mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-05-03 16:22:49 +00:00
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
1
lib/crewai/tests/utilities/__init__.py
Normal file
1
lib/crewai/tests/utilities/__init__.py
Normal file
@@ -0,0 +1 @@
|
||||
"""Tests for utilities."""
|
||||
@@ -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
|
||||
@@ -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
@@ -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
@@ -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 |
|
||||
Cq0TCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkShBMKEgoQY3Jld2FpLnRl
|
||||
bGVtZXRyeRKkBwoQzBQBWCz+GLuI1awj3OPWrRIIGpT16t5bk6MqDENyZXcgQ3JlYXRlZDABOUBz
|
||||
OyuEGSEYQYDBSCuEGSEYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTAwLjBKGgoOcHl0aG9uX3Zl
|
||||
cnNpb24SCAoGMy4xMi44Si4KCGNyZXdfa2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhj
|
||||
NzQ2MjhjSjEKB2NyZXdfaWQSJgokMDE3NjQ5ZWMtYTBlMS00MzYxLWFlNjgtYzA1N2E3ZGM5YzI5
|
||||
ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
|
||||
X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrRAgoLY3Jl
|
||||
d19hZ2VudHMSwQIKvgJbeyJrZXkiOiAiYWQxNTMxNjFjNWM1YTg1NmFhMGQwNmIyNDljNGM2NGEi
|
||||
LCAiaWQiOiAiOGU3NzgyN2QtN2Y2OC00ZDA2LWI2YTctOWI4YjRkMGE0YzMzIiwgInJvbGUiOiAi
|
||||
YmFzZV9hZ2VudCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0i
|
||||
OiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIs
|
||||
ICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBm
|
||||
YWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/wEKCmNyZXdf
|
||||
dGFza3MS8AEK7QFbeyJrZXkiOiAiMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEzZDIiLCAi
|
||||
aWQiOiAiOTJiZDIzMWYtYzAxMC00ZDI3LWIxNGYtZjE5NjEyZTBmZTkzIiwgImFzeW5jX2V4ZWN1
|
||||
dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJiYXNl
|
||||
X2FnZW50IiwgImFnZW50X2tleSI6ICJhZDE1MzE2MWM1YzVhODU2YWEwZDA2YjI0OWM0YzY0YSIs
|
||||
ICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChC22Au0eMkAAjV6cfU1NrNIEggxb1Bq
|
||||
Xnll/ioMVGFzayBDcmVhdGVkMAE5IOJaK4QZIRhBwG5bK4QZIRhKLgoIY3Jld19rZXkSIgogZTU4
|
||||
MDcwMWQ1MmViNjVhZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiQwMTc2NDllYy1hMGUx
|
||||
LTQzNjEtYWU2OC1jMDU3YTdkYzljMjlKLgoIdGFza19rZXkSIgogMWIxNWVmMjM5MTViMjc1NWU4
|
||||
OWEwZWMzYjI2YTEzZDJKMQoHdGFza19pZBImCiQ5MmJkMjMxZi1jMDEwLTRkMjctYjE0Zi1mMTk2
|
||||
MTJlMGZlOTN6AhgBhQEAAQAAEqQHChC63jCLGR8RP8RmYiHrdNVeEggZ39ffmGm5xyoMQ3JldyBD
|
||||
cmVhdGVkMAE5GFEe04QZIRhBELEq04QZIRhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMDAuMEoa
|
||||
Cg5weXRob25fdmVyc2lvbhIICgYzLjEyLjhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmViNjVh
|
||||
ZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiQ5MTY4YmQxNC0yN2Q2LTQ3NWMtODljOC01
|
||||
NjJjOTAyMGIxOTBKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkS
|
||||
AhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMS
|
||||
AhgBStECCgtjcmV3X2FnZW50cxLBAgq+Alt7ImtleSI6ICJhZDE1MzE2MWM1YzVhODU2YWEwZDA2
|
||||
YjI0OWM0YzY0YSIsICJpZCI6ICI4ZTc3ODI3ZC03ZjY4LTRkMDYtYjZhNy05YjhiNGQwYTRjMzMi
|
||||
LCAicm9sZSI6ICJiYXNlX2FnZW50IiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIw
|
||||
LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdw
|
||||
dC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhl
|
||||
Y3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119
|
||||
XUr/AQoKY3Jld190YXNrcxLwAQrtAVt7ImtleSI6ICIxYjE1ZWYyMzkxNWIyNzU1ZTg5YTBlYzNi
|
||||
MjZhMTNkMiIsICJpZCI6ICI5MmJkMjMxZi1jMDEwLTRkMjctYjE0Zi1mMTk2MTJlMGZlOTMiLCAi
|
||||
YXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9y
|
||||
b2xlIjogImJhc2VfYWdlbnQiLCAiYWdlbnRfa2V5IjogImFkMTUzMTYxYzVjNWE4NTZhYTBkMDZi
|
||||
MjQ5YzRjNjRhIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEOo6FGs7r9hHrN+f
|
||||
qhMTUysSCJgbYV+vQMbCKgxUYXNrIENyZWF0ZWQwATlAxjrThBkhGEEYIDvThBkhGEouCghjcmV3
|
||||
X2tleRIiCiBlNTgwNzAxZDUyZWI2NWFmZjI0ZWVmZTc4Yzc0NjI4Y0oxCgdjcmV3X2lkEiYKJDkx
|
||||
NjhiZDE0LTI3ZDYtNDc1Yy04OWM4LTU2MmM5MDIwYjE5MEouCgh0YXNrX2tleRIiCiAxYjE1ZWYy
|
||||
MzkxNWIyNzU1ZTg5YTBlYzNiMjZhMTNkMkoxCgd0YXNrX2lkEiYKJDkyYmQyMzFmLWMwMTAtNGQy
|
||||
Ny1iMTRmLWYxOTYxMmUwZmU5M3oCGAGFAQABAAA=
|
||||
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
@@ -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
|
||||
@@ -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
|
||||
@@ -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
|
||||
@@ -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
@@ -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
|
||||
@@ -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
|
||||
@@ -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
|
||||
@@ -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
|
||||
@@ -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
|
||||
@@ -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
|
||||
@@ -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
|
||||
@@ -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
|
||||
@@ -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
13056
lib/crewai/tests/utilities/cassettes/test_tools_emits_error_events.yaml
Normal file
13056
lib/crewai/tests/utilities/cassettes/test_tools_emits_error_events.yaml
Normal file
File diff suppressed because it is too large
Load Diff
@@ -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 |
|
||||
CoMzCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS2jIKEgoQY3Jld2FpLnRl
|
||||
bGVtZXRyeRKOAgoQ2EINIGZRoXD589od63oHmBIIMfUgEWudUbIqDFRhc2sgQ3JlYXRlZDABOcjI
|
||||
7lbu8CIYQZB471bu8CIYSi4KCGNyZXdfa2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhj
|
||||
NzQ2MjhjSjEKB2NyZXdfaWQSJgokNTE4ODdiOTktY2FlMy00Yjc4LWJjMGEtMDY4MmVmNWEzNGQ0
|
||||
Si4KCHRhc2tfa2V5EiIKIDFiMTVlZjIzOTE1YjI3NTVlODlhMGVjM2IyNmExM2QySjEKB3Rhc2tf
|
||||
aWQSJgokMzlmMDlmMWUtOTJmOC00ZGJiLTgzNDAtNjU2ZmVkMDk3ZjM0egIYAYUBAAEAABKkBwoQ
|
||||
RzhWoF6ewSTS/qUc9yeFRhIIM3SNZCwjz5AqDENyZXcgQ3JlYXRlZDABOQjrGlru8CIYQdgbKVru
|
||||
8CIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTAwLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4x
|
||||
Mi44Si4KCGNyZXdfa2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhjNzQ2MjhjSjEKB2Ny
|
||||
ZXdfaWQSJgokYzk4ODFkY2YtMmM0MS00ZjRlLTgzMjctNjJjYjFhYjJkOTg4ShwKDGNyZXdfcHJv
|
||||
Y2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90
|
||||
YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrRAgoLY3Jld19hZ2VudHMSwQIK
|
||||
vgJbeyJrZXkiOiAiYWQxNTMxNjFjNWM1YTg1NmFhMGQwNmIyNDljNGM2NGEiLCAiaWQiOiAiNTU2
|
||||
NzJiMDgtOTU4ZC00MjljLWE3ZTctY2ZlN2U4Y2MwOGZkIiwgInJvbGUiOiAiYmFzZV9hZ2VudCIs
|
||||
ICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVu
|
||||
Y3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9u
|
||||
X2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9y
|
||||
ZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/wEKCmNyZXdfdGFza3MS8AEK7QFb
|
||||
eyJrZXkiOiAiMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEzZDIiLCAiaWQiOiAiMzlmMDlm
|
||||
MWUtOTJmOC00ZGJiLTgzNDAtNjU2ZmVkMDk3ZjM0IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxz
|
||||
ZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJiYXNlX2FnZW50IiwgImFn
|
||||
ZW50X2tleSI6ICJhZDE1MzE2MWM1YzVhODU2YWEwZDA2YjI0OWM0YzY0YSIsICJ0b29sc19uYW1l
|
||||
cyI6IFtdfV16AhgBhQEAAQAAEo4CChB8AxWkb2Uwpdc8RpyCRqw5EggJAxbgNu81XyoMVGFzayBD
|
||||
cmVhdGVkMAE5+HQ8Wu7wIhhB+PE8Wu7wIhhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmViNjVh
|
||||
ZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiRjOTg4MWRjZi0yYzQxLTRmNGUtODMyNy02
|
||||
MmNiMWFiMmQ5ODhKLgoIdGFza19rZXkSIgogMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEz
|
||||
ZDJKMQoHdGFza19pZBImCiQzOWYwOWYxZS05MmY4LTRkYmItODM0MC02NTZmZWQwOTdmMzR6AhgB
|
||||
hQEAAQAAEqQHChCcXvdbsgYC+gzCMrXs3LN/EgijKwJLCRIiHioMQ3JldyBDcmVhdGVkMAE5iJqz
|
||||
vu7wIhhBqKC/vu7wIhhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMDAuMEoaCg5weXRob25fdmVy
|
||||
c2lvbhIICgYzLjEyLjhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmViNjVhZmYyNGVlZmU3OGM3
|
||||
NDYyOGNKMQoHY3Jld19pZBImCiQ2Zjk1ZWI3Yy0wOWM5LTQxOTYtYWFiYi1kOWIxNmMxMzZjODdK
|
||||
HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
|
||||
bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBStECCgtjcmV3
|
||||
X2FnZW50cxLBAgq+Alt7ImtleSI6ICJhZDE1MzE2MWM1YzVhODU2YWEwZDA2YjI0OWM0YzY0YSIs
|
||||
ICJpZCI6ICI1NTY3MmIwOC05NThkLTQyOWMtYTdlNy1jZmU3ZThjYzA4ZmQiLCAicm9sZSI6ICJi
|
||||
YXNlX2FnZW50IiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6
|
||||
IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwg
|
||||
ImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZh
|
||||
bHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUr/AQoKY3Jld190
|
||||
YXNrcxLwAQrtAVt7ImtleSI6ICIxYjE1ZWYyMzkxNWIyNzU1ZTg5YTBlYzNiMjZhMTNkMiIsICJp
|
||||
ZCI6ICIzOWYwOWYxZS05MmY4LTRkYmItODM0MC02NTZmZWQwOTdmMzQiLCAiYXN5bmNfZXhlY3V0
|
||||
aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogImJhc2Vf
|
||||
YWdlbnQiLCAiYWdlbnRfa2V5IjogImFkMTUzMTYxYzVjNWE4NTZhYTBkMDZiMjQ5YzRjNjRhIiwg
|
||||
InRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEExDo5nPLyHb2H8DfYjPoX4SCLEYs+24
|
||||
8EenKgxUYXNrIENyZWF0ZWQwATmI4NG+7vAiGEFYZdK+7vAiGEouCghjcmV3X2tleRIiCiBlNTgw
|
||||
NzAxZDUyZWI2NWFmZjI0ZWVmZTc4Yzc0NjI4Y0oxCgdjcmV3X2lkEiYKJDZmOTVlYjdjLTA5Yzkt
|
||||
NDE5Ni1hYWJiLWQ5YjE2YzEzNmM4N0ouCgh0YXNrX2tleRIiCiAxYjE1ZWYyMzkxNWIyNzU1ZTg5
|
||||
YTBlYzNiMjZhMTNkMkoxCgd0YXNrX2lkEiYKJDM5ZjA5ZjFlLTkyZjgtNGRiYi04MzQwLTY1NmZl
|
||||
ZDA5N2YzNHoCGAGFAQABAAASpAcKEBBQzR2bcR/7woQ+VkaJ4kQSCD1LFx3SNPPPKgxDcmV3IENy
|
||||
ZWF0ZWQwATlotsW/7vAiGEEgA9C/7vAiGEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjEwMC4wShoK
|
||||
DnB5dGhvbl92ZXJzaW9uEggKBjMuMTIuOEouCghjcmV3X2tleRIiCiBlNTgwNzAxZDUyZWI2NWFm
|
||||
ZjI0ZWVmZTc4Yzc0NjI4Y0oxCgdjcmV3X2lkEiYKJDJiMWI2MGYzLTNlZTMtNGNjYi05MDM2LTdk
|
||||
MzE4OTJiYjVkZkocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRIC
|
||||
EABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxIC
|
||||
GAFK0QIKC2NyZXdfYWdlbnRzEsECCr4CW3sia2V5IjogImFkMTUzMTYxYzVjNWE4NTZhYTBkMDZi
|
||||
MjQ5YzRjNjRhIiwgImlkIjogIjU1NjcyYjA4LTk1OGQtNDI5Yy1hN2U3LWNmZTdlOGNjMDhmZCIs
|
||||
ICJyb2xlIjogImJhc2VfYWdlbnQiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjAs
|
||||
ICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0
|
||||
LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVj
|
||||
dXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1d
|
||||
Sv8BCgpjcmV3X3Rhc2tzEvABCu0BW3sia2V5IjogIjFiMTVlZjIzOTE1YjI3NTVlODlhMGVjM2Iy
|
||||
NmExM2QyIiwgImlkIjogIjM5ZjA5ZjFlLTkyZjgtNGRiYi04MzQwLTY1NmZlZDA5N2YzNCIsICJh
|
||||
c3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3Jv
|
||||
bGUiOiAiYmFzZV9hZ2VudCIsICJhZ2VudF9rZXkiOiAiYWQxNTMxNjFjNWM1YTg1NmFhMGQwNmIy
|
||||
NDljNGM2NGEiLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKOAgoQmT07KMiFRgzOOPQf
|
||||
I4bJPhIIqzN+pCYM6IUqDFRhc2sgQ3JlYXRlZDABOYjr3r/u8CIYQehY37/u8CIYSi4KCGNyZXdf
|
||||
a2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhjNzQ2MjhjSjEKB2NyZXdfaWQSJgokMmIx
|
||||
YjYwZjMtM2VlMy00Y2NiLTkwMzYtN2QzMTg5MmJiNWRmSi4KCHRhc2tfa2V5EiIKIDFiMTVlZjIz
|
||||
OTE1YjI3NTVlODlhMGVjM2IyNmExM2QySjEKB3Rhc2tfaWQSJgokMzlmMDlmMWUtOTJmOC00ZGJi
|
||||
LTgzNDAtNjU2ZmVkMDk3ZjM0egIYAYUBAAEAABKkBwoQE53vZNAWshkoNK1bqTvovRII83djkBUL
|
||||
EbcqDENyZXcgQ3JlYXRlZDABORBBzsDu8CIYQbAU2MDu8CIYShsKDmNyZXdhaV92ZXJzaW9uEgkK
|
||||
BzAuMTAwLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMi44Si4KCGNyZXdfa2V5EiIKIGU1ODA3
|
||||
MDFkNTJlYjY1YWZmMjRlZWZlNzhjNzQ2MjhjSjEKB2NyZXdfaWQSJgokNTQ0MWY0MWYtOTVjMC00
|
||||
YzdkLTkxM2QtNDUxODcwY2YyZjYzShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2Ny
|
||||
ZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJf
|
||||
b2ZfYWdlbnRzEgIYAUrRAgoLY3Jld19hZ2VudHMSwQIKvgJbeyJrZXkiOiAiYWQxNTMxNjFjNWM1
|
||||
YTg1NmFhMGQwNmIyNDljNGM2NGEiLCAiaWQiOiAiNTU2NzJiMDgtOTU4ZC00MjljLWE3ZTctY2Zl
|
||||
N2U4Y2MwOGZkIiwgInJvbGUiOiAiYmFzZV9hZ2VudCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4
|
||||
X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwg
|
||||
ImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxv
|
||||
d19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19u
|
||||
YW1lcyI6IFtdfV1K/wEKCmNyZXdfdGFza3MS8AEK7QFbeyJrZXkiOiAiMWIxNWVmMjM5MTViMjc1
|
||||
NWU4OWEwZWMzYjI2YTEzZDIiLCAiaWQiOiAiMzlmMDlmMWUtOTJmOC00ZGJiLTgzNDAtNjU2ZmVk
|
||||
MDk3ZjM0IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNl
|
||||
LCAiYWdlbnRfcm9sZSI6ICJiYXNlX2FnZW50IiwgImFnZW50X2tleSI6ICJhZDE1MzE2MWM1YzVh
|
||||
ODU2YWEwZDA2YjI0OWM0YzY0YSIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChBV
|
||||
JNEz3VIdOlQM9VT3bctVEgisogN707a2AioMVGFzayBDcmVhdGVkMAE5kGbnwO7wIhhBaMDnwO7w
|
||||
IhhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmViNjVhZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jl
|
||||
d19pZBImCiQ1NDQxZjQxZi05NWMwLTRjN2QtOTEzZC00NTE4NzBjZjJmNjNKLgoIdGFza19rZXkS
|
||||
IgogMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEzZDJKMQoHdGFza19pZBImCiQzOWYwOWYx
|
||||
ZS05MmY4LTRkYmItODM0MC02NTZmZWQwOTdmMzR6AhgBhQEAAQAAErQHChDA7zaLCfy56rd5t3oS
|
||||
rDPZEgjYoSW3mq6WJyoMQ3JldyBDcmVhdGVkMAE5cP/5we7wIhhBIH0Dwu7wIhhKGwoOY3Jld2Fp
|
||||
X3ZlcnNpb24SCQoHMC4xMDAuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjEyLjhKLgoIY3Jld19r
|
||||
ZXkSIgogZTU4MDcwMWQ1MmViNjVhZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiRmNjcz
|
||||
MTc1ZS04Y2Q1LTQ1ZWUtYTZiOS0xYWFjMTliODQxZWJKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVl
|
||||
bnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVj
|
||||
cmV3X251bWJlcl9vZl9hZ2VudHMSAhgBStkCCgtjcmV3X2FnZW50cxLJAgrGAlt7ImtleSI6ICJh
|
||||
ZDE1MzE2MWM1YzVhODU2YWEwZDA2YjI0OWM0YzY0YSIsICJpZCI6ICJmMGUwMGIzZi0wZWNmLTQ2
|
||||
OGQtYjdjMC0yZmJhN2I5OTc5YjMiLCAicm9sZSI6ICJiYXNlX2FnZW50IiwgInZlcmJvc2U/Ijog
|
||||
ZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5n
|
||||
X2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBm
|
||||
YWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0Ijog
|
||||
MiwgInRvb2xzX25hbWVzIjogWyJzYXlfaGkiXX1dSocCCgpjcmV3X3Rhc2tzEvgBCvUBW3sia2V5
|
||||
IjogIjFiMTVlZjIzOTE1YjI3NTVlODlhMGVjM2IyNmExM2QyIiwgImlkIjogImFhMGFmMmE2LTdm
|
||||
MTktNDZmNi1iMjMxLTg1M2JjYzYxYzhiZiIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJo
|
||||
dW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiYmFzZV9hZ2VudCIsICJhZ2VudF9r
|
||||
ZXkiOiAiYWQxNTMxNjFjNWM1YTg1NmFhMGQwNmIyNDljNGM2NGEiLCAidG9vbHNfbmFtZXMiOiBb
|
||||
InNheV9oaSJdfV16AhgBhQEAAQAAEo4CChBH8NUZY1Cv8sM2lfQLaEogEgiFlW7Wp7QpdyoMVGFz
|
||||
ayBDcmVhdGVkMAE5MNkPwu7wIhhBUCcQwu7wIhhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmVi
|
||||
NjVhZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiRmNjczMTc1ZS04Y2Q1LTQ1ZWUtYTZi
|
||||
OS0xYWFjMTliODQxZWJKLgoIdGFza19rZXkSIgogMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2
|
||||
YTEzZDJKMQoHdGFza19pZBImCiRhYTBhZjJhNi03ZjE5LTQ2ZjYtYjIzMS04NTNiY2M2MWM4YmZ6
|
||||
AhgBhQEAAQAAEooBChCJg/wSACw+HIDy4vvYISP/EgjoC/oI/1V0cCoKVG9vbCBVc2FnZTABOWA0
|
||||
ifTu8CIYQTD0lPTu8CIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTAwLjBKFQoJdG9vbF9uYW1l
|
||||
EggKBnNheV9oaUoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
|
||||
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
|
||||
0
lib/crewai/tests/utilities/crew/__init__.py
Normal file
0
lib/crewai/tests/utilities/crew/__init__.py
Normal file
87
lib/crewai/tests/utilities/crew/test_crew_context.py
Normal file
87
lib/crewai/tests/utilities/crew/test_crew_context.py
Normal file
@@ -0,0 +1,87 @@
|
||||
import uuid
|
||||
|
||||
import pytest
|
||||
from crewai.utilities.crew.crew_context import get_crew_context
|
||||
from crewai.utilities.crew.models import CrewContext
|
||||
from opentelemetry import baggage
|
||||
from opentelemetry.context import attach, detach
|
||||
|
||||
|
||||
def test_crew_context_creation():
|
||||
crew_id = str(uuid.uuid4())
|
||||
context = CrewContext(id=crew_id, key="test-crew")
|
||||
assert context.id == crew_id
|
||||
assert context.key == "test-crew"
|
||||
|
||||
|
||||
def test_get_crew_context_with_baggage():
|
||||
crew_id = str(uuid.uuid4())
|
||||
assert get_crew_context() is None
|
||||
|
||||
crew_ctx = CrewContext(id=crew_id, key="test-key")
|
||||
ctx = baggage.set_baggage("crew_context", crew_ctx)
|
||||
token = attach(ctx)
|
||||
|
||||
try:
|
||||
context = get_crew_context()
|
||||
assert context is not None
|
||||
assert context.id == crew_id
|
||||
assert context.key == "test-key"
|
||||
finally:
|
||||
detach(token)
|
||||
|
||||
assert get_crew_context() is None
|
||||
|
||||
|
||||
def test_get_crew_context_empty():
|
||||
assert get_crew_context() is None
|
||||
|
||||
|
||||
def test_baggage_nested_contexts():
|
||||
crew_id1 = str(uuid.uuid4())
|
||||
crew_id2 = str(uuid.uuid4())
|
||||
|
||||
crew_ctx1 = CrewContext(id=crew_id1, key="outer")
|
||||
ctx1 = baggage.set_baggage("crew_context", crew_ctx1)
|
||||
token1 = attach(ctx1)
|
||||
|
||||
try:
|
||||
outer_context = get_crew_context()
|
||||
assert outer_context.id == crew_id1
|
||||
assert outer_context.key == "outer"
|
||||
|
||||
crew_ctx2 = CrewContext(id=crew_id2, key="inner")
|
||||
ctx2 = baggage.set_baggage("crew_context", crew_ctx2)
|
||||
token2 = attach(ctx2)
|
||||
|
||||
try:
|
||||
inner_context = get_crew_context()
|
||||
assert inner_context.id == crew_id2
|
||||
assert inner_context.key == "inner"
|
||||
finally:
|
||||
detach(token2)
|
||||
|
||||
restored_context = get_crew_context()
|
||||
assert restored_context.id == crew_id1
|
||||
assert restored_context.key == "outer"
|
||||
finally:
|
||||
detach(token1)
|
||||
|
||||
assert get_crew_context() is None
|
||||
|
||||
|
||||
def test_baggage_exception_handling():
|
||||
crew_id = str(uuid.uuid4())
|
||||
|
||||
crew_ctx = CrewContext(id=crew_id, key="test")
|
||||
ctx = baggage.set_baggage("crew_context", crew_ctx)
|
||||
token = attach(ctx)
|
||||
|
||||
with pytest.raises(ValueError):
|
||||
try:
|
||||
assert get_crew_context() is not None
|
||||
raise ValueError("Test exception")
|
||||
finally:
|
||||
detach(token)
|
||||
|
||||
assert get_crew_context() is None
|
||||
1
lib/crewai/tests/utilities/evaluators/__init__.py
Normal file
1
lib/crewai/tests/utilities/evaluators/__init__.py
Normal file
@@ -0,0 +1 @@
|
||||
"""Tests for evaluators."""
|
||||
@@ -0,0 +1,141 @@
|
||||
from unittest import mock
|
||||
|
||||
import pytest
|
||||
from crewai.agent import Agent
|
||||
from crewai.crew import Crew
|
||||
from crewai.task import Task
|
||||
from crewai.tasks.task_output import TaskOutput
|
||||
from crewai.utilities.evaluators.crew_evaluator_handler import (
|
||||
CrewEvaluator,
|
||||
TaskEvaluationPydanticOutput,
|
||||
)
|
||||
|
||||
|
||||
class InternalCrewEvaluator:
|
||||
@pytest.fixture
|
||||
def crew_planner(self):
|
||||
agent = Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1")
|
||||
task = Task(
|
||||
description="Task 1",
|
||||
expected_output="Output 1",
|
||||
agent=agent,
|
||||
)
|
||||
crew = Crew(agents=[agent], tasks=[task])
|
||||
|
||||
return CrewEvaluator(crew, openai_model_name="gpt-4o-mini")
|
||||
|
||||
def test_setup_for_evaluating(self, crew_planner):
|
||||
crew_planner._setup_for_evaluating()
|
||||
assert crew_planner.crew.tasks[0].callback == crew_planner.evaluate
|
||||
|
||||
def test_set_iteration(self, crew_planner):
|
||||
crew_planner.set_iteration(1)
|
||||
assert crew_planner.iteration == 1
|
||||
|
||||
def test_evaluator_agent(self, crew_planner):
|
||||
agent = crew_planner._evaluator_agent()
|
||||
assert agent.role == "Task Execution Evaluator"
|
||||
assert (
|
||||
agent.goal
|
||||
== "Your goal is to evaluate the performance of the agents in the crew based on the tasks they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance."
|
||||
)
|
||||
assert (
|
||||
agent.backstory
|
||||
== "Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed"
|
||||
)
|
||||
assert agent.verbose is False
|
||||
assert agent.llm.model == "gpt-4o-mini"
|
||||
|
||||
def test_evaluation_task(self, crew_planner):
|
||||
evaluator_agent = Agent(
|
||||
role="Evaluator Agent",
|
||||
goal="Evaluate the performance of the agents in the crew",
|
||||
backstory="Master in Evaluation",
|
||||
)
|
||||
task_to_evaluate = Task(
|
||||
description="Task 1",
|
||||
expected_output="Output 1",
|
||||
agent=Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1"),
|
||||
)
|
||||
task_output = "Task Output 1"
|
||||
task = crew_planner._evaluation_task(
|
||||
evaluator_agent, task_to_evaluate, task_output
|
||||
)
|
||||
|
||||
assert task.description.startswith(
|
||||
"Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance."
|
||||
)
|
||||
|
||||
assert task.agent == evaluator_agent
|
||||
assert (
|
||||
task.description
|
||||
== "Based on the task description and the expected output, compare and evaluate "
|
||||
"the performance of the agents in the crew based on the Task Output they have "
|
||||
"performed using score from 1 to 10 evaluating on completion, quality, and overall "
|
||||
"performance.task_description: Task 1 task_expected_output: Output 1 "
|
||||
"agent: Agent 1 agent_goal: Goal 1 Task Output: Task Output 1"
|
||||
)
|
||||
|
||||
@mock.patch("crewai.utilities.evaluators.crew_evaluator_handler.Console")
|
||||
@mock.patch("crewai.utilities.evaluators.crew_evaluator_handler.Table")
|
||||
def test_print_crew_evaluation_result(self, table, console, crew_planner):
|
||||
# Set up task scores and execution times
|
||||
crew_planner.tasks_scores = {
|
||||
1: [10, 9, 8],
|
||||
2: [9, 8, 7],
|
||||
}
|
||||
crew_planner.run_execution_times = {
|
||||
1: [24, 45, 66],
|
||||
2: [55, 33, 67],
|
||||
}
|
||||
|
||||
# Mock agents and assign them to tasks
|
||||
crew_planner.crew.agents = [
|
||||
mock.Mock(role="Agent 1"),
|
||||
mock.Mock(role="Agent 2"),
|
||||
]
|
||||
crew_planner.crew.tasks = [
|
||||
mock.Mock(
|
||||
agent=crew_planner.crew.agents[0], processed_by_agents=["Agent 1"]
|
||||
),
|
||||
mock.Mock(
|
||||
agent=crew_planner.crew.agents[1], processed_by_agents=["Agent 2"]
|
||||
),
|
||||
]
|
||||
|
||||
# Run the method
|
||||
crew_planner.print_crew_evaluation_result()
|
||||
|
||||
# Verify that the table is created with the appropriate structure and rows
|
||||
table.assert_has_calls(
|
||||
[
|
||||
mock.call(
|
||||
title="Tasks Scores \n (1-10 Higher is better)", box=mock.ANY
|
||||
), # Title and styling
|
||||
mock.call().add_column("Tasks/Crew/Agents", style="cyan"), # Columns
|
||||
mock.call().add_column("Run 1", justify="center"),
|
||||
mock.call().add_column("Run 2", justify="center"),
|
||||
mock.call().add_column("Avg. Total", justify="center"),
|
||||
mock.call().add_column("Agents", style="green"),
|
||||
# Verify rows for tasks with agents
|
||||
mock.call().add_row("Task 1", "10.0", "9.0", "9.5", "- Agent 1"),
|
||||
mock.call().add_row("", "", "", "", "", ""), # Blank row between tasks
|
||||
mock.call().add_row("Task 2", "9.0", "8.0", "8.5", "- Agent 2"),
|
||||
# Add crew averages and execution times
|
||||
mock.call().add_row("Crew", "9.00", "8.00", "8.5", ""),
|
||||
mock.call().add_row("Execution Time (s)", "135", "155", "145", ""),
|
||||
]
|
||||
)
|
||||
|
||||
# Ensure the console prints the table
|
||||
console.assert_has_calls([mock.call(), mock.call().print(table())])
|
||||
|
||||
def test_evaluate(self, crew_planner):
|
||||
task_output = TaskOutput(
|
||||
description="Task 1", agent=str(crew_planner.crew.agents[0])
|
||||
)
|
||||
|
||||
with mock.patch.object(Task, "execute_sync") as execute:
|
||||
execute().pydantic = TaskEvaluationPydanticOutput(quality=9.5)
|
||||
crew_planner.evaluate(task_output)
|
||||
assert crew_planner.tasks_scores[0] == [9.5]
|
||||
105
lib/crewai/tests/utilities/evaluators/test_task_evaluator.py
Normal file
105
lib/crewai/tests/utilities/evaluators/test_task_evaluator.py
Normal file
@@ -0,0 +1,105 @@
|
||||
from unittest import mock
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
from crewai.utilities.converter import ConverterError
|
||||
from crewai.utilities.evaluators.task_evaluator import (
|
||||
TaskEvaluator,
|
||||
TrainingTaskEvaluation,
|
||||
)
|
||||
|
||||
|
||||
@patch("crewai.utilities.evaluators.task_evaluator.TrainingConverter")
|
||||
def test_evaluate_training_data(converter_mock):
|
||||
training_data = {
|
||||
"agent_id": {
|
||||
"data1": {
|
||||
"initial_output": "Initial output 1",
|
||||
"human_feedback": "Human feedback 1",
|
||||
"improved_output": "Improved output 1",
|
||||
},
|
||||
"data2": {
|
||||
"initial_output": "Initial output 2",
|
||||
"human_feedback": "Human feedback 2",
|
||||
"improved_output": "Improved output 2",
|
||||
},
|
||||
}
|
||||
}
|
||||
agent_id = "agent_id"
|
||||
original_agent = MagicMock()
|
||||
original_agent.llm.supports_function_calling.return_value = False
|
||||
function_return_value = TrainingTaskEvaluation(
|
||||
suggestions=[
|
||||
"The initial output was already good, having a detailed explanation. However, the improved output "
|
||||
"gave similar information but in a more professional manner using better vocabulary. For future tasks, "
|
||||
"try to implement more elaborate language and precise terminology from the beginning."
|
||||
],
|
||||
quality=8.0,
|
||||
final_summary="The agent responded well initially. However, the improved output showed that there is room "
|
||||
"for enhancement in terms of language usage, precision, and professionalism. For future tasks, the agent "
|
||||
"should focus more on these points from the start to increase performance.",
|
||||
)
|
||||
converter_mock.return_value.to_pydantic.return_value = function_return_value
|
||||
result = TaskEvaluator(original_agent=original_agent).evaluate_training_data(
|
||||
training_data, agent_id
|
||||
)
|
||||
|
||||
assert result == function_return_value
|
||||
converter_mock.assert_has_calls(
|
||||
[
|
||||
mock.call(
|
||||
llm=original_agent.llm,
|
||||
text="Assess the quality of the training data based on the llm output, human feedback , and llm "
|
||||
"output improved result.\n\nIteration: data1\nInitial Output:\nInitial output 1\n\nHuman Feedback:\nHuman feedback "
|
||||
"1\n\nImproved Output:\nImproved output 1\n\n------------------------------------------------\n\nIteration: data2\nInitial Output:\nInitial output 2\n\nHuman "
|
||||
"Feedback:\nHuman feedback 2\n\nImproved Output:\nImproved output 2\n\n------------------------------------------------\n\nPlease provide:\n- Provide "
|
||||
"a list of clear, actionable instructions derived from the Human Feedbacks to enhance the Agent's "
|
||||
"performance. Analyze the differences between Initial Outputs and Improved Outputs to generate specific "
|
||||
"action items for future tasks. Ensure all key and specificpoints from the human feedback are "
|
||||
"incorporated into these instructions.\n- A score from 0 to 10 evaluating on completion, quality, and "
|
||||
"overall performance from the improved output to the initial output based on the human feedback\n",
|
||||
model=TrainingTaskEvaluation,
|
||||
instructions="I'm gonna convert this raw text into valid JSON.\n\nThe json should have the "
|
||||
"following structure, with the following keys:\n{\n suggestions: List[str],\n quality: float,\n final_summary: str\n}",
|
||||
),
|
||||
mock.call().to_pydantic(),
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
@patch("crewai.utilities.converter.Converter.to_pydantic")
|
||||
@patch("crewai.utilities.training_converter.TrainingConverter._convert_field_by_field")
|
||||
def test_training_converter_fallback_mechanism(
|
||||
convert_field_by_field_mock, to_pydantic_mock
|
||||
):
|
||||
training_data = {
|
||||
"agent_id": {
|
||||
"data1": {
|
||||
"initial_output": "Initial output 1",
|
||||
"human_feedback": "Human feedback 1",
|
||||
"improved_output": "Improved output 1",
|
||||
},
|
||||
"data2": {
|
||||
"initial_output": "Initial output 2",
|
||||
"human_feedback": "Human feedback 2",
|
||||
"improved_output": "Improved output 2",
|
||||
},
|
||||
}
|
||||
}
|
||||
agent_id = "agent_id"
|
||||
to_pydantic_mock.side_effect = ConverterError("Failed to convert directly")
|
||||
|
||||
expected_result = TrainingTaskEvaluation(
|
||||
suggestions=["Fallback suggestion"],
|
||||
quality=6.5,
|
||||
final_summary="Fallback summary",
|
||||
)
|
||||
convert_field_by_field_mock.return_value = expected_result
|
||||
|
||||
original_agent = MagicMock()
|
||||
result = TaskEvaluator(original_agent=original_agent).evaluate_training_data(
|
||||
training_data, agent_id
|
||||
)
|
||||
|
||||
assert result == expected_result
|
||||
to_pydantic_mock.assert_called_once()
|
||||
convert_field_by_field_mock.assert_called_once()
|
||||
1
lib/crewai/tests/utilities/events/__init__.py
Normal file
1
lib/crewai/tests/utilities/events/__init__.py
Normal file
@@ -0,0 +1 @@
|
||||
"""Tests for events."""
|
||||
206
lib/crewai/tests/utilities/events/test_async_event_bus.py
Normal file
206
lib/crewai/tests/utilities/events/test_async_event_bus.py
Normal file
@@ -0,0 +1,206 @@
|
||||
"""Tests for async event handling in CrewAI event bus.
|
||||
|
||||
This module tests async handler registration, execution, and the aemit method.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
|
||||
import pytest
|
||||
|
||||
from crewai.events.base_events import BaseEvent
|
||||
from crewai.events.event_bus import crewai_event_bus
|
||||
|
||||
|
||||
class AsyncTestEvent(BaseEvent):
|
||||
pass
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_async_handler_execution():
|
||||
received_events = []
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
|
||||
@crewai_event_bus.on(AsyncTestEvent)
|
||||
async def async_handler(source: object, event: BaseEvent) -> None:
|
||||
await asyncio.sleep(0.01)
|
||||
received_events.append(event)
|
||||
|
||||
event = AsyncTestEvent(type="async_test")
|
||||
crewai_event_bus.emit("test_source", event)
|
||||
|
||||
await asyncio.sleep(0.1)
|
||||
|
||||
assert len(received_events) == 1
|
||||
assert received_events[0] == event
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_aemit_with_async_handlers():
|
||||
received_events = []
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
|
||||
@crewai_event_bus.on(AsyncTestEvent)
|
||||
async def async_handler(source: object, event: BaseEvent) -> None:
|
||||
await asyncio.sleep(0.01)
|
||||
received_events.append(event)
|
||||
|
||||
event = AsyncTestEvent(type="async_test")
|
||||
await crewai_event_bus.aemit("test_source", event)
|
||||
|
||||
assert len(received_events) == 1
|
||||
assert received_events[0] == event
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_multiple_async_handlers():
|
||||
received_events_1 = []
|
||||
received_events_2 = []
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
|
||||
@crewai_event_bus.on(AsyncTestEvent)
|
||||
async def handler_1(source: object, event: BaseEvent) -> None:
|
||||
await asyncio.sleep(0.01)
|
||||
received_events_1.append(event)
|
||||
|
||||
@crewai_event_bus.on(AsyncTestEvent)
|
||||
async def handler_2(source: object, event: BaseEvent) -> None:
|
||||
await asyncio.sleep(0.02)
|
||||
received_events_2.append(event)
|
||||
|
||||
event = AsyncTestEvent(type="async_test")
|
||||
await crewai_event_bus.aemit("test_source", event)
|
||||
|
||||
assert len(received_events_1) == 1
|
||||
assert len(received_events_2) == 1
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_mixed_sync_and_async_handlers():
|
||||
sync_events = []
|
||||
async_events = []
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
|
||||
@crewai_event_bus.on(AsyncTestEvent)
|
||||
def sync_handler(source: object, event: BaseEvent) -> None:
|
||||
sync_events.append(event)
|
||||
|
||||
@crewai_event_bus.on(AsyncTestEvent)
|
||||
async def async_handler(source: object, event: BaseEvent) -> None:
|
||||
await asyncio.sleep(0.01)
|
||||
async_events.append(event)
|
||||
|
||||
event = AsyncTestEvent(type="mixed_test")
|
||||
crewai_event_bus.emit("test_source", event)
|
||||
|
||||
await asyncio.sleep(0.1)
|
||||
|
||||
assert len(sync_events) == 1
|
||||
assert len(async_events) == 1
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_async_handler_error_handling():
|
||||
successful_handler_called = []
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
|
||||
@crewai_event_bus.on(AsyncTestEvent)
|
||||
async def failing_handler(source: object, event: BaseEvent) -> None:
|
||||
raise ValueError("Async handler error")
|
||||
|
||||
@crewai_event_bus.on(AsyncTestEvent)
|
||||
async def successful_handler(source: object, event: BaseEvent) -> None:
|
||||
await asyncio.sleep(0.01)
|
||||
successful_handler_called.append(True)
|
||||
|
||||
event = AsyncTestEvent(type="error_test")
|
||||
await crewai_event_bus.aemit("test_source", event)
|
||||
|
||||
assert len(successful_handler_called) == 1
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_aemit_with_no_handlers():
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
event = AsyncTestEvent(type="no_handlers")
|
||||
await crewai_event_bus.aemit("test_source", event)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_async_handler_registration_via_register_handler():
|
||||
received_events = []
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
|
||||
async def custom_async_handler(source: object, event: BaseEvent) -> None:
|
||||
await asyncio.sleep(0.01)
|
||||
received_events.append(event)
|
||||
|
||||
crewai_event_bus.register_handler(AsyncTestEvent, custom_async_handler)
|
||||
|
||||
event = AsyncTestEvent(type="register_test")
|
||||
await crewai_event_bus.aemit("test_source", event)
|
||||
|
||||
assert len(received_events) == 1
|
||||
assert received_events[0] == event
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_emit_async_handlers_fire_and_forget():
|
||||
received_events = []
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
|
||||
@crewai_event_bus.on(AsyncTestEvent)
|
||||
async def slow_async_handler(source: object, event: BaseEvent) -> None:
|
||||
await asyncio.sleep(0.05)
|
||||
received_events.append(event)
|
||||
|
||||
event = AsyncTestEvent(type="fire_forget_test")
|
||||
crewai_event_bus.emit("test_source", event)
|
||||
|
||||
assert len(received_events) == 0
|
||||
|
||||
await asyncio.sleep(0.1)
|
||||
|
||||
assert len(received_events) == 1
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_scoped_handlers_with_async():
|
||||
received_before = []
|
||||
received_during = []
|
||||
received_after = []
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
|
||||
@crewai_event_bus.on(AsyncTestEvent)
|
||||
async def before_handler(source: object, event: BaseEvent) -> None:
|
||||
received_before.append(event)
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
|
||||
@crewai_event_bus.on(AsyncTestEvent)
|
||||
async def scoped_handler(source: object, event: BaseEvent) -> None:
|
||||
received_during.append(event)
|
||||
|
||||
event1 = AsyncTestEvent(type="during_scope")
|
||||
await crewai_event_bus.aemit("test_source", event1)
|
||||
|
||||
assert len(received_before) == 0
|
||||
assert len(received_during) == 1
|
||||
|
||||
@crewai_event_bus.on(AsyncTestEvent)
|
||||
async def after_handler(source: object, event: BaseEvent) -> None:
|
||||
received_after.append(event)
|
||||
|
||||
event2 = AsyncTestEvent(type="after_scope")
|
||||
await crewai_event_bus.aemit("test_source", event2)
|
||||
|
||||
assert len(received_before) == 1
|
||||
assert len(received_during) == 1
|
||||
assert len(received_after) == 1
|
||||
63
lib/crewai/tests/utilities/events/test_crewai_event_bus.py
Normal file
63
lib/crewai/tests/utilities/events/test_crewai_event_bus.py
Normal file
@@ -0,0 +1,63 @@
|
||||
import threading
|
||||
from unittest.mock import Mock
|
||||
|
||||
from crewai.events.base_events import BaseEvent
|
||||
from crewai.events.event_bus import crewai_event_bus
|
||||
|
||||
|
||||
class TestEvent(BaseEvent):
|
||||
pass
|
||||
|
||||
|
||||
def test_specific_event_handler():
|
||||
mock_handler = Mock()
|
||||
|
||||
@crewai_event_bus.on(TestEvent)
|
||||
def handler(source, event):
|
||||
mock_handler(source, event)
|
||||
|
||||
event = TestEvent(type="test_event")
|
||||
crewai_event_bus.emit("source_object", event)
|
||||
|
||||
mock_handler.assert_called_once_with("source_object", event)
|
||||
|
||||
|
||||
def test_multiple_handlers_same_event():
|
||||
"""Test that multiple handlers can be registered for the same event type."""
|
||||
mock_handler1 = Mock()
|
||||
mock_handler2 = Mock()
|
||||
|
||||
@crewai_event_bus.on(TestEvent)
|
||||
def handler1(source, event):
|
||||
mock_handler1(source, event)
|
||||
|
||||
@crewai_event_bus.on(TestEvent)
|
||||
def handler2(source, event):
|
||||
mock_handler2(source, event)
|
||||
|
||||
event = TestEvent(type="test_event")
|
||||
crewai_event_bus.emit("source_object", event)
|
||||
|
||||
mock_handler1.assert_called_once_with("source_object", event)
|
||||
mock_handler2.assert_called_once_with("source_object", event)
|
||||
|
||||
|
||||
def test_event_bus_error_handling():
|
||||
"""Test that handler exceptions are caught and don't break the event bus."""
|
||||
called = threading.Event()
|
||||
error_caught = threading.Event()
|
||||
|
||||
@crewai_event_bus.on(TestEvent)
|
||||
def broken_handler(source, event):
|
||||
called.set()
|
||||
raise ValueError("Simulated handler failure")
|
||||
|
||||
@crewai_event_bus.on(TestEvent)
|
||||
def working_handler(source, event):
|
||||
error_caught.set()
|
||||
|
||||
event = TestEvent(type="test_event")
|
||||
crewai_event_bus.emit("source_object", event)
|
||||
|
||||
assert called.wait(timeout=2), "Broken handler was never called"
|
||||
assert error_caught.wait(timeout=2), "Working handler was never called after error"
|
||||
264
lib/crewai/tests/utilities/events/test_rw_lock.py
Normal file
264
lib/crewai/tests/utilities/events/test_rw_lock.py
Normal file
@@ -0,0 +1,264 @@
|
||||
"""Tests for read-write lock implementation.
|
||||
|
||||
This module tests the RWLock class for correct concurrent read and write behavior.
|
||||
"""
|
||||
|
||||
import threading
|
||||
import time
|
||||
|
||||
from crewai.utilities.rw_lock import RWLock
|
||||
|
||||
|
||||
def test_multiple_readers_concurrent():
|
||||
lock = RWLock()
|
||||
active_readers = [0]
|
||||
max_concurrent_readers = [0]
|
||||
lock_for_counters = threading.Lock()
|
||||
|
||||
def reader(reader_id: int) -> None:
|
||||
with lock.r_locked():
|
||||
with lock_for_counters:
|
||||
active_readers[0] += 1
|
||||
max_concurrent_readers[0] = max(
|
||||
max_concurrent_readers[0], active_readers[0]
|
||||
)
|
||||
|
||||
time.sleep(0.1)
|
||||
|
||||
with lock_for_counters:
|
||||
active_readers[0] -= 1
|
||||
|
||||
threads = [threading.Thread(target=reader, args=(i,)) for i in range(5)]
|
||||
|
||||
for thread in threads:
|
||||
thread.start()
|
||||
|
||||
for thread in threads:
|
||||
thread.join()
|
||||
|
||||
assert max_concurrent_readers[0] == 5
|
||||
|
||||
|
||||
def test_writer_blocks_readers():
|
||||
lock = RWLock()
|
||||
writer_holding_lock = [False]
|
||||
reader_accessed_during_write = [False]
|
||||
|
||||
def writer() -> None:
|
||||
with lock.w_locked():
|
||||
writer_holding_lock[0] = True
|
||||
time.sleep(0.2)
|
||||
writer_holding_lock[0] = False
|
||||
|
||||
def reader() -> None:
|
||||
time.sleep(0.05)
|
||||
with lock.r_locked():
|
||||
if writer_holding_lock[0]:
|
||||
reader_accessed_during_write[0] = True
|
||||
|
||||
writer_thread = threading.Thread(target=writer)
|
||||
reader_thread = threading.Thread(target=reader)
|
||||
|
||||
writer_thread.start()
|
||||
reader_thread.start()
|
||||
|
||||
writer_thread.join()
|
||||
reader_thread.join()
|
||||
|
||||
assert not reader_accessed_during_write[0]
|
||||
|
||||
|
||||
def test_writer_blocks_other_writers():
|
||||
lock = RWLock()
|
||||
execution_order: list[int] = []
|
||||
lock_for_order = threading.Lock()
|
||||
|
||||
def writer(writer_id: int) -> None:
|
||||
with lock.w_locked():
|
||||
with lock_for_order:
|
||||
execution_order.append(writer_id)
|
||||
time.sleep(0.1)
|
||||
|
||||
threads = [threading.Thread(target=writer, args=(i,)) for i in range(3)]
|
||||
|
||||
for thread in threads:
|
||||
thread.start()
|
||||
|
||||
for thread in threads:
|
||||
thread.join()
|
||||
|
||||
assert len(execution_order) == 3
|
||||
assert len(set(execution_order)) == 3
|
||||
|
||||
|
||||
def test_readers_block_writers():
|
||||
lock = RWLock()
|
||||
reader_count = [0]
|
||||
writer_accessed_during_read = [False]
|
||||
lock_for_counters = threading.Lock()
|
||||
|
||||
def reader() -> None:
|
||||
with lock.r_locked():
|
||||
with lock_for_counters:
|
||||
reader_count[0] += 1
|
||||
time.sleep(0.2)
|
||||
with lock_for_counters:
|
||||
reader_count[0] -= 1
|
||||
|
||||
def writer() -> None:
|
||||
time.sleep(0.05)
|
||||
with lock.w_locked():
|
||||
with lock_for_counters:
|
||||
if reader_count[0] > 0:
|
||||
writer_accessed_during_read[0] = True
|
||||
|
||||
reader_thread = threading.Thread(target=reader)
|
||||
writer_thread = threading.Thread(target=writer)
|
||||
|
||||
reader_thread.start()
|
||||
writer_thread.start()
|
||||
|
||||
reader_thread.join()
|
||||
writer_thread.join()
|
||||
|
||||
assert not writer_accessed_during_read[0]
|
||||
|
||||
|
||||
def test_alternating_readers_and_writers():
|
||||
lock = RWLock()
|
||||
operations: list[str] = []
|
||||
lock_for_operations = threading.Lock()
|
||||
|
||||
def reader(reader_id: int) -> None:
|
||||
with lock.r_locked():
|
||||
with lock_for_operations:
|
||||
operations.append(f"r{reader_id}_start")
|
||||
time.sleep(0.05)
|
||||
with lock_for_operations:
|
||||
operations.append(f"r{reader_id}_end")
|
||||
|
||||
def writer(writer_id: int) -> None:
|
||||
with lock.w_locked():
|
||||
with lock_for_operations:
|
||||
operations.append(f"w{writer_id}_start")
|
||||
time.sleep(0.05)
|
||||
with lock_for_operations:
|
||||
operations.append(f"w{writer_id}_end")
|
||||
|
||||
threads = [
|
||||
threading.Thread(target=reader, args=(0,)),
|
||||
threading.Thread(target=writer, args=(0,)),
|
||||
threading.Thread(target=reader, args=(1,)),
|
||||
threading.Thread(target=writer, args=(1,)),
|
||||
threading.Thread(target=reader, args=(2,)),
|
||||
]
|
||||
|
||||
for thread in threads:
|
||||
thread.start()
|
||||
|
||||
for thread in threads:
|
||||
thread.join()
|
||||
|
||||
assert len(operations) == 10
|
||||
|
||||
start_ops = [op for op in operations if "_start" in op]
|
||||
end_ops = [op for op in operations if "_end" in op]
|
||||
assert len(start_ops) == 5
|
||||
assert len(end_ops) == 5
|
||||
|
||||
|
||||
def test_context_manager_releases_on_exception():
|
||||
lock = RWLock()
|
||||
exception_raised = False
|
||||
|
||||
try:
|
||||
with lock.r_locked():
|
||||
raise ValueError("Test exception")
|
||||
except ValueError:
|
||||
exception_raised = True
|
||||
|
||||
assert exception_raised
|
||||
|
||||
acquired = False
|
||||
with lock.w_locked():
|
||||
acquired = True
|
||||
|
||||
assert acquired
|
||||
|
||||
|
||||
def test_write_lock_releases_on_exception():
|
||||
lock = RWLock()
|
||||
exception_raised = False
|
||||
|
||||
try:
|
||||
with lock.w_locked():
|
||||
raise ValueError("Test exception")
|
||||
except ValueError:
|
||||
exception_raised = True
|
||||
|
||||
assert exception_raised
|
||||
|
||||
acquired = False
|
||||
with lock.r_locked():
|
||||
acquired = True
|
||||
|
||||
assert acquired
|
||||
|
||||
|
||||
def test_stress_many_readers_few_writers():
|
||||
lock = RWLock()
|
||||
read_count = [0]
|
||||
write_count = [0]
|
||||
lock_for_counters = threading.Lock()
|
||||
|
||||
def reader() -> None:
|
||||
for _ in range(10):
|
||||
with lock.r_locked():
|
||||
with lock_for_counters:
|
||||
read_count[0] += 1
|
||||
time.sleep(0.001)
|
||||
|
||||
def writer() -> None:
|
||||
for _ in range(5):
|
||||
with lock.w_locked():
|
||||
with lock_for_counters:
|
||||
write_count[0] += 1
|
||||
time.sleep(0.01)
|
||||
|
||||
reader_threads = [threading.Thread(target=reader) for _ in range(10)]
|
||||
writer_threads = [threading.Thread(target=writer) for _ in range(2)]
|
||||
|
||||
all_threads = reader_threads + writer_threads
|
||||
|
||||
for thread in all_threads:
|
||||
thread.start()
|
||||
|
||||
for thread in all_threads:
|
||||
thread.join()
|
||||
|
||||
assert read_count[0] == 100
|
||||
assert write_count[0] == 10
|
||||
|
||||
|
||||
def test_nested_read_locks_same_thread():
|
||||
lock = RWLock()
|
||||
nested_acquired = False
|
||||
|
||||
with lock.r_locked():
|
||||
with lock.r_locked():
|
||||
nested_acquired = True
|
||||
|
||||
assert nested_acquired
|
||||
|
||||
|
||||
def test_manual_acquire_release():
|
||||
lock = RWLock()
|
||||
|
||||
lock.r_acquire()
|
||||
lock.r_release()
|
||||
|
||||
lock.w_acquire()
|
||||
lock.w_release()
|
||||
|
||||
with lock.r_locked():
|
||||
pass
|
||||
247
lib/crewai/tests/utilities/events/test_shutdown.py
Normal file
247
lib/crewai/tests/utilities/events/test_shutdown.py
Normal file
@@ -0,0 +1,247 @@
|
||||
"""Tests for event bus shutdown and cleanup behavior.
|
||||
|
||||
This module tests graceful shutdown, task completion, and cleanup operations.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import threading
|
||||
import time
|
||||
|
||||
import pytest
|
||||
|
||||
from crewai.events.base_events import BaseEvent
|
||||
from crewai.events.event_bus import CrewAIEventsBus
|
||||
|
||||
|
||||
class ShutdownTestEvent(BaseEvent):
|
||||
pass
|
||||
|
||||
|
||||
def test_shutdown_prevents_new_events():
|
||||
bus = CrewAIEventsBus()
|
||||
received_events = []
|
||||
|
||||
with bus.scoped_handlers():
|
||||
|
||||
@bus.on(ShutdownTestEvent)
|
||||
def handler(source: object, event: BaseEvent) -> None:
|
||||
received_events.append(event)
|
||||
|
||||
bus._shutting_down = True
|
||||
|
||||
event = ShutdownTestEvent(type="after_shutdown")
|
||||
bus.emit("test_source", event)
|
||||
|
||||
time.sleep(0.1)
|
||||
|
||||
assert len(received_events) == 0
|
||||
|
||||
bus._shutting_down = False
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_aemit_during_shutdown():
|
||||
bus = CrewAIEventsBus()
|
||||
received_events = []
|
||||
|
||||
with bus.scoped_handlers():
|
||||
|
||||
@bus.on(ShutdownTestEvent)
|
||||
async def handler(source: object, event: BaseEvent) -> None:
|
||||
received_events.append(event)
|
||||
|
||||
bus._shutting_down = True
|
||||
|
||||
event = ShutdownTestEvent(type="aemit_during_shutdown")
|
||||
await bus.aemit("test_source", event)
|
||||
|
||||
assert len(received_events) == 0
|
||||
|
||||
bus._shutting_down = False
|
||||
|
||||
|
||||
def test_shutdown_flag_prevents_emit():
|
||||
bus = CrewAIEventsBus()
|
||||
emitted_count = [0]
|
||||
|
||||
with bus.scoped_handlers():
|
||||
|
||||
@bus.on(ShutdownTestEvent)
|
||||
def handler(source: object, event: BaseEvent) -> None:
|
||||
emitted_count[0] += 1
|
||||
|
||||
event1 = ShutdownTestEvent(type="before_shutdown")
|
||||
bus.emit("test_source", event1)
|
||||
|
||||
time.sleep(0.1)
|
||||
assert emitted_count[0] == 1
|
||||
|
||||
bus._shutting_down = True
|
||||
|
||||
event2 = ShutdownTestEvent(type="during_shutdown")
|
||||
bus.emit("test_source", event2)
|
||||
|
||||
time.sleep(0.1)
|
||||
assert emitted_count[0] == 1
|
||||
|
||||
bus._shutting_down = False
|
||||
|
||||
|
||||
def test_concurrent_access_during_shutdown_flag():
|
||||
bus = CrewAIEventsBus()
|
||||
received_events = []
|
||||
lock = threading.Lock()
|
||||
|
||||
with bus.scoped_handlers():
|
||||
|
||||
@bus.on(ShutdownTestEvent)
|
||||
def handler(source: object, event: BaseEvent) -> None:
|
||||
with lock:
|
||||
received_events.append(event)
|
||||
|
||||
def emit_events() -> None:
|
||||
for i in range(10):
|
||||
event = ShutdownTestEvent(type=f"event_{i}")
|
||||
bus.emit("source", event)
|
||||
time.sleep(0.01)
|
||||
|
||||
def set_shutdown_flag() -> None:
|
||||
time.sleep(0.05)
|
||||
bus._shutting_down = True
|
||||
|
||||
emit_thread = threading.Thread(target=emit_events)
|
||||
shutdown_thread = threading.Thread(target=set_shutdown_flag)
|
||||
|
||||
emit_thread.start()
|
||||
shutdown_thread.start()
|
||||
|
||||
emit_thread.join()
|
||||
shutdown_thread.join()
|
||||
|
||||
time.sleep(0.2)
|
||||
|
||||
assert len(received_events) < 10
|
||||
assert len(received_events) > 0
|
||||
|
||||
bus._shutting_down = False
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_async_handlers_complete_before_shutdown_flag():
|
||||
bus = CrewAIEventsBus()
|
||||
completed_handlers = []
|
||||
|
||||
with bus.scoped_handlers():
|
||||
|
||||
@bus.on(ShutdownTestEvent)
|
||||
async def async_handler(source: object, event: BaseEvent) -> None:
|
||||
await asyncio.sleep(0.05)
|
||||
if not bus._shutting_down:
|
||||
completed_handlers.append(event)
|
||||
|
||||
for i in range(5):
|
||||
event = ShutdownTestEvent(type=f"event_{i}")
|
||||
bus.emit("source", event)
|
||||
|
||||
await asyncio.sleep(0.3)
|
||||
|
||||
assert len(completed_handlers) == 5
|
||||
|
||||
|
||||
def test_scoped_handlers_cleanup():
|
||||
bus = CrewAIEventsBus()
|
||||
received_before = []
|
||||
received_during = []
|
||||
received_after = []
|
||||
|
||||
with bus.scoped_handlers():
|
||||
|
||||
@bus.on(ShutdownTestEvent)
|
||||
def before_handler(source: object, event: BaseEvent) -> None:
|
||||
received_before.append(event)
|
||||
|
||||
with bus.scoped_handlers():
|
||||
|
||||
@bus.on(ShutdownTestEvent)
|
||||
def during_handler(source: object, event: BaseEvent) -> None:
|
||||
received_during.append(event)
|
||||
|
||||
event1 = ShutdownTestEvent(type="during")
|
||||
bus.emit("source", event1)
|
||||
time.sleep(0.1)
|
||||
|
||||
assert len(received_before) == 0
|
||||
assert len(received_during) == 1
|
||||
|
||||
event2 = ShutdownTestEvent(type="after_inner_scope")
|
||||
bus.emit("source", event2)
|
||||
time.sleep(0.1)
|
||||
|
||||
assert len(received_before) == 1
|
||||
assert len(received_during) == 1
|
||||
|
||||
event3 = ShutdownTestEvent(type="after_outer_scope")
|
||||
bus.emit("source", event3)
|
||||
time.sleep(0.1)
|
||||
|
||||
assert len(received_before) == 1
|
||||
assert len(received_during) == 1
|
||||
assert len(received_after) == 0
|
||||
|
||||
|
||||
def test_handler_registration_thread_safety():
|
||||
bus = CrewAIEventsBus()
|
||||
handlers_registered = [0]
|
||||
lock = threading.Lock()
|
||||
|
||||
with bus.scoped_handlers():
|
||||
|
||||
def register_handlers() -> None:
|
||||
for _ in range(20):
|
||||
|
||||
@bus.on(ShutdownTestEvent)
|
||||
def handler(source: object, event: BaseEvent) -> None:
|
||||
pass
|
||||
|
||||
with lock:
|
||||
handlers_registered[0] += 1
|
||||
|
||||
time.sleep(0.001)
|
||||
|
||||
threads = [threading.Thread(target=register_handlers) for _ in range(3)]
|
||||
|
||||
for thread in threads:
|
||||
thread.start()
|
||||
|
||||
for thread in threads:
|
||||
thread.join()
|
||||
|
||||
assert handlers_registered[0] == 60
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_mixed_sync_async_handler_execution():
|
||||
bus = CrewAIEventsBus()
|
||||
sync_executed = []
|
||||
async_executed = []
|
||||
|
||||
with bus.scoped_handlers():
|
||||
|
||||
@bus.on(ShutdownTestEvent)
|
||||
def sync_handler(source: object, event: BaseEvent) -> None:
|
||||
time.sleep(0.01)
|
||||
sync_executed.append(event)
|
||||
|
||||
@bus.on(ShutdownTestEvent)
|
||||
async def async_handler(source: object, event: BaseEvent) -> None:
|
||||
await asyncio.sleep(0.01)
|
||||
async_executed.append(event)
|
||||
|
||||
for i in range(5):
|
||||
event = ShutdownTestEvent(type=f"event_{i}")
|
||||
bus.emit("source", event)
|
||||
|
||||
await asyncio.sleep(0.2)
|
||||
|
||||
assert len(sync_executed) == 5
|
||||
assert len(async_executed) == 5
|
||||
189
lib/crewai/tests/utilities/events/test_thread_safety.py
Normal file
189
lib/crewai/tests/utilities/events/test_thread_safety.py
Normal file
@@ -0,0 +1,189 @@
|
||||
"""Tests for thread safety in CrewAI event bus.
|
||||
|
||||
This module tests concurrent event emission and handler registration.
|
||||
"""
|
||||
|
||||
import threading
|
||||
import time
|
||||
from collections.abc import Callable
|
||||
|
||||
from crewai.events.base_events import BaseEvent
|
||||
from crewai.events.event_bus import crewai_event_bus
|
||||
|
||||
|
||||
class ThreadSafetyTestEvent(BaseEvent):
|
||||
pass
|
||||
|
||||
|
||||
def test_concurrent_emit_from_multiple_threads():
|
||||
received_events: list[BaseEvent] = []
|
||||
lock = threading.Lock()
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
|
||||
@crewai_event_bus.on(ThreadSafetyTestEvent)
|
||||
def handler(source: object, event: BaseEvent) -> None:
|
||||
with lock:
|
||||
received_events.append(event)
|
||||
|
||||
threads: list[threading.Thread] = []
|
||||
num_threads = 10
|
||||
events_per_thread = 10
|
||||
|
||||
def emit_events(thread_id: int) -> None:
|
||||
for i in range(events_per_thread):
|
||||
event = ThreadSafetyTestEvent(type=f"thread_{thread_id}_event_{i}")
|
||||
crewai_event_bus.emit(f"source_{thread_id}", event)
|
||||
|
||||
for i in range(num_threads):
|
||||
thread = threading.Thread(target=emit_events, args=(i,))
|
||||
threads.append(thread)
|
||||
thread.start()
|
||||
|
||||
for thread in threads:
|
||||
thread.join()
|
||||
|
||||
time.sleep(0.5)
|
||||
|
||||
assert len(received_events) == num_threads * events_per_thread
|
||||
|
||||
|
||||
def test_concurrent_handler_registration():
|
||||
handlers_executed: list[int] = []
|
||||
lock = threading.Lock()
|
||||
|
||||
def create_handler(handler_id: int) -> Callable[[object, BaseEvent], None]:
|
||||
def handler(source: object, event: BaseEvent) -> None:
|
||||
with lock:
|
||||
handlers_executed.append(handler_id)
|
||||
|
||||
return handler
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
threads: list[threading.Thread] = []
|
||||
num_handlers = 20
|
||||
|
||||
def register_handler(handler_id: int) -> None:
|
||||
crewai_event_bus.register_handler(
|
||||
ThreadSafetyTestEvent, create_handler(handler_id)
|
||||
)
|
||||
|
||||
for i in range(num_handlers):
|
||||
thread = threading.Thread(target=register_handler, args=(i,))
|
||||
threads.append(thread)
|
||||
thread.start()
|
||||
|
||||
for thread in threads:
|
||||
thread.join()
|
||||
|
||||
event = ThreadSafetyTestEvent(type="registration_test")
|
||||
crewai_event_bus.emit("test_source", event)
|
||||
|
||||
time.sleep(0.5)
|
||||
|
||||
assert len(handlers_executed) == num_handlers
|
||||
assert set(handlers_executed) == set(range(num_handlers))
|
||||
|
||||
|
||||
def test_concurrent_emit_and_registration():
|
||||
received_events: list[BaseEvent] = []
|
||||
lock = threading.Lock()
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
|
||||
def emit_continuously() -> None:
|
||||
for i in range(50):
|
||||
event = ThreadSafetyTestEvent(type=f"emit_event_{i}")
|
||||
crewai_event_bus.emit("emitter", event)
|
||||
time.sleep(0.001)
|
||||
|
||||
def register_continuously() -> None:
|
||||
for _ in range(10):
|
||||
|
||||
@crewai_event_bus.on(ThreadSafetyTestEvent)
|
||||
def handler(source: object, event: BaseEvent) -> None:
|
||||
with lock:
|
||||
received_events.append(event)
|
||||
|
||||
time.sleep(0.005)
|
||||
|
||||
emit_thread = threading.Thread(target=emit_continuously)
|
||||
register_thread = threading.Thread(target=register_continuously)
|
||||
|
||||
emit_thread.start()
|
||||
register_thread.start()
|
||||
|
||||
emit_thread.join()
|
||||
register_thread.join()
|
||||
|
||||
time.sleep(0.5)
|
||||
|
||||
assert len(received_events) > 0
|
||||
|
||||
|
||||
def test_stress_test_rapid_emit():
|
||||
received_count = [0]
|
||||
lock = threading.Lock()
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
|
||||
@crewai_event_bus.on(ThreadSafetyTestEvent)
|
||||
def counter_handler(source: object, event: BaseEvent) -> None:
|
||||
with lock:
|
||||
received_count[0] += 1
|
||||
|
||||
num_events = 1000
|
||||
|
||||
for i in range(num_events):
|
||||
event = ThreadSafetyTestEvent(type=f"rapid_event_{i}")
|
||||
crewai_event_bus.emit("rapid_source", event)
|
||||
|
||||
time.sleep(1.0)
|
||||
|
||||
assert received_count[0] == num_events
|
||||
|
||||
|
||||
def test_multiple_event_types_concurrent():
|
||||
class EventTypeA(BaseEvent):
|
||||
pass
|
||||
|
||||
class EventTypeB(BaseEvent):
|
||||
pass
|
||||
|
||||
received_a: list[BaseEvent] = []
|
||||
received_b: list[BaseEvent] = []
|
||||
lock = threading.Lock()
|
||||
|
||||
with crewai_event_bus.scoped_handlers():
|
||||
|
||||
@crewai_event_bus.on(EventTypeA)
|
||||
def handler_a(source: object, event: BaseEvent) -> None:
|
||||
with lock:
|
||||
received_a.append(event)
|
||||
|
||||
@crewai_event_bus.on(EventTypeB)
|
||||
def handler_b(source: object, event: BaseEvent) -> None:
|
||||
with lock:
|
||||
received_b.append(event)
|
||||
|
||||
def emit_type_a() -> None:
|
||||
for i in range(50):
|
||||
crewai_event_bus.emit("source_a", EventTypeA(type=f"type_a_{i}"))
|
||||
|
||||
def emit_type_b() -> None:
|
||||
for i in range(50):
|
||||
crewai_event_bus.emit("source_b", EventTypeB(type=f"type_b_{i}"))
|
||||
|
||||
thread_a = threading.Thread(target=emit_type_a)
|
||||
thread_b = threading.Thread(target=emit_type_b)
|
||||
|
||||
thread_a.start()
|
||||
thread_b.start()
|
||||
|
||||
thread_a.join()
|
||||
thread_b.join()
|
||||
|
||||
time.sleep(0.5)
|
||||
|
||||
assert len(received_a) == 50
|
||||
assert len(received_b) == 50
|
||||
40
lib/crewai/tests/utilities/prompts.json
Normal file
40
lib/crewai/tests/utilities/prompts.json
Normal file
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"hierarchical_manager_agent": {
|
||||
"role": "Lorem ipsum dolor sit amet",
|
||||
"goal": "Lorem ipsum dolor sit amet",
|
||||
"backstory": "Lorem ipsum dolor sit amet."
|
||||
},
|
||||
"planning_manager_agent": {
|
||||
"role": "Lorem ipsum dolor sit amet",
|
||||
"goal": "Lorem ipsum dolor sit amet",
|
||||
"backstory": "Lorem ipsum dolor sit amet."
|
||||
},
|
||||
"slices": {
|
||||
"observation": "Lorem ipsum dolor sit amet",
|
||||
"task": "Lorem ipsum dolor sit amet",
|
||||
"memory": "Lorem ipsum dolor sit amet",
|
||||
"role_playing": "Lorem ipsum dolor sit amet",
|
||||
"tools": "Lorem ipsum dolor sit amet",
|
||||
"no_tools": "Lorem ipsum dolor sit amet",
|
||||
"format": "Lorem ipsum dolor sit amet",
|
||||
"final_answer_format": "Lorem ipsum dolor sit amet",
|
||||
"format_without_tools": "Lorem ipsum dolor sit amet",
|
||||
"task_with_context": "Lorem ipsum dolor sit amet",
|
||||
"expected_output": "Lorem ipsum dolor sit amet",
|
||||
"human_feedback": "Lorem ipsum dolor sit amet",
|
||||
"getting_input": "Lorem ipsum dolor sit amet "
|
||||
},
|
||||
"errors": {
|
||||
"force_final_answer": "Lorem ipsum dolor sit amet",
|
||||
"agent_tool_unexisting_coworker": "Lorem ipsum dolor sit amet",
|
||||
"task_repeated_usage": "Lorem ipsum dolor sit amet",
|
||||
"tool_usage_error": "Lorem ipsum dolor sit amet",
|
||||
"tool_arguments_error": "Lorem ipsum dolor sit amet",
|
||||
"wrong_tool_name": "Lorem ipsum dolor sit amet",
|
||||
"tool_usage_exception": "Lorem ipsum dolor sit amet"
|
||||
},
|
||||
"tools": {
|
||||
"delegate_work": "Lorem ipsum dolor sit amet",
|
||||
"ask_question": "Lorem ipsum dolor sit amet"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,116 @@
|
||||
from unittest.mock import MagicMock, patch
|
||||
from rich.tree import Tree
|
||||
from rich.live import Live
|
||||
from crewai.events.utils.console_formatter import ConsoleFormatter
|
||||
|
||||
|
||||
class TestConsoleFormatterPauseResume:
|
||||
"""Test ConsoleFormatter pause/resume functionality."""
|
||||
|
||||
def test_pause_live_updates_with_active_session(self):
|
||||
"""Test pausing when Live session is active."""
|
||||
formatter = ConsoleFormatter()
|
||||
|
||||
mock_live = MagicMock(spec=Live)
|
||||
formatter._live = mock_live
|
||||
formatter._live_paused = False
|
||||
|
||||
formatter.pause_live_updates()
|
||||
|
||||
mock_live.stop.assert_called_once()
|
||||
assert formatter._live_paused
|
||||
|
||||
def test_pause_live_updates_when_already_paused(self):
|
||||
"""Test pausing when already paused does nothing."""
|
||||
formatter = ConsoleFormatter()
|
||||
|
||||
mock_live = MagicMock(spec=Live)
|
||||
formatter._live = mock_live
|
||||
formatter._live_paused = True
|
||||
|
||||
formatter.pause_live_updates()
|
||||
|
||||
mock_live.stop.assert_not_called()
|
||||
assert formatter._live_paused
|
||||
|
||||
def test_pause_live_updates_with_no_session(self):
|
||||
"""Test pausing when no Live session exists."""
|
||||
formatter = ConsoleFormatter()
|
||||
|
||||
formatter._live = None
|
||||
formatter._live_paused = False
|
||||
|
||||
formatter.pause_live_updates()
|
||||
|
||||
assert formatter._live_paused
|
||||
|
||||
def test_resume_live_updates_when_paused(self):
|
||||
"""Test resuming when paused."""
|
||||
formatter = ConsoleFormatter()
|
||||
|
||||
formatter._live_paused = True
|
||||
|
||||
formatter.resume_live_updates()
|
||||
|
||||
assert not formatter._live_paused
|
||||
|
||||
def test_resume_live_updates_when_not_paused(self):
|
||||
"""Test resuming when not paused does nothing."""
|
||||
formatter = ConsoleFormatter()
|
||||
|
||||
formatter._live_paused = False
|
||||
|
||||
formatter.resume_live_updates()
|
||||
|
||||
assert not formatter._live_paused
|
||||
|
||||
def test_print_after_resume_restarts_live_session(self):
|
||||
"""Test that printing a Tree after resume creates new Live session."""
|
||||
formatter = ConsoleFormatter()
|
||||
|
||||
formatter._live_paused = True
|
||||
formatter._live = None
|
||||
|
||||
formatter.resume_live_updates()
|
||||
assert not formatter._live_paused
|
||||
|
||||
tree = Tree("Test")
|
||||
|
||||
with patch("crewai.events.utils.console_formatter.Live") as mock_live_class:
|
||||
mock_live_instance = MagicMock()
|
||||
mock_live_class.return_value = mock_live_instance
|
||||
|
||||
formatter.print(tree)
|
||||
|
||||
mock_live_class.assert_called_once()
|
||||
mock_live_instance.start.assert_called_once()
|
||||
assert formatter._live == mock_live_instance
|
||||
|
||||
def test_multiple_pause_resume_cycles(self):
|
||||
"""Test multiple pause/resume cycles work correctly."""
|
||||
formatter = ConsoleFormatter()
|
||||
|
||||
mock_live = MagicMock(spec=Live)
|
||||
formatter._live = mock_live
|
||||
formatter._live_paused = False
|
||||
|
||||
formatter.pause_live_updates()
|
||||
assert formatter._live_paused
|
||||
mock_live.stop.assert_called_once()
|
||||
assert formatter._live is None # Live session should be cleared
|
||||
|
||||
formatter.resume_live_updates()
|
||||
assert not formatter._live_paused
|
||||
|
||||
formatter.pause_live_updates()
|
||||
assert formatter._live_paused
|
||||
|
||||
formatter.resume_live_updates()
|
||||
assert not formatter._live_paused
|
||||
|
||||
def test_pause_resume_state_initialization(self):
|
||||
"""Test that _live_paused is properly initialized."""
|
||||
formatter = ConsoleFormatter()
|
||||
|
||||
assert hasattr(formatter, "_live_paused")
|
||||
assert not formatter._live_paused
|
||||
599
lib/crewai/tests/utilities/test_converter.py
Normal file
599
lib/crewai/tests/utilities/test_converter.py
Normal file
@@ -0,0 +1,599 @@
|
||||
# Tests for enums
|
||||
from enum import Enum
|
||||
import json
|
||||
import os
|
||||
from unittest.mock import MagicMock, Mock, patch
|
||||
|
||||
from crewai.llm import LLM
|
||||
from crewai.utilities.converter import (
|
||||
Converter,
|
||||
ConverterError,
|
||||
convert_to_model,
|
||||
convert_with_instructions,
|
||||
create_converter,
|
||||
generate_model_description,
|
||||
get_conversion_instructions,
|
||||
handle_partial_json,
|
||||
validate_model,
|
||||
)
|
||||
from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
|
||||
from pydantic import BaseModel
|
||||
import pytest
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def vcr_config(request) -> dict:
|
||||
return {
|
||||
"cassette_library_dir": os.path.join(os.path.dirname(__file__), "cassettes"),
|
||||
}
|
||||
|
||||
|
||||
# Sample Pydantic models for testing
|
||||
class EmailResponse(BaseModel):
|
||||
previous_message_content: str
|
||||
|
||||
|
||||
class EmailResponses(BaseModel):
|
||||
responses: list[EmailResponse]
|
||||
|
||||
|
||||
class SimpleModel(BaseModel):
|
||||
name: str
|
||||
age: int
|
||||
|
||||
|
||||
class NestedModel(BaseModel):
|
||||
id: int
|
||||
data: SimpleModel
|
||||
|
||||
|
||||
class Address(BaseModel):
|
||||
street: str
|
||||
city: str
|
||||
zip_code: str
|
||||
|
||||
|
||||
class Person(BaseModel):
|
||||
name: str
|
||||
age: int
|
||||
address: Address
|
||||
|
||||
|
||||
class CustomConverter(Converter):
|
||||
pass
|
||||
|
||||
|
||||
# Fixtures
|
||||
@pytest.fixture
|
||||
def mock_agent():
|
||||
agent = Mock()
|
||||
agent.function_calling_llm = None
|
||||
agent.llm = Mock()
|
||||
return agent
|
||||
|
||||
|
||||
# Tests for convert_to_model
|
||||
def test_convert_to_model_with_valid_json():
|
||||
result = '{"name": "John", "age": 30}'
|
||||
output = convert_to_model(result, SimpleModel, None, None)
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "John"
|
||||
assert output.age == 30
|
||||
|
||||
|
||||
def test_convert_to_model_with_invalid_json():
|
||||
result = '{"name": "John", "age": "thirty"}'
|
||||
with patch("crewai.utilities.converter.handle_partial_json") as mock_handle:
|
||||
mock_handle.return_value = "Fallback result"
|
||||
output = convert_to_model(result, SimpleModel, None, None)
|
||||
assert output == "Fallback result"
|
||||
|
||||
|
||||
def test_convert_to_model_with_no_model():
|
||||
result = "Plain text"
|
||||
output = convert_to_model(result, None, None, None)
|
||||
assert output == "Plain text"
|
||||
|
||||
|
||||
def test_convert_to_model_with_special_characters():
|
||||
json_string_test = """
|
||||
{
|
||||
"responses": [
|
||||
{
|
||||
"previous_message_content": "Hi Tom,\r\n\r\nNiamh has chosen the Mika phonics on"
|
||||
}
|
||||
]
|
||||
}
|
||||
"""
|
||||
output = convert_to_model(json_string_test, EmailResponses, None, None)
|
||||
assert isinstance(output, EmailResponses)
|
||||
assert len(output.responses) == 1
|
||||
assert (
|
||||
output.responses[0].previous_message_content
|
||||
== "Hi Tom,\r\n\r\nNiamh has chosen the Mika phonics on"
|
||||
)
|
||||
|
||||
|
||||
def test_convert_to_model_with_escaped_special_characters():
|
||||
json_string_test = json.dumps(
|
||||
{
|
||||
"responses": [
|
||||
{
|
||||
"previous_message_content": "Hi Tom,\r\n\r\nNiamh has chosen the Mika phonics on"
|
||||
}
|
||||
]
|
||||
}
|
||||
)
|
||||
output = convert_to_model(json_string_test, EmailResponses, None, None)
|
||||
assert isinstance(output, EmailResponses)
|
||||
assert len(output.responses) == 1
|
||||
assert (
|
||||
output.responses[0].previous_message_content
|
||||
== "Hi Tom,\r\n\r\nNiamh has chosen the Mika phonics on"
|
||||
)
|
||||
|
||||
|
||||
def test_convert_to_model_with_multiple_special_characters():
|
||||
json_string_test = """
|
||||
{
|
||||
"responses": [
|
||||
{
|
||||
"previous_message_content": "Line 1\r\nLine 2\tTabbed\nLine 3\r\n\rEscaped newline"
|
||||
}
|
||||
]
|
||||
}
|
||||
"""
|
||||
output = convert_to_model(json_string_test, EmailResponses, None, None)
|
||||
assert isinstance(output, EmailResponses)
|
||||
assert len(output.responses) == 1
|
||||
assert (
|
||||
output.responses[0].previous_message_content
|
||||
== "Line 1\r\nLine 2\tTabbed\nLine 3\r\n\rEscaped newline"
|
||||
)
|
||||
|
||||
|
||||
# Tests for validate_model
|
||||
def test_validate_model_pydantic_output():
|
||||
result = '{"name": "Alice", "age": 25}'
|
||||
output = validate_model(result, SimpleModel, False)
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "Alice"
|
||||
assert output.age == 25
|
||||
|
||||
|
||||
def test_validate_model_json_output():
|
||||
result = '{"name": "Bob", "age": 40}'
|
||||
output = validate_model(result, SimpleModel, True)
|
||||
assert isinstance(output, dict)
|
||||
assert output == {"name": "Bob", "age": 40}
|
||||
|
||||
|
||||
# Tests for handle_partial_json
|
||||
def test_handle_partial_json_with_valid_partial():
|
||||
result = 'Some text {"name": "Charlie", "age": 35} more text'
|
||||
output = handle_partial_json(result, SimpleModel, False, None)
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "Charlie"
|
||||
assert output.age == 35
|
||||
|
||||
|
||||
def test_handle_partial_json_with_invalid_partial(mock_agent):
|
||||
result = "No valid JSON here"
|
||||
with patch("crewai.utilities.converter.convert_with_instructions") as mock_convert:
|
||||
mock_convert.return_value = "Converted result"
|
||||
output = handle_partial_json(result, SimpleModel, False, mock_agent)
|
||||
assert output == "Converted result"
|
||||
|
||||
|
||||
# Tests for convert_with_instructions
|
||||
@patch("crewai.utilities.converter.create_converter")
|
||||
@patch("crewai.utilities.converter.get_conversion_instructions")
|
||||
def test_convert_with_instructions_success(
|
||||
mock_get_instructions, mock_create_converter, mock_agent
|
||||
):
|
||||
mock_get_instructions.return_value = "Instructions"
|
||||
mock_converter = Mock()
|
||||
mock_converter.to_pydantic.return_value = SimpleModel(name="David", age=50)
|
||||
mock_create_converter.return_value = mock_converter
|
||||
|
||||
result = "Some text to convert"
|
||||
output = convert_with_instructions(result, SimpleModel, False, mock_agent)
|
||||
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "David"
|
||||
assert output.age == 50
|
||||
|
||||
|
||||
@patch("crewai.utilities.converter.create_converter")
|
||||
@patch("crewai.utilities.converter.get_conversion_instructions")
|
||||
def test_convert_with_instructions_failure(
|
||||
mock_get_instructions, mock_create_converter, mock_agent
|
||||
):
|
||||
mock_get_instructions.return_value = "Instructions"
|
||||
mock_converter = Mock()
|
||||
mock_converter.to_pydantic.return_value = ConverterError("Conversion failed")
|
||||
mock_create_converter.return_value = mock_converter
|
||||
|
||||
result = "Some text to convert"
|
||||
with patch("crewai.utilities.converter.Printer") as mock_printer:
|
||||
output = convert_with_instructions(result, SimpleModel, False, mock_agent)
|
||||
assert output == result
|
||||
mock_printer.return_value.print.assert_called_once()
|
||||
|
||||
|
||||
# Tests for get_conversion_instructions
|
||||
def test_get_conversion_instructions_gpt():
|
||||
llm = LLM(model="gpt-4o-mini")
|
||||
with patch.object(LLM, "supports_function_calling") as supports_function_calling:
|
||||
supports_function_calling.return_value = True
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
model_schema = PydanticSchemaParser(model=SimpleModel).get_schema()
|
||||
expected_instructions = (
|
||||
"Please convert the following text into valid JSON.\n\n"
|
||||
"Output ONLY the valid JSON and nothing else.\n\n"
|
||||
"The JSON must follow this schema exactly:\n```json\n"
|
||||
f"{model_schema}\n```"
|
||||
)
|
||||
assert instructions == expected_instructions
|
||||
|
||||
|
||||
def test_get_conversion_instructions_non_gpt():
|
||||
llm = LLM(model="ollama/llama3.1", base_url="http://localhost:11434")
|
||||
with patch.object(LLM, "supports_function_calling", return_value=False):
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
assert '"name": str' in instructions
|
||||
assert '"age": int' in instructions
|
||||
|
||||
|
||||
# Tests for is_gpt
|
||||
def test_supports_function_calling_true():
|
||||
llm = LLM(model="gpt-4o")
|
||||
assert llm.supports_function_calling() is True
|
||||
|
||||
|
||||
def test_supports_function_calling_false():
|
||||
llm = LLM(model="non-existent-model", is_litellm=True)
|
||||
assert llm.supports_function_calling() is False
|
||||
|
||||
|
||||
def test_create_converter_with_mock_agent():
|
||||
mock_agent = MagicMock()
|
||||
mock_agent.get_output_converter.return_value = MagicMock(spec=Converter)
|
||||
|
||||
converter = create_converter(
|
||||
agent=mock_agent,
|
||||
llm=Mock(),
|
||||
text="Sample",
|
||||
model=SimpleModel,
|
||||
instructions="Convert",
|
||||
)
|
||||
|
||||
assert isinstance(converter, Converter)
|
||||
mock_agent.get_output_converter.assert_called_once()
|
||||
|
||||
|
||||
def test_create_converter_with_custom_converter():
|
||||
converter = create_converter(
|
||||
converter_cls=CustomConverter,
|
||||
llm=LLM(model="gpt-4o-mini"),
|
||||
text="Sample",
|
||||
model=SimpleModel,
|
||||
instructions="Convert",
|
||||
)
|
||||
|
||||
assert isinstance(converter, CustomConverter)
|
||||
|
||||
|
||||
def test_create_converter_fails_without_agent_or_converter_cls():
|
||||
with pytest.raises(
|
||||
ValueError, match="Either agent or converter_cls must be provided"
|
||||
):
|
||||
create_converter(
|
||||
llm=Mock(), text="Sample", model=SimpleModel, instructions="Convert"
|
||||
)
|
||||
|
||||
|
||||
def test_generate_model_description_simple_model():
|
||||
description = generate_model_description(SimpleModel)
|
||||
expected_description = '{\n "name": str,\n "age": int\n}'
|
||||
assert description == expected_description
|
||||
|
||||
|
||||
def test_generate_model_description_nested_model():
|
||||
description = generate_model_description(NestedModel)
|
||||
expected_description = (
|
||||
'{\n "id": int,\n "data": {\n "name": str,\n "age": int\n}\n}'
|
||||
)
|
||||
assert description == expected_description
|
||||
|
||||
|
||||
def test_generate_model_description_optional_field():
|
||||
class ModelWithOptionalField(BaseModel):
|
||||
name: str
|
||||
age: int | None
|
||||
|
||||
description = generate_model_description(ModelWithOptionalField)
|
||||
expected_description = '{\n "name": str,\n "age": int | None\n}'
|
||||
assert description == expected_description
|
||||
|
||||
|
||||
def test_generate_model_description_list_field():
|
||||
class ModelWithListField(BaseModel):
|
||||
items: list[int]
|
||||
|
||||
description = generate_model_description(ModelWithListField)
|
||||
expected_description = '{\n "items": List[int]\n}'
|
||||
assert description == expected_description
|
||||
|
||||
|
||||
def test_generate_model_description_dict_field():
|
||||
class ModelWithDictField(BaseModel):
|
||||
attributes: dict[str, int]
|
||||
|
||||
description = generate_model_description(ModelWithDictField)
|
||||
expected_description = '{\n "attributes": Dict[str, int]\n}'
|
||||
assert description == expected_description
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_convert_with_instructions():
|
||||
llm = LLM(model="gpt-4o-mini")
|
||||
sample_text = "Name: Alice, Age: 30"
|
||||
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=SimpleModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
# Act
|
||||
output = converter.to_pydantic()
|
||||
|
||||
# Assert
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "Alice"
|
||||
assert output.age == 30
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_converter_with_llama3_2_model():
|
||||
llm = LLM(model="openrouter/meta-llama/llama-3.2-3b-instruct")
|
||||
sample_text = "Name: Alice Llama, Age: 30"
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=SimpleModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
output = converter.to_pydantic()
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "Alice Llama"
|
||||
assert output.age == 30
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_converter_with_llama3_1_model():
|
||||
llm = LLM(model="ollama/llama3.1", base_url="http://localhost:11434")
|
||||
sample_text = "Name: Alice Llama, Age: 30"
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=SimpleModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
output = converter.to_pydantic()
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "Alice Llama"
|
||||
assert output.age == 30
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_converter_with_nested_model():
|
||||
llm = LLM(model="gpt-4o-mini")
|
||||
sample_text = "Name: John Doe\nAge: 30\nAddress: 123 Main St, Anytown, 12345"
|
||||
|
||||
instructions = get_conversion_instructions(Person, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=Person,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, Person)
|
||||
assert output.name == "John Doe"
|
||||
assert output.age == 30
|
||||
assert isinstance(output.address, Address)
|
||||
assert output.address.street == "123 Main St"
|
||||
assert output.address.city == "Anytown"
|
||||
assert output.address.zip_code == "12345"
|
||||
|
||||
|
||||
# Tests for error handling
|
||||
def test_converter_error_handling():
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = False
|
||||
llm.call.return_value = "Invalid JSON"
|
||||
sample_text = "Name: Alice, Age: 30"
|
||||
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=SimpleModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
with pytest.raises(ConverterError) as exc_info:
|
||||
converter.to_pydantic()
|
||||
|
||||
assert "Failed to convert text into a Pydantic model" in str(exc_info.value)
|
||||
|
||||
|
||||
# Tests for retry logic
|
||||
def test_converter_retry_logic():
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = False
|
||||
llm.call.side_effect = [
|
||||
"Invalid JSON",
|
||||
"Still invalid",
|
||||
'{"name": "Retry Alice", "age": 30}',
|
||||
]
|
||||
sample_text = "Name: Retry Alice, Age: 30"
|
||||
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=SimpleModel,
|
||||
instructions=instructions,
|
||||
max_attempts=3,
|
||||
)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "Retry Alice"
|
||||
assert output.age == 30
|
||||
assert llm.call.call_count == 3
|
||||
|
||||
|
||||
# Tests for optional fields
|
||||
def test_converter_with_optional_fields():
|
||||
class OptionalModel(BaseModel):
|
||||
name: str
|
||||
age: int | None
|
||||
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = False
|
||||
# Simulate the LLM's response with 'age' explicitly set to null
|
||||
llm.call.return_value = '{"name": "Bob", "age": null}'
|
||||
sample_text = "Name: Bob, age: None"
|
||||
|
||||
instructions = get_conversion_instructions(OptionalModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=OptionalModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, OptionalModel)
|
||||
assert output.name == "Bob"
|
||||
assert output.age is None
|
||||
|
||||
|
||||
# Tests for list fields
|
||||
def test_converter_with_list_field():
|
||||
class ListModel(BaseModel):
|
||||
items: list[int]
|
||||
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = False
|
||||
llm.call.return_value = '{"items": [1, 2, 3]}'
|
||||
sample_text = "Items: 1, 2, 3"
|
||||
|
||||
instructions = get_conversion_instructions(ListModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=ListModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, ListModel)
|
||||
assert output.items == [1, 2, 3]
|
||||
|
||||
|
||||
def test_converter_with_enum():
|
||||
class Color(Enum):
|
||||
RED = "red"
|
||||
GREEN = "green"
|
||||
BLUE = "blue"
|
||||
|
||||
class EnumModel(BaseModel):
|
||||
name: str
|
||||
color: Color
|
||||
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = False
|
||||
llm.call.return_value = '{"name": "Alice", "color": "red"}'
|
||||
sample_text = "Name: Alice, Color: Red"
|
||||
|
||||
instructions = get_conversion_instructions(EnumModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=EnumModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, EnumModel)
|
||||
assert output.name == "Alice"
|
||||
assert output.color == Color.RED
|
||||
|
||||
|
||||
# Tests for ambiguous input
|
||||
def test_converter_with_ambiguous_input():
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = False
|
||||
llm.call.return_value = '{"name": "Charlie", "age": "Not an age"}'
|
||||
sample_text = "Charlie is thirty years old"
|
||||
|
||||
instructions = get_conversion_instructions(SimpleModel, llm)
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text=sample_text,
|
||||
model=SimpleModel,
|
||||
instructions=instructions,
|
||||
)
|
||||
|
||||
with pytest.raises(ConverterError) as exc_info:
|
||||
converter.to_pydantic()
|
||||
|
||||
assert "failed to convert text into a pydantic model" in str(exc_info.value).lower()
|
||||
|
||||
|
||||
# Tests for function calling support
|
||||
def test_converter_with_function_calling():
|
||||
llm = Mock(spec=LLM)
|
||||
llm.supports_function_calling.return_value = True
|
||||
|
||||
instructor = Mock()
|
||||
instructor.to_pydantic.return_value = SimpleModel(name="Eve", age=35)
|
||||
|
||||
converter = Converter(
|
||||
llm=llm,
|
||||
text="Name: Eve, Age: 35",
|
||||
model=SimpleModel,
|
||||
instructions="Convert this text.",
|
||||
)
|
||||
converter._create_instructor = Mock(return_value=instructor)
|
||||
|
||||
output = converter.to_pydantic()
|
||||
|
||||
assert isinstance(output, SimpleModel)
|
||||
assert output.name == "Eve"
|
||||
assert output.age == 35
|
||||
instructor.to_pydantic.assert_called_once()
|
||||
|
||||
|
||||
def test_generate_model_description_union_field():
|
||||
class UnionModel(BaseModel):
|
||||
field: int | str | None
|
||||
|
||||
description = generate_model_description(UnionModel)
|
||||
expected_description = '{\n "field": int | str | None\n}'
|
||||
assert description == expected_description
|
||||
1106
lib/crewai/tests/utilities/test_events.py
Normal file
1106
lib/crewai/tests/utilities/test_events.py
Normal file
File diff suppressed because it is too large
Load Diff
49
lib/crewai/tests/utilities/test_file_handler.py
Normal file
49
lib/crewai/tests/utilities/test_file_handler.py
Normal file
@@ -0,0 +1,49 @@
|
||||
import os
|
||||
import unittest
|
||||
import uuid
|
||||
|
||||
import pytest
|
||||
from crewai.utilities.file_handler import PickleHandler
|
||||
|
||||
|
||||
class TestPickleHandler(unittest.TestCase):
|
||||
def setUp(self):
|
||||
# Use a unique file name for each test to avoid race conditions in parallel test execution
|
||||
unique_id = str(uuid.uuid4())
|
||||
self.file_name = f"test_data_{unique_id}.pkl"
|
||||
self.file_path = os.path.join(os.getcwd(), self.file_name)
|
||||
self.handler = PickleHandler(self.file_name)
|
||||
|
||||
def tearDown(self):
|
||||
if os.path.exists(self.file_path):
|
||||
os.remove(self.file_path)
|
||||
|
||||
def test_initialize_file(self):
|
||||
assert os.path.exists(self.file_path) is False
|
||||
|
||||
self.handler.initialize_file()
|
||||
|
||||
assert os.path.exists(self.file_path) is True
|
||||
assert os.path.getsize(self.file_path) >= 0
|
||||
|
||||
def test_save_and_load(self):
|
||||
data = {"key": "value"}
|
||||
self.handler.save(data)
|
||||
loaded_data = self.handler.load()
|
||||
assert loaded_data == data
|
||||
|
||||
def test_load_empty_file(self):
|
||||
loaded_data = self.handler.load()
|
||||
assert loaded_data == {}
|
||||
|
||||
def test_load_corrupted_file(self):
|
||||
with open(self.file_path, "wb") as file:
|
||||
file.write(b"corrupted data")
|
||||
file.flush()
|
||||
os.fsync(file.fileno()) # Ensure data is written to disk
|
||||
|
||||
with pytest.raises(Exception) as exc:
|
||||
self.handler.load()
|
||||
|
||||
assert str(exc.value) == "pickle data was truncated"
|
||||
assert "<class '_pickle.UnpicklingError'>" == str(exc.type)
|
||||
43
lib/crewai/tests/utilities/test_i18n.py
Normal file
43
lib/crewai/tests/utilities/test_i18n.py
Normal file
@@ -0,0 +1,43 @@
|
||||
import pytest
|
||||
from crewai.utilities.i18n import I18N
|
||||
|
||||
|
||||
def test_load_prompts():
|
||||
i18n = I18N()
|
||||
i18n.load_prompts()
|
||||
assert i18n._prompts is not None
|
||||
|
||||
|
||||
def test_slice():
|
||||
i18n = I18N()
|
||||
i18n.load_prompts()
|
||||
assert isinstance(i18n.slice("role_playing"), str)
|
||||
|
||||
|
||||
def test_tools():
|
||||
i18n = I18N()
|
||||
i18n.load_prompts()
|
||||
assert isinstance(i18n.tools("ask_question"), str)
|
||||
|
||||
|
||||
def test_retrieve():
|
||||
i18n = I18N()
|
||||
i18n.load_prompts()
|
||||
assert isinstance(i18n.retrieve("slices", "role_playing"), str)
|
||||
|
||||
|
||||
def test_retrieve_not_found():
|
||||
i18n = I18N()
|
||||
i18n.load_prompts()
|
||||
with pytest.raises(Exception):
|
||||
i18n.retrieve("nonexistent_kind", "nonexistent_key")
|
||||
|
||||
|
||||
def test_prompt_file():
|
||||
import os
|
||||
|
||||
path = os.path.join(os.path.dirname(__file__), "prompts.json")
|
||||
i18n = I18N(prompt_file=path)
|
||||
i18n.load_prompts()
|
||||
assert isinstance(i18n.retrieve("slices", "role_playing"), str)
|
||||
assert i18n.retrieve("slices", "role_playing") == "Lorem ipsum dolor sit amet"
|
||||
188
lib/crewai/tests/utilities/test_import_utils.py
Normal file
188
lib/crewai/tests/utilities/test_import_utils.py
Normal file
@@ -0,0 +1,188 @@
|
||||
"""Tests for import utilities."""
|
||||
|
||||
import sys
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
import pytest
|
||||
from crewai.utilities.import_utils import (
|
||||
OptionalDependencyError,
|
||||
import_and_validate_definition,
|
||||
require,
|
||||
validate_import_path,
|
||||
)
|
||||
|
||||
|
||||
class TestRequire:
|
||||
"""Test the require function."""
|
||||
|
||||
def test_require_existing_module(self):
|
||||
"""Test requiring a module that exists."""
|
||||
module = require("json", purpose="testing")
|
||||
assert module.__name__ == "json"
|
||||
|
||||
def test_require_missing_module(self):
|
||||
"""Test requiring a module that doesn't exist."""
|
||||
with pytest.raises(OptionalDependencyError) as exc_info:
|
||||
require("nonexistent_module_xyz", purpose="testing missing module")
|
||||
|
||||
error_msg = str(exc_info.value)
|
||||
assert (
|
||||
"testing missing module requires the optional dependency 'nonexistent_module_xyz'"
|
||||
in error_msg
|
||||
)
|
||||
assert "uv add nonexistent_module_xyz" in error_msg
|
||||
|
||||
def test_require_with_import_error(self):
|
||||
"""Test that ImportError is properly chained."""
|
||||
with patch("importlib.import_module") as mock_import:
|
||||
mock_import.side_effect = ImportError("Module import failed")
|
||||
|
||||
with pytest.raises(OptionalDependencyError) as exc_info:
|
||||
require("some_module", purpose="testing error handling")
|
||||
|
||||
assert isinstance(exc_info.value.__cause__, ImportError)
|
||||
assert str(exc_info.value.__cause__) == "Module import failed"
|
||||
|
||||
def test_optional_dependency_error_is_import_error(self):
|
||||
"""Test that OptionalDependencyError is a subclass of ImportError."""
|
||||
assert issubclass(OptionalDependencyError, ImportError)
|
||||
|
||||
def test_require_with_attr(self):
|
||||
"""Test requiring a specific attribute from a module."""
|
||||
loads = require("json", purpose="testing", attr="loads")
|
||||
import json
|
||||
|
||||
assert loads == json.loads
|
||||
|
||||
def test_require_with_nonexistent_attr(self):
|
||||
"""Test requiring a nonexistent attribute raises AttributeError."""
|
||||
with pytest.raises(AttributeError) as exc_info:
|
||||
require("json", purpose="testing", attr="nonexistent_attr")
|
||||
|
||||
assert "Module 'json' has no attribute 'nonexistent_attr'" in str(
|
||||
exc_info.value
|
||||
)
|
||||
|
||||
def test_require_extracts_package_name(self):
|
||||
"""Test that require correctly extracts package name from module path."""
|
||||
with pytest.raises(OptionalDependencyError) as exc_info:
|
||||
require("some.nested.module.path", purpose="testing")
|
||||
|
||||
error_msg = str(exc_info.value)
|
||||
assert "uv add some" in error_msg
|
||||
|
||||
|
||||
class TestValidateImportPath:
|
||||
"""Test the validate_import_path function."""
|
||||
|
||||
def test_validate_import_path_success(self):
|
||||
"""Test successful import of a class."""
|
||||
result = validate_import_path("json.JSONDecoder")
|
||||
import json
|
||||
|
||||
assert result == json.JSONDecoder
|
||||
|
||||
def test_validate_import_path_malformed_no_module(self):
|
||||
"""Test validation with no module path."""
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
validate_import_path("ClassName")
|
||||
|
||||
assert "import_path 'ClassName' must be of the form 'module.ClassName'" in str(
|
||||
exc_info.value
|
||||
)
|
||||
|
||||
def test_validate_import_path_empty_string(self):
|
||||
"""Test validation with empty string."""
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
validate_import_path("")
|
||||
|
||||
assert "import_path '' must be of the form 'module.ClassName'" in str(
|
||||
exc_info.value
|
||||
)
|
||||
|
||||
def test_validate_import_path_module_not_found(self):
|
||||
"""Test validation with non-existent module."""
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
validate_import_path("nonexistent_module.ClassName")
|
||||
|
||||
error_msg = str(exc_info.value)
|
||||
assert "Package 'nonexistent_module' could not be imported" in error_msg
|
||||
assert "uv add nonexistent_module" in error_msg
|
||||
|
||||
def test_validate_import_path_attribute_not_found(self):
|
||||
"""Test validation when attribute doesn't exist in module."""
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
validate_import_path("json.NonExistentClass")
|
||||
|
||||
assert "Attribute 'NonExistentClass' not found in module 'json'" in str(
|
||||
exc_info.value
|
||||
)
|
||||
|
||||
def test_validate_import_path_nested_module(self):
|
||||
"""Test validation with nested module path."""
|
||||
result = validate_import_path("unittest.mock.MagicMock")
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
assert result == MagicMock
|
||||
|
||||
def test_validate_import_path_extracts_package_name(self):
|
||||
"""Test that package name is correctly extracted for error message."""
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
validate_import_path("some.nested.module.path.ClassName")
|
||||
|
||||
error_msg = str(exc_info.value)
|
||||
assert "Package 'some' could not be imported" in error_msg
|
||||
assert "uv add some" in error_msg
|
||||
|
||||
|
||||
class TestImportAndValidateDefinition:
|
||||
"""Test the import_and_validate_definition function."""
|
||||
|
||||
def test_import_and_validate_definition_success(self):
|
||||
"""Test successful import through Pydantic adapter."""
|
||||
result = import_and_validate_definition("json.JSONEncoder")
|
||||
import json
|
||||
|
||||
assert result == json.JSONEncoder
|
||||
|
||||
def test_import_and_validate_definition_with_function(self):
|
||||
"""Test importing a function instead of a class."""
|
||||
result = import_and_validate_definition("json.loads")
|
||||
import json
|
||||
|
||||
assert result == json.loads
|
||||
|
||||
def test_import_and_validate_definition_invalid(self):
|
||||
"""Test that invalid paths raise ValueError."""
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
import_and_validate_definition("InvalidPath")
|
||||
|
||||
assert "must be of the form 'module.ClassName'" in str(exc_info.value)
|
||||
|
||||
def test_import_and_validate_definition_module_error(self):
|
||||
"""Test error handling for missing modules."""
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
import_and_validate_definition("missing_package.SomeClass")
|
||||
|
||||
error_msg = str(exc_info.value)
|
||||
assert "Package 'missing_package' could not be imported" in error_msg
|
||||
assert "uv add missing_package" in error_msg
|
||||
|
||||
def test_import_and_validate_definition_attribute_error(self):
|
||||
"""Test error handling for missing attributes."""
|
||||
with pytest.raises(ValueError) as exc_info:
|
||||
import_and_validate_definition("json.MissingClass")
|
||||
|
||||
assert "Attribute 'MissingClass' not found in module 'json'" in str(
|
||||
exc_info.value
|
||||
)
|
||||
|
||||
def test_import_and_validate_definition_with_mock(self):
|
||||
"""Test that mocked modules work correctly."""
|
||||
mock_module = MagicMock()
|
||||
mock_class = MagicMock()
|
||||
mock_module.MockClass = mock_class
|
||||
|
||||
with patch.dict(sys.modules, {"mocked_module": mock_module}):
|
||||
result = import_and_validate_definition("mocked_module.MockClass")
|
||||
assert result == mock_class
|
||||
91
lib/crewai/tests/utilities/test_knowledge_planning.py
Normal file
91
lib/crewai/tests/utilities/test_knowledge_planning.py
Normal file
@@ -0,0 +1,91 @@
|
||||
"""
|
||||
Tests for verifying the integration of knowledge sources in the planning process.
|
||||
This module ensures that agent knowledge is properly included during task planning.
|
||||
"""
|
||||
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
from crewai.agent import Agent
|
||||
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
|
||||
from crewai.task import Task
|
||||
from crewai.utilities.planning_handler import CrewPlanner
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_knowledge_source():
|
||||
"""
|
||||
Create a mock knowledge source with test content.
|
||||
Returns:
|
||||
StringKnowledgeSource:
|
||||
A knowledge source containing AI-related test content
|
||||
"""
|
||||
content = """
|
||||
Important context about AI:
|
||||
1. AI systems use machine learning algorithms
|
||||
2. Neural networks are a key component
|
||||
3. Training data is essential for good performance
|
||||
"""
|
||||
return StringKnowledgeSource(content=content)
|
||||
|
||||
|
||||
@patch("crewai.rag.config.utils.get_rag_client")
|
||||
def test_knowledge_included_in_planning(mock_get_client):
|
||||
"""Test that verifies knowledge sources are properly included in planning."""
|
||||
# Mock RAG client
|
||||
mock_client = mock_get_client.return_value
|
||||
mock_client.get_or_create_collection.return_value = None
|
||||
mock_client.add_documents.return_value = None
|
||||
|
||||
# Create an agent with knowledge
|
||||
agent = Agent(
|
||||
role="AI Researcher",
|
||||
goal="Research and explain AI concepts",
|
||||
backstory="Expert in artificial intelligence",
|
||||
knowledge_sources=[
|
||||
StringKnowledgeSource(
|
||||
content="AI systems require careful training and validation."
|
||||
)
|
||||
],
|
||||
)
|
||||
|
||||
# Create a task for the agent
|
||||
task = Task(
|
||||
description="Explain the basics of AI systems",
|
||||
expected_output="A clear explanation of AI fundamentals",
|
||||
agent=agent,
|
||||
)
|
||||
|
||||
# Create a crew planner
|
||||
planner = CrewPlanner([task], None)
|
||||
|
||||
# Get the task summary
|
||||
task_summary = planner._create_tasks_summary()
|
||||
|
||||
# Verify that knowledge is included in planning when present
|
||||
assert "AI systems require careful training" in task_summary, (
|
||||
"Knowledge content should be present in task summary when knowledge exists"
|
||||
)
|
||||
assert '"agent_knowledge"' in task_summary, (
|
||||
"agent_knowledge field should be present in task summary when knowledge exists"
|
||||
)
|
||||
|
||||
# Verify that knowledge is properly formatted
|
||||
assert isinstance(task.agent.knowledge_sources, list), (
|
||||
"Knowledge sources should be stored in a list"
|
||||
)
|
||||
assert len(task.agent.knowledge_sources) > 0, (
|
||||
"At least one knowledge source should be present"
|
||||
)
|
||||
assert task.agent.knowledge_sources[0].content in task_summary, (
|
||||
"Knowledge source content should be included in task summary"
|
||||
)
|
||||
|
||||
# Verify that other expected components are still present
|
||||
assert task.description in task_summary, (
|
||||
"Task description should be present in task summary"
|
||||
)
|
||||
assert task.expected_output in task_summary, (
|
||||
"Expected output should be present in task summary"
|
||||
)
|
||||
assert agent.role in task_summary, "Agent role should be present in task summary"
|
||||
114
lib/crewai/tests/utilities/test_llm_utils.py
Normal file
114
lib/crewai/tests/utilities/test_llm_utils.py
Normal file
@@ -0,0 +1,114 @@
|
||||
import os
|
||||
from unittest.mock import patch
|
||||
|
||||
from crewai.llm import LLM
|
||||
from crewai.llms.base_llm import BaseLLM
|
||||
from crewai.utilities.llm_utils import create_llm
|
||||
import pytest
|
||||
|
||||
|
||||
try:
|
||||
from litellm.exceptions import BadRequestError
|
||||
except ImportError:
|
||||
BadRequestError = Exception
|
||||
|
||||
|
||||
def test_create_llm_with_llm_instance():
|
||||
existing_llm = LLM(model="gpt-4o")
|
||||
llm = create_llm(llm_value=existing_llm)
|
||||
assert llm is existing_llm
|
||||
|
||||
|
||||
def test_create_llm_with_valid_model_string():
|
||||
llm = create_llm(llm_value="gpt-4o")
|
||||
assert isinstance(llm, BaseLLM)
|
||||
assert llm.model == "gpt-4o"
|
||||
|
||||
|
||||
def test_create_llm_with_invalid_model_string():
|
||||
# For invalid model strings, create_llm succeeds but call() fails with API error
|
||||
llm = create_llm(llm_value="invalid-model")
|
||||
assert llm is not None
|
||||
assert isinstance(llm, BaseLLM)
|
||||
|
||||
# The error should occur when making the actual API call
|
||||
# We expect some kind of API error (NotFoundError, etc.)
|
||||
with pytest.raises(Exception): # noqa: B017
|
||||
llm.call(messages=[{"role": "user", "content": "Hello, world!"}])
|
||||
|
||||
|
||||
def test_create_llm_with_unknown_object_missing_attributes():
|
||||
class UnknownObject:
|
||||
pass
|
||||
|
||||
unknown_obj = UnknownObject()
|
||||
llm = create_llm(llm_value=unknown_obj)
|
||||
|
||||
# Should succeed because str(unknown_obj) provides a model name
|
||||
assert llm is not None
|
||||
assert isinstance(llm, BaseLLM)
|
||||
|
||||
|
||||
def test_create_llm_with_none_uses_default_model():
|
||||
with patch.dict(os.environ, {"OPENAI_API_KEY": "fake-key"}, clear=True):
|
||||
with patch("crewai.utilities.llm_utils.DEFAULT_LLM_MODEL", "gpt-4o-mini"):
|
||||
llm = create_llm(llm_value=None)
|
||||
assert isinstance(llm, BaseLLM)
|
||||
assert llm.model == "gpt-4o-mini"
|
||||
|
||||
|
||||
def test_create_llm_with_unknown_object():
|
||||
class UnknownObject:
|
||||
model_name = "gpt-4o"
|
||||
temperature = 0.7
|
||||
max_tokens = 1500
|
||||
|
||||
unknown_obj = UnknownObject()
|
||||
llm = create_llm(llm_value=unknown_obj)
|
||||
assert isinstance(llm, BaseLLM)
|
||||
assert llm.model == "gpt-4o"
|
||||
assert llm.temperature == 0.7
|
||||
assert llm.max_tokens == 1500
|
||||
|
||||
|
||||
def test_create_llm_from_env_with_unaccepted_attributes():
|
||||
with patch.dict(
|
||||
os.environ,
|
||||
{
|
||||
"OPENAI_MODEL_NAME": "gpt-3.5-turbo",
|
||||
"OPENAI_API_KEY": "fake-key",
|
||||
"AWS_ACCESS_KEY_ID": "fake-access-key",
|
||||
"AWS_SECRET_ACCESS_KEY": "fake-secret-key",
|
||||
"AWS_REGION_NAME": "us-west-2",
|
||||
},
|
||||
):
|
||||
llm = create_llm(llm_value=None)
|
||||
assert isinstance(llm, BaseLLM)
|
||||
assert llm.model == "gpt-3.5-turbo"
|
||||
assert not hasattr(llm, "AWS_ACCESS_KEY_ID")
|
||||
assert not hasattr(llm, "AWS_SECRET_ACCESS_KEY")
|
||||
assert not hasattr(llm, "AWS_REGION_NAME")
|
||||
|
||||
|
||||
def test_create_llm_with_partial_attributes():
|
||||
class PartialAttributes:
|
||||
model_name = "gpt-4o"
|
||||
# temperature is missing
|
||||
|
||||
obj = PartialAttributes()
|
||||
llm = create_llm(llm_value=obj)
|
||||
assert isinstance(llm, BaseLLM)
|
||||
assert llm.model == "gpt-4o"
|
||||
assert llm.temperature is None # Should handle missing attributes gracefully
|
||||
|
||||
|
||||
def test_create_llm_with_invalid_type():
|
||||
# For integers, create_llm succeeds because str(42) becomes "42"
|
||||
llm = create_llm(llm_value=42)
|
||||
assert llm is not None
|
||||
assert isinstance(llm, BaseLLM)
|
||||
assert llm.model == "42"
|
||||
|
||||
# The error should occur when making the actual API call
|
||||
with pytest.raises(Exception): # noqa: B017
|
||||
llm.call(messages=[{"role": "user", "content": "Hello, world!"}])
|
||||
179
lib/crewai/tests/utilities/test_planning_handler.py
Normal file
179
lib/crewai/tests/utilities/test_planning_handler.py
Normal file
@@ -0,0 +1,179 @@
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
from crewai.agent import Agent
|
||||
from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
|
||||
from crewai.task import Task
|
||||
from crewai.tasks.task_output import TaskOutput
|
||||
from crewai.tools.base_tool import BaseTool
|
||||
from crewai.utilities.planning_handler import (
|
||||
CrewPlanner,
|
||||
PlannerTaskPydanticOutput,
|
||||
PlanPerTask,
|
||||
)
|
||||
|
||||
|
||||
class InternalCrewPlanner:
|
||||
@pytest.fixture
|
||||
def crew_planner(self):
|
||||
tasks = [
|
||||
Task(
|
||||
description="Task 1",
|
||||
expected_output="Output 1",
|
||||
agent=Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1"),
|
||||
),
|
||||
Task(
|
||||
description="Task 2",
|
||||
expected_output="Output 2",
|
||||
agent=Agent(role="Agent 2", goal="Goal 2", backstory="Backstory 2"),
|
||||
),
|
||||
Task(
|
||||
description="Task 3",
|
||||
expected_output="Output 3",
|
||||
agent=Agent(role="Agent 3", goal="Goal 3", backstory="Backstory 3"),
|
||||
),
|
||||
]
|
||||
return CrewPlanner(tasks, None)
|
||||
|
||||
@pytest.fixture
|
||||
def crew_planner_different_llm(self):
|
||||
tasks = [
|
||||
Task(
|
||||
description="Task 1",
|
||||
expected_output="Output 1",
|
||||
agent=Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1"),
|
||||
)
|
||||
]
|
||||
planning_agent_llm = "gpt-3.5-turbo"
|
||||
return CrewPlanner(tasks, planning_agent_llm)
|
||||
|
||||
def test_handle_crew_planning(self, crew_planner):
|
||||
list_of_plans_per_task = [
|
||||
PlanPerTask(task="Task1", plan="Plan 1"),
|
||||
PlanPerTask(task="Task2", plan="Plan 2"),
|
||||
PlanPerTask(task="Task3", plan="Plan 3"),
|
||||
]
|
||||
with patch.object(Task, "execute_sync") as execute:
|
||||
execute.return_value = TaskOutput(
|
||||
description="Description",
|
||||
agent="agent",
|
||||
pydantic=PlannerTaskPydanticOutput(
|
||||
list_of_plans_per_task=list_of_plans_per_task
|
||||
),
|
||||
)
|
||||
result = crew_planner._handle_crew_planning()
|
||||
assert crew_planner.planning_agent_llm == "gpt-4o-mini"
|
||||
assert isinstance(result, PlannerTaskPydanticOutput)
|
||||
assert len(result.list_of_plans_per_task) == len(crew_planner.tasks)
|
||||
execute.assert_called_once()
|
||||
|
||||
def test_create_planning_agent(self, crew_planner):
|
||||
agent = crew_planner._create_planning_agent()
|
||||
assert isinstance(agent, Agent)
|
||||
assert agent.role == "Task Execution Planner"
|
||||
|
||||
def test_create_planner_task(self, crew_planner):
|
||||
planning_agent = Agent(
|
||||
role="Planning Agent",
|
||||
goal="Plan Step by Step Plan",
|
||||
backstory="Master in Planning",
|
||||
)
|
||||
tasks_summary = "Summary of tasks"
|
||||
task = crew_planner._create_planner_task(planning_agent, tasks_summary)
|
||||
|
||||
assert isinstance(task, Task)
|
||||
assert task.description.startswith("Based on these tasks summary")
|
||||
assert task.agent == planning_agent
|
||||
assert (
|
||||
task.expected_output
|
||||
== "Step by step plan on how the agents can execute their tasks using the available tools with mastery"
|
||||
)
|
||||
|
||||
def test_create_tasks_summary(self, crew_planner):
|
||||
tasks_summary = crew_planner._create_tasks_summary()
|
||||
assert isinstance(tasks_summary, str)
|
||||
assert tasks_summary.startswith("\n Task Number 1 - Task 1")
|
||||
assert '"agent_tools": "agent has no tools"' in tasks_summary
|
||||
# Knowledge field should not be present when empty
|
||||
assert '"agent_knowledge"' not in tasks_summary
|
||||
|
||||
@patch("crewai.knowledge.storage.knowledge_storage.chromadb")
|
||||
def test_create_tasks_summary_with_knowledge_and_tools(self, mock_chroma):
|
||||
"""Test task summary generation with both knowledge and tools present."""
|
||||
# Mock ChromaDB collection
|
||||
mock_collection = mock_chroma.return_value.get_or_create_collection.return_value
|
||||
mock_collection.add.return_value = None
|
||||
|
||||
# Create mock tools with proper string descriptions and structured tool support
|
||||
class MockTool(BaseTool):
|
||||
name: str
|
||||
description: str
|
||||
|
||||
def __init__(self, name: str, description: str):
|
||||
tool_data = {"name": name, "description": description}
|
||||
super().__init__(**tool_data)
|
||||
|
||||
def __str__(self):
|
||||
return self.name
|
||||
|
||||
def __repr__(self):
|
||||
return self.name
|
||||
|
||||
def to_structured_tool(self):
|
||||
return self
|
||||
|
||||
def _run(self, *args, **kwargs):
|
||||
pass
|
||||
|
||||
def _generate_description(self) -> str:
|
||||
"""Override _generate_description to avoid args_schema handling."""
|
||||
return self.description
|
||||
|
||||
tool1 = MockTool("tool1", "Tool 1 description")
|
||||
tool2 = MockTool("tool2", "Tool 2 description")
|
||||
|
||||
# Create a task with knowledge and tools
|
||||
task = Task(
|
||||
description="Task with knowledge and tools",
|
||||
expected_output="Expected output",
|
||||
agent=Agent(
|
||||
role="Test Agent",
|
||||
goal="Test Goal",
|
||||
backstory="Test Backstory",
|
||||
tools=[tool1, tool2],
|
||||
knowledge_sources=[
|
||||
StringKnowledgeSource(content="Test knowledge content")
|
||||
],
|
||||
),
|
||||
)
|
||||
|
||||
# Create planner with the new task
|
||||
planner = CrewPlanner([task], None)
|
||||
tasks_summary = planner._create_tasks_summary()
|
||||
|
||||
# Verify task summary content
|
||||
assert isinstance(tasks_summary, str)
|
||||
assert task.description in tasks_summary
|
||||
assert task.expected_output in tasks_summary
|
||||
assert '"agent_tools": [tool1, tool2]' in tasks_summary
|
||||
assert '"agent_knowledge": "[\\"Test knowledge content\\"]"' in tasks_summary
|
||||
assert task.agent.role in tasks_summary
|
||||
assert task.agent.goal in tasks_summary
|
||||
|
||||
def test_handle_crew_planning_different_llm(self, crew_planner_different_llm):
|
||||
with patch.object(Task, "execute_sync") as execute:
|
||||
execute.return_value = TaskOutput(
|
||||
description="Description",
|
||||
agent="agent",
|
||||
pydantic=PlannerTaskPydanticOutput(
|
||||
list_of_plans_per_task=[PlanPerTask(task="Task1", plan="Plan 1")]
|
||||
),
|
||||
)
|
||||
result = crew_planner_different_llm._handle_crew_planning()
|
||||
|
||||
assert crew_planner_different_llm.planning_agent_llm == "gpt-3.5-turbo"
|
||||
assert isinstance(result, PlannerTaskPydanticOutput)
|
||||
assert len(result.list_of_plans_per_task) == len(
|
||||
crew_planner_different_llm.tasks
|
||||
)
|
||||
execute.assert_called_once()
|
||||
94
lib/crewai/tests/utilities/test_pydantic_schema_parser.py
Normal file
94
lib/crewai/tests/utilities/test_pydantic_schema_parser.py
Normal file
@@ -0,0 +1,94 @@
|
||||
from typing import Any, Dict, List, Optional, Set, Tuple, Union
|
||||
|
||||
import pytest
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
|
||||
|
||||
|
||||
def test_simple_model():
|
||||
class SimpleModel(BaseModel):
|
||||
field1: int
|
||||
field2: str
|
||||
|
||||
parser = PydanticSchemaParser(model=SimpleModel)
|
||||
schema = parser.get_schema()
|
||||
|
||||
expected_schema = """{
|
||||
field1: int,
|
||||
field2: str
|
||||
}"""
|
||||
assert schema.strip() == expected_schema.strip()
|
||||
|
||||
|
||||
def test_nested_model():
|
||||
class NestedModel(BaseModel):
|
||||
nested_field: int
|
||||
|
||||
class ParentModel(BaseModel):
|
||||
parent_field: str
|
||||
nested: NestedModel
|
||||
|
||||
parser = PydanticSchemaParser(model=ParentModel)
|
||||
schema = parser.get_schema()
|
||||
|
||||
expected_schema = """{
|
||||
parent_field: str,
|
||||
nested: NestedModel
|
||||
{
|
||||
nested_field: int
|
||||
}
|
||||
}"""
|
||||
assert schema.strip() == expected_schema.strip()
|
||||
|
||||
|
||||
def test_model_with_list():
|
||||
class ListModel(BaseModel):
|
||||
list_field: List[int]
|
||||
|
||||
parser = PydanticSchemaParser(model=ListModel)
|
||||
schema = parser.get_schema()
|
||||
|
||||
expected_schema = """{
|
||||
list_field: List[int]
|
||||
}"""
|
||||
assert schema.strip() == expected_schema.strip()
|
||||
|
||||
|
||||
def test_model_with_optional_field():
|
||||
class OptionalModel(BaseModel):
|
||||
optional_field: Optional[str]
|
||||
|
||||
parser = PydanticSchemaParser(model=OptionalModel)
|
||||
schema = parser.get_schema()
|
||||
|
||||
expected_schema = """{
|
||||
optional_field: Optional[str]
|
||||
}"""
|
||||
assert schema.strip() == expected_schema.strip()
|
||||
|
||||
|
||||
def test_model_with_union():
|
||||
class UnionModel(BaseModel):
|
||||
union_field: Union[int, str]
|
||||
|
||||
parser = PydanticSchemaParser(model=UnionModel)
|
||||
schema = parser.get_schema()
|
||||
|
||||
expected_schema = """{
|
||||
union_field: Union[int, str]
|
||||
}"""
|
||||
assert schema.strip() == expected_schema.strip()
|
||||
|
||||
|
||||
def test_model_with_dict():
|
||||
class DictModel(BaseModel):
|
||||
dict_field: Dict[str, int]
|
||||
|
||||
parser = PydanticSchemaParser(model=DictModel)
|
||||
schema = parser.get_schema()
|
||||
|
||||
expected_schema = """{
|
||||
dict_field: Dict[str, int]
|
||||
}"""
|
||||
assert schema.strip() == expected_schema.strip()
|
||||
150
lib/crewai/tests/utilities/test_serialization.py
Normal file
150
lib/crewai/tests/utilities/test_serialization.py
Normal file
@@ -0,0 +1,150 @@
|
||||
from datetime import date, datetime
|
||||
from typing import List
|
||||
|
||||
import pytest
|
||||
from crewai.utilities.serialization import to_serializable, to_string
|
||||
from pydantic import BaseModel
|
||||
|
||||
|
||||
class Address(BaseModel):
|
||||
street: str
|
||||
city: str
|
||||
country: str
|
||||
|
||||
|
||||
class Person(BaseModel):
|
||||
name: str
|
||||
age: int
|
||||
address: Address
|
||||
birthday: date
|
||||
skills: List[str]
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"test_input,expected",
|
||||
[
|
||||
({"text": "hello world"}, {"text": "hello world"}),
|
||||
({"number": 42}, {"number": 42}),
|
||||
({"decimal": 3.14}, {"decimal": 3.14}),
|
||||
({"flag": True}, {"flag": True}),
|
||||
({"empty": None}, {"empty": None}),
|
||||
({"list": [1, 2, 3]}, {"list": [1, 2, 3]}),
|
||||
({"tuple": (1, 2, 3)}, {"tuple": [1, 2, 3]}),
|
||||
({"set": {1, 2, 3}}, {"set": [1, 2, 3]}),
|
||||
({"nested": [1, [2, 3], {4, 5}]}, {"nested": [1, [2, 3], [4, 5]]}),
|
||||
],
|
||||
)
|
||||
def test_basic_serialization(test_input, expected):
|
||||
result = to_serializable(test_input)
|
||||
assert result == expected
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"input_date,expected",
|
||||
[
|
||||
(date(2024, 1, 1), "2024-01-01"),
|
||||
(datetime(2024, 1, 1, 12, 30), "2024-01-01T12:30:00"),
|
||||
],
|
||||
)
|
||||
def test_temporal_serialization(input_date, expected):
|
||||
result = to_serializable({"date": input_date})
|
||||
assert result["date"] == expected
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"key,value,expected_key_type",
|
||||
[
|
||||
(("tuple", "key"), "value", str),
|
||||
(None, "value", str),
|
||||
(123, "value", str),
|
||||
("normal", "value", str),
|
||||
],
|
||||
)
|
||||
def test_dictionary_key_serialization(key, value, expected_key_type):
|
||||
result = to_serializable({key: value})
|
||||
assert len(result) == 1
|
||||
result_key = next(iter(result.keys()))
|
||||
assert isinstance(result_key, expected_key_type)
|
||||
assert result[result_key] == value
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"callable_obj,expected_in_result",
|
||||
[
|
||||
(lambda x: x * 2, "lambda"),
|
||||
(str.upper, "upper"),
|
||||
],
|
||||
)
|
||||
def test_callable_serialization(callable_obj, expected_in_result):
|
||||
result = to_serializable({"func": callable_obj})
|
||||
assert isinstance(result["func"], str)
|
||||
assert expected_in_result in result["func"].lower()
|
||||
|
||||
|
||||
def test_pydantic_model_serialization():
|
||||
address = Address(street="123 Main St", city="Tech City", country="Pythonia")
|
||||
|
||||
person = Person(
|
||||
name="John Doe",
|
||||
age=30,
|
||||
address=address,
|
||||
birthday=date(1994, 1, 1),
|
||||
skills=["Python", "Testing"],
|
||||
)
|
||||
|
||||
data = {
|
||||
"single_model": address,
|
||||
"nested_model": person,
|
||||
"model_list": [address, address],
|
||||
"model_dict": {"home": address},
|
||||
}
|
||||
|
||||
result = to_serializable(data)
|
||||
assert (
|
||||
to_string(result)
|
||||
== '{"single_model": {"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}, "nested_model": {"name": "John Doe", "age": 30, "address": {"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}, "birthday": "1994-01-01", "skills": ["Python", "Testing"]}, "model_list": [{"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}, {"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}], "model_dict": {"home": {"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}}}'
|
||||
)
|
||||
|
||||
|
||||
def test_depth_limit():
|
||||
"""Test max depth handling with a deeply nested structure"""
|
||||
|
||||
def create_nested(depth):
|
||||
if depth == 0:
|
||||
return "value"
|
||||
return {"next": create_nested(depth - 1)}
|
||||
|
||||
deep_structure = create_nested(10)
|
||||
result = to_serializable(deep_structure)
|
||||
|
||||
assert result == {
|
||||
"next": {
|
||||
"next": {
|
||||
"next": {
|
||||
"next": {
|
||||
"next": "{'next': {'next': {'next': {'next': {'next': 'value'}}}}}"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
def test_exclude_keys():
|
||||
result = to_serializable({"key1": "value1", "key2": "value2"}, exclude={"key1"})
|
||||
assert result == {"key2": "value2"}
|
||||
|
||||
model = Person(
|
||||
name="John Doe",
|
||||
age=30,
|
||||
address=Address(street="123 Main St", city="Tech City", country="Pythonia"),
|
||||
birthday=date(1994, 1, 1),
|
||||
skills=["Python", "Testing"],
|
||||
)
|
||||
result = to_serializable(model, exclude={"address"})
|
||||
assert result == {
|
||||
"name": "John Doe",
|
||||
"age": 30,
|
||||
"birthday": "1994-01-01",
|
||||
"skills": ["Python", "Testing"],
|
||||
}
|
||||
186
lib/crewai/tests/utilities/test_string_utils.py
Normal file
186
lib/crewai/tests/utilities/test_string_utils.py
Normal file
@@ -0,0 +1,186 @@
|
||||
from typing import Any, Dict, List, Union
|
||||
|
||||
import pytest
|
||||
from crewai.utilities.string_utils import interpolate_only
|
||||
|
||||
|
||||
class TestInterpolateOnly:
|
||||
"""Tests for the interpolate_only function in string_utils.py."""
|
||||
|
||||
def test_basic_variable_interpolation(self):
|
||||
"""Test basic variable interpolation works correctly."""
|
||||
template = "Hello, {name}! Welcome to {company}."
|
||||
inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
|
||||
"name": "Alice",
|
||||
"company": "CrewAI",
|
||||
}
|
||||
|
||||
result = interpolate_only(template, inputs)
|
||||
|
||||
assert result == "Hello, Alice! Welcome to CrewAI."
|
||||
|
||||
def test_multiple_occurrences_of_same_variable(self):
|
||||
"""Test that multiple occurrences of the same variable are replaced."""
|
||||
template = "{name} is using {name}'s account."
|
||||
inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
|
||||
"name": "Bob"
|
||||
}
|
||||
|
||||
result = interpolate_only(template, inputs)
|
||||
|
||||
assert result == "Bob is using Bob's account."
|
||||
|
||||
def test_json_structure_preservation(self):
|
||||
"""Test that JSON structures are preserved and not interpolated incorrectly."""
|
||||
template = """
|
||||
Instructions for {agent}:
|
||||
|
||||
Please return the following object:
|
||||
|
||||
{"name": "person's name", "age": 25, "skills": ["coding", "testing"]}
|
||||
"""
|
||||
inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
|
||||
"agent": "DevAgent"
|
||||
}
|
||||
|
||||
result = interpolate_only(template, inputs)
|
||||
|
||||
assert "Instructions for DevAgent:" in result
|
||||
assert (
|
||||
'{"name": "person\'s name", "age": 25, "skills": ["coding", "testing"]}'
|
||||
in result
|
||||
)
|
||||
|
||||
def test_complex_nested_json(self):
|
||||
"""Test with complex JSON structures containing curly braces."""
|
||||
template = """
|
||||
{agent} needs to process:
|
||||
{
|
||||
"config": {
|
||||
"nested": {
|
||||
"value": 42
|
||||
},
|
||||
"arrays": [1, 2, {"inner": "value"}]
|
||||
}
|
||||
}
|
||||
"""
|
||||
inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
|
||||
"agent": "DataProcessor"
|
||||
}
|
||||
|
||||
result = interpolate_only(template, inputs)
|
||||
|
||||
assert "DataProcessor needs to process:" in result
|
||||
assert '"nested": {' in result
|
||||
assert '"value": 42' in result
|
||||
assert '[1, 2, {"inner": "value"}]' in result
|
||||
|
||||
def test_missing_variable(self):
|
||||
"""Test that an error is raised when a required variable is missing."""
|
||||
template = "Hello, {name}!"
|
||||
inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
|
||||
"not_name": "Alice"
|
||||
}
|
||||
|
||||
with pytest.raises(KeyError) as excinfo:
|
||||
interpolate_only(template, inputs)
|
||||
|
||||
assert "template variable" in str(excinfo.value).lower()
|
||||
assert "name" in str(excinfo.value)
|
||||
|
||||
def test_invalid_input_types(self):
|
||||
"""Test that an error is raised with invalid input types."""
|
||||
template = "Hello, {name}!"
|
||||
# Using Any for this test since we're intentionally testing an invalid type
|
||||
inputs: Dict[str, Any] = {"name": object()} # Object is not a valid input type
|
||||
|
||||
with pytest.raises(ValueError) as excinfo:
|
||||
interpolate_only(template, inputs)
|
||||
|
||||
assert "unsupported type" in str(excinfo.value).lower()
|
||||
|
||||
def test_empty_input_string(self):
|
||||
"""Test handling of empty or None input string."""
|
||||
inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
|
||||
"name": "Alice"
|
||||
}
|
||||
|
||||
assert interpolate_only("", inputs) == ""
|
||||
assert interpolate_only(None, inputs) == ""
|
||||
|
||||
def test_no_variables_in_template(self):
|
||||
"""Test a template with no variables to replace."""
|
||||
template = "This is a static string with no variables."
|
||||
inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
|
||||
"name": "Alice"
|
||||
}
|
||||
|
||||
result = interpolate_only(template, inputs)
|
||||
|
||||
assert result == template
|
||||
|
||||
def test_variable_name_starting_with_underscore(self):
|
||||
"""Test variables starting with underscore are replaced correctly."""
|
||||
template = "Variable: {_special_var}"
|
||||
inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
|
||||
"_special_var": "Special Value"
|
||||
}
|
||||
|
||||
result = interpolate_only(template, inputs)
|
||||
|
||||
assert result == "Variable: Special Value"
|
||||
|
||||
def test_preserves_non_matching_braces(self):
|
||||
"""Test that non-matching braces patterns are preserved."""
|
||||
template = (
|
||||
"This {123} and {!var} should not be replaced but {valid_var} should."
|
||||
)
|
||||
inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
|
||||
"valid_var": "works"
|
||||
}
|
||||
|
||||
result = interpolate_only(template, inputs)
|
||||
|
||||
assert (
|
||||
result == "This {123} and {!var} should not be replaced but works should."
|
||||
)
|
||||
|
||||
def test_complex_mixed_scenario(self):
|
||||
"""Test a complex scenario with both valid variables and JSON structures."""
|
||||
template = """
|
||||
{agent_name} is working on task {task_id}.
|
||||
|
||||
Instructions:
|
||||
1. Process the data
|
||||
2. Return results as:
|
||||
|
||||
{
|
||||
"taskId": "{task_id}",
|
||||
"results": {
|
||||
"processed_by": "agent_name",
|
||||
"status": "complete",
|
||||
"values": [1, 2, 3]
|
||||
}
|
||||
}
|
||||
"""
|
||||
inputs: Dict[str, Union[str, int, float, Dict[str, Any], List[Any]]] = {
|
||||
"agent_name": "AnalyticsAgent",
|
||||
"task_id": "T-12345",
|
||||
}
|
||||
|
||||
result = interpolate_only(template, inputs)
|
||||
|
||||
assert "AnalyticsAgent is working on task T-12345" in result
|
||||
assert '"taskId": "T-12345"' in result
|
||||
assert '"processed_by": "agent_name"' in result # This shouldn't be replaced
|
||||
assert '"values": [1, 2, 3]' in result
|
||||
|
||||
def test_empty_inputs_dictionary(self):
|
||||
"""Test that an error is raised with empty inputs dictionary."""
|
||||
template = "Hello, {name}!"
|
||||
inputs: Dict[str, Any] = {}
|
||||
|
||||
with pytest.raises(ValueError) as excinfo:
|
||||
interpolate_only(template, inputs)
|
||||
|
||||
assert "inputs dictionary cannot be empty" in str(excinfo.value).lower()
|
||||
97
lib/crewai/tests/utilities/test_training_converter.py
Normal file
97
lib/crewai/tests/utilities/test_training_converter.py
Normal file
@@ -0,0 +1,97 @@
|
||||
from typing import List
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
from crewai.utilities.converter import ConverterError
|
||||
from crewai.utilities.training_converter import TrainingConverter
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class TestModel(BaseModel):
|
||||
string_field: str = Field(description="A simple string field")
|
||||
list_field: List[str] = Field(description="A list of strings")
|
||||
number_field: float = Field(description="A number field")
|
||||
|
||||
|
||||
class TestTrainingConverter:
|
||||
def setup_method(self):
|
||||
self.llm_mock = MagicMock()
|
||||
self.test_text = "Sample text for evaluation"
|
||||
self.test_instructions = "Convert to JSON format"
|
||||
self.converter = TrainingConverter(
|
||||
llm=self.llm_mock,
|
||||
text=self.test_text,
|
||||
model=TestModel,
|
||||
instructions=self.test_instructions,
|
||||
)
|
||||
|
||||
@patch("crewai.utilities.converter.Converter.to_pydantic")
|
||||
def test_fallback_to_field_by_field(self, parent_to_pydantic_mock):
|
||||
parent_to_pydantic_mock.side_effect = ConverterError(
|
||||
"Failed to convert directly"
|
||||
)
|
||||
|
||||
llm_responses = {
|
||||
"string_field": "test string value",
|
||||
"list_field": "- item1\n- item2\n- item3",
|
||||
"number_field": "8.5",
|
||||
}
|
||||
|
||||
def llm_side_effect(messages):
|
||||
prompt = messages[1]["content"]
|
||||
if "string_field" in prompt:
|
||||
return llm_responses["string_field"]
|
||||
if "list_field" in prompt:
|
||||
return llm_responses["list_field"]
|
||||
if "number_field" in prompt:
|
||||
return llm_responses["number_field"]
|
||||
return "unknown field"
|
||||
|
||||
self.llm_mock.call.side_effect = llm_side_effect
|
||||
|
||||
result = self.converter.to_pydantic()
|
||||
|
||||
assert result.string_field == "test string value"
|
||||
assert result.list_field == ["item1", "item2", "item3"]
|
||||
assert result.number_field == 8.5
|
||||
|
||||
parent_to_pydantic_mock.assert_called_once()
|
||||
assert self.llm_mock.call.call_count == 3
|
||||
|
||||
def test_ask_llm_for_field(self):
|
||||
field_name = "test_field"
|
||||
field_description = "This is a test field description"
|
||||
expected_response = "Test response"
|
||||
self.llm_mock.call.return_value = expected_response
|
||||
response = self.converter._ask_llm_for_field(field_name, field_description)
|
||||
|
||||
assert response == expected_response
|
||||
self.llm_mock.call.assert_called_once()
|
||||
|
||||
call_args = self.llm_mock.call.call_args[0][0]
|
||||
assert call_args[0]["role"] == "system"
|
||||
assert f"Extract the {field_name}" in call_args[0]["content"]
|
||||
assert call_args[1]["role"] == "user"
|
||||
assert field_name in call_args[1]["content"]
|
||||
assert field_description in call_args[1]["content"]
|
||||
|
||||
def test_process_field_value_string(self):
|
||||
response = " This is a string with extra whitespace "
|
||||
result = self.converter._process_field_value(response, str)
|
||||
assert result == "This is a string with extra whitespace"
|
||||
|
||||
def test_process_field_value_list_with_bullet_points(self):
|
||||
response = "- Item 1\n- Item 2\n- Item 3"
|
||||
result = self.converter._process_field_value(response, List[str])
|
||||
assert result == ["Item 1", "Item 2", "Item 3"]
|
||||
|
||||
def test_process_field_value_list_with_json(self):
|
||||
response = '["Item 1", "Item 2", "Item 3"]'
|
||||
with patch("crewai.utilities.training_converter.json.loads") as json_mock:
|
||||
json_mock.return_value = ["Item 1", "Item 2", "Item 3"]
|
||||
result = self.converter._process_field_value(response, List[str])
|
||||
assert result == ["Item 1", "Item 2", "Item 3"]
|
||||
|
||||
def test_process_field_value_float(self):
|
||||
response = "The quality score is 8.5 out of 10"
|
||||
result = self.converter._process_field_value(response, float)
|
||||
assert result == 8.5
|
||||
55
lib/crewai/tests/utilities/test_training_handler.py
Normal file
55
lib/crewai/tests/utilities/test_training_handler.py
Normal file
@@ -0,0 +1,55 @@
|
||||
import os
|
||||
import tempfile
|
||||
import unittest
|
||||
|
||||
from crewai.utilities.training_handler import CrewTrainingHandler
|
||||
|
||||
|
||||
class InternalCrewTrainingHandler(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.temp_file = tempfile.NamedTemporaryFile(suffix=".pkl", delete=False)
|
||||
self.temp_file.close()
|
||||
self.handler = CrewTrainingHandler(self.temp_file.name)
|
||||
|
||||
def tearDown(self):
|
||||
if os.path.exists(self.temp_file.name):
|
||||
os.remove(self.temp_file.name)
|
||||
del self.handler
|
||||
|
||||
def test_save_trained_data(self):
|
||||
agent_id = "agent1"
|
||||
trained_data = {"param1": 1, "param2": 2}
|
||||
self.handler.save_trained_data(agent_id, trained_data)
|
||||
|
||||
# Assert that the trained data is saved correctly
|
||||
data = self.handler.load()
|
||||
assert data[agent_id] == trained_data
|
||||
|
||||
def test_append_existing_agent(self):
|
||||
agent_id = "agent1"
|
||||
initial_iteration = 0
|
||||
initial_data = {"param1": 1, "param2": 2}
|
||||
|
||||
self.handler.append(initial_iteration, agent_id, initial_data)
|
||||
|
||||
train_iteration = 1
|
||||
new_data = {"param3": 3, "param4": 4}
|
||||
self.handler.append(train_iteration, agent_id, new_data)
|
||||
|
||||
# Assert that the new data is appended correctly to the existing agent
|
||||
data = self.handler.load()
|
||||
assert agent_id in data
|
||||
assert initial_iteration in data[agent_id]
|
||||
assert train_iteration in data[agent_id]
|
||||
assert data[agent_id][initial_iteration] == initial_data
|
||||
assert data[agent_id][train_iteration] == new_data
|
||||
|
||||
def test_append_new_agent(self):
|
||||
train_iteration = 1
|
||||
agent_id = "agent2"
|
||||
new_data = {"param5": 5, "param6": 6}
|
||||
self.handler.append(train_iteration, agent_id, new_data)
|
||||
|
||||
# Assert that the new agent and data are appended correctly
|
||||
data = self.handler.load()
|
||||
assert data[agent_id][train_iteration] == new_data
|
||||
Reference in New Issue
Block a user