Refactor LLM route-first provider API (#28523)

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

@@ -3,14 +3,13 @@ import { describe, expect } from "bun:test"
 import { Effect } from "effect"
 import { CacheHint, LLM } from "../../src"
 import { LLMClient } from "../../src/route"
-import * as AnthropicMessages from "../../src/protocols/anthropic-messages"
+import * as Anthropic from "../../src/providers/anthropic"
 import { LARGE_CACHEABLE_SYSTEM } from "../recorded-scenarios"
 import { recordedTests } from "../recorded-test"
 
-const model = AnthropicMessages.model({
-  id: "claude-haiku-4-5-20251001",
+const model = Anthropic.configure({
   apiKey: process.env.ANTHROPIC_API_KEY ?? "fixture",
-})
+}).model("claude-haiku-4-5-20251001")
 
 // Two identical generations in a row. The first call writes the prefix into
 // Anthropic's cache; the second should report a cache read against the same