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/memory/working.py

@@ -9,7 +9,7 @@ Working memory provides short-term storage for active tasks:
 
 from collections import defaultdict
 from datetime import datetime
-from typing import Any, Iterator
+from typing import Any
 
 from fusionagi._logger import logger
 from fusionagi._time import utc_now
@@ -18,7 +18,7 @@ from fusionagi._time import utc_now
 class WorkingMemory:
     """
     Short-term working memory per task/session.
-    
+
     Features:
     - Key-value get/set operations
     - List append with automatic coercion
@@ -30,7 +30,7 @@ class WorkingMemory:
     def __init__(self, max_entries_per_session: int = 1000) -> None:
         """
         Initialize working memory.
-        
+
         Args:
             max_entries_per_session: Maximum entries per session before oldest are removed.
         """
@@ -90,12 +90,12 @@ class WorkingMemory:
     def get_context_summary(self, session_id: str, max_items: int = 10) -> dict[str, Any]:
         """
         Get a summary of working memory for context injection.
-        
+
         Useful for including relevant context in LLM prompts.
         """
         session_data = self._store.get(session_id, {})
         summary = {}
-        
+
         for key, value in list(session_data.items())[:max_items]:
             if isinstance(value, list):
                 # For lists, include count and last few items
@@ -113,10 +113,10 @@ class WorkingMemory:
             else:
                 # For scalars, include the value (truncated if string)
                 if isinstance(value, str) and len(value) > 200:
-                    summary[key] = value[:200] + "..."
+                    summary[key] = value[:200] + "..."  # type: ignore[assignment]
                 else:
-                    summary[key] = value
-        
+                    summary[key] = value  # type: ignore[assignment]
+
         return summary
 
     def get_all(self, session_id: str) -> dict[str, Any]:
@@ -142,7 +142,7 @@ class WorkingMemory:
             len(v) if isinstance(v, (list, dict)) else 1
             for v in session_data.values()
         )
-        
+
         if total_items > self._max_entries:
             logger.warning(
                 "Working memory size limit exceeded",