2026-02-09 21:51:42 -08:00
|
|
|
"""
|
|
|
|
|
Self-improvement subsystem for FusionAGI: self-correction, auto-recommend/suggest, auto-training.
|
|
|
|
|
|
|
|
|
|
Enables the world's most advanced agentic AGI system to improve, correct, and train itself
|
|
|
|
|
from execution outcomes and reflection.
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
from fusionagi.self_improvement.correction import SelfCorrectionLoop
|
fix: deep GPU integration, fix all ruff/mypy issues, add .dockerignore
- Integrate GPU scoring inline into reasoning/multi_path.py (auto-uses GPU when available)
- Integrate GPU deduplication into multi_agent/consensus_engine.py
- Add semantic_search() method to memory/semantic_graph.py with GPU acceleration
- Integrate GPU training into self_improvement/training.py AutoTrainer
- Fix all 758 ruff lint issues (whitespace, import sorting, unused imports, ambiguous vars, undefined names)
- Fix all 40 mypy type errors across the codebase (no-any-return, union-attr, arg-type, etc.)
- Fix deprecated ruff config keys (select/ignore -> [tool.ruff.lint])
- Add .dockerignore to exclude .venv/, tests/, docs/ from Docker builds
- Add type hints and docstrings to verification/outcome.py
- Fix E402 import ordering in witness_agent.py
- Fix F821 undefined names in vector_pgvector.py and native.py
- Fix E741 ambiguous variable names in reflective.py and recommender.py
All 276 tests pass. 0 ruff errors. 0 mypy errors.
Co-Authored-By: Nakamoto, S <defi@defi-oracle.io>
2026-04-28 05:48:37 +00:00
|
|
|
from fusionagi.self_improvement.loop import FusionAGILoop
|
2026-02-09 21:51:42 -08:00
|
|
|
from fusionagi.self_improvement.recommender import AutoRecommender
|
|
|
|
|
from fusionagi.self_improvement.training import AutoTrainer
|
|
|
|
|
|
|
|
|
|
__all__ = [
|
|
|
|
|
"SelfCorrectionLoop",
|
|
|
|
|
"AutoRecommender",
|
|
|
|
|
"AutoTrainer",
|
|
|
|
|
"FusionAGILoop",
|
|
|
|
|
]
|
