feat: replace custom Gitea client with MCP servers

Replace the bespoke GiteaHand httpx client and tools_gitea.py wrappers
with official MCP tool servers (gitea-mcp + filesystem MCP), wired into
Agno via MCPTools. Switch all session functions to async (arun/acontinue_run)
so MCP tools auto-connect. Delete ~1070 lines of custom Gitea code.

- Create src/timmy/mcp_tools.py with MCP factories + standalone issue bridge
- Wire MCPTools into agent.py tool list (Gitea + filesystem)
- Switch session.py chat/chat_with_tools/continue_chat to async
- Update all callers (dashboard routes, Discord vendor, CLI, thinking engine)
- Add gitea_token fallback from ~/.config/gitea/token
- Add MCP session cleanup to app shutdown hook
- Update tool_safety.py for MCP tool names
- 11 new tests, all 1417 passing, coverage 74.2%

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

tests/dashboard/test_agents_confirmation.py

@@ -1,6 +1,6 @@
 """Tests for dashboard tool confirmation flow using native Agno RunOutput."""
 
-from unittest.mock import MagicMock, patch
+from unittest.mock import AsyncMock, MagicMock, patch
 
 
 def _mock_completed_run(content="Just a reply."):
@@ -47,7 +47,7 @@ def test_chat_with_tool_call_shows_approval_card(client):
     item = _mock_approval_item()
 
     with (
-        patch("dashboard.routes.agents.chat_with_tools", return_value=run),
+        patch("dashboard.routes.agents.chat_with_tools", new_callable=AsyncMock, return_value=run),
         patch("timmy.approvals.create_item", return_value=item),
     ):
         response = client.post("/agents/default/chat", data={"message": "run echo hello"})
@@ -76,7 +76,7 @@ def test_chat_tool_card_contains_impact_badge(client):
     item = _mock_approval_item()
 
     with (
-        patch("dashboard.routes.agents.chat_with_tools", return_value=run),
+        patch("dashboard.routes.agents.chat_with_tools", new_callable=AsyncMock, return_value=run),
         patch("timmy.approvals.create_item", return_value=item),
     ):
         response = client.post("/agents/default/chat", data={"message": "run it"})
@@ -90,7 +90,7 @@ def test_chat_tool_card_has_htmx_approve_endpoint(client):
     item = _mock_approval_item()
 
     with (
-        patch("dashboard.routes.agents.chat_with_tools", return_value=run),
+        patch("dashboard.routes.agents.chat_with_tools", new_callable=AsyncMock, return_value=run),
         patch("timmy.approvals.create_item", return_value=item),
     ):
         response = client.post("/agents/default/chat", data={"message": "run it"})
@@ -109,7 +109,7 @@ def _create_pending_tool(client, approval_id="test-approval-123"):
     item = _mock_approval_item(approval_id)
 
     with (
-        patch("dashboard.routes.agents.chat_with_tools", return_value=run),
+        patch("dashboard.routes.agents.chat_with_tools", new_callable=AsyncMock, return_value=run),
         patch("timmy.approvals.create_item", return_value=item),
     ):
         response = client.post("/agents/default/chat", data={"message": "run it"})
@@ -131,7 +131,9 @@ def test_approve_executes_tool_and_returns_result(client):
     result_run.content = "Done."
 
     with (
-        patch("dashboard.routes.agents.continue_chat", return_value=result_run),
+        patch(
+            "dashboard.routes.agents.continue_chat", new_callable=AsyncMock, return_value=result_run
+        ),
         patch("timmy.approvals.approve"),
     ):
         response = client.post(f"/agents/default/tool/{approval_id}/approve")
@@ -153,7 +155,9 @@ def test_approve_same_id_twice_returns_404(client):
     result_run = _mock_completed_run("ok")
 
     with (
-        patch("dashboard.routes.agents.continue_chat", return_value=result_run),
+        patch(
+            "dashboard.routes.agents.continue_chat", new_callable=AsyncMock, return_value=result_run
+        ),
         patch("timmy.approvals.approve"),
     ):
         client.post(f"/agents/default/tool/{approval_id}/approve")
@@ -171,7 +175,11 @@ def test_reject_returns_rejected_card(client):
     approval_id = _create_pending_tool(client)
 
     with (
-        patch("dashboard.routes.agents.continue_chat", return_value=_mock_completed_run()),
+        patch(
+            "dashboard.routes.agents.continue_chat",
+            new_callable=AsyncMock,
+            return_value=_mock_completed_run(),
+        ),
         patch("timmy.approvals.reject"),
     ):
         response = client.post(f"/agents/default/tool/{approval_id}/reject")

tests/dashboard/test_dashboard.py

@@ -104,7 +104,9 @@ def _mock_run(content="Operational and ready."):
 
 
 def test_chat_agent_success(client):
-    with patch("dashboard.routes.agents.chat_with_tools", return_value=_mock_run()):
+    with patch(
+        "dashboard.routes.agents.chat_with_tools", new_callable=AsyncMock, return_value=_mock_run()
+    ):
         response = client.post("/agents/default/chat", data={"message": "status?"})
 
     assert response.status_code == 200
@@ -113,7 +115,11 @@ def test_chat_agent_success(client):
 
 
 def test_chat_agent_shows_user_message(client):
-    with patch("dashboard.routes.agents.chat_with_tools", return_value=_mock_run("Acknowledged.")):
+    with patch(
+        "dashboard.routes.agents.chat_with_tools",
+        new_callable=AsyncMock,
+        return_value=_mock_run("Acknowledged."),
+    ):
         response = client.post("/agents/default/chat", data={"message": "hello there"})
 
     assert "hello there" in response.text
@@ -123,6 +129,7 @@ def test_chat_agent_ollama_offline(client):
     # When Ollama is unreachable, chat shows the user message + error.
     with patch(
         "dashboard.routes.agents.chat_with_tools",
+        new_callable=AsyncMock,
         side_effect=Exception("Ollama unreachable"),
     ):
         response = client.post("/agents/default/chat", data={"message": "ping"})
@@ -147,7 +154,9 @@ def test_history_empty_shows_init_message(client):
 
 def test_history_records_user_and_agent_messages(client):
     with patch(
-        "dashboard.routes.agents.chat_with_tools", return_value=_mock_run("I am operational.")
+        "dashboard.routes.agents.chat_with_tools",
+        new_callable=AsyncMock,
+        return_value=_mock_run("I am operational."),
     ):
         client.post("/agents/default/chat", data={"message": "status check"})
 
@@ -158,6 +167,7 @@ def test_history_records_user_and_agent_messages(client):
 def test_history_records_error_when_offline(client):
     with patch(
         "dashboard.routes.agents.chat_with_tools",
+        new_callable=AsyncMock,
         side_effect=Exception("Ollama unreachable"),
     ):
         client.post("/agents/default/chat", data={"message": "ping"})
@@ -167,7 +177,11 @@ def test_history_records_error_when_offline(client):
 
 
 def test_history_clear_resets_to_init_message(client):
-    with patch("dashboard.routes.agents.chat_with_tools", return_value=_mock_run("Acknowledged.")):
+    with patch(
+        "dashboard.routes.agents.chat_with_tools",
+        new_callable=AsyncMock,
+        return_value=_mock_run("Acknowledged."),
+    ):
         client.post("/agents/default/chat", data={"message": "hello"})
 
     response = client.delete("/agents/default/history")
@@ -176,7 +190,11 @@ def test_history_clear_resets_to_init_message(client):
 
 
 def test_history_empty_after_clear(client):
-    with patch("dashboard.routes.agents.chat_with_tools", return_value=_mock_run("OK.")):
+    with patch(
+        "dashboard.routes.agents.chat_with_tools",
+        new_callable=AsyncMock,
+        return_value=_mock_run("OK."),
+    ):
         client.post("/agents/default/chat", data={"message": "test"})
 
     client.delete("/agents/default/history")