feat: migrate to Agno native HITL tool confirmation flow (#158)

Replace the homebrew regex-based tool extraction and manual dispatch
(tool_executor.py) with Agno's built-in Human-In-The-Loop confirmation:

- Toolkit(requires_confirmation_tools=...) marks dangerous tools
- agent.run() returns RunOutput with status=paused when confirmation needed
- RunRequirement.confirm()/reject() + agent.continue_run() resumes execution

Dashboard and Discord vendor both use the native flow. DuckDuckGo import
isolated so its absence doesn't kill all tools. Test stubs cleaned up
(agno is a real dependency, only truly optional packages stubbed).

1384 tests pass in parallel (~14s).

Co-authored-by: Trip T <trip@local>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

tests/timmy/test_ollama_timeout.py

@@ -5,11 +5,15 @@ This caused socket read errors in production. The agno Ollama class uses
 ``timeout`` (not ``request_timeout``).
 """
 
+import importlib
 from unittest.mock import MagicMock, patch
 
 
 def test_base_agent_sets_timeout():
     """BaseAgent creates Ollama with timeout=300."""
+    # Ensure module is loaded before patching — prevents xdist ordering issues
+    importlib.import_module("timmy.agents.base")
+
     with patch("timmy.agents.base.Ollama") as mock_ollama, patch("timmy.agents.base.Agent"):
         mock_ollama.return_value = MagicMock()