refactor(llm): normalize Usage as inclusive total + non-overlapping breakdown (#26735)

packages/llm/test/provider/anthropic-messages.test.ts

@@ -1,6 +1,6 @@
 import { describe, expect } from "bun:test"
 import { Effect } from "effect"
-import { CacheHint, LLM, LLMError } from "../../src"
+import { CacheHint, LLM, LLMError, Usage } from "../../src"
 import { LLMClient } from "../../src/route"
 import * as AnthropicMessages from "../../src/protocols/anthropic-messages"
 import { it } from "../lib/effect"
@@ -110,10 +110,11 @@ describe("Anthropic Messages route", () => {
       expect(response.text).toBe("Hello!")
       expect(response.reasoning).toBe("thinking")
       expect(response.usage).toMatchObject({
-        inputTokens: 5,
+        inputTokens: 6,
         outputTokens: 2,
+        nonCachedInputTokens: 5,
         cacheReadInputTokens: 1,
-        totalTokens: 7,
+        totalTokens: 8,
       })
       expect(response.events.find((event) => event.type === "reasoning-end")).toMatchObject({
         providerMetadata: { anthropic: { signature: "sig_1" } },
@@ -152,7 +153,13 @@ describe("Anthropic Messages route", () => {
         {
           type: "request-finish",
           reason: "tool-calls",
-          usage: { inputTokens: 5, outputTokens: 1, totalTokens: 6, native: { input_tokens: 5, output_tokens: 1 } },
+          usage: new Usage({
+            inputTokens: 5,
+            outputTokens: 1,
+            nonCachedInputTokens: 5,
+            totalTokens: 6,
+            providerMetadata: { anthropic: { input_tokens: 5, output_tokens: 1 } },
+          }),
         },
       ])
     }),