andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-08 15:48:29 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
e8a559bf2429e8bd6ec3ad20894ae98dee1636c5
crewAI/tests/utilities/cassettes/test_crew_emits_end_task_event.yaml
Lorenze Jay 00c2f5043e WIP crew events emitter (#2048) 
* 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
2025-02-19 13:52:47 -08:00

358 lines
18 KiB
YAML
Raw Blame History

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
Reference in New Issue View Git Blame Copy Permalink