Summary

• Extracts a single isClaudeModel() helper in transform.ts to replace three inconsistent detection strategies for identifying Claude/Anthropic models
• Fixes 400 "assistant message prefill" errors when Claude models are routed through OpenAI-compatible proxies

Problem

ProviderTransform uses three different conditions to detect Anthropic/Claude models, and they disagree:

When a Claude model is accessed through an OpenAI-compatible proxy (@ai-sdk/openai-compatible), the model name may contain "claude" but the npm package is not @ai-sdk/anthropic. This causes caching and tool-ID scrubbing to activate while empty-content stripping does not. Empty assistant messages survive, get cache metadata attached, and Anthropic rejects them as invalid prefill.

Fix

Single isClaudeModel(model) function used at all three sites:

function isClaudeModel(model: Provider.Model): boolean {
  return (
    model.providerID === "anthropic" ||
    model.providerID === "google-vertex-anthropic" ||
    model.api.id.includes("anthropic") ||
    model.api.id.includes("claude") ||
    model.id.includes("anthropic") ||
    model.id.includes("claude") ||
    model.api.npm === "@ai-sdk/anthropic" ||
    model.api.npm === "@ai-sdk/google-vertex/anthropic" ||
    model.api.npm === "@ai-sdk/amazon-bedrock"
  )
}

Testing

• No new errors introduced (5 pre-existing switch clause lint warnings unchanged)
• Single file change: packages/opencode/src/provider/transform.ts