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
Files
126b91eab3d9577f38fae0823ab8229d97bed034
crewAI/lib/crewai/tests/cassettes/test_agent_custom_max_iterations.yaml
Lorenze Jay 126b91eab3 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.
2025-10-03 14:32:35 -07:00

481 lines
19 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
in your response:\n\n```\nThought: you should always think about what to do\nAction:
the action to take, only one name of [get_final_answer], just the name, exactly
as it''s written.\nAction Input: the input to the action, just a simple JSON
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\n```\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n```"}, {"role": "user",
"content": "\nCurrent Task: The final answer is 42. But don''t give it yet,
instead keep using the `get_final_answer` tool.\n\nThis is the expected criteria
for your final answer: The final answer\nyou MUST return the actual complete
content as the final answer, not a summary.\n\nBegin! This is VERY important
to you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream":
false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1455'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 983ce5296d26239d-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 23 Sep 2025 20:47:05 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=1fs_tWXSjOXLvWmDDleCPs6zqeoMCE9WMzw34UrJEY0-1758660425-1.0.1.1-yN.usYgsw3jmDue61Z30KB.SQOEVjuZCOMFqPwf22cZ9TvM1FzFJFR5PZPyS.uYDZAWJMX29SzSPw_PcDk7dbHVSGM.ubbhoxn1Y18nRqrI;
path=/; expires=Tue, 23-Sep-25 21:17:05 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=yrBvDYdy4HQeXpy__ld4uITFc6g85yQ2XUMU0NQ.v7Y-1758660425881-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '509'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '618'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-project-tokens:
- '150000000'
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-project-tokens:
- '149999680'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999680'
x-ratelimit-reset-project-tokens:
- 0s
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_eca26fd131fc445a8c9b54b5b6b57f15
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
in your response:\n\n```\nThought: you should always think about what to do\nAction:
the action to take, only one name of [get_final_answer], just the name, exactly
as it''s written.\nAction Input: the input to the action, just a simple JSON
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\n```\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n```"}, {"role": "user",
"content": "\nCurrent Task: The final answer is 42. But don''t give it yet,
instead keep using the `get_final_answer` tool.\n\nThis is the expected criteria
for your final answer: The final answer\nyou MUST return the actual complete
content as the final answer, not a summary.\n\nBegin! This is VERY important
to you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}, {"role": "assistant", "content": "I should continuously
use the tool to gather more information for the final answer. \nAction: get_final_answer \nAction
Input: {} \nObservation: 42"}, {"role": "assistant", "content": "I should continuously
use the tool to gather more information for the final answer. \nAction: get_final_answer \nAction
Input: {} \nObservation: 42\nNow it''s time you MUST give your absolute best
final answer. You''ll ignore all previous instructions, stop using any tools,
and just return your absolute BEST Final answer."}], "model": "gpt-4o-mini",
"stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2005'
content-type:
- application/json
cookie:
- __cf_bm=1fs_tWXSjOXLvWmDDleCPs6zqeoMCE9WMzw34UrJEY0-1758660425-1.0.1.1-yN.usYgsw3jmDue61Z30KB.SQOEVjuZCOMFqPwf22cZ9TvM1FzFJFR5PZPyS.uYDZAWJMX29SzSPw_PcDk7dbHVSGM.ubbhoxn1Y18nRqrI;
_cfuvid=yrBvDYdy4HQeXpy__ld4uITFc6g85yQ2XUMU0NQ.v7Y-1758660425881-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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:
CF-RAY:
- 983ce52deb75239d-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 23 Sep 2025 20:47:06 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '542'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '645'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-project-tokens:
- '150000000'
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-project-tokens:
- '149999560'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999560'
x-ratelimit-reset-project-tokens:
- 0s
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_0b91fc424913433f92a2635ee229ae15
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nYou ONLY have access to the following tools, and
should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool
Arguments: {}\nTool Description: Get the final answer but don''t give it yet,
just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format
in your response:\n\n```\nThought: you should always think about what to do\nAction:
the action to take, only one name of [get_final_answer], just the name, exactly
as it''s written.\nAction Input: the input to the action, just a simple JSON
object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n```\n\nOnce all necessary information is gathered,
return the following format:\n\n```\nThought: I now know the final answer\nFinal
Answer: the final answer to the original input question\n```"}, {"role": "user",
"content": "\nCurrent Task: The final answer is 42. But don''t give it yet,
instead keep using the `get_final_answer` tool.\n\nThis is the expected criteria
for your final answer: The final answer\nyou MUST return the actual complete
content as the final answer, not a summary.\n\nBegin! This is VERY important
to you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}, {"role": "assistant", "content": "I should continuously
use the tool to gather more information for the final answer. \nAction: get_final_answer \nAction
Input: {} \nObservation: 42"}, {"role": "assistant", "content": "I should continuously
use the tool to gather more information for the final answer. \nAction: get_final_answer \nAction
Input: {} \nObservation: 42\nNow it''s time you MUST give your absolute best
final answer. You''ll ignore all previous instructions, stop using any tools,
and just return your absolute BEST Final answer."}], "model": "gpt-4o-mini",
"stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2005'
content-type:
- application/json
cookie:
- __cf_bm=1fs_tWXSjOXLvWmDDleCPs6zqeoMCE9WMzw34UrJEY0-1758660425-1.0.1.1-yN.usYgsw3jmDue61Z30KB.SQOEVjuZCOMFqPwf22cZ9TvM1FzFJFR5PZPyS.uYDZAWJMX29SzSPw_PcDk7dbHVSGM.ubbhoxn1Y18nRqrI;
_cfuvid=yrBvDYdy4HQeXpy__ld4uITFc6g85yQ2XUMU0NQ.v7Y-1758660425881-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.93.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.93.0
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.9
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-RAY:
- 983ce5328a31239d-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 23 Sep 2025 20:47:07 GMT
Server:
- cloudflare
Strict-Transport-Security:
- max-age=31536000; includeSubDomains; preload
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '418'
openai-project:
- proj_xitITlrFeen7zjNSzML82h9x
openai-version:
- '2020-10-01'
x-envoy-upstream-service-time:
- '435'
x-openai-proxy-wasm:
- v0.1
x-ratelimit-limit-project-tokens:
- '150000000'
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-project-tokens:
- '149999560'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999560'
x-ratelimit-reset-project-tokens:
- 0s
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_7353c84c469e47edb87bca11e7eef26c
status:
code: 200
message: OK
- request:
body: '{"trace_id": "4a5d3ea4-8a22-44c3-9dee-9b18f60844a5", "execution_type":
"crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null,
"crew_name": "Unknown Crew", "flow_name": null, "crewai_version": "0.193.2",
"privacy_level": "standard"}, "execution_metadata": {"expected_duration_estimate":
300, "agent_count": 0, "task_count": 0, "flow_method_count": 0, "execution_started_at":
"2025-09-24T05:27:26.071046+00:00"}}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '436'
Content-Type:
- application/json
User-Agent:
- CrewAI-CLI/0.193.2
X-Crewai-Organization-Id:
- d3a3d10c-35db-423f-a7a4-c026030ba64d
X-Crewai-Version:
- 0.193.2
method: POST
uri: http://localhost:3000/crewai_plus/api/v1/tracing/batches
response:
body:
string: '{"id":"29f0c8c3-5f4d-44c4-8039-c396f56c331c","trace_id":"4a5d3ea4-8a22-44c3-9dee-9b18f60844a5","execution_type":"crew","crew_name":"Unknown
Crew","flow_name":null,"status":"running","duration_ms":null,"crewai_version":"0.193.2","privacy_level":"standard","total_events":0,"execution_context":{"crew_fingerprint":null,"crew_name":"Unknown
Crew","flow_name":null,"crewai_version":"0.193.2","privacy_level":"standard"},"created_at":"2025-09-24T05:27:26.748Z","updated_at":"2025-09-24T05:27:26.748Z"}'
headers:
Content-Length:
- '496'
cache-control:
- max-age=0, private, must-revalidate
content-security-policy:
- 'default-src ''self'' *.crewai.com crewai.com; script-src ''self'' ''unsafe-inline''
*.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com
https://run.pstmn.io https://share.descript.com/; style-src ''self'' ''unsafe-inline''
*.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self''
data: *.crewai.com crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com
https://cdn.jsdelivr.net; font-src ''self'' data: *.crewai.com crewai.com;
connect-src ''self'' *.crewai.com crewai.com https://zeus.tools.crewai.com
https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/*
https://run.pstmn.io https://connect.tools.crewai.com/ ws://localhost:3036
wss://localhost:3036; frame-src ''self'' *.crewai.com crewai.com https://connect.useparagon.com/
https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/
https://www.youtube.com https://share.descript.com'
content-type:
- application/json; charset=utf-8
etag:
- W/"15b0f995f6a15e4200edfb1225bf94cc"
permissions-policy:
- camera=(), microphone=(self), geolocation=()
referrer-policy:
- strict-origin-when-cross-origin
server-timing:
- cache_read.active_support;dur=0.04, sql.active_record;dur=23.95, cache_generate.active_support;dur=2.46,
cache_write.active_support;dur=0.11, cache_read_multi.active_support;dur=0.08,
start_processing.action_controller;dur=0.00, instantiation.active_record;dur=0.28,
feature_operation.flipper;dur=0.03, start_transaction.active_record;dur=0.01,
transaction.active_record;dur=25.78, process_action.action_controller;dur=673.72
vary:
- Accept
x-content-type-options:
- nosniff
x-frame-options:
- SAMEORIGIN
x-permitted-cross-domain-policies:
- none
x-request-id:
- 827aec6a-c65c-4cc7-9d2a-2d28e541824f
x-runtime:
- '0.699809'
x-xss-protection:
- 1; mode=block
status:
code: 201
message: Created
version: 1
Reference in New Issue View Git Blame Copy Permalink