andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 00:28:31 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Release/v1.0.0 (#3618)

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

* feat: add app attributes to Agent

* feat: add actions attribute to Agent

* chore: resolve linter issues

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

* fix: remove unnecessary print

* feat: logging error when CrewaiPlatformTools fails

* chore: export CrewaiPlatformTools directly from crewai_tools

* style: resolver linter issues

* test: fix broken tests

* style: solve linter issues

* fix: fix broken test

* feat: monorepo restructure and test/ci updates

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

* chore: update python version to 3.13 and package metadata

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

* feat: add crewai-tools workspace structure

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

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

* feat: configure crewai-tools workspace package with dependencies

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

* chore: update lockfile

* fix: don't allow tool tests yet

* fix: comment out extra pytest flags for now

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

* fix: resolve dependency conflicts and test issues

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

* chore: update CI workflows and docs for monorepo structure

* chore: update CI workflows and docs for monorepo structure

* fix: actions syntax

* chore: ci publish and pin versions

* fix: add permission to action

* chore: bump version to 1.0.0a1 across all packages

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

* WIP: v1 docs (#3626)

(cherry picked from commit d46e20fa09bcd2f5916282f5553ddeb7183bd92c)

* docs: parity for all translations

* docs: full name of acronym AMP

* docs: fix lingering unused code

* docs: expand contextual options in docs.json

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

* chore: apply linting fixes to crewai-tools

* feat: add required env var validation for brightdata

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

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

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

* feat: bump version to 1.0.0a2

* Lorenze/native inference sdks (#3619)

* ruff linted

* using native sdks with litellm fallback

* drop exa

* drop print on completion

* Refactor LLM and utility functions for type consistency

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

* fix agent_tests

* fix litellm tests and usagemetrics fix

* drop print

* Refactor LLM event handling and improve test coverage

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

* fix test_converter

* fixed tests/agents/test_agent.py

* Refactor LLM context length exception handling and improve provider integration

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

* Enhance LLM context window handling across providers

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

* fix test agent again

* fix test agent

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

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

* chore: update dependencies and improve context management

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

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

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

* linter

* linted

* revert constants

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

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

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

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

* fixed test

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

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

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

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

* feat: add base devtooling

* fix: ensure dep refs are updated for devtools

* fix: allow pre-release

* feat: allow release after tag

* feat: bump versions to 1.0.0a3 

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

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

* fix: allow failed pypi publish

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

* chore: exclude tests from ruff linting

* chore: exclude tests from GitHub Actions linter

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

* chore: add noqa for intentional print in printer utility

* fix: resolve linting errors across codebase

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

* fix: remove duplicate line and add explicit env var

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

* Update triggers docs (#3678)

* docs: introduce triggers list & triggers run command

* docs: add KO triggers docs

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

* Lorenze/bedrock llm (#3693)

* feat: add AWS Bedrock support and update dependencies

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

* using converse api

* converse

* linted

* refactor: update BedrockCompletion class to improve parameter handling

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

* feat: improve event bus thread safety and async support

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

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

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

* feat: enhance OpenAICompletion class with additional client parameters

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

* fix: correct test case for unsupported OpenAI model

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

* fix: enhance error handling in OpenAICompletion class

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

* fix: improve test for unsupported OpenAI model handling

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

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

* Lorenze/tools drop litellm (#3710)

* completely drop litellm and correctly pass config for qdrant

* feat: add support for additional embedding models in EmbeddingService

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

* fix: update collection parameter handling in CrewAIRagAdapter

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

* moved stagehand as optional dep (#3712)

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

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

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

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

* drop print statements

* test: add fixture to mock ANTHROPIC_API_KEY for tests

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

* refactor: streamline streaming message handling in AnthropicCompletion class

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

* fix streaming here too

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

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

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

* feat: enhance GeminiCompletion class with client parameter support

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

* add optional dependancies

* refactor: update test fixture to mock GOOGLE_API_KEY

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

* fix tests

* feat: enhance BedrockCompletion class with advanced features

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

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

* chore: add boto typing

* fix: use typing_extensions.Required for Python 3.10 compatibility

---------

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

* feat: azure native tests

* feat: add Azure AI Inference support and related tests

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

* feat: enhance AzureCompletion class with Azure OpenAI support

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

* refactor: convert project module to metaclass with full typing

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

* fix: enhance OpenAICompletion class base URL handling

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

* feat: enhance OpenAICompletion class with api_base support

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

* fix: improve OpenAICompletion class configuration handling

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

* drop print

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

* feat: add support for Anthropic provider and enhance logging

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

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

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

* test: update native provider fallback tests to expect ImportError

* adjust the test with the expected bevaior - raising ImportError

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

---------

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

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

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

Fixes #3715

Added explicit return statements for trace-related tests.

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

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

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

* feat: enhance task guardrail functionality and validation

* feat: enhance task guardrail functionality and validation

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

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

* refactor: enhance guardrail type handling in Task model

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

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

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

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

* chore: 1.0.0b3 bump (#3734)

* chore: full ruff and mypy

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

* New MCL DSL (#3738)

* Adding MCP implementation

* New tests for MCP implementation

* fix tests

* update docs

* Revert "New tests for MCP implementation"

This reverts commit 0bbe6dee90.

* linter

* linter

* fix

* verify mcp pacakge exists

* adjust docs to be clear only remote servers are supported

* reverted

* ensure args schema generated properly

* properly close out

---------

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

* feat: a2a experimental

experimental a2a support

---------

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

0
lib/crewai/tests/tools/agent_tools/__init__.py Normal file
View File

115
lib/crewai/tests/tools/agent_tools/cassettes/test_ask_question.yaml Normal file
View File

@@ -0,0 +1,115 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
the best research and analysis on content about AI and AI agents\nTo give my
best complete final answer to the task use 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: do you hate AI Agents?\n\nThis is the expect criteria for your final answer:
Your best answer to your coworker asking you this, accounting for the context
shared.\nyou MUST return the actual complete content as the final answer, not
a summary.\n\nThis is the context you''re working with:\nI heard you LOVE them\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1021'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7WnyWZFoccBH9YB7ghLbR1L8Wqa\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213909,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: As an expert researcher specialized in technology, I don't harbor emotions
such as hate towards AI agents. Instead, my focus is on understanding, analyzing,
and leveraging their potential to advance various fields. AI agents, when designed
and implemented effectively, can greatly augment human capabilities, streamline
processes, and provide valuable insights that might otherwise be overlooked.
My enthusiasm for AI agents stems from their ability to transform industries
and improve everyday life, making complex tasks more manageable and enhancing
overall efficiency. This passion drives my research and commitment to making
meaningful contributions in the realm of AI and AI agents.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\":
126,\n \"total_tokens\": 325,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85ebf47e661cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:31 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '2498'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_b7e2cb0620e45d3d74310d3f0166551f
http_version: HTTP/1.1
status_code: 200
version: 1

116
lib/crewai/tests/tools/agent_tools/cassettes/test_ask_question_with_coworker_as_array.yaml Normal file
View File

@@ -0,0 +1,116 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
the best research and analysis on content about AI and AI agents\nTo give my
best complete final answer to the task use 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: do you hate AI Agents?\n\nThis is the expect criteria for your final answer:
Your best answer to your coworker asking you this, accounting for the context
shared.\nyou MUST return the actual complete content as the final answer, not
a summary.\n\nThis is the context you''re working with:\nI heard you LOVE them\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1021'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7Wy6aW1XM0lWaMyQUNB9qhbCZlH\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213920,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: As an expert researcher specializing in technology and AI, I have a
deep appreciation for AI agents. These advanced tools have the potential to
revolutionize countless industries by improving efficiency, accuracy, and decision-making
processes. They can augment human capabilities, handle mundane and repetitive
tasks, and even offer insights that might be beyond human reach. While it's
crucial to approach AI with a balanced perspective, understanding both its capabilities
and limitations, my stance is one of optimism and fascination. Properly developed
and ethically managed, AI agents hold immense promise for driving innovation
and solving complex problems. So yes, I do love AI agents for their transformative
potential and the positive impact they can have on society.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\":
146,\n \"total_tokens\": 345,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85ec3c6f3b1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:42 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1675'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a249567d37ada11bc8857404338b24cc
http_version: HTTP/1.1
status_code: 200
version: 1

114
lib/crewai/tests/tools/agent_tools/cassettes/test_ask_question_with_wrong_co_worker_variable.yaml Normal file
View File

@@ -0,0 +1,114 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
the best research and analysis on content about AI and AI agents\nTo give my
best complete final answer to the task use 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: do you hate AI Agents?\n\nThis is the expect criteria for your final answer:
Your best answer to your coworker asking you this, accounting for the context
shared.\nyou MUST return the actual complete content as the final answer, not
a summary.\n\nThis is the context you''re working with:\nI heard you LOVE them\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1021'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7Wq7edXMCGJR1zDd2QoySLdo8mM\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213912,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: I don't hate AI agents; on the contrary, I find them fascinating and
incredibly useful. Considering the rapid advancements in AI technology, these
agents have the potential to revolutionize various industries by automating
tasks, improving efficiency, and providing insights that were previously unattainable.
My expertise in researching and analyzing AI and AI agents has allowed me to
appreciate the intricate design and the vast possibilities they offer. Therefore,
it's more accurate to say that I love AI agents for their potential to drive
innovation and improve our daily lives.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\": 116,\n
\ \"total_tokens\": 315,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85ec05f8651cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:33 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1739'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_d9e1e9458d5539061397a618345c27d4
http_version: HTTP/1.1
status_code: 200
version: 1

132
lib/crewai/tests/tools/agent_tools/cassettes/test_delegate_work.yaml Normal file
View File

@@ -0,0 +1,132 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
the best research and analysis on content about AI and AI agents\nTo give my
best complete final answer to the task use 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: share your take on AI Agents\n\nThis is the expect criteria for your final
answer: Your best answer to your coworker asking you this, accounting for the
context shared.\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nThis is the context you''re working with:\nI heard you hate
them\n\nBegin! This is VERY important to you, use the tools available and give
your best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1027'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7WbKt7If02iTLuH5cJJjeYo9uDi\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213897,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: I understand why you might think I dislike AI agents, but my perspective
is more nuanced. AI agents, in essence, are incredibly versatile tools designed
to perform specific tasks autonomously or semi-autonomously. They harness various
artificial intelligence techniques, such as machine learning, natural language
processing, and computer vision, to interpret data, understand tasks, and execute
them efficiently. \\n\\nFrom a technological standpoint, AI agents have revolutionized
numerous industries. In customer service, for instance, AI agents like chatbots
and virtual assistants handle customer inquiries 24/7, providing quick and efficient
solutions. In healthcare, AI agents can assist in diagnosing diseases, managing
patient data, and even predicting outbreaks. The automation capabilities of
AI agents also enhance productivity in areas such as logistics, finance, and
cybersecurity by identifying patterns and anomalies at speeds far beyond human
capabilities.\\n\\nHowever, it's important to acknowledge the potential downsides
and challenges associated with AI agents. Ethical considerations are paramount.
Issues such as data privacy, security, and biases in AI algorithms need to be
carefully managed. There is also the human aspect to consider\u2014over-reliance
on AI agents might lead to job displacement in certain sectors, and ensuring
a fair transition for affected workers is crucial.\\n\\nMy concerns generally
stem from these ethical and societal implications rather than from the technology
itself. I advocate for responsible AI development, which includes transparency,
fairness, and accountability. By addressing these concerns, we can harness the
full potential of AI agents while mitigating the associated risks.\\n\\nSo,
to clarify, I don't hate AI agents; I recognize their immense potential and
the significant benefits they bring to various fields. However, I am equally
aware of the challenges they present and advocate for a balanced approach to
their development and deployment.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 200,\n \"completion_tokens\": 359,\n
\ \"total_tokens\": 559,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_3537616b13\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85ebaa5c061cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:22 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '4928'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_761796305026b5adfbb5a6237f14e32a
http_version: HTTP/1.1
status_code: 200
version: 1

136
lib/crewai/tests/tools/agent_tools/cassettes/test_delegate_work_with_wrong_co_worker_variable.yaml Normal file
View File

@@ -0,0 +1,136 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
the best research and analysis on content about AI and AI agents\nTo give my
best complete final answer to the task use 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: share your take on AI Agents\n\nThis is the expect criteria for your final
answer: Your best answer to your coworker asking you this, accounting for the
context shared.\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nThis is the context you''re working with:\nI heard you hate
them\n\nBegin! This is VERY important to you, use the tools available and give
your best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1027'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7Wh4RzroZdiwUNOc4oRRhwfdRzs\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213903,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: AI agents are essentially autonomous software programs that perform
tasks or provide services on behalf of humans. They're built on complex algorithms
and often leverage machine learning and neural networks to adapt and improve
over time. \\n\\nIt's important to clarify that I don't \\\"hate\\\" AI agents,
but I do approach them with a critical eye for a couple of reasons. AI agents
have enormous potential to transform industries, making processes more efficient,
providing insightful data analytics, and even learning from user behavior to
offer personalized experiences. However, this potential comes with significant
challenges and risks:\\n\\n1. **Ethical Concerns**: AI agents operate on data,
and the biases present in data can lead to unfair or unethical outcomes. Ensuring
that AI operates within ethical boundaries requires rigorous oversight, which
is not always in place.\\n\\n2. **Privacy Issues**: AI agents often need access
to large amounts of data, raising questions about privacy and data security.
If not managed correctly, this can lead to unauthorized data access and potential
misuse of sensitive information.\\n\\n3. **Transparency and Accountability**:
The decision-making process of AI agents can be opaque, making it difficult
to understand how they arrive at specific conclusions or actions. This lack
of transparency poses challenges for accountability, especially if something
goes wrong.\\n\\n4. **Job Displacement**: As AI agents become more capable,
there are valid concerns about their impact on employment. Tasks that were traditionally
performed by humans are increasingly being automated, which can lead to job
loss in certain sectors.\\n\\n5. **Reliability**: While AI agents can outperform
humans in many areas, they are not infallible. They can make mistakes, sometimes
with serious consequences. Continuous monitoring and regular updates are essential
to maintain their performance and reliability.\\n\\nIn summary, while AI agents
offer substantial benefits and opportunities, it's critical to approach their
adoption and deployment with careful consideration of the associated risks.
Balancing innovation with responsibility is key to leveraging AI agents effectively
and ethically. So, rather than \\\"hating\\\" AI agents, I advocate for a balanced,
cautious approach that maximizes benefits while mitigating potential downsides.\",\n
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 200,\n \"completion_tokens\":
429,\n \"total_tokens\": 629,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_3537616b13\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85ebcdae971cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:29 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '5730'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_5da5b18b3cee10548a217ba97e133815
http_version: HTTP/1.1
status_code: 200
version: 1

137
lib/crewai/tests/tools/agent_tools/cassettes/test_delegate_work_withwith_coworker_as_array.yaml Normal file
View File

@@ -0,0 +1,137 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
the best research and analysis on content about AI and AI agents\nTo give my
best complete final answer to the task use 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: share your take on AI Agents\n\nThis is the expect criteria for your final
answer: Your best answer to your coworker asking you this, accounting for the
context shared.\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nThis is the context you''re working with:\nI heard you hate
them\n\nBegin! This is VERY important to you, use the tools available and give
your best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1027'
content-type:
- application/json
cookie:
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.47.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.47.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AB7Wsv05NzccAAGC0CZVg03mE72wi\",\n \"object\":
\"chat.completion\",\n \"created\": 1727213914,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: My perspective on AI agents is quite nuanced and not a matter of simple
like or dislike. AI agents, depending on their design, deployment, and use cases,
can bring about both significant benefits and substantial challenges.\\n\\nOn
the positive side, AI agents have the potential to automate mundane tasks, enhance
productivity, and provide personalized services in ways that were previously
unimaginable. For instance, in customer service, AI agents can handle inquiries
24/7, reducing waiting times and improving user satisfaction. In healthcare,
they can assist in diagnosing diseases by analyzing vast datasets much faster
than humans. These applications demonstrate the transformative power of AI in
improving efficiency and delivering better outcomes across various industries.\\n\\nHowever,
my reservations stem from several critical concerns. Firstly, there's the issue
of reliability and accuracy. Mismanaged or poorly designed AI systems can lead
to significant errors, which could be particularly detrimental in high-stakes
environments like healthcare or autonomous vehicles. Second, there's a risk
of job displacement as AI agents become capable of performing tasks traditionally
done by humans. This raises socio-economic concerns that need to be addressed
through effective policy-making and upskilling programs.\\n\\nAdditionally,
there are ethical and privacy considerations. AI agents often require large
amounts of data to function effectively, which can lead to issues concerning
consent, data security, and individual privacy rights. The lack of transparency
in how these agents make decisions can also pose challenges\u2014this is often
referred to as the \\\"black box\\\" problem, where even the developers may
not fully understand how specific AI outputs are generated.\\n\\nFinally, the
deployment of AI agents by bad actors for malicious purposes, such as deepfakes,
misinformation, and hacking, remains a pertinent concern. These potential downsides
imply that while AI technology is extremely powerful and promising, it must
be developed and implemented with care, consideration, and robust ethical guidelines.\\n\\nSo,
in summary, I don't hate AI agents\u2014rather, I approach them critically with
a balanced perspective, recognizing both their profound potential and the significant
challenges they present. Thoughtful development, responsible deployment, and
ethical governance are crucial to harness the benefits while mitigating the
risks associated with AI agents.\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
200,\n \"completion_tokens\": 436,\n \"total_tokens\": 636,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_3537616b13\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c85ec12ab0d1cf3-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 24 Sep 2024 21:38:40 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '6251'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '30000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_50aa23cad48cfb83b754a5a92939638e
http_version: HTTP/1.1
status_code: 200
version: 1

133
lib/crewai/tests/tools/agent_tools/test_agent_tools.py Normal file
View File

@@ -0,0 +1,133 @@
"""Test Agent creation and execution basic functionality."""
import os
import pytest
from crewai.agent import Agent
from crewai.tools.agent_tools.agent_tools import AgentTools
researcher = Agent(
role="researcher",
goal="make the best research and analysis on content about AI and AI agents",
backstory="You're an expert researcher, specialized in technology",
allow_delegation=False,
)
tools = AgentTools(agents=[researcher]).tools()
delegate_tool = tools[0]
ask_tool = tools[1]
@pytest.fixture(scope="module")
def vcr_config(request) -> dict:
return {
"cassette_library_dir": os.path.join(os.path.dirname(__file__), "cassettes"),
}
@pytest.mark.vcr(filter_headers=["authorization"])
def test_delegate_work():
result = delegate_tool.run(
coworker="researcher",
task="share your take on AI Agents",
context="I heard you hate them",
)
assert (
result
== "I understand why you might think I dislike AI agents, but my perspective is more nuanced. AI agents, in essence, are incredibly versatile tools designed to perform specific tasks autonomously or semi-autonomously. They harness various artificial intelligence techniques, such as machine learning, natural language processing, and computer vision, to interpret data, understand tasks, and execute them efficiently. \n\nFrom a technological standpoint, AI agents have revolutionized numerous industries. In customer service, for instance, AI agents like chatbots and virtual assistants handle customer inquiries 24/7, providing quick and efficient solutions. In healthcare, AI agents can assist in diagnosing diseases, managing patient data, and even predicting outbreaks. The automation capabilities of AI agents also enhance productivity in areas such as logistics, finance, and cybersecurity by identifying patterns and anomalies at speeds far beyond human capabilities.\n\nHowever, it's important to acknowledge the potential downsides and challenges associated with AI agents. Ethical considerations are paramount. Issues such as data privacy, security, and biases in AI algorithms need to be carefully managed. There is also the human aspect to consider—over-reliance on AI agents might lead to job displacement in certain sectors, and ensuring a fair transition for affected workers is crucial.\n\nMy concerns generally stem from these ethical and societal implications rather than from the technology itself. I advocate for responsible AI development, which includes transparency, fairness, and accountability. By addressing these concerns, we can harness the full potential of AI agents while mitigating the associated risks.\n\nSo, to clarify, I don't hate AI agents; I recognize their immense potential and the significant benefits they bring to various fields. However, I am equally aware of the challenges they present and advocate for a balanced approach to their development and deployment."
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_delegate_work_with_wrong_co_worker_variable():
result = delegate_tool.run(
coworker="researcher",
task="share your take on AI Agents",
context="I heard you hate them",
)
assert (
result
== "AI agents are essentially autonomous software programs that perform tasks or provide services on behalf of humans. They're built on complex algorithms and often leverage machine learning and neural networks to adapt and improve over time. \n\nIt's important to clarify that I don't \"hate\" AI agents, but I do approach them with a critical eye for a couple of reasons. AI agents have enormous potential to transform industries, making processes more efficient, providing insightful data analytics, and even learning from user behavior to offer personalized experiences. However, this potential comes with significant challenges and risks:\n\n1. **Ethical Concerns**: AI agents operate on data, and the biases present in data can lead to unfair or unethical outcomes. Ensuring that AI operates within ethical boundaries requires rigorous oversight, which is not always in place.\n\n2. **Privacy Issues**: AI agents often need access to large amounts of data, raising questions about privacy and data security. If not managed correctly, this can lead to unauthorized data access and potential misuse of sensitive information.\n\n3. **Transparency and Accountability**: The decision-making process of AI agents can be opaque, making it difficult to understand how they arrive at specific conclusions or actions. This lack of transparency poses challenges for accountability, especially if something goes wrong.\n\n4. **Job Displacement**: As AI agents become more capable, there are valid concerns about their impact on employment. Tasks that were traditionally performed by humans are increasingly being automated, which can lead to job loss in certain sectors.\n\n5. **Reliability**: While AI agents can outperform humans in many areas, they are not infallible. They can make mistakes, sometimes with serious consequences. Continuous monitoring and regular updates are essential to maintain their performance and reliability.\n\nIn summary, while AI agents offer substantial benefits and opportunities, it's critical to approach their adoption and deployment with careful consideration of the associated risks. Balancing innovation with responsibility is key to leveraging AI agents effectively and ethically. So, rather than \"hating\" AI agents, I advocate for a balanced, cautious approach that maximizes benefits while mitigating potential downsides."
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_ask_question():
result = ask_tool.run(
coworker="researcher",
question="do you hate AI Agents?",
context="I heard you LOVE them",
)
assert (
result
== "As an expert researcher specialized in technology, I don't harbor emotions such as hate towards AI agents. Instead, my focus is on understanding, analyzing, and leveraging their potential to advance various fields. AI agents, when designed and implemented effectively, can greatly augment human capabilities, streamline processes, and provide valuable insights that might otherwise be overlooked. My enthusiasm for AI agents stems from their ability to transform industries and improve everyday life, making complex tasks more manageable and enhancing overall efficiency. This passion drives my research and commitment to making meaningful contributions in the realm of AI and AI agents."
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_ask_question_with_wrong_co_worker_variable():
result = ask_tool.run(
coworker="researcher",
question="do you hate AI Agents?",
context="I heard you LOVE them",
)
assert (
result
== "I don't hate AI agents; on the contrary, I find them fascinating and incredibly useful. Considering the rapid advancements in AI technology, these agents have the potential to revolutionize various industries by automating tasks, improving efficiency, and providing insights that were previously unattainable. My expertise in researching and analyzing AI and AI agents has allowed me to appreciate the intricate design and the vast possibilities they offer. Therefore, it's more accurate to say that I love AI agents for their potential to drive innovation and improve our daily lives."
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_delegate_work_withwith_coworker_as_array():
result = delegate_tool.run(
coworker="[researcher]",
task="share your take on AI Agents",
context="I heard you hate them",
)
assert (
result
== "My perspective on AI agents is quite nuanced and not a matter of simple like or dislike. AI agents, depending on their design, deployment, and use cases, can bring about both significant benefits and substantial challenges.\n\nOn the positive side, AI agents have the potential to automate mundane tasks, enhance productivity, and provide personalized services in ways that were previously unimaginable. For instance, in customer service, AI agents can handle inquiries 24/7, reducing waiting times and improving user satisfaction. In healthcare, they can assist in diagnosing diseases by analyzing vast datasets much faster than humans. These applications demonstrate the transformative power of AI in improving efficiency and delivering better outcomes across various industries.\n\nHowever, my reservations stem from several critical concerns. Firstly, there's the issue of reliability and accuracy. Mismanaged or poorly designed AI systems can lead to significant errors, which could be particularly detrimental in high-stakes environments like healthcare or autonomous vehicles. Second, there's a risk of job displacement as AI agents become capable of performing tasks traditionally done by humans. This raises socio-economic concerns that need to be addressed through effective policy-making and upskilling programs.\n\nAdditionally, there are ethical and privacy considerations. AI agents often require large amounts of data to function effectively, which can lead to issues concerning consent, data security, and individual privacy rights. The lack of transparency in how these agents make decisions can also pose challenges—this is often referred to as the \"black box\" problem, where even the developers may not fully understand how specific AI outputs are generated.\n\nFinally, the deployment of AI agents by bad actors for malicious purposes, such as deepfakes, misinformation, and hacking, remains a pertinent concern. These potential downsides imply that while AI technology is extremely powerful and promising, it must be developed and implemented with care, consideration, and robust ethical guidelines.\n\nSo, in summary, I don't hate AI agents—rather, I approach them critically with a balanced perspective, recognizing both their profound potential and the significant challenges they present. Thoughtful development, responsible deployment, and ethical governance are crucial to harness the benefits while mitigating the risks associated with AI agents."
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_ask_question_with_coworker_as_array():
result = ask_tool.run(
coworker="[researcher]",
question="do you hate AI Agents?",
context="I heard you LOVE them",
)
assert (
result
== "As an expert researcher specializing in technology and AI, I have a deep appreciation for AI agents. These advanced tools have the potential to revolutionize countless industries by improving efficiency, accuracy, and decision-making processes. They can augment human capabilities, handle mundane and repetitive tasks, and even offer insights that might be beyond human reach. While it's crucial to approach AI with a balanced perspective, understanding both its capabilities and limitations, my stance is one of optimism and fascination. Properly developed and ethically managed, AI agents hold immense promise for driving innovation and solving complex problems. So yes, I do love AI agents for their transformative potential and the positive impact they can have on society."
)
def test_delegate_work_to_wrong_agent():
result = ask_tool.run(
coworker="writer",
question="share your take on AI Agents",
context="I heard you hate them",
)
assert (
result
== "\nError executing tool. coworker mentioned not found, it must be one of the following options:\n- researcher\n"
)
def test_ask_question_to_wrong_agent():
result = ask_tool.run(
coworker="writer",
question="do you hate AI Agents?",
context="I heard you LOVE them",
)
assert (
result
== "\nError executing tool. coworker mentioned not found, it must be one of the following options:\n- researcher\n"
)