feat: Add Memory Reasoning Engine with derived knowledge inference

[Nsuccess]

Closes #250

What this PR does

Adds a Memory Reasoning Engine (MRE) that transforms MemU from a retrieval system into a reasoning system.

The core insight: Memory should not be static. Memory should produce new memory.

Current State vs Enhancement

Capability	Current MemU	With MRE
Memory access	Retrieve by similarity	Reason over relationships
Output	Stored memories	Stored + derived knowledge
Agent behavior	Reactive (answer when asked)	Reflective (infer before asked)

The Reasoning Loop

RETRIEVE → TRAVERSE → FILTER → SCORE → INFER → WRITE BACK

1. RETRIEVE - Get candidate memories matching query constraints
2. TRAVERSE - Walk knowledge graph relationships (requires feat: Add Knowledge Graph with entity extraction and graph traversal #249)
3. FILTER - Apply type, time range, confidence thresholds
4. SCORE - Rank by relevance + tool success rates (requires feat: Add Tool Memory type with specialized metadata and statistics #247)
5. INFER - LLM-assisted conclusion generation
6. WRITE BACK - Store derived memories with provenance

Key Components

ReasoningQuery DSL - Structured queries with constraints:

query = ReasoningQuery(
    goal="Who can help with database optimization?",
    constraints=ReasoningConstraints(
        entity_types=["Person"],
        memory_types=["knowledge", "tool"],
        relationships=["works_on", "expert_in"],
        time_range_days=30,
        require_tool_success=True
    ),
    reasoning_depth=2
)

DerivedMemory - Machine-generated knowledge with full provenance:

DerivedMemory(
    content="John is the best database expert",
    inference_type="deduction",
    source_memory_ids=["mem_1", "mem_2", "mem_3"],
    confidence_score=0.85,
    expires_at=datetime(2026, 2, 1)
)

Self-Consistency Verification - Run inference N times with different seeds:

• Consistent results → reinforce confidence
• Inconsistent results → weaken confidence
• Prevents hallucination from becoming "memory"

Files Added

File	Purpose
src/memu/reasoning/__init__.py	Module exports
src/memu/reasoning/query_dsl.py	ReasoningQuery, ReasoningConstraints, ReasoningTrace
src/memu/reasoning/derived_memory.py	DerivedMemory, DerivedMemoryStore
src/memu/reasoning/memory_reasoner.py	Core MemoryReasoner class
src/memu/reasoning/prompts.py	LLM prompts for inference
tests/test_memory_reasoner.py	29 unit tests

Tests

All 29 tests passing.

[sairin1202]

Same with PR#249, the knowledge graph approach conflicts with our current system architecture, so we’re unable to accept it. Appreciate your understanding.