andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 08:08:32 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

WIP crew events emitter (#2048)

Browse Source 
* WIP crew events emitter

* Refactor event handling and introduce new event types

- Migrate from global `emit` function to `event_bus.emit`
- Add new event types for task failures, tool usage, and agent execution
- Update event listeners and event bus to support more granular event tracking
- Remove deprecated event emission methods
- Improve event type consistency and add more detailed event information

* Add event emission for agent execution lifecycle

- Emit AgentExecutionStarted and AgentExecutionError events
- Update CrewAgentExecutor to use event_bus for tracking agent execution
- Refactor error handling to include event emission
- Minor code formatting improvements in task.py and crew_agent_executor.py
- Fix a typo in test file

* Refactor event system and add third-party event listeners

- Move event_bus import to correct module paths
- Introduce BaseEventListener abstract base class
- Add AgentOpsListener for third-party event tracking
- Update event listener initialization and setup
- Clean up event-related imports and exports

* Enhance event system type safety and error handling

- Improve type annotations for event bus and event types
- Add null checks for agent and task in event emissions
- Update import paths for base tool and base agent
- Refactor event listener type hints
- Remove unnecessary print statements
- Update test configurations to match new event handling

* Refactor event classes to improve type safety and naming consistency

- Rename event classes to have explicit 'Event' suffix (e.g., TaskStartedEvent)
- Update import statements and references across multiple files
- Remove deprecated events.py module
- Enhance event type hints and configurations
- Clean up unnecessary event-related code

* Add default model for CrewEvaluator and fix event import order

- Set default model to "gpt-4o-mini" in CrewEvaluator when no model is specified
- Reorder event-related imports in task.py to follow standard import conventions
- Update event bus initialization method return type hint
- Export event_bus in events/__init__.py

* Fix tool usage and event import handling

- Update tool usage to use `.get()` method when checking tool name
- Remove unnecessary `__all__` export list in events/__init__.py

* Refactor Flow and Agent event handling to use event_bus

- Remove `event_emitter` from Flow class and replace with `event_bus.emit()`
- Update Flow and Agent tests to use event_bus event listeners
- Remove redundant event emissions in Flow methods
- Add debug print statements in Flow execution
- Simplify event tracking in test cases

* Enhance event handling for Crew, Task, and Event classes

- Add crew name to failed event types (CrewKickoffFailedEvent, CrewTrainFailedEvent, CrewTestFailedEvent)
- Update Task events to remove redundant task and context attributes
- Refactor EventListener to use Logger for consistent event logging
- Add new event types for Crew train and test events
- Improve event bus event tracking in test cases

* Remove telemetry and tracing dependencies from Task and Flow classes

- Remove telemetry-related imports and private attributes from Task class
- Remove `_telemetry` attribute from Flow class
- Update event handling to emit events without direct telemetry tracking
- Simplify task and flow execution by removing explicit telemetry spans
- Move telemetry-related event handling to EventListener

* Clean up unused imports and event-related code

- Remove unused imports from various event and flow-related files
- Reorder event imports to follow standard conventions
- Remove unnecessary event type references
- Simplify import statements in event and flow modules

* Update crew test to validate verbose output and kickoff_for_each method

- Enhance test_crew_verbose_output to check specific listener log messages
- Modify test_kickoff_for_each_invalid_input to use Pydantic validation error
- Improve test coverage for crew logging and input validation

* Update crew test verbose output with improved emoji icons

- Replace task and agent completion icons from 👍 to ✅
- Enhance readability of test output logging
- Maintain consistent test coverage for crew verbose output

* Add MethodExecutionFailedEvent to handle flow method execution failures

- Introduce new MethodExecutionFailedEvent in flow_events module
- Update Flow class to catch and emit method execution failures
- Add event listener for method execution failure events
- Update event-related imports to include new event type
- Enhance test coverage for method execution failure handling

* Propagate method execution failures in Flow class

- Modify Flow class to re-raise exceptions after emitting MethodExecutionFailedEvent
- Reorder MethodExecutionFailedEvent import to maintain consistent import style

* Enable test coverage for Flow method execution failure event

- Uncomment pytest.raises() in test_events to verify exception handling
- Ensure test validates MethodExecutionFailedEvent emission during flow kickoff

* Add event handling for tool usage events

- Introduce event listeners for ToolUsageFinishedEvent and ToolUsageErrorEvent
- Log tool usage events with descriptive emoji icons (✅ and ❌)
- Update event_listener to track and log tool usage lifecycle

* Reorder and clean up event imports in event_listener

- Reorganize imports for tool usage events and other event types
- Maintain consistent import ordering and remove unused imports
- Ensure clean and organized import structure in event_listener module

* moving to dedicated eventlistener

* dont forget crew level

* Refactor AgentOps event listener for crew-level tracking

- Modify AgentOpsListener to handle crew-level events
- Initialize and end AgentOps session at crew kickoff and completion
- Create agents for each crew member during session initialization
- Improve session management and event recording
- Clean up and simplify event handling logic

* Update test_events to validate tool usage error event handling

- Modify test to assert single error event with correct attributes
- Use pytest.raises() to verify error event generation
- Simplify error event validation in test case

* Improve AgentOps listener type hints and formatting

- Add string type hints for AgentOps classes to resolve potential import issues
- Clean up unnecessary whitespace and improve code indentation
- Simplify initialization and event handling logic

* Update test_events to validate multiple tool usage events

- Modify test to assert 75 events instead of a single error event
- Remove pytest.raises() check, allowing crew kickoff to complete
- Adjust event validation to support broader event tracking

* Rename event_bus to crewai_event_bus for improved clarity and specificity

- Replace all references to `event_bus` with `crewai_event_bus`
- Update import statements across multiple files
- Remove the old `event_bus.py` file
- Maintain existing event handling functionality

* Enhance EventListener with singleton pattern and color configuration

- Implement singleton pattern for EventListener to ensure single instance
- Add default color configuration using EMITTER_COLOR from constants
- Modify log method calls to use default color and remove redundant color parameters
- Improve initialization logic to prevent multiple initializations

* Add FlowPlotEvent and update event bus to support flow plotting

- Introduce FlowPlotEvent to track flow plotting events
- Replace Telemetry method with event bus emission in Flow.plot()
- Update event bus to support new FlowPlotEvent type
- Add test case to validate flow plotting event emission

* Remove RunType enum and clean up crew events module

- Delete unused RunType enum from crew_events.py
- Simplify crew_events.py by removing unnecessary enum definition
- Improve code clarity by removing unneeded imports

* Enhance event handling for tool usage and agent execution

- Add new events for tool usage: ToolSelectionErrorEvent, ToolValidateInputErrorEvent
- Improve error tracking and event emission in ToolUsage and LLM classes
- Update AgentExecutionStartedEvent to use task_prompt instead of inputs
- Add comprehensive test coverage for new event types and error scenarios

* Refactor event system and improve crew testing

- Extract base CrewEvent class to a new base_events.py module
- Update event imports across multiple event-related files
- Modify CrewTestStartedEvent to use eval_llm instead of openai_model_name
- Add LLM creation validation in crew testing method
- Improve type handling and event consistency

* Refactor task events to use base CrewEvent

- Move CrewEvent import from crew_events to base_events
- Remove unnecessary blank lines in task_events.py
- Simplify event class structure for task-related events

* Update AgentExecutionStartedEvent to use task_prompt

- Modify test_events.py to use task_prompt instead of inputs
- Simplify event input validation in test case
- Align with recent event system refactoring

* Improve type hinting for TaskCompletedEvent handler

- Add explicit type annotation for TaskCompletedEvent in event_listener.py
- Enhance type safety for event handling in EventListener

* Improve test_validate_tool_input_invalid_input with mock objects

- Add explicit mock objects for agent and action in test case
- Ensure proper string values for mock agent and action attributes
- Simplify test setup for ToolUsage validation method

* Remove ToolUsageStartedEvent emission in tool usage process

- Remove unnecessary event emission for tool usage start
- Simplify tool usage event handling
- Eliminate redundant event data preparation step

* refactor: clean up and organize imports in llm and flow modules

* test: Improve flow persistence test cases and logging
This commit is contained in:
Lorenze Jay
2025-02-19 13:52:47 -08:00
committed by GitHub
parent bcd90e26b0
commit 00c2f5043e
48 changed files with 13885 additions and 594 deletions
Download Patch File Download Diff File Expand all files Collapse all files

243
tests/utilities/cassettes/test_agent_emits_execution_started_and_completed_events.yaml Normal file
View File

@@ -0,0 +1,243 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
give my best complete final answer to the task respond using the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
"content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzTXAk4GatJOmLO9sEOCCITIjf1Dx\",\n \"object\":
\"chat.completion\",\n \"created\": 1739214900,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90fe6ce92eba67b3-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 10 Feb 2025 19:15:01 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=pjX1I6y8RlqCjS.gvOqvXk4vM69UNwFwmslh1BhALNg-1739214901-1.0.1.1-nJcNlSdNcug82eDl7KSvteLbsg0xCiEh2yI1TZX2jMAblL7AMQ8LFhvXkJLlAMfk49RMzRzWy2aiQgeM7WRHPg;
path=/; expires=Mon, 10-Feb-25 19:45:01 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '571'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a95183a7a85e6bdfe381b2510bf70f34
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
from 0 to 10 evaluating on completion, quality, and overall performance- Entities
extracted from the task output, if any, their type, description, and relationships"}],
"model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
"TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
"description": "Correctly extracted `TaskEvaluation` with all the required parameters
with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
{"description": "The name of the entity.", "title": "Name", "type": "string"},
"type": {"description": "The type of the entity.", "title": "Type", "type":
"string"}, "description": {"description": "Description of the entity.", "title":
"Description", "type": "string"}, "relationships": {"description": "Relationships
of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
"array"}}, "required": ["name", "type", "description", "relationships"], "title":
"Entity", "type": "object"}}, "properties": {"suggestions": {"description":
"Suggestions to improve future similar tasks.", "items": {"type": "string"},
"title": "Suggestions", "type": "array"}, "quality": {"description": "A score
from 0 to 10 evaluating on completion, quality, and overall performance, all
taking into account the task description, expected output, and the result of
the task.", "title": "Quality", "type": "number"}, "entities": {"description":
"Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
"title": "Entities", "type": "array"}}, "required": ["entities", "quality",
"suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1962'
content-type:
- application/json
cookie:
- __cf_bm=pjX1I6y8RlqCjS.gvOqvXk4vM69UNwFwmslh1BhALNg-1739214901-1.0.1.1-nJcNlSdNcug82eDl7KSvteLbsg0xCiEh2yI1TZX2jMAblL7AMQ8LFhvXkJLlAMfk49RMzRzWy2aiQgeM7WRHPg;
_cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzTXDcgKWq3yosIyBal8LcY8dDrn1\",\n \"object\":
\"chat.completion\",\n \"created\": 1739214903,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_c41SAnqyEKNXEAZd5XV3jKF3\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"TaskEvaluation\",\n
\ \"arguments\": \"{\\\"suggestions\\\":[\\\"Consider specifying
the tone or context of the greeting for more engaging interactions.\\\",\\\"Clarify
if additional greetings or responses are acceptable to enhance the task's scope.\\\"],\\\"quality\\\":10,\\\"entities\\\":[]
}\"\n }\n }\n ],\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 273,\n \"completion_tokens\": 43,\n
\ \"total_tokens\": 316,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 90fe6cf8c96e67b3-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 10 Feb 2025 19:15:04 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1181'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999876'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_b2286c8ae6f9b2a42f46a3e2c52b4211
http_version: HTTP/1.1
status_code: 200
version: 1

315
tests/utilities/cassettes/test_crew_emits_end_kickoff_event.yaml Normal file
View File

@@ -0,0 +1,315 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
give my best complete final answer to the task respond using the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
"content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
cookie:
- __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
_cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJK2OCJSkUj1plgbj59b4dC39QV2\",\n \"object\":
\"chat.completion\",\n \"created\": 1738698990,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90cd396c0ab71698-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 19:56:30 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '951'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_2c3cb5caed61ccd1e058ef3e6301c691
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '2480'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Tue, 04 Feb 2025 19:56:31 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
from 0 to 10 evaluating on completion, quality, and overall performance- Entities
extracted from the task output, if any, their type, description, and relationships"}],
"model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
"TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
"description": "Correctly extracted `TaskEvaluation` with all the required parameters
with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
{"description": "The name of the entity.", "title": "Name", "type": "string"},
"type": {"description": "The type of the entity.", "title": "Type", "type":
"string"}, "description": {"description": "Description of the entity.", "title":
"Description", "type": "string"}, "relationships": {"description": "Relationships
of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
"array"}}, "required": ["name", "type", "description", "relationships"], "title":
"Entity", "type": "object"}}, "properties": {"suggestions": {"description":
"Suggestions to improve future similar tasks.", "items": {"type": "string"},
"title": "Suggestions", "type": "array"}, "quality": {"description": "A score
from 0 to 10 evaluating on completion, quality, and overall performance, all
taking into account the task description, expected output, and the result of
the task.", "title": "Quality", "type": "number"}, "entities": {"description":
"Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
"title": "Entities", "type": "array"}}, "required": ["entities", "quality",
"suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1962'
content-type:
- application/json
cookie:
- __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
_cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJK3bJiyqGhPeqdCcCjoeNavGHrR\",\n \"object\":
\"chat.completion\",\n \"created\": 1738698991,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_uAFkclWHIRqgrXFrQFcEoUIS\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"TaskEvaluation\",\n
\ \"arguments\": \"{\\\"suggestions\\\":[\\\"Include additional
context for the greeting to make it more meaningful.\\\",\\\"Specify if you
want a casual or formal tone for greetings.\\\",\\\"Provide examples of variations
of the greeting if necessary.\\\"],\\\"quality\\\":10,\\\"entities\\\":[],\\\"relationships\\\":[]}\"\n
\ }\n }\n ],\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 273,\n \"completion_tokens\": 50,\n
\ \"total_tokens\": 323,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_bd83329f63\"\n}\n"
headers:
CF-RAY:
- 90cd3973589f1698-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 19:56:32 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1408'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999876'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_519fd27ca3d5da4d541c4331654e0520
http_version: HTTP/1.1
status_code: 200
version: 1

357
tests/utilities/cassettes/test_crew_emits_end_task_event.yaml Normal file
View File

@@ -0,0 +1,357 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
give my best complete final answer to the task respond using the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
"content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
cookie:
- __cf_bm=nedOdWE1YnKQYt1kSbrcA.zhwa3bZDzmZqTOjZYER0c-1738700521-1.0.1.1-xQk9iXOvqvyXNhkIOgc8Ws2WYcT1mJFkDCvCC8xA5joFD8QfNrBIAr_Qs6sIxt2EzXyeFwBA6gA8ZgWApCHx0Q;
_cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJlK2np8dMxYgsDIuyz2TSKKELWh\",\n \"object\":
\"chat.completion\",\n \"created\": 1738700682,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90cd62c1fdb0fa6a-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 20:24:42 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '326'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_22be86be6fd9d69ca8d310ef534e7bec
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '4896'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Tue, 04 Feb 2025 20:24:47 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
from 0 to 10 evaluating on completion, quality, and overall performance- Entities
extracted from the task output, if any, their type, description, and relationships"}],
"model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
"TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
"description": "Correctly extracted `TaskEvaluation` with all the required parameters
with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
{"description": "The name of the entity.", "title": "Name", "type": "string"},
"type": {"description": "The type of the entity.", "title": "Type", "type":
"string"}, "description": {"description": "Description of the entity.", "title":
"Description", "type": "string"}, "relationships": {"description": "Relationships
of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
"array"}}, "required": ["name", "type", "description", "relationships"], "title":
"Entity", "type": "object"}}, "properties": {"suggestions": {"description":
"Suggestions to improve future similar tasks.", "items": {"type": "string"},
"title": "Suggestions", "type": "array"}, "quality": {"description": "A score
from 0 to 10 evaluating on completion, quality, and overall performance, all
taking into account the task description, expected output, and the result of
the task.", "title": "Quality", "type": "number"}, "entities": {"description":
"Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
"title": "Entities", "type": "array"}}, "required": ["entities", "quality",
"suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1962'
content-type:
- application/json
cookie:
- __cf_bm=nedOdWE1YnKQYt1kSbrcA.zhwa3bZDzmZqTOjZYER0c-1738700521-1.0.1.1-xQk9iXOvqvyXNhkIOgc8Ws2WYcT1mJFkDCvCC8xA5joFD8QfNrBIAr_Qs6sIxt2EzXyeFwBA6gA8ZgWApCHx0Q;
_cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJlLVC3gCB9gRI0ZSkoPCZY7EwpQ\",\n \"object\":
\"chat.completion\",\n \"created\": 1738700683,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_mgwImOITW8lkjzAyf9Pp76cL\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"TaskEvaluation\",\n
\ \"arguments\": \"{\\\"suggestions\\\":[\\\"Provide context or
additional information to make tasks more engaging.\\\",\\\"Encourage variations
in responses to make the interaction more dynamic.\\\"],\\\"quality\\\":10,\\\"entities\\\":[{\\\"name\\\":\\\"hi\\\",\\\"type\\\":\\\"greeting\\\",\\\"description\\\":\\\"A
common word used to initiate a conversation or express friendliness.\\\",\\\"relationships\\\":[\\\"initiates
conversation\\\",\\\"expresses friendliness\\\"]}]}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
273,\n \"completion_tokens\": 71,\n \"total_tokens\": 344,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_bd83329f63\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 90cd62c4ba41fa6a-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 20:24:50 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:
- '7347'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999876'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_aec28dd3fe998d628754e8429623bf9e
http_version: HTTP/1.1
status_code: 200
version: 1

245
tests/utilities/cassettes/test_crew_emits_kickoff_events.yaml Normal file
View File

@@ -0,0 +1,245 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
give my best complete final answer to the task respond using the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
"content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJIrSWAFqDEsNtLRhcM8vMHO9Ejw\",\n \"object\":
\"chat.completion\",\n \"created\": 1738698917,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90cd37a83f5f176a-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 19:55:18 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=rKQWp4fbAvcCp4rasEN6DqiTjQfiWYpLfjcLpWcmzi0-1738698918-1.0.1.1-qlcCSdBY3KWbzVms0eLtz5ub5SSLGs_sRLxTdNhDk_purQuz9k6EFp8PHJfN3aP_sLnuyKnFlppM3.2k_dCtPQ;
path=/; expires=Tue, 04-Feb-25 20:25:18 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=Oi91zDXvjWohBYXSVqK4hFsq3_GZePEIIbi7b7wrjcI-1738698918130-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '894'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_864253996bbc0f797f9a2c1b9247a0d5
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
from 0 to 10 evaluating on completion, quality, and overall performance- Entities
extracted from the task output, if any, their type, description, and relationships"}],
"model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
"TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
"description": "Correctly extracted `TaskEvaluation` with all the required parameters
with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
{"description": "The name of the entity.", "title": "Name", "type": "string"},
"type": {"description": "The type of the entity.", "title": "Type", "type":
"string"}, "description": {"description": "Description of the entity.", "title":
"Description", "type": "string"}, "relationships": {"description": "Relationships
of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
"array"}}, "required": ["name", "type", "description", "relationships"], "title":
"Entity", "type": "object"}}, "properties": {"suggestions": {"description":
"Suggestions to improve future similar tasks.", "items": {"type": "string"},
"title": "Suggestions", "type": "array"}, "quality": {"description": "A score
from 0 to 10 evaluating on completion, quality, and overall performance, all
taking into account the task description, expected output, and the result of
the task.", "title": "Quality", "type": "number"}, "entities": {"description":
"Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
"title": "Entities", "type": "array"}}, "required": ["entities", "quality",
"suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1962'
content-type:
- application/json
cookie:
- __cf_bm=rKQWp4fbAvcCp4rasEN6DqiTjQfiWYpLfjcLpWcmzi0-1738698918-1.0.1.1-qlcCSdBY3KWbzVms0eLtz5ub5SSLGs_sRLxTdNhDk_purQuz9k6EFp8PHJfN3aP_sLnuyKnFlppM3.2k_dCtPQ;
_cfuvid=Oi91zDXvjWohBYXSVqK4hFsq3_GZePEIIbi7b7wrjcI-1738698918130-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJIsVEppA04iGQh0k6sanKnVObrO\",\n \"object\":
\"chat.completion\",\n \"created\": 1738698918,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_AQ3iizjGWjEvk1SmhGCzjbf1\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"TaskEvaluation\",\n
\ \"arguments\": \"{\\\"suggestions\\\":[\\\"Provide context for
the greeting, like a specific scenario or recipient.\\\",\\\"Encourage responses
or follow-ups to promote engagement.\\\",\\\"Specify the tone or formality of
the greeting, if relevant.\\\"],\\\"quality\\\":10,\\\"entities\\\":[{\\\"name\\\":\\\"hi\\\",\\\"type\\\":\\\"greeting\\\",\\\"description\\\":\\\"A
common informal expression used to initiate conversation or acknowledge someone.\\\",\\\"relationships\\\":[\\\"used
in conversation\\\",\\\"expresses friendliness\\\"]}]}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
273,\n \"completion_tokens\": 84,\n \"total_tokens\": 357,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_bd83329f63\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 90cd37aec8c8176a-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 19:55:21 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '3269'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999876'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_e6e67a3f5c6f2d48e0351cdce95edd97
http_version: HTTP/1.1
status_code: 200
version: 1

243
tests/utilities/cassettes/test_crew_emits_start_kickoff_event.yaml Normal file
View File

@@ -0,0 +1,243 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
give my best complete final answer to the task respond using the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
"content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJJzafmayYpGTsTAWbOyZkmQJNa5\",\n \"object\":
\"chat.completion\",\n \"created\": 1738698987,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 90cd395b0e641698-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 19:56:27 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
path=/; expires=Tue, 04-Feb-25 20:26:27 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '839'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_577b484a927b455c40ed80f9fd4d9106
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
from 0 to 10 evaluating on completion, quality, and overall performance- Entities
extracted from the task output, if any, their type, description, and relationships"}],
"model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
"TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
"description": "Correctly extracted `TaskEvaluation` with all the required parameters
with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
{"description": "The name of the entity.", "title": "Name", "type": "string"},
"type": {"description": "The type of the entity.", "title": "Type", "type":
"string"}, "description": {"description": "Description of the entity.", "title":
"Description", "type": "string"}, "relationships": {"description": "Relationships
of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
"array"}}, "required": ["name", "type", "description", "relationships"], "title":
"Entity", "type": "object"}}, "properties": {"suggestions": {"description":
"Suggestions to improve future similar tasks.", "items": {"type": "string"},
"title": "Suggestions", "type": "array"}, "quality": {"description": "A score
from 0 to 10 evaluating on completion, quality, and overall performance, all
taking into account the task description, expected output, and the result of
the task.", "title": "Quality", "type": "number"}, "entities": {"description":
"Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
"title": "Entities", "type": "array"}}, "required": ["entities", "quality",
"suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1962'
content-type:
- application/json
cookie:
- __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
_cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJJz10KP7iadNPdKsbcsvHBa7cic\",\n \"object\":
\"chat.completion\",\n \"created\": 1738698987,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_czeHQgy5eiOVa0zlrtcfwepe\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"TaskEvaluation\",\n
\ \"arguments\": \"{\\\"suggestions\\\":[\\\"Provide more context
or details for similar tasks to enhance output expectations.\\\",\\\"Encourage
creativity in responses for simple tasks to engage users more effectively.\\\"],\\\"quality\\\":10,\\\"entities\\\":[]
}\"\n }\n }\n ],\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 273,\n \"completion_tokens\": 40,\n
\ \"total_tokens\": 313,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_bd83329f63\"\n}\n"
headers:
CF-RAY:
- 90cd39615b281698-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 19:56:29 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1411'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999876'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_3e717a80c7d9c5ea19893dd990aaae26
http_version: HTTP/1.1
status_code: 200
version: 1

245
tests/utilities/cassettes/test_crew_emits_start_task_event.yaml Normal file
View File

@@ -0,0 +1,245 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
give my best complete final answer to the task respond using the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
"content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
cookie:
- __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
_cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJiiHEQwIXsiG0Sd5wofcuhxVbo9\",\n \"object\":
\"chat.completion\",\n \"created\": 1738700520,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90cd5ecd0f7667ee-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 20:22:01 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=nedOdWE1YnKQYt1kSbrcA.zhwa3bZDzmZqTOjZYER0c-1738700521-1.0.1.1-xQk9iXOvqvyXNhkIOgc8Ws2WYcT1mJFkDCvCC8xA5joFD8QfNrBIAr_Qs6sIxt2EzXyeFwBA6gA8ZgWApCHx0Q;
path=/; expires=Tue, 04-Feb-25 20:52:01 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '450'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_10eaafc81640a98a0a4789d270dd94d9
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
from 0 to 10 evaluating on completion, quality, and overall performance- Entities
extracted from the task output, if any, their type, description, and relationships"}],
"model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
"TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
"description": "Correctly extracted `TaskEvaluation` with all the required parameters
with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
{"description": "The name of the entity.", "title": "Name", "type": "string"},
"type": {"description": "The type of the entity.", "title": "Type", "type":
"string"}, "description": {"description": "Description of the entity.", "title":
"Description", "type": "string"}, "relationships": {"description": "Relationships
of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
"array"}}, "required": ["name", "type", "description", "relationships"], "title":
"Entity", "type": "object"}}, "properties": {"suggestions": {"description":
"Suggestions to improve future similar tasks.", "items": {"type": "string"},
"title": "Suggestions", "type": "array"}, "quality": {"description": "A score
from 0 to 10 evaluating on completion, quality, and overall performance, all
taking into account the task description, expected output, and the result of
the task.", "title": "Quality", "type": "number"}, "entities": {"description":
"Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
"title": "Entities", "type": "array"}}, "required": ["entities", "quality",
"suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1962'
content-type:
- application/json
cookie:
- __cf_bm=nedOdWE1YnKQYt1kSbrcA.zhwa3bZDzmZqTOjZYER0c-1738700521-1.0.1.1-xQk9iXOvqvyXNhkIOgc8Ws2WYcT1mJFkDCvCC8xA5joFD8QfNrBIAr_Qs6sIxt2EzXyeFwBA6gA8ZgWApCHx0Q;
_cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AxJijOhk12Ua6lS23IwtZTachfjq9\",\n \"object\":
\"chat.completion\",\n \"created\": 1738700521,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_DSteeMHHPf5RanJb8qjCo4qx\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"TaskEvaluation\",\n
\ \"arguments\": \"{\\\"suggestions\\\":[\\\"Consider adding context
for the greeting to make it more engaging.\\\",\\\"Specify if any additional
information or tone is desired in the greeting.\\\"],\\\"quality\\\":10,\\\"entities\\\":[{\\\"name\\\":\\\"greeting\\\",\\\"type\\\":\\\"text\\\",\\\"description\\\":\\\"A
simple greeting phrase\\\",\\\"relationships\\\":[\\\"is a\\\",\\\"is part of
a conversation\\\"]}]}\"\n }\n }\n ],\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 273,\n \"completion_tokens\":
67,\n \"total_tokens\": 340,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_bd83329f63\"\n}\n"
headers:
CF-RAY:
- 90cd5ed20cb267ee-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 04 Feb 2025 20:22:02 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1624'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999876'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_4ee944acdd3928afbf6c5562403b064a
http_version: HTTP/1.1
status_code: 200
version: 1

114
tests/utilities/cassettes/test_crew_emits_task_failed_event.yaml Normal file
View File

@@ -0,0 +1,114 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
give my best complete final answer to the task respond using the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
"content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzpkZLpCyjKT5d6Udfx4zAme2sOMy\",\n \"object\":
\"chat.completion\",\n \"created\": 1739300299,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 910691d3ab90ebef-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 11 Feb 2025 18:58:20 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=MOH5EY6n3p8JKY53.yz7qzLuLYsEB8QdQXH09loUMBM-1739300300-1.0.1.1-hjb4mk04sMygPFhoFyiySKZSqB_fN5PbhbOyn.kipa3.eLvk7EtriDyjvGkBFIAV13DYnc08BfF_l2kxdx9hfQ;
path=/; expires=Tue, 11-Feb-25 19:28:20 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=uu.cEiV.FfgvSvCdKOooDYJWrwjVEuFeGdQodijGUUI-1739300300232-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1357'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_2277503f851195e7d7a43b66eb044454
http_version: HTTP/1.1
status_code: 200
version: 1

111
tests/utilities/cassettes/test_multiple_handlers_for_same_event.yaml Normal file
View File

@@ -0,0 +1,111 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
give my best complete final answer to the task respond using the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
"content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
cookie:
- _cfuvid=gsNyCo_jrDOolzf8SXHDaxQQrEgdR3jgv4OAH8MziDE-1739291824699-0.0.1.1-604800000;
__cf_bm=cRijYuylMGzRGxv3udQL5PhHOR5mRN_9_eLLwevlM_o-1739299455-1.0.1.1-Fszr_Msw0B1.IBMkiunP.VF2ilul1YGZZV8TqMcO3Q2SHvSlqfgm9NHgns1bJrm0wWRvHiCE7wdZfUAOx7T3Lg
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzpWx6pctOvzu6xsbyg0XfSAc0q9V\",\n \"object\":
\"chat.completion\",\n \"created\": 1739299455,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 91067d3ddc68fa16-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 11 Feb 2025 18:44:16 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '703'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_89222c00e4608e8557a135e91b223556
http_version: HTTP/1.1
status_code: 200
version: 1

114
tests/utilities/cassettes/test_register_handler_adds_new_handler.yaml Normal file
View File

@@ -0,0 +1,114 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
give my best complete final answer to the task respond using the exact following
format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
answer must be the great and the most complete as possible, it must be outcome
described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
"content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
final answer: hi\nyou MUST return the actual complete content as the final answer,
not a summary.\n\nBegin! This is VERY important to you, use the tools available
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '836'
content-type:
- application/json
cookie:
- _cfuvid=gsNyCo_jrDOolzf8SXHDaxQQrEgdR3jgv4OAH8MziDE-1739291824699-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzpWxLzAcRzigZuIGmjP3ckQgxAom\",\n \"object\":
\"chat.completion\",\n \"created\": 1739299455,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
161,\n \"completion_tokens\": 12,\n \"total_tokens\": 173,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 91067d389e90fa16-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 11 Feb 2025 18:44:15 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=cRijYuylMGzRGxv3udQL5PhHOR5mRN_9_eLLwevlM_o-1739299455-1.0.1.1-Fszr_Msw0B1.IBMkiunP.VF2ilul1YGZZV8TqMcO3Q2SHvSlqfgm9NHgns1bJrm0wWRvHiCE7wdZfUAOx7T3Lg;
path=/; expires=Tue, 11-Feb-25 19:14:15 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '716'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999810'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_ef807dc3223d40332aae8a313e96ef3a
http_version: HTTP/1.1
status_code: 200
version: 1

1004
tests/utilities/cassettes/test_task_emits_failed_event_on_execution_error.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

7984
tests/utilities/cassettes/test_tools_emits_error_events.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

512
tests/utilities/cassettes/test_tools_emits_finished_events.yaml Normal file
View File

@@ -0,0 +1,512 @@
interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: say_hi\nTool Arguments: {}\nTool Description:
Say hi\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [say_hi], just the name, exactly as it''s written.\nAction Input: the
input to the action, just a simple JSON object, enclosed in curly braces, using
\" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
all necessary information is gathered, return the following format:\n\n```\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n```"}, {"role": "user", "content": "\nCurrent Task: Just say
hi\n\nThis is the expect criteria for your final answer: hi\nyou MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1275'
content-type:
- application/json
cookie:
- _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzUA6kJQfpUvB4CGot4gSfAIR0foh\",\n \"object\":
\"chat.completion\",\n \"created\": 1739217314,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"you should always think about what to
do \\nAction: say_hi \\nAction Input: {} \",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 257,\n \"completion_tokens\":
19,\n \"total_tokens\": 276,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90fea7d78e1fceb9-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 10 Feb 2025 19:55:15 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=fmlg1wjOwuOwZhUUOEtL1tQYluAPumn7AHLF8s0EU2Y-1739217315-1.0.1.1-PQDvxn8TOhzaznlHjwVsqPZUzbAyJWFkvzCubfNJydTu2_AyA1cJ8hkM0khsEE4UY_xp8iPe2gSGmH1ydrDa0Q;
path=/; expires=Mon, 10-Feb-25 20:25:15 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '526'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999703'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_f6358ff0cc7a2b8d2e167ab00a40f2a4
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
a helpful assistant that just says hi\nYour personal goal is: Just say hi\nYou
ONLY have access to the following tools, and should NEVER make up tools that
are not listed here:\n\nTool Name: say_hi\nTool Arguments: {}\nTool Description:
Say hi\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought:
you should always think about what to do\nAction: the action to take, only one
name of [say_hi], just the name, exactly as it''s written.\nAction Input: the
input to the action, just a simple JSON object, enclosed in curly braces, using
\" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
all necessary information is gathered, return the following format:\n\n```\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question\n```"}, {"role": "user", "content": "\nCurrent Task: Just say
hi\n\nThis is the expect criteria for your final answer: hi\nyou MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "you
should always think about what to do \nAction: say_hi \nAction Input: {} \nObservation:
hi"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1410'
content-type:
- application/json
cookie:
- _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000;
__cf_bm=fmlg1wjOwuOwZhUUOEtL1tQYluAPumn7AHLF8s0EU2Y-1739217315-1.0.1.1-PQDvxn8TOhzaznlHjwVsqPZUzbAyJWFkvzCubfNJydTu2_AyA1cJ8hkM0khsEE4UY_xp8iPe2gSGmH1ydrDa0Q
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzUA7QdlQy1WZZijxNWUv25sZycg0\",\n \"object\":
\"chat.completion\",\n \"created\": 1739217315,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"```\\nThought: I now know the final answer\\nFinal
Answer: hi\\n```\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
283,\n \"completion_tokens\": 17,\n \"total_tokens\": 300,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90fea7dc5ba6ceb9-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 10 Feb 2025 19:55:15 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '388'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999680'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_7d7c68b90b3a9c3ac6092fe17ac1185a
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '6534'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Mon, 10 Feb 2025 19:55:17 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
completed based on the description, expected output, and actual results.\n\nTask
Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n```\n\nPlease
provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
from 0 to 10 evaluating on completion, quality, and overall performance- Entities
extracted from the task output, if any, their type, description, and relationships"}],
"model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
"TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
"description": "Correctly extracted `TaskEvaluation` with all the required parameters
with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
{"description": "The name of the entity.", "title": "Name", "type": "string"},
"type": {"description": "The type of the entity.", "title": "Type", "type":
"string"}, "description": {"description": "Description of the entity.", "title":
"Description", "type": "string"}, "relationships": {"description": "Relationships
of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
"array"}}, "required": ["name", "type", "description", "relationships"], "title":
"Entity", "type": "object"}}, "properties": {"suggestions": {"description":
"Suggestions to improve future similar tasks.", "items": {"type": "string"},
"title": "Suggestions", "type": "array"}, "quality": {"description": "A score
from 0 to 10 evaluating on completion, quality, and overall performance, all
taking into account the task description, expected output, and the result of
the task.", "title": "Quality", "type": "number"}, "entities": {"description":
"Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
"title": "Entities", "type": "array"}}, "required": ["entities", "quality",
"suggestions"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1967'
content-type:
- application/json
cookie:
- _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000;
__cf_bm=fmlg1wjOwuOwZhUUOEtL1tQYluAPumn7AHLF8s0EU2Y-1739217315-1.0.1.1-PQDvxn8TOhzaznlHjwVsqPZUzbAyJWFkvzCubfNJydTu2_AyA1cJ8hkM0khsEE4UY_xp8iPe2gSGmH1ydrDa0Q
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.61.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.61.0
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.8
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AzUA8oE0A2d99i1Khpu0CI7fSgRtZ\",\n \"object\":
\"chat.completion\",\n \"created\": 1739217316,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n
\ \"id\": \"call_bk3duHRErK1qCyvWJ1uVmmGl\",\n \"type\":
\"function\",\n \"function\": {\n \"name\": \"TaskEvaluation\",\n
\ \"arguments\": \"{\\\"suggestions\\\":[\\\"Provide more context
or details for similar tasks to enhance clarity.\\\",\\\"Specify desired tone
or style for the output.\\\",\\\"Consider adding more variety in tasks to keep
engagement high.\\\"],\\\"quality\\\":10,\\\"entities\\\":[{\\\"name\\\":\\\"hi\\\",\\\"type\\\":\\\"greeting\\\",\\\"description\\\":\\\"A
casual way to say hello or acknowledge someone's presence.\\\",\\\"relationships\\\":[\\\"used
as a greeting\\\",\\\"expresses friendliness\\\"]}]}\"\n }\n }\n
\ ],\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
275,\n \"completion_tokens\": 80,\n \"total_tokens\": 355,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":
\"default\",\n \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
headers:
CF-RAY:
- 90fea7dfef41ceb9-SJC
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 10 Feb 2025 19:55:17 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
cf-cache-status:
- DYNAMIC
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1535'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999874'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_55d8eb91b4318245556b73d3f4c1e7c4
http_version: HTTP/1.1
status_code: 200
version: 1

497
tests/utilities/test_events.py Normal file
View File

@@ -0,0 +1,497 @@
import json
from datetime import datetime
from unittest.mock import MagicMock, patch
import pytest
from pydantic import Field
from crewai.agent import Agent
from crewai.agents.crew_agent_executor import CrewAgentExecutor
from crewai.crew import Crew
from crewai.flow.flow import Flow, listen, start
from crewai.task import Task
from crewai.tools.base_tool import BaseTool
from crewai.tools.tool_usage import ToolUsage
from crewai.utilities.events.agent_events import (
AgentExecutionCompletedEvent,
AgentExecutionErrorEvent,
AgentExecutionStartedEvent,
)
from crewai.utilities.events.crew_events import (
CrewKickoffCompletedEvent,
CrewKickoffFailedEvent,
CrewKickoffStartedEvent,
)
from crewai.utilities.events.crewai_event_bus import crewai_event_bus
from crewai.utilities.events.event_types import ToolUsageFinishedEvent
from crewai.utilities.events.flow_events import (
FlowCreatedEvent,
FlowFinishedEvent,
FlowStartedEvent,
MethodExecutionFailedEvent,
MethodExecutionStartedEvent,
)
from crewai.utilities.events.task_events import (
TaskCompletedEvent,
TaskFailedEvent,
TaskStartedEvent,
)
from crewai.utilities.events.tool_usage_events import (
ToolUsageErrorEvent,
)
base_agent = Agent(
role="base_agent",
llm="gpt-4o-mini",
goal="Just say hi",
backstory="You are a helpful assistant that just says hi",
)
base_task = Task(
description="Just say hi",
expected_output="hi",
agent=base_agent,
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_emits_start_kickoff_event():
received_events = []
with crewai_event_bus.scoped_handlers():
@crewai_event_bus.on(CrewKickoffStartedEvent)
def handle_crew_start(source, event):
received_events.append(event)
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
assert len(received_events) == 1
assert received_events[0].crew_name == "TestCrew"
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "crew_kickoff_started"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_emits_end_kickoff_event():
received_events = []
@crewai_event_bus.on(CrewKickoffCompletedEvent)
def handle_crew_end(source, event):
received_events.append(event)
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
assert len(received_events) == 1
assert received_events[0].crew_name == "TestCrew"
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "crew_kickoff_completed"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_emits_kickoff_failed_event():
received_events = []
with crewai_event_bus.scoped_handlers():
@crewai_event_bus.on(CrewKickoffFailedEvent)
def handle_crew_failed(source, event):
received_events.append(event)
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
with patch.object(Crew, "_execute_tasks") as mock_execute:
error_message = "Simulated crew kickoff failure"
mock_execute.side_effect = Exception(error_message)
with pytest.raises(Exception):
crew.kickoff()
assert len(received_events) == 1
assert received_events[0].error == error_message
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "crew_kickoff_failed"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_emits_start_task_event():
received_events = []
@crewai_event_bus.on(TaskStartedEvent)
def handle_task_start(source, event):
received_events.append(event)
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
assert len(received_events) == 1
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "task_started"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_emits_end_task_event():
received_events = []
@crewai_event_bus.on(TaskCompletedEvent)
def handle_task_end(source, event):
received_events.append(event)
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
assert len(received_events) == 1
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "task_completed"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_task_emits_failed_event_on_execution_error():
received_events = []
received_sources = []
@crewai_event_bus.on(TaskFailedEvent)
def handle_task_failed(source, event):
received_events.append(event)
received_sources.append(source)
with patch.object(
Task,
"_execute_core",
) as mock_execute:
error_message = "Simulated task failure"
mock_execute.side_effect = Exception(error_message)
agent = Agent(
role="base_agent",
goal="Just say hi",
backstory="You are a helpful assistant that just says hi",
)
task = Task(
description="Just say hi",
expected_output="hi",
agent=agent,
)
with pytest.raises(Exception):
agent.execute_task(task=task)
assert len(received_events) == 1
assert received_sources[0] == task
assert received_events[0].error == error_message
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "task_failed"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_agent_emits_execution_started_and_completed_events():
received_events = []
@crewai_event_bus.on(AgentExecutionStartedEvent)
def handle_agent_start(source, event):
received_events.append(event)
@crewai_event_bus.on(AgentExecutionCompletedEvent)
def handle_agent_completed(source, event):
received_events.append(event)
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
assert len(received_events) == 2
assert received_events[0].agent == base_agent
assert received_events[0].task == base_task
assert received_events[0].tools == []
assert isinstance(received_events[0].task_prompt, str)
assert (
received_events[0].task_prompt
== "Just say hi\n\nThis is the expected criteria for your final answer: hi\nyou MUST return the actual complete content as the final answer, not a summary."
)
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "agent_execution_started"
assert isinstance(received_events[1].timestamp, datetime)
assert received_events[1].type == "agent_execution_completed"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_agent_emits_execution_error_event():
received_events = []
@crewai_event_bus.on(AgentExecutionErrorEvent)
def handle_agent_start(source, event):
received_events.append(event)
error_message = "Error happening while sending prompt to model."
base_agent.max_retry_limit = 0
with patch.object(
CrewAgentExecutor, "invoke", wraps=base_agent.agent_executor.invoke
) as invoke_mock:
invoke_mock.side_effect = Exception(error_message)
with pytest.raises(Exception) as e:
base_agent.execute_task(
task=base_task,
)
assert len(received_events) == 1
assert received_events[0].agent == base_agent
assert received_events[0].task == base_task
assert received_events[0].error == error_message
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "agent_execution_error"
class SayHiTool(BaseTool):
name: str = Field(default="say_hi", description="The name of the tool")
description: str = Field(
default="Say hi", description="The description of the tool"
)
def _run(self) -> str:
return "hi"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_tools_emits_finished_events():
received_events = []
@crewai_event_bus.on(ToolUsageFinishedEvent)
def handle_tool_end(source, event):
received_events.append(event)
agent = Agent(
role="base_agent",
goal="Just say hi",
backstory="You are a helpful assistant that just says hi",
tools=[SayHiTool()],
)
task = Task(
description="Just say hi",
expected_output="hi",
agent=agent,
)
crew = Crew(agents=[agent], tasks=[task], name="TestCrew")
crew.kickoff()
assert len(received_events) == 1
assert received_events[0].agent_key == agent.key
assert received_events[0].agent_role == agent.role
assert received_events[0].tool_name == SayHiTool().name
assert received_events[0].tool_args == {}
assert received_events[0].type == "tool_usage_finished"
assert isinstance(received_events[0].timestamp, datetime)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_tools_emits_error_events():
received_events = []
@crewai_event_bus.on(ToolUsageErrorEvent)
def handle_tool_end(source, event):
received_events.append(event)
class ErrorTool(BaseTool):
name: str = Field(
default="error_tool", description="A tool that raises an error"
)
description: str = Field(
default="This tool always raises an error",
description="The description of the tool",
)
def _run(self) -> str:
raise Exception("Simulated tool error")
agent = Agent(
role="base_agent",
goal="Try to use the error tool",
backstory="You are an assistant that tests error handling",
tools=[ErrorTool()],
)
task = Task(
description="Use the error tool",
expected_output="This should error",
agent=agent,
)
crew = Crew(agents=[agent], tasks=[task], name="TestCrew")
crew.kickoff()
assert len(received_events) == 75
assert received_events[0].agent_key == agent.key
assert received_events[0].agent_role == agent.role
assert received_events[0].tool_name == "error_tool"
assert received_events[0].tool_args == {}
assert str(received_events[0].error) == "Simulated tool error"
assert received_events[0].type == "tool_usage_error"
assert isinstance(received_events[0].timestamp, datetime)
def test_flow_emits_start_event():
received_events = []
with crewai_event_bus.scoped_handlers():
@crewai_event_bus.on(FlowStartedEvent)
def handle_flow_start(source, event):
received_events.append(event)
class TestFlow(Flow[dict]):
@start()
def begin(self):
return "started"
flow = TestFlow()
flow.kickoff()
assert len(received_events) == 1
assert received_events[0].flow_name == "TestFlow"
assert received_events[0].type == "flow_started"
def test_flow_emits_finish_event():
received_events = []
with crewai_event_bus.scoped_handlers():
@crewai_event_bus.on(FlowFinishedEvent)
def handle_flow_finish(source, event):
received_events.append(event)
class TestFlow(Flow[dict]):
@start()
def begin(self):
return "completed"
flow = TestFlow()
result = flow.kickoff()
assert len(received_events) == 1
assert received_events[0].flow_name == "TestFlow"
assert received_events[0].type == "flow_finished"
assert received_events[0].result == "completed"
assert result == "completed"
def test_flow_emits_method_execution_started_event():
received_events = []
with crewai_event_bus.scoped_handlers():
@crewai_event_bus.on(MethodExecutionStartedEvent)
def handle_method_start(source, event):
print("event in method name", event.method_name)
received_events.append(event)
class TestFlow(Flow[dict]):
@start()
def begin(self):
return "started"
@listen("begin")
def second_method(self):
return "executed"
flow = TestFlow()
flow.kickoff()
assert len(received_events) == 2
assert received_events[0].method_name == "begin"
assert received_events[0].flow_name == "TestFlow"
assert received_events[0].type == "method_execution_started"
assert received_events[1].method_name == "second_method"
assert received_events[1].flow_name == "TestFlow"
assert received_events[1].type == "method_execution_started"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_register_handler_adds_new_handler():
received_events = []
def custom_handler(source, event):
received_events.append(event)
with crewai_event_bus.scoped_handlers():
crewai_event_bus.register_handler(CrewKickoffStartedEvent, custom_handler)
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
assert len(received_events) == 1
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "crew_kickoff_started"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_multiple_handlers_for_same_event():
received_events_1 = []
received_events_2 = []
def handler_1(source, event):
received_events_1.append(event)
def handler_2(source, event):
received_events_2.append(event)
with crewai_event_bus.scoped_handlers():
crewai_event_bus.register_handler(CrewKickoffStartedEvent, handler_1)
crewai_event_bus.register_handler(CrewKickoffStartedEvent, handler_2)
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
assert len(received_events_1) == 1
assert len(received_events_2) == 1
assert received_events_1[0].type == "crew_kickoff_started"
assert received_events_2[0].type == "crew_kickoff_started"
def test_flow_emits_created_event():
received_events = []
@crewai_event_bus.on(FlowCreatedEvent)
def handle_flow_created(source, event):
received_events.append(event)
class TestFlow(Flow[dict]):
@start()
def begin(self):
return "started"
flow = TestFlow()
flow.kickoff()
assert len(received_events) == 1
assert received_events[0].flow_name == "TestFlow"
assert received_events[0].type == "flow_created"
def test_flow_emits_method_execution_failed_event():
received_events = []
error = Exception("Simulated method failure")
@crewai_event_bus.on(MethodExecutionFailedEvent)
def handle_method_failed(source, event):
received_events.append(event)
class TestFlow(Flow[dict]):
@start()
def begin(self):
raise error
flow = TestFlow()
with pytest.raises(Exception):
flow.kickoff()
assert len(received_events) == 1
assert received_events[0].method_name == "begin"
assert received_events[0].flow_name == "TestFlow"
assert received_events[0].type == "method_execution_failed"
assert received_events[0].error == error