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_067.md

@@ -0,0 +1,64 @@
+# Task ID: 67
+
+**Title:** Add integration tests for gated session flow
+
+**Status:** done
+
+**Dependencies:** 65 ✓
+
+**Priority:** high
+
+**Description:** Create end-to-end integration tests for the complete gated session flow including connect, begin_session, tool calls, and read_prompts.
+
+**Details:**
+
+1. Add tests in `/src/mcplocal/tests/integration/gated-flow.test.ts`:
+   ```typescript
+   describe('Gated Session Flow Integration', () => {
+     let app: FastifyInstance;
+     let mcpClient: McpClient;
+     
+     beforeAll(async () => {
+       app = await createTestApp();
+       // Seed test project with gated=true and test prompts
+     });
+     
+     describe('end-to-end gated flow', () => {
+       it('connect → begin_session with tags → tools available → correct prompts', async () => {
+         // 1. Connect to MCP endpoint
+         const session = await mcpClient.connect(app, 'test-project');
+         
+         // 2. Verify only begin_session available
+         const toolsBefore = await session.listTools();
+         expect(toolsBefore.map(t => t.name)).toEqual(['begin_session']);
+         
+         // 3. Call begin_session
+         const briefing = await session.callTool('begin_session', {
+           tags: ['test', 'integration']
+         });
+         expect(briefing).toContain('matched prompt content');
+         
+         // 4. Verify all tools now available
+         const toolsAfter = await session.listTools();
+         expect(toolsAfter.map(t => t.name)).toContain('read_prompts');
+       });
+     });
+     
+     describe('end-to-end intercept flow', () => {
+       it('connect → skip begin_session → call tool → keywords extracted → briefing injected', async () => { ... });
+     });
+     
+     describe('end-to-end read_prompts', () => {
+       it('after ungating → request more context → additional prompts → no duplicates', async () => { ... });
+     });
+   });
+   ```
+
+**Test Strategy:**
+
+This task IS the test implementation. Verify:
+- Happy path tests pass
+- Intercept path tests pass
+- read_prompts deduplication works
+- Tests use realistic data
+- Tests clean up properly