feat: Add evaluation hooks, skill adaptation and team pipeline config

- Add EvaluationHook for post-execution agent evaluation
- Add SkillAdaptationHook for dynamic skill adaptation
- Add team/ directory with team coordination logic
- Add TEAM_PIPELINE.yaml for smoke_fullstack pipeline config
- Update RuntimeView, TraderView and RuntimeSettingsPanel UI
- Add runtimeApi and websocket services
- Add runtime_state.json to smoke_fullstack state

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

backend/agents/prompt_factory.py

@@ -50,7 +50,13 @@ def build_agent_system_prompt(
     toolkit: Any,
     analyst_type: Optional[str] = None,
 ) -> str:
-    """Build the final system prompt for an agent."""
+    """Build the final system prompt for an agent.
+
+    Always reads fresh from disk — no caching.
+    """
+    # Clear any cached templates before building (CoPaw-style, no caching)
+    _prompt_loader.clear_cache()
+
     sections: list[str] = []
     canonical_agent_id = (
         "portfolio_manager"