,
enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n"}, {"role": "user", "content": "\nCurrent Task: What is 3 times
1? Return only the number after using the multiplication tool.\n\nThis is the
expect criteria for your final answer: the result of multiplication\nyou MUST
return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\n12\n\nBegin! This is VERY important to
you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1680'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7d296whjtw9JfyheZgQZKh54qG5\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214296,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to multiply 3 times 1
using the provided multiplication tool.\\n\\nAction: multiplcation_tool\\nAction
Input: {\\\"first_number\\\": 3, \\\"second_number\\\": 1}\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 352,\n \"completion_tokens\":
40,\n \"total_tokens\": 392,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_52a7f40b0b\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f56aaa6f1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:44:57 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '583'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999594'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_87c580e175461ca074f9cb1ed780f79c
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are Writer. You''re an
expert in writing and you love to teach kids but you know nothing of math.\nYour
personal goal is: You write lessons of math for kids.\nYou ONLY have access
to the following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: multiplcation_tool(*args: Any, **kwargs: Any) -> Any\nTool Description:
multiplcation_tool(first_number: ''integer'', second_number: ''integer'') -
Useful for when you need to multiply two numbers together. \nTool Arguments:
{''first_number'': {''title'': ''First Number'', ''type'': ''integer''}, ''second_number'':
{''title'': ''Second Number'', ''type'': ''integer''}}\n\nUse the following
format:\n\nThought: you should always think about what to do\nAction: the action
to take, only one name of [multiplcation_tool], just the name, exactly as it''s
written.\nAction Input: the input to the action, just a simple python dictionary,
enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n"}, {"role": "user", "content": "\nCurrent Task: What is 3 times
1? Return only the number after using the multiplication tool.\n\nThis is the
expect criteria for your final answer: the result of multiplication\nyou MUST
return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\n12\n\nBegin! This is VERY important to
you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}, {"role": "assistant", "content": "Thought: I need to multiply
3 times 1 using the provided multiplication tool.\n\nAction: multiplcation_tool\nAction
Input: {\"first_number\": 3, \"second_number\": 1}\nObservation: 3"}], "model":
"gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1900'
content-type:
- application/json
cookie:
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7d3DIRqvFoxRziBHCyxWSi9eSOG\",\n \"object\":
\"chat.completion\",\n \"created\": 1727214297,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now know the final answer\\nFinal
Answer: 3\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
400,\n \"completion_tokens\": 14,\n \"total_tokens\": 414,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_9f2bfdaa89\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85f570db341cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:44:58 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '218'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999550'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_39924da573e3a4c6fae259e14fb19341
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink