docs: 交付文档、维护指引与端到端回归

补齐 README、开发计划、维护交接与 E2E 用例，执行最终验收。

e2e/specs/analytics/analytics.spec.ts

@@ -0,0 +1,25 @@
+import { test, expect, AI_REPLY } from '@e2e'
+
+interface AgentPerformance { bot_agents: Array<{ id: string; total_chats: number }> }
+
+test.describe('analytics', () => {
+  test('a conversation shows up in the agent\'s numbers, and the dashboard renders without errors @analytics', async ({ agent, widget, llm, adminApi, page }) => {
+    await llm.script(agent, (s) => s.otherwise().reply('Happy to help!'))
+    await widget.embed()
+    await widget.open()
+    await widget.send('Hello')
+    await expect(widget.lastAgentMessage()).toHaveText('Happy to help!', AI_REPLY)
+
+    const chatsOf = async () => (await adminApi.get<AgentPerformance>('/analytics/agent-performance', { params: { time_range: '24h' } }))
+      .bot_agents.find((a) => a.id === agent.id)?.total_chats
+    await expect.poll(chatsOf).toBe(1)
+
+    const errors: string[] = []
+    page.on('pageerror', (error) => errors.push(error.message))
+    await page.goto('/analytics')
+    await expect(page.getByRole('main').getByRole('heading', { name: 'Total Conversations' })).toBeVisible()
+    // The shared test org has hundreds of agents; the dashboard lists the busiest,
+    // so this one's row is checked through the API above.
+    expect(errors).toEqual([])
+  })
+})