mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-06 22:58:30 +00:00
00c2f5043e
* 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
115 lines
4.2 KiB
YAML
115 lines
4.2 KiB
YAML
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
|