Ship the batch: undo, parallel subagents, lazy MCP, hot-reloaded skills; docs and CI/CD

Loop and ergonomics batch across Now/Next and Maintenance:
- /undo and /redo via pre-prompt file snapshots (snapshot.ts)
- task takes a tasks[] array and runs investigations concurrently (subagent.ts)
- lazy MCP tools: mcp_list/mcp_inspect/mcp_call meta-tools, eager opt-in (mcp.ts, config.ts)
- skill tool reads its list live so a mid-session install is callable next turn (skills.ts)
- tool-name lists (tool-kinds.ts) derived from a mutating() marker; gates previously ungated writes
- prune/session recovery path summarized, and step-back doom-loop primitive (step-back.ts)
- @file completion re-walks on a slow cooldown; estimateTokens and pricing labeled as estimates

Docs: README, CHANGELOG, docs/{mcp,architecture,development} updated to match.
CI/CD: bun install-store cache and concurrency gates on both workflows; release.yml now
composes file-based release notes via scripts/make-release-notes.ts and verifies every binary.

test/memory.test.ts

@@ -1,4 +1,4 @@
-import { usageOf } from './helpers';
+import { generateResult, usageOf } from './helpers';
 import { afterEach, beforeEach, expect, test } from 'bun:test';
 import { MockLanguageModelV4 } from 'ai/test';
 import { mkdtempSync, rmSync } from 'node:fs';
@@ -31,16 +31,7 @@ const call = (tools: ToolSet, name: string, input: Record<string, unknown>) => {
 
 const usage = usageOf(1);
 
-const summarizer = (text: string) =>
-  new MockLanguageModelV4({
-    doGenerate: async () =>
-      ({
-        content: [{ type: 'text', text }],
-        finishReason: { unified: 'stop', raw: 'stop' },
-        usage,
-        warnings: [],
-      }) as any,
-  });
+const summarizer = (text: string) => new MockLanguageModelV4({ doGenerate: async () => generateResult(text, usage) });
 
 test('a fresh project has no memory and renders nothing', async () => {
   const m = new Memory('/repo');