- Finish editing of Specialists with overview, agent - task - tool editor

- Split differrent caching mechanisms (types, version tree, config) into different cachers
- Improve resource usage on starting components, and correct gevent usage
- Refine repopack usage for eveai_app (too large)
- Change nginx dockerfile to allow for specialist overviews being served statically

common/models/interaction.py

@@ -73,6 +73,7 @@ class EveAITask(db.Model):
     description = db.Column(db.Text, nullable=True)
     type = db.Column(db.String(50), nullable=False, default="STANDARD_RAG")
     type_version = db.Column(db.String(20), nullable=True, default="1.0.0")
+    task_description = db.Column(db.Text, nullable=True)
     expected_output = db.Column(db.Text, nullable=True)
     tuning = db.Column(db.Boolean, nullable=True, default=False)
     configuration = db.Column(JSONB, nullable=True)