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_084.md

@@ -0,0 +1,47 @@
+# Task ID: 84
+
+**Title:** Implement Section Drill-Down for Tool Results
+
+**Status:** done
+
+**Dependencies:** 82 ✓
+
+**Priority:** medium
+
+**Description:** Extend tool result handling to support _section parameter for drilling into specific sections of large tool responses.
+
+**Details:**
+
+Modify tool call handling in `src/mcplocal/src/router.ts`:
+
+```typescript
+// When processing tool calls
+if (args._section) {
+  const sectionId = args._section;
+  delete args._section; // Don't pass to upstream
+  
+  // Check cache for previous full result
+  const cacheKey = `tool:${serverName}/${toolName}:${JSON.stringify(args)}`;
+  const cachedResult = this.toolResultCache.get(cacheKey);
+  
+  if (cachedResult?.sections) {
+    const section = findSection(cachedResult.sections, sectionId);
+    if (section) {
+      return { content: [{ type: 'text', text: section.content }] };
+    }
+  }
+  // If no cache, make the full call and process, then serve section
+}
+
+// After receiving tool result, process through pipeline
+const processed = await this.processContent(result, 'toolResult', `${serverName}/${toolName}`, sessionId);
+if (processed.sections) {
+  this.toolResultCache.set(cacheKey, processed);
+}
+```
+
+Add a toolResultCache Map with appropriate TTL.
+
+**Test Strategy:**
+
+Integration tests: large tool result gets processed into sections, _section parameter returns specific section, _section removed before upstream call, cache hit serves from cache, cache miss processes and caches.