Anthropic

The Anthropic SDK is the production path for Claude. agentfootprint's anthropic() factory wraps it as an LLMProvider — same interface as mock(), so the rest of your agent code is identical between dev and prod.

Install

npm install @anthropic-ai/sdk

The SDK is a peer dependency declared in peerDependenciesMeta with optional: true — npm doesn't auto-install it. Lazy-required at first call; friendly install hint if missing.

anthropic() is imported from the agentfootprint/providers subpath (the agentfootprint/providers alias also works), NOT the main agentfootprint barrel. Vendor-SDK-backed providers live on that subpath so bundlers walking the main entry never touch the optional peer-dep requires — automatic tree-shaking. (The main barrel only re-exports the zero-peer-dep providers: mock, browserAnthropic, browserOpenai, createProvider.)

Use

import { Agent } from 'agentfootprint';
import { anthropic } from 'agentfootprint/providers';

const provider = anthropic({
  apiKey: process.env.ANTHROPIC_API_KEY!,
  // defaultModel: 'claude-sonnet-4-5-20250929',  // optional, used when Agent doesn't override
});

const agent = Agent.create({
  provider,
  model: 'claude-sonnet-4-5-20250929',
}).build();

Model strings need date suffixes (claude-sonnet-4-5-20250929, claude-haiku-4-5-20251001) — Anthropic's API requires the explicit version for stability.

Tools (native function calling)

Anthropic's Messages API has native tool_use blocks. The provider translates the agent's Tool[] into the API's tool format and round-trips assistant tool_calls via LLMMessage.toolCalls. ReAct correctness preserved across multi-iteration runs.

One tool per reply — parallelToolCalls: false

By default Claude may ask for several tools at once: one assistant message carries many tool_use blocks, and the agent runs them all inside a single loop iteration. That is usually what you want — it is faster and cheaper.

It is not what you want when the shape of the loop is part of what you are measuring. Per-iteration analysis reads one tool source per iteration: localizeContextBug seeds one 'tool' suspect from that iteration's lastToolResult, and removableSources de-duplicates by tool name. So a reply that batched three tools is attributed to the last tool of the batch — the other two never appear as their own influence rows, and you cannot ablate them individually.

Set parallelToolCalls: false to cap the model at one tool per reply:

const provider = anthropic({
  apiKey: process.env.ANTHROPIC_API_KEY!,
  parallelToolCalls: false, // one tool per reply → one tool per iteration
});

On the wire this sends tool_choice: { type: 'auto', disable_parallel_tool_use: true }. auto is deliberate: the model still decides which tool to call, and whether to call one at all — only the count is capped. Nothing is sent on requests that carry no tools (Anthropic rejects tool_choice there), and parallelToolCalls: true sends nothing either, because allowing batches is already Anthropic's default.

Asking for this in the system prompt ("call one tool at a time") is not equivalent — that is a request the model may ignore, this is a request parameter the API enforces. Cost: one extra round trip per tool.

The same option exists on browserAnthropic(), and both adapters put the identical field on the wire.

Streaming

provider.stream(req) uses the SDK's native iterator; chunks land as they arrive. Final chunk carries the full LLMResponse (toolCalls + usage + stopReason) — single round-trip serves UI tokens AND ReAct decisioning.

Production patterns

Wrap with resilience decorators for production:

import { withRetry, withFallback } from 'agentfootprint/resilience';
import { anthropic, openai } from 'agentfootprint/providers';

const provider = withRetry(
  withFallback(
    anthropic({ apiKey: process.env.ANTHROPIC_API_KEY! }),
    openai({ apiKey: process.env.OPENAI_API_KEY! }),
  ),
  { maxAttempts: 5 },
);

See Resilience guide.

Browser variant

For browser environments where the Anthropic Node SDK doesn't bundle cleanly, use BrowserAnthropicProvider — fetch-based, zero peer deps. Requires the anthropic-dangerous-direct-browser-access: true header (which the provider sets automatically). Production browser apps should proxy through a backend.

Limitations

• Multi-modal content (images, video) not supported — LLMMessage.content is string.
• responseFormat (JSON-Schema-coerced output) not exposed yet — pass schema instructions via systemPrompt.

Next steps

• Resilience — wrap with withRetry / withFallback
• Streaming — token-by-token UI rendering