merge: AgentProject membership — the junction is now load-bearing

Merges feat/agent-project-membership (task 166/152). An agent can finally join
many projects: membership routes, per-membership role and optional brain
override, chat resolving context from the membership, and CLI attach-agent /
detach-agent / get memberships. The legacy Agent.projectId fallback is kept for
this release as the schema comment promises.

Conflict resolved in main.ts: that branch added its RBAC case to
mapUrlToPermission inline, while this branch had extracted the function to
middleware/url-permission.ts so it could be tested. Kept the extraction and
ported the case into it — joining a team is `edit:agents:<name>`, not
`create:agents`, which is the authority to mint a whole agent.

Also fixes something the extraction makes possible. security.test.ts contained a
hand-copied reproduction of mapUrlToPermission, because main.ts self-invokes
main() and nothing in it was importable. A security test asserting against a
copy stops testing the system the moment the real one changes, and this copy had
already drifted. It now imports the real function; all 18 assertions still pass,
against the code that actually runs.

Local: build clean, workspace 2550 passed, lint unchanged at 794 errors.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4wNHWf7xSwnZCWpJcyv9p

.taskmaster/tasks/task_111.md

@@ -0,0 +1,76 @@
+# Task ID: 111
+
+**Title:** Write Integration Tests for subindex Model
+
+**Status:** done
+
+**Dependencies:** 75 ✓, 76 ✓, 82 ✓, 83 ✗
+
+**Priority:** high
+
+**Description:** Create comprehensive integration tests for the subindex proxymodel processing real content through section-split and summarize-tree.
+
+**Details:**
+
+Create `src/mcplocal/tests/proxymodel/subindex.test.ts`:
+
+```typescript
+import { describe, it, expect, beforeAll } from 'vitest';
+import { executePipeline } from '../../src/proxymodel/executor';
+import { loadProxyModels } from '../../src/proxymodel/loader';
+import { createMockProviderRegistry } from '../mocks/providers';
+
+describe('subindex proxymodel', () => {
+  let proxyModel;
+  let mockRegistry;
+  
+  beforeAll(async () => {
+    const models = await loadProxyModels();
+    proxyModel = models.get('subindex');
+    mockRegistry = createMockProviderRegistry({
+      complete: async (prompt) => 'Mock summary of the content',
+    });
+  });
+  
+  it('splits JSON array into sections', async () => {
+    const content = JSON.stringify([
+      { id: 'flow1', label: 'Thermostat', nodes: [] },
+      { id: 'flow2', label: 'Lighting', nodes: [] },
+    ]);
+    
+    const result = await executePipeline({
+      content,
+      contentType: 'toolResult',
+      sourceName: 'test/get_flows',
+      projectName: 'test',
+      sessionId: 'test-session',
+      proxyModel,
+      providerRegistry: mockRegistry,
+    });
+    
+    expect(result.sections).toHaveLength(2);
+    expect(result.sections[0].id).toBe('flow1');
+    expect(result.content).toContain('2 sections');
+  });
+  
+  it('provides drill-down to exact JSON content', async () => {
+    // Test that drilling into a section returns exact original JSON
+  });
+  
+  it('uses structural summaries for JSON (no LLM call)', async () => {
+    // Verify LLM not called for JSON content
+  });
+  
+  it('uses LLM summaries for prose content', async () => {
+    // Verify LLM called for markdown content
+  });
+  
+  it('caches summaries across requests', async () => {
+    // Verify cache hit on second request with same content
+  });
+});
+```
+
+**Test Strategy:**
+
+Run with vitest, verify all test cases pass, check LLM call counts are as expected (structural vs prose), verify cache behavior.