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>

fusionagi/reasoning/multi_path.py

@@ -1,13 +1,17 @@
-"""Multi-path inference: parallel hypothesis generation and scoring."""
+"""Multi-path inference: parallel hypothesis generation and scoring.
+
+Supports GPU-accelerated scoring when ``fusionagi[gpu]`` is installed;
+falls back to CPU ``ThreadPoolExecutor`` otherwise.
+"""
 
 from __future__ import annotations
 
 from concurrent.futures import ThreadPoolExecutor, as_completed
-from typing import Any, Callable
+from typing import Callable
 
-from fusionagi.schemas.atomic import AtomicSemanticUnit
-from fusionagi.reasoning.tot import ThoughtNode
 from fusionagi._logger import logger
+from fusionagi.reasoning.tot import ThoughtNode
+from fusionagi.schemas.atomic import AtomicSemanticUnit
 
 
 def _score_coherence(node: ThoughtNode, _units: list[AtomicSemanticUnit]) -> float:
@@ -24,12 +28,42 @@ def _score_consistency(node: ThoughtNode, units: list[AtomicSemanticUnit]) -> fl
     return min(1.0, overlap * 2)
 
 
+def _try_gpu_score(
+    hypotheses: list[str],
+    units: list[AtomicSemanticUnit],
+) -> list[tuple[ThoughtNode, float]] | None:
+    """Attempt GPU-accelerated scoring; return ``None`` if unavailable."""
+    try:
+        from fusionagi.gpu.tensor_scoring import gpu_score_hypotheses
+
+        results = gpu_score_hypotheses(hypotheses, units)
+        logger.debug(
+            "multi_path: GPU scoring used",
+            extra={"count": len(hypotheses)},
+        )
+        return results
+    except ImportError:
+        return None
+
+
 def generate_and_score_parallel(
     hypotheses: list[str],
     units: list[AtomicSemanticUnit],
     score_fn: Callable[[ThoughtNode, list[AtomicSemanticUnit]], float] | None = None,
+    *,
+    use_gpu: bool = True,
 ) -> list[tuple[ThoughtNode, float]]:
-    """Score multiple hypotheses in parallel."""
+    """Score multiple hypotheses in parallel.
+
+    When *use_gpu* is ``True`` (default) and no custom *score_fn* is
+    provided, tries GPU-accelerated scoring first.  Falls back to the
+    threaded CPU implementation when the GPU module is unavailable.
+    """
+    if use_gpu and score_fn is None:
+        gpu_result = _try_gpu_score(hypotheses, units)
+        if gpu_result is not None:
+            return gpu_result
+
     score_fn = score_fn or (lambda n, u: _score_coherence(n, u) * 0.5 + _score_consistency(n, u) * 0.5)
 
     def score_one(h: str, i: int) -> tuple[ThoughtNode, float]: