64b800c6cf
Items completed: 1. Merged PR #2 (starlette/httpx deps) 2. Fixed async race condition in multimodal_ui.py 3. Wired TTSAdapter (ElevenLabs, Azure) in API routes 4. Moved super_big_brain.py from core/ to reasoning/ (backward compat shim) 5. Added API authentication middleware (Bearer token via FUSIONAGI_API_KEY) 6. Added async adapter interface (acomplete/acomplete_structured) 7. Migrated FastAPI on_event to lifespan (fixes 20 deprecation warnings) 8. Liquid Neural Networks (continuous-time adaptive weights) 9. Quantum-AI Hybrid compute backend (simulator + optimization) 10. Embodied Intelligence / Robotics bridge (actuator + sensor protocols) 11. Consciousness Engineering (formal self-model with introspection) 12. ASI Scoring Rubric (C/A/L/N/R self-assessment harness) 13. GPU integration tests for TensorFlow backend 14. Multi-stage production Dockerfile 15. Gitea CI/CD pipeline (lint, test matrix, Docker build) 16. API rate limiting middleware (per-IP sliding window) 17. OpenAPI docs cleanup (auth + rate limiting descriptions) 18. Benchmarking suite (decomposition, multi-path, recomposition, e2e) 19. Plugin system (head registry for custom heads) 427 tests passing, 0 ruff errors, 0 mypy errors. Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
63 lines
2.1 KiB
Python
63 lines
2.1 KiB
Python
"""Tests for the benchmarking suite."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from fusionagi.evaluation.benchmarks import BenchmarkSuite, run_benchmark
|
|
|
|
|
|
class TestRunBenchmark:
|
|
def test_basic_benchmark(self) -> None:
|
|
result = run_benchmark("test", lambda: sum(range(100)), iterations=10, warmup=2)
|
|
assert result.name == "test"
|
|
assert result.iterations == 10
|
|
assert result.mean_ms > 0
|
|
assert result.min_ms <= result.mean_ms
|
|
assert result.max_ms >= result.mean_ms
|
|
|
|
def test_summary_format(self) -> None:
|
|
result = run_benchmark("test", lambda: None, iterations=5)
|
|
summary = result.summary()
|
|
assert "test" in summary
|
|
assert "mean=" in summary
|
|
|
|
|
|
class TestBenchmarkSuite:
|
|
def test_decomposition_benchmark(self) -> None:
|
|
suite = BenchmarkSuite()
|
|
result = suite.run_decomposition_benchmark(iterations=3)
|
|
assert result.name == "decomposition"
|
|
|
|
def test_multi_path_benchmark(self) -> None:
|
|
suite = BenchmarkSuite()
|
|
result = suite.run_multi_path_benchmark(iterations=3)
|
|
assert result.name == "multi_path_scoring"
|
|
|
|
def test_recomposition_benchmark(self) -> None:
|
|
suite = BenchmarkSuite()
|
|
result = suite.run_recomposition_benchmark(iterations=3)
|
|
assert result.name == "recomposition"
|
|
|
|
def test_end_to_end_benchmark(self) -> None:
|
|
suite = BenchmarkSuite()
|
|
result = suite.run_end_to_end_benchmark(iterations=2)
|
|
assert result.name == "end_to_end_super_big_brain"
|
|
|
|
def test_run_all(self) -> None:
|
|
suite = BenchmarkSuite()
|
|
results = suite.run_all(iterations=2)
|
|
assert len(results) >= 4
|
|
|
|
def test_summary(self) -> None:
|
|
suite = BenchmarkSuite()
|
|
assert suite.summary() == "No benchmarks run."
|
|
suite.run_decomposition_benchmark(iterations=2)
|
|
summary = suite.summary()
|
|
assert "decomposition" in summary
|
|
|
|
def test_to_dict(self) -> None:
|
|
suite = BenchmarkSuite()
|
|
suite.run_decomposition_benchmark(iterations=2)
|
|
data = suite.to_dict()
|
|
assert len(data) == 1
|
|
assert "mean_ms" in data[0]
|