feat: audit console TUI, system prompt management, and CLI improvements

Audit Console Phase 1: tool_call_trace emission from mcplocal router,
session_bind/rbac_decision event kinds, GET /audit/sessions endpoint,
full Ink TUI with session sidebar, event timeline, and detail view
(mcpctl console --audit).

System prompts: move 6 hardcoded LLM prompts to mcpctl-system project
with extensible ResourceRuleRegistry validation framework, template
variable enforcement ({{maxTokens}}, {{pageCount}}), and delete-resets-
to-default behavior. All consumers fetch via SystemPromptFetcher with
hardcoded fallbacks.

CLI: -p shorthand for --project across get/create/delete/config commands,
console auto-scroll improvements, shell completions regenerated.

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

src/mcpd/tests/bootstrap-system-project.test.ts

@@ -89,13 +89,18 @@ describe('bootstrapSystemProject', () => {
     expect(prisma.prompt.create).toHaveBeenCalledTimes(expectedNames.length);
   });
 
-  it('creates system prompts with priority 10', async () => {
+  it('creates system prompts with expected priorities', async () => {
     await bootstrapSystemProject(prisma);
 
     const createCalls = vi.mocked(prisma.prompt.create).mock.calls;
     for (const call of createCalls) {
-      const data = (call[0] as { data: { priority: number } }).data;
-      expect(data.priority).toBe(10);
+      const data = (call[0] as { data: { name: string; priority: number } }).data;
+      // Gate prompts have priority 10, LLM pipeline prompts have priority 5
+      if (data.name.startsWith('gate-') || data.name === 'session-greeting') {
+        expect(data.priority).toBe(10);
+      } else {
+        expect(data.priority).toBe(5);
+      }
     }
   });