Claude の『このモデルは現在利用できません』が出る時に効くモデル選択フォールバックの設計

type ModelTier = "frontier" | "balanced" | "fast";
 
interface ModelFallbackChain {
  primary: string;
  fallbacks: string[];
}
 
// ID は実在するものだけを書く。書き換え前に公式のモデル一覧で確認してください
const FALLBACK_CHAINS: Record<ModelTier, ModelFallbackChain> = {
  frontier: {
    primary: "claude-opus-4-6",
    fallbacks: ["claude-sonnet-4-6"],
  },
  balanced: {
    primary: "claude-sonnet-4-6",
    fallbacks: ["claude-sonnet-4-5", "claude-haiku-4-5-20251001"],
  },
  fast: {
    primary: "claude-haiku-4-5-20251001",
    fallbacks: ["claude-sonnet-4-6"],
  },
};

import Anthropic from "@anthropic-ai/sdk";
 
type Verdict = "fallback" | "alert" | "rethrow";
 
// 404: モデルが見つからない → 切り替える
// 403: 権限がない → 切り替えず、人に知らせる
// 429 / 529 / その他: SDK の再試行に任せ、フォールバックしない
function classify(err: unknown): Verdict {
  if (err instanceof Anthropic.NotFoundError) return "fallback";
  if (err instanceof Anthropic.PermissionDeniedError) return "alert";
  if (err instanceof Anthropic.BadRequestError) {
    // 400 はパラメータ不備でも返る。モデル起因と読める文面のときだけ切り替える
    const msg = (err.message ?? "").toLowerCase();
    if (msg.includes("unavailable") || msg.includes("not available")) return "fallback";
  }
  return "rethrow";
}
 
async function invokeWithFallback(
  client: Anthropic,
  tier: ModelTier,
  buildRequest: (modelId: string) => Anthropic.Messages.MessageCreateParamsNonStreaming
): Promise<Anthropic.Messages.Message> {
  const chain = FALLBACK_CHAINS[tier];
  const candidates = [chain.primary, ...chain.fallbacks];
  let lastError: unknown;
 
  for (const modelId of candidates) {
    try {
      return await client.messages.create(buildRequest(modelId));
    } catch (err) {
      const verdict = classify(err);
      if (verdict === "fallback") {
        console.warn(`model ${modelId} rejected, trying next`);
        lastError = err;
        continue;
      }
      if (verdict === "alert") {
        await notifyOwner(`permission denied for ${modelId}`); // 通知先は各自の環境で
      }
      throw err; // 切り替え対象でないものは、握りつぶさずに上へ返す
    }
  }
  throw lastError;
}

interface ModelCapabilities {
  extendedThinking: boolean;
}
 
// 値は例です。対応状況は公式ドキュメントで確かめ、実際の値に書き換えてください
const CAPABILITY_MATRIX: Record<string, ModelCapabilities> = {
  "claude-opus-4-6": { extendedThinking: true },
  "claude-sonnet-4-6": { extendedThinking: true },
  "claude-sonnet-4-5": { extendedThinking: true },
  "claude-haiku-4-5-20251001": { extendedThinking: false },
};
 
function buildRequestForModel(
  modelId: string,
  prompt: string,
  tools: Anthropic.Messages.Tool[]
): Anthropic.Messages.MessageCreateParamsNonStreaming {
  const caps = CAPABILITY_MATRIX[modelId] ?? { extendedThinking: false };
  return {
    model: modelId,
    // 拡張思考を使うときは budget_tokens より大きい max_tokens が必要
    max_tokens: caps.extendedThinking ? 20000 : 4096,
    messages: [{ role: "user", content: prompt }],
    tools,
    ...(caps.extendedThinking
      ? { thinking: { type: "enabled" as const, budget_tokens: 16384 } }
      : {}),
  };
}

interface ModelInvocationLog {
  timestamp: string;
  intendedModel: string;
  actualModel: string;
  fallbackDepth: number; // 0 = 優先モデルで成功
  taskType: string;
  outcome: "success" | "all_failed";
}