anth-known-pitfalls

# Anthropic Known Pitfalls ## Pitfall 1: Wrong Import / Class Name ```python # WRONG — common mistake from OpenAI muscle memory from anthropic import AnthropicClient # Does not exist # CORRECT import anthropic client = anthropic.Anthropic() ``` ```typescript // WRONG import { Anthropic } from '@anthropic-ai/sdk'; // CORRECT import Anthropic from '@anthropic-ai/sdk'; // Default export ``` ## Pitfall 2: Forgetting max_tokens (Required) ```python # WRONG — max_tokens is REQUIRED, unlike OpenAI msg = client.messages.create( model="claude-sonnet-4-20250514", messages=[{"role": "user", "content": "Hello"}] ) # Error: max_tokens is required # CORRECT msg = client.messages.create( model="claude-sonnet-4-20250514", max_tokens=1024, # Always specify messages=[{"role": "user", "content": "Hello"}] ) ``` ## Pitfall 3: System Prompt in Messages Array ```python # WRONG — putting system message in messages array (OpenAI pattern) messages = [ {"role": "system", "content": "You are helpful."}, # Will cause error {"role": "user", "content": "Hello"} ] # CORRECT — use the system parameter msg = client.messages.create( model="claude-sonnet-4-20250514", max_tokens=1024, system="You are helpful.", # Separate parameter messages=[{"role": "user", "content": "Hello"}] ) ``` ## Pitfall 4: Accessing Response Wrong ```python # WRONG — OpenAI response pattern text = response.choices[0].message.content # AttributeError # CORRECT — Anthropic ...