feat(memory): add database schema and storage layer (Issue #88)

Add SQLAlchemy models for the Agent Memory System:
- WorkingMemory: Key-value storage with TTL for active sessions
- Episode: Experiential memories from task executions
- Fact: Semantic knowledge triples with confidence scores
- Procedure: Learned skills and procedures with success tracking
- MemoryConsolidationLog: Tracks consolidation jobs between memory tiers

Create enums for memory system:
- ScopeType: global, project, agent_type, agent_instance, session
- EpisodeOutcome: success, failure, partial
- ConsolidationType: working_to_episodic, episodic_to_semantic, etc.
- ConsolidationStatus: pending, running, completed, failed

Add Alembic migration (0005) for all memory tables with:
- Foreign key relationships to projects, agent_instances, agent_types
- Comprehensive indexes for query patterns
- Unique constraints for key lookups and triple uniqueness
- Vector embedding column placeholders (Text fallback until pgvector enabled)

Fix timezone-naive datetime.now() in types.py TaskState (review feedback)

Includes 30 unit tests for models and enums.

Closes #88

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

backend/app/models/memory/consolidation.py

@@ -0,0 +1,72 @@
+# app/models/memory/consolidation.py
+"""
+Memory Consolidation Log database model.
+
+Tracks memory consolidation jobs that transfer knowledge
+between memory tiers.
+"""
+
+from sqlalchemy import Column, DateTime, Enum, Index, Integer, Text
+
+from app.models.base import Base, TimestampMixin, UUIDMixin
+
+from .enums import ConsolidationStatus, ConsolidationType
+
+
+class MemoryConsolidationLog(Base, UUIDMixin, TimestampMixin):
+    """
+    Memory consolidation job log.
+
+    Tracks consolidation operations:
+    - Working -> Episodic (session end)
+    - Episodic -> Semantic (fact extraction)
+    - Episodic -> Procedural (procedure learning)
+    - Pruning (removing low-value memories)
+    """
+
+    __tablename__ = "memory_consolidation_log"
+
+    # Consolidation type
+    consolidation_type: Column[ConsolidationType] = Column(
+        Enum(ConsolidationType),
+        nullable=False,
+        index=True,
+    )
+
+    # Counts
+    source_count = Column(Integer, nullable=False, default=0)
+    result_count = Column(Integer, nullable=False, default=0)
+
+    # Timing
+    started_at = Column(DateTime(timezone=True), nullable=False)
+    completed_at = Column(DateTime(timezone=True), nullable=True)
+
+    # Status
+    status: Column[ConsolidationStatus] = Column(
+        Enum(ConsolidationStatus),
+        nullable=False,
+        default=ConsolidationStatus.PENDING,
+        index=True,
+    )
+
+    # Error details if failed
+    error = Column(Text, nullable=True)
+
+    __table_args__ = (
+        # Query patterns
+        Index("ix_consolidation_type_status", "consolidation_type", "status"),
+        Index("ix_consolidation_started", "started_at"),
+    )
+
+    @property
+    def duration_seconds(self) -> float | None:
+        """Calculate duration of the consolidation job."""
+        if self.completed_at is None or self.started_at is None:
+            return None
+        return (self.completed_at - self.started_at).total_seconds()
+
+    def __repr__(self) -> str:
+        return (
+            f"<MemoryConsolidationLog {self.id} "
+            f"type={self.consolidation_type.value} status={self.status.value}>"
+        )