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_072.md

@@ -0,0 +1,49 @@
+# Task ID: 72
+
+**Title:** Implement LLMProvider Adapter
+
+**Status:** done
+
+**Dependencies:** 71 ✓
+
+**Priority:** high
+
+**Description:** Create an adapter that wraps the existing ProviderRegistry to implement the StageContext.llm interface, providing stages with a simplified LLM access API.
+
+**Details:**
+
+Create `src/mcplocal/src/proxymodel/llm-adapter.ts`:
+
+```typescript
+import type { LLMProvider } from './types';
+import type { ProviderRegistry } from '../providers/registry';
+
+export function createLLMAdapter(registry: ProviderRegistry, projectName: string): LLMProvider {
+  return {
+    async complete(prompt: string, options?: { system?: string; maxTokens?: number }): Promise<string> {
+      const provider = registry.getProvider('heavy');
+      if (!provider) throw new Error('No LLM provider configured');
+      
+      const messages = options?.system 
+        ? [{ role: 'system', content: options.system }, { role: 'user', content: prompt }]
+        : [{ role: 'user', content: prompt }];
+      
+      const result = await provider.complete({
+        messages,
+        maxTokens: options?.maxTokens ?? 1000,
+      });
+      return result.content;
+    },
+    
+    available(): boolean {
+      return registry.getProvider('heavy') !== null;
+    }
+  };
+}
+```
+
+This adapter uses the 'heavy' tier from the existing registry, preserving the project-level LLM configuration.
+
+**Test Strategy:**
+
+Unit test with mocked ProviderRegistry verifying complete() calls are delegated correctly. Test available() returns false when no provider is configured. Integration test with a real provider.