mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-08 15:48:29 +00:00
1b6b2b36d9
* feat: add exchanged messages in LLMCallCompletedEvent * feat: add GoalAlignment metric for Agent evaluation * feat: add SemanticQuality metric for Agent evaluation * feat: add Tool Metrics for Agent evaluation * feat: add Reasoning Metrics for Agent evaluation, still in progress * feat: add AgentEvaluator class This class will evaluate Agent' results and report to user * fix: do not evaluate Agent by default This is a experimental feature we still need refine it further * test: add Agent eval tests * fix: render all feedback per iteration * style: resolve linter issues * style: fix mypy issues * fix: allow messages be empty on LLMCallCompletedEvent * feat: add Experiment evaluation framework with baseline comparison * fix: reset evaluator for each experiement iteraction * fix: fix track of new test cases * chore: split Experimental evaluation classes * refactor: remove unused method * refactor: isolate Console print in a dedicated class * fix: make crew required to run an experiment * fix: use time-aware to define experiment result * test: add tests for Evaluator Experiment * style: fix linter issues * fix: encode string before hashing * style: resolve linter issues * feat: add experimental folder for beta features (#3141) * test: move tests to experimental folder
28 lines
793 B
Python
28 lines
793 B
Python
import pytest
|
|
from unittest.mock import MagicMock
|
|
from crewai.agent import Agent
|
|
from crewai.task import Task
|
|
|
|
class BaseEvaluationMetricsTest:
|
|
@pytest.fixture
|
|
def mock_agent(self):
|
|
agent = MagicMock(spec=Agent)
|
|
agent.id = "test_agent_id"
|
|
agent.role = "Test Agent"
|
|
agent.goal = "Test goal"
|
|
agent.tools = []
|
|
return agent
|
|
|
|
@pytest.fixture
|
|
def mock_task(self):
|
|
task = MagicMock(spec=Task)
|
|
task.description = "Test task description"
|
|
task.expected_output = "Test expected output"
|
|
return task
|
|
|
|
@pytest.fixture
|
|
def execution_trace(self):
|
|
return {
|
|
"thinking": ["I need to analyze this data carefully"],
|
|
"actions": ["Gathered information", "Analyzed data"]
|
|
} |