andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 16:18:30 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
Files
d1343b96ed6ebf94fedf6384731bae6a03c1c9e0
crewAI/lib/crewai/tests/cassettes/test_before_crew_modification.yaml
Lorenze Jay d1343b96ed Release/v1.0.0 (#3618) 
* feat: add `apps` & `actions` attributes to Agent (#3504)

* feat: add app attributes to Agent

* feat: add actions attribute to Agent

* chore: resolve linter issues

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

* fix: remove unnecessary print

* feat: logging error when CrewaiPlatformTools fails

* chore: export CrewaiPlatformTools directly from crewai_tools

* style: resolver linter issues

* test: fix broken tests

* style: solve linter issues

* fix: fix broken test

* feat: monorepo restructure and test/ci updates

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

* chore: update python version to 3.13 and package metadata

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

* feat: add crewai-tools workspace structure

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

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

* feat: configure crewai-tools workspace package with dependencies

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

* chore: update lockfile

* fix: don't allow tool tests yet

* fix: comment out extra pytest flags for now

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

* fix: resolve dependency conflicts and test issues

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

* chore: update CI workflows and docs for monorepo structure

* chore: update CI workflows and docs for monorepo structure

* fix: actions syntax

* chore: ci publish and pin versions

* fix: add permission to action

* chore: bump version to 1.0.0a1 across all packages

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

* WIP: v1 docs (#3626)

(cherry picked from commit d46e20fa09bcd2f5916282f5553ddeb7183bd92c)

* docs: parity for all translations

* docs: full name of acronym AMP

* docs: fix lingering unused code

* docs: expand contextual options in docs.json

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

* chore: apply linting fixes to crewai-tools

* feat: add required env var validation for brightdata

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

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

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

* feat: bump version to 1.0.0a2

* Lorenze/native inference sdks (#3619)

* ruff linted

* using native sdks with litellm fallback

* drop exa

* drop print on completion

* Refactor LLM and utility functions for type consistency

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

* fix agent_tests

* fix litellm tests and usagemetrics fix

* drop print

* Refactor LLM event handling and improve test coverage

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

* fix test_converter

* fixed tests/agents/test_agent.py

* Refactor LLM context length exception handling and improve provider integration

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

* Enhance LLM context window handling across providers

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

* fix test agent again

* fix test agent

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

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

* chore: update dependencies and improve context management

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

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

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

* linter

* linted

* revert constants

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

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

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

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

* fixed test

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

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

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

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

* feat: add base devtooling

* fix: ensure dep refs are updated for devtools

* fix: allow pre-release

* feat: allow release after tag

* feat: bump versions to 1.0.0a3 

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

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

* fix: allow failed pypi publish

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

* chore: exclude tests from ruff linting

* chore: exclude tests from GitHub Actions linter

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

* chore: add noqa for intentional print in printer utility

* fix: resolve linting errors across codebase

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

* fix: remove duplicate line and add explicit env var

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

* Update triggers docs (#3678)

* docs: introduce triggers list & triggers run command

* docs: add KO triggers docs

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

* Lorenze/bedrock llm (#3693)

* feat: add AWS Bedrock support and update dependencies

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

* using converse api

* converse

* linted

* refactor: update BedrockCompletion class to improve parameter handling

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

* feat: improve event bus thread safety and async support

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

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

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

* feat: enhance OpenAICompletion class with additional client parameters

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

* fix: correct test case for unsupported OpenAI model

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

* fix: enhance error handling in OpenAICompletion class

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

* fix: improve test for unsupported OpenAI model handling

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

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

* Lorenze/tools drop litellm (#3710)

* completely drop litellm and correctly pass config for qdrant

* feat: add support for additional embedding models in EmbeddingService

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

* fix: update collection parameter handling in CrewAIRagAdapter

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

* moved stagehand as optional dep (#3712)

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

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

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

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

* drop print statements

* test: add fixture to mock ANTHROPIC_API_KEY for tests

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

* refactor: streamline streaming message handling in AnthropicCompletion class

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

* fix streaming here too

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

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

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

* feat: enhance GeminiCompletion class with client parameter support

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

* add optional dependancies

* refactor: update test fixture to mock GOOGLE_API_KEY

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

* fix tests

* feat: enhance BedrockCompletion class with advanced features

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

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

* chore: add boto typing

* fix: use typing_extensions.Required for Python 3.10 compatibility

---------

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

* feat: azure native tests

* feat: add Azure AI Inference support and related tests

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

* feat: enhance AzureCompletion class with Azure OpenAI support

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

* refactor: convert project module to metaclass with full typing

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

* fix: enhance OpenAICompletion class base URL handling

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

* feat: enhance OpenAICompletion class with api_base support

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

* fix: improve OpenAICompletion class configuration handling

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

* drop print

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

* feat: add support for Anthropic provider and enhance logging

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

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

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

* test: update native provider fallback tests to expect ImportError

* adjust the test with the expected bevaior - raising ImportError

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

---------

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

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

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

Fixes #3715

Added explicit return statements for trace-related tests.

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

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

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

* feat: enhance task guardrail functionality and validation

* feat: enhance task guardrail functionality and validation

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

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

* refactor: enhance guardrail type handling in Task model

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

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

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

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

* chore: 1.0.0b3 bump (#3734)

* chore: full ruff and mypy

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

* New MCL DSL (#3738)

* Adding MCP implementation

* New tests for MCP implementation

* fix tests

* update docs

* Revert "New tests for MCP implementation"

This reverts commit 0bbe6dee90.

* linter

* linter

* fix

* verify mcp pacakge exists

* adjust docs to be clear only remote servers are supported

* reverted

* ensure args schema generated properly

* properly close out

---------

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

* feat: a2a experimental

experimental a2a support

---------

Co-authored-by: Lucas Gomide <lucaslg200@gmail.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Tony Kipkemboi <iamtonykipkemboi@gmail.com>
Co-authored-by: Mike Plachta <mplachta@users.noreply.github.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2025-10-20 14:10:19 -07:00

446 lines
22 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Bicycles Senior Data
Researcher\n. You''re a seasoned researcher with a knack for uncovering the
latest developments in Bicycles. Known for your ability to find the most relevant
information and present it in a clear and concise manner.\n\nYour personal goal
is: Uncover cutting-edge developments in Bicycles\n\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:
Conduct a thorough research about Bicycles Make sure you find any interesting
and relevant information given the current year is 2024.\n\n\nThis is the expect
criteria for your final answer: A list with 10 bullet points of the most relevant
information about Bicycles\n\nyou MUST return the actual complete content as
the final answer, not a summary.\n\nBegin! This is VERY important to you, use
the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
"model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1255'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8e44d29989a61ab0-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 18 Nov 2024 03:20:10 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=elWqsM.3Jt5.vyzDrpCmVftKrlxb0_fRVMZxBGUYfcE-1731900010-1.0.1.1-AxUZI4aRPPnqgUcewvytSN0TcEpcfBqYEZ.h2A96g3wUsy6Ui_pr4y81nyHf2Pcn1S3lz4zSmufsGDmnNKtHDQ;
path=/; expires=Mon, 18-Nov-24 03:50:10 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=lzrs54cKet3l28qlaoF9_vtIs55.7H9Sbr6IhTssBmk-1731900010790-0.0.1.1-604800000;
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:
- '5249'
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:
- '29999708'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a9781a68655042f161d8089cc3819728
status:
code: 200
message: OK
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '1892'
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, 18 Nov 2024 03:20:10 GMT
status:
code: 200
message: OK
- request:
body: !!binary |
Cs4CCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSpQIKEgoQY3Jld2FpLnRl
bGVtZXRyeRKOAgoQwB8k3adY9mK031pcBVZJKhII3fxizKFNiGkqDFRhc2sgQ3JlYXRlZDABOaj7
K0Xi8QgYQUiCLUXi8QgYSi4KCGNyZXdfa2V5EiIKIDFmMTI4YmRiN2JhYTRiNjc3MTRmMWRhZWRj
MmYzYWI2SjEKB2NyZXdfaWQSJgokMzQxMGJiNjItNTc2MS00YTBkLThmNWYtYTk5YmVmOTQ2MTNl
Si4KCHRhc2tfa2V5EiIKIGIxN2IxODhkYmYxNGY5M2E5OGU1Yjk1YWFkMzY3NTc3SjEKB3Rhc2tf
aWQSJgokNzRhOWVhMjMtNzVmYy00NWFiLWIyMDAtMTllZTk0ZjU0Y2JkegIYAYUBAAEAAA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '337'
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, 18 Nov 2024 03:20:15 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Bicycles Reporting
Analyst\n. You''re a meticulous analyst with a keen eye for detail. You''re
known for your ability to turn complex data into clear and concise reports,
making it easy for others to understand and act on the information you provide.\n\nYour
personal goal is: Create detailed reports based on Bicycles data analysis and
research findings\n\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: Review the context you got and
expand each topic into a full section for a report. Make sure the report is
detailed and contains any and all relevant information.\n\n\nThis is the expect
criteria for your final answer: A fully fledge reports with the mains topics,
each with a full section of information. Formatted as markdown without ''```''\n\nyou
MUST return the actual complete content as the final answer, not a summary.\n\nThis
is the context you''re working with:\n1. **Electric Bicycles (E-Bikes) Dominate
the Market:** In 2024, e-bikes continue to lead in sales growth globally. Their
popularity is fueled by the advancement in battery technology, offering longer
ranges and shorter charging times, making commuting more efficient and sustainable
in urban environments.\n\n2. **Integration with Smart Technology:** Bicycle
manufacturers are increasingly incorporating IoT technology to enhance user
experience. Features like GPS tracking, fitness data logging, and anti-theft
systems directly linked to smartphones are becoming standard in newer models.\n\n3.
**Sustainable Manufacturing Techniques:** Environmental concerns have pushed
companies to adopt greener manufacturing processes, such as utilizing recycled
materials, reducing carbon footprints in production, and implementing circular
economies within the bicycle industry.\n\n4. **Innovations in Lightweight Materials:**
The development of new composite materials, including carbon and graphene, results
in extremely lightweight and durable frames. This advancement is particularly
noticeable in racing and mountain bikes, enhancing performance and speed.\n\n5.
**Customizable and Modular Bike Designs:** In 2024, there is a notable trend
toward bikes with modular designs that allow riders to customize parts and accessories
easily. This trend caters to diverse consumer needs and promotes longer bike
life cycles by allowing for parts replacement instead of whole bikes.\n\n6.
**Expansion of Urban Cycling Infrastructure:** More cities worldwide are investing
in cycling-friendly infrastructure, such as dedicated bike lanes and bike-sharing
schemes, to encourage eco-friendly commuting and reduce traffic congestion.\n\n7.
**Health and Wellness Benefits:** With growing awareness of health and fitness,
more people are choosing cycling as a daily exercise routine. The industry sees
a surge in sales of fitness-oriented bicycles designed to maximize cardiovascular
and strength training benefits.\n\n8. **Rise of Cargo and Utility Bicycles:**
There is an increase in demand for cargo bicycles, which are used for transporting
goods over short distances, reflecting a shift towards sustainable business
delivery options, particularly in urban settings.\n\n9. **Competitive Cycling
and Esports:** Competitive cycling has embraced digital platforms, with virtual
reality and augmented reality races gaining traction among cycling enthusiasts
and professional athletes for training and competition purposes.\n\n10. **Focus
on Bike Safety Innovations:** Advances in bicycle safety technology, including
smart helmets with built-in communication systems and advanced lighting for
night visibility, are considerably improving rider security, making cycling
a safer mode of transport.\n\nBegin! This is VERY important to you, use the
tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
"model": "gpt-4o", "stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4197'
content-type:
- application/json
cookie:
- __cf_bm=elWqsM.3Jt5.vyzDrpCmVftKrlxb0_fRVMZxBGUYfcE-1731900010-1.0.1.1-AxUZI4aRPPnqgUcewvytSN0TcEpcfBqYEZ.h2A96g3wUsy6Ui_pr4y81nyHf2Pcn1S3lz4zSmufsGDmnNKtHDQ;
_cfuvid=lzrs54cKet3l28qlaoF9_vtIs55.7H9Sbr6IhTssBmk-1731900010790-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8e44d2bc2bec1ab0-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 18 Nov 2024 03:20:25 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:
- '13936'
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:
- '29998979'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 2ms
x-request-id:
- req_602e9ec1c4bc0da2fdb284f809c50872
status:
code: 200
message: OK
version: 1
Reference in New Issue View Git Blame Copy Permalink