Enhance MCP development features and introduce skills management

- Added configuration options for requiring human approval before applying LLM-generated MCP patches.
- Updated Docker setup to include skills directory.
- Integrated skills management into the backend, allowing for procedural guides and skill matching.
- Refactored database initialization to apply Alembic migrations.
- Enhanced task approval process to handle MCP patch applications with optional approval.
- Introduced new schemas for skills and updated existing APIs to support skills functionality.

This commit lays the groundwork for improved agent capabilities and better management of MCP development processes.

backend/app/config.py

@@ -75,11 +75,17 @@ class Settings(BaseSettings):
     # Troubleshooting decision rules (YAML, editable via Admin → Rules)
     troubleshooting_rules_path: str = "/app/rules/troubleshooting.yaml"
 
+    # Agent skills (procedural guides in skills/*/SKILL.md)
+    skills_path: str = "/app/skills"
+    skills_max_matched: int = 2
+    skills_max_body_chars: int = 8000
+
     # Runtime paths (inside container)
     runtime_dir: str = "/runtime"
 
     # MCP self-development: agent patches MCP source on tool failure / missing capability
     mcp_development_enabled: bool = True
+    mcp_dev_require_approval: bool = True  # when true, apply/reload waits for human approval
     mcp_dev_auto_push: bool = False  # when false, patch applies + reload; git push needs approval
     mcp_dev_model_tier: str = "premium"