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_082.md

@@ -0,0 +1,66 @@
+# Task ID: 82
+
+**Title:** Integrate Pipeline Executor into Router
+
+**Status:** done
+
+**Dependencies:** 80 ✓, 81 ✓
+
+**Priority:** high
+
+**Description:** Modify the McpRouter to route content through the proxymodel pipeline, keeping the gating logic cleanly separated from content processing.
+
+**Details:**
+
+Modify `src/mcplocal/src/router.ts` to:
+
+1. Add proxyModel resolution during router creation:
+```typescript
+import { loadProxyModels } from './proxymodel/loader';
+import { executePipeline } from './proxymodel/executor';
+
+interface RouterOptions {
+  proxyModelName?: string;
+  // ... existing options
+}
+
+async function createRouter(opts: RouterOptions): Promise<McpRouter> {
+  const proxyModels = await loadProxyModels();
+  const proxyModel = proxyModels.get(opts.proxyModelName ?? 'default');
+  // ...
+}
+```
+
+2. Add content processing method:
+```typescript
+async processContent(
+  content: string,
+  type: 'prompt' | 'toolResult',
+  sourceName: string,
+  sessionId: string
+): Promise<StageResult> {
+  if (!this.proxyModel) return { content };
+  
+  const appliesTo = this.proxyModel.spec.appliesTo ?? ['prompts', 'toolResults'];
+  if (!appliesTo.includes(type === 'prompt' ? 'prompts' : 'toolResults')) {
+    return { content };
+  }
+  
+  return executePipeline({
+    content,
+    contentType: type,
+    sourceName,
+    projectName: this.projectName,
+    sessionId,
+    proxyModel: this.proxyModel,
+    providerRegistry: this.providerRegistry,
+    cache: this.cache,
+  });
+}
+```
+
+3. Call processContent at the appropriate points in the request flow (prompt serving, tool result handling) WITHOUT interweaving with gating logic.
+
+**Test Strategy:**
+
+Integration tests: default proxymodel passes content through unchanged, subindex proxymodel produces summaries, appliesTo filtering works correctly, gating still works as before with proxymodel processing happening at the right stage.