feat: 品牌替换 + 启动优化 + AGENTS.md 模板定制

- 品牌替换：OpenCode/opencode → AirCoding/aircoding（16+ 文件）
- Logo ASCII art：修复 left/right 行数不匹配导致的启动崩溃
- 启动诊断：添加 OPENCODE_PRINT_TIMING 计时探针
- dev 模式默认 --pure 跳过外部插件加载
- AGENTS.md 模板：追加 AirCoding 多 Agent 专项段落
- architect prompt + plugin：强化 AGENTS.md 产出验证

packages/console/app/test/providerUsage.test.ts

@@ -0,0 +1,68 @@
+import { describe, expect, test } from "bun:test"
+import type { ZenData } from "@opencode-ai/console-core/model.js"
+import type { ProviderHelper } from "../src/routes/zen/util/provider/provider"
+import { anthropicHelper } from "../src/routes/zen/util/provider/anthropic"
+import { googleHelper } from "../src/routes/zen/util/provider/google"
+import { oaCompatHelper } from "../src/routes/zen/util/provider/openai-compatible"
+import { openaiHelper } from "../src/routes/zen/util/provider/openai"
+
+const providers = {
+  anthropic: anthropicHelper({ reqModel: "claude-haiku-4-5", providerModel: "claude-haiku-4-5" }),
+  google: googleHelper({ reqModel: "gemini-3-flash", providerModel: "gemini-3-flash" }),
+  openai: openaiHelper({ reqModel: "gpt-5", providerModel: "gpt-5" }),
+  "oa-compat": oaCompatHelper({ reqModel: "gpt-5-nano", providerModel: "gpt-5-nano" }),
+} satisfies Record<ZenData.Format, ReturnType<ProviderHelper>>
+
+describe("provider usage extraction", () => {
+  test("extracts Google non-stream usage metadata", () => {
+    const usage = providers.google.extractUsage({
+      usageMetadata: {
+        promptTokenCount: 10,
+        candidatesTokenCount: 3,
+        thoughtsTokenCount: 2,
+        cachedContentTokenCount: 4,
+      },
+    })
+
+    expect(providers.google.normalizeUsage(usage)).toEqual({
+      inputTokens: 6,
+      outputTokens: 3,
+      reasoningTokens: 2,
+      cacheReadTokens: 4,
+      cacheWrite5mTokens: undefined,
+      cacheWrite1hTokens: undefined,
+    })
+  })
+
+  test("parses Google stream usage metadata", () => {
+    const usageParser = providers.google.createUsageParser()
+    usageParser.parse(
+      'data: {"usageMetadata":{"promptTokenCount":10,"candidatesTokenCount":3,"thoughtsTokenCount":2,"cachedContentTokenCount":4}}',
+    )
+
+    expect(providers.google.normalizeUsage(usageParser.retrieve())).toEqual({
+      inputTokens: 6,
+      outputTokens: 3,
+      reasoningTokens: 2,
+      cacheReadTokens: 4,
+      cacheWrite5mTokens: undefined,
+      cacheWrite1hTokens: undefined,
+    })
+  })
+
+  test("extracts nested OpenAI Responses usage", () => {
+    expect(
+      providers.openai.extractUsage({
+        response: {
+          usage: {
+            input_tokens: 5,
+            output_tokens: 7,
+          },
+        },
+      }),
+    ).toEqual({
+      input_tokens: 5,
+      output_tokens: 7,
+    })
+  })
+})