feat(F): F-MEM agent_memory + frontend agent overview components

- F-MEM: app/ai/agent_memory.py (236 lines) — store/retrieve/search agent memory with embeddings
- Frontend: AgentDashboard.tsx (831 lines), AgentsOverview.tsx (35 lines) — agent list and dashboard
- agent_memory plugin models updated

app/plugins/builtins/agent_memory/migrations/0002_metadata.sql

@@ -0,0 +1,3 @@
+-- Agent Memory: add metadata JSONB column for structured memory metadata
+
+ALTER TABLE agent_memories ADD COLUMN IF NOT EXISTS metadata JSONB;

app/plugins/builtins/agent_memory/models.py

@@ -3,8 +3,10 @@
 from __future__ import annotations
 
 import uuid
+from typing import Any
 
 from sqlalchemy import Index, String, Text
+from sqlalchemy.dialects.postgresql import JSONB
 from sqlalchemy.dialects.postgresql import UUID as PGUUID
 from sqlalchemy.orm import Mapped, mapped_column
 
@@ -35,5 +37,8 @@ class AgentMemory(Base, TenantMixin, OwnedMixin):
         String(50), nullable=False, default="fact"
     )
     content: Mapped[str] = mapped_column(Text, nullable=False)
+    metadata_: Mapped[dict[str, Any] | None] = mapped_column(
+        "metadata", JSONB, nullable=True
+    )
     # embedding column is managed via raw SQL (pgvector extension)
     # embedding vector(768) — see migration 0001_initial.sql