Anth Migration Deep Dive

Anthropic Migration Deep Dive

Overview

Migration strategies for switching to Claude from OpenAI, Google, or other LLM providers, including API mapping, prompt translation, and multi-provider abstraction.

OpenAI to Anthropic API Mapping

Side-by-Side Code Comparison

# === OpenAI ===
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "system", "content": "You are helpful."},
        {"role": "user", "content": "Hello"}
    ],
    max_tokens=1024,
    temperature=0.7
)
text = response.choices[0].message.content

# === Anthropic ===
import anthropic
client = anthropic.Anthropic()
response = client.messages.create(
    model="claude-sonnet-4-20250514",
    system="You are helpful.",           # System prompt is separate
    messages=[
        {"role": "user", "content": "Hello"}
    ],
    max_tokens=1024,                     # Required (not optional)
    temperature=0.7
)
text = response.content[0].text

Tool Use Migration

# OpenAI tools format
openai_tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "parameters": {"type": "object", "properties": {"city": {"type": "string"}}}
    }
}]

# Anthropic tools format — flatter structure
anthropic_tools = [{
    "name": "get_weather",
    "description": "Get weather for a city",  # Required in Anthropic
    "input_schema": {"type": "object", "properties": {"city": {"type": "string"}}}
}]

Multi-Provider Abstraction

from abc import ABC, abstractmethod

class LLMProvider(ABC):
    @abstractmethod
    def complete(self, prompt: str, system: str = "", **kwargs) -> str: ...

class AnthropicProvider(LLMProvider):
    def __init__(self):
        import anthropic
        self.client = anthropic.Anthropic()

    def complete(self, prompt: str, system: str = "", **kwargs) -> str:
        msg = self.client.messages.create(
            model=kwargs.get("model", "claude-sonnet-4-20250514"),
            max_tokens=kwargs.get("max_tokens", 1024),
            system=system,
            messages=[{"role": "user", "content": prompt}]
        )
        return msg.content[0].text

class OpenAIProvider(LLMProvider):
    def __init__(self):
        from openai import OpenAI
        self.client = OpenAI()

    def complete(self, prompt: str, system: str = "", **kwargs) -> str:
        messages = []
        if system:
            messages.append({"role": "system", "content": system})
        messages.append({"role": "user", "content": prompt})
        resp = self.client.chat.completions.create(
            model=kwargs.get("model", "gpt-4"),
            messages=messages,
            max_tokens=kwargs.get("max_tokens", 1024)
        )
        return resp.choices[0].message.content

Migration Checklist

• Map model names (GPT-4 → Claude Sonnet, GPT-3.5 → Claude Haiku)
• Move system prompts from messages[] to system parameter
• Update response access path (.choices[0].message.content → .content[0].text)
• Make max_tokens explicit (required in Anthropic, optional in OpenAI)
• Update tool definitions to Anthropic format
• Test prompt behavior (Claude may respond differently to same prompts)
• Update error handling for Anthropic error types

Resources

• Anthropic vs OpenAI Migration
• Messages API Reference

Next Steps

For advanced debugging, see anth-advanced-troubleshooting.

Source: jeremylongshore/claude-code-plugins-plus-skills → plugins/saas-packs/anthropic-pack/skills/anth-migration-deep-dive/SKILL.md