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/enums.py

@@ -0,0 +1,73 @@
+# app/models/memory/enums.py
+"""
+Enums for Memory System database models.
+
+These enums define the database-level constraints for memory types
+and scoping levels.
+"""
+
+from enum import Enum as PyEnum
+
+
+class ScopeType(str, PyEnum):
+    """
+    Memory scope levels matching the memory service types.
+
+    GLOBAL: System-wide memories accessible by all
+    PROJECT: Project-scoped memories
+    AGENT_TYPE: Type-specific memories (shared by instances of same type)
+    AGENT_INSTANCE: Instance-specific memories
+    SESSION: Session-scoped ephemeral memories
+    """
+
+    GLOBAL = "global"
+    PROJECT = "project"
+    AGENT_TYPE = "agent_type"
+    AGENT_INSTANCE = "agent_instance"
+    SESSION = "session"
+
+
+class EpisodeOutcome(str, PyEnum):
+    """
+    Outcome of an episode (task execution).
+
+    SUCCESS: Task completed successfully
+    FAILURE: Task failed
+    PARTIAL: Task partially completed
+    """
+
+    SUCCESS = "success"
+    FAILURE = "failure"
+    PARTIAL = "partial"
+
+
+class ConsolidationType(str, PyEnum):
+    """
+    Types of memory consolidation operations.
+
+    WORKING_TO_EPISODIC: Transfer session state to episodic
+    EPISODIC_TO_SEMANTIC: Extract facts from episodes
+    EPISODIC_TO_PROCEDURAL: Extract procedures from episodes
+    PRUNING: Remove low-value memories
+    """
+
+    WORKING_TO_EPISODIC = "working_to_episodic"
+    EPISODIC_TO_SEMANTIC = "episodic_to_semantic"
+    EPISODIC_TO_PROCEDURAL = "episodic_to_procedural"
+    PRUNING = "pruning"
+
+
+class ConsolidationStatus(str, PyEnum):
+    """
+    Status of a consolidation job.
+
+    PENDING: Job is queued
+    RUNNING: Job is currently executing
+    COMPLETED: Job finished successfully
+    FAILED: Job failed with errors
+    """
+
+    PENDING = "pending"
+    RUNNING = "running"
+    COMPLETED = "completed"
+    FAILED = "failed"