Documentation Index
Fetch the complete documentation index at: https://docs.voight.xyz/llms.txt
Use this file to discover all available pages before exploring further.
@voightxyz/anthropic instruments the official Anthropic Node SDK. Wrap your client once and every messages.create call — non-streaming or streaming — lands in Voight with prompts, tokens, cache reads, cache creations, tool use, latency, and errors.
Same backend, same dashboard as @voightxyz/openai and library mode — events from all three land side-by-side under the same agent.
Install
npm install @anthropic-ai/sdk @voightxyz/anthropic
- Node.js 18+ (uses global
fetch)
@anthropic-ai/sdk 0.30.0+
Quick start
import Anthropic from '@anthropic-ai/sdk'
import { wrapAnthropic } from '@voightxyz/anthropic'
const client = wrapAnthropic(new Anthropic(), {
voightApiKey: process.env.VOIGHT_KEY,
agent: 'my-prod-agent',
})
const response = await client.messages.create({
model: 'claude-haiku-4-5',
max_tokens: 1024,
messages: [{ role: 'user', content: 'Hello' }],
})
Options
| Option | Type | Default | Purpose |
|---|
voightApiKey | string | env VOIGHT_KEY | Your Voight key from the dashboard |
agent | string | env VOIGHT_AGENT → HOSTNAME → 'unknown-agent' | Stable identifier surfaced in the dashboard |
apiBase | string | https://api.voight.xyz | Override for self-hosted deployments |
privacy | 'minimal' | 'standard' | 'full' | 'standard' | Capture aggressiveness |
sessionId | string | auto UUID v4 | Trace grouping. Stable across calls of one wrapper instance — events sharing a sessionId render as a single trace in the dashboard |
enabled | boolean | true | Kill switch — when false, returns the original client untouched |
What’s captured
| Signal | Field on the event |
|---|
Model id (with version suffix, e.g. claude-haiku-4-5-20251001) | model |
| Prompt messages | input.messages |
Response text (aggregated from content[].text blocks) | metadata.responseText |
| Token counts (input / output / total) | metadata.tokens |
Cache reads (cache_read_input_tokens) | metadata.tokens.cache_read |
Cache creations (cache_creation_input_tokens) | metadata.tokens.cache_creation |
| Tool use (full array) | metadata.toolCalls |
| First tool’s name (audit-log compat) | toolExecuted |
| Streaming flag | metadata.streaming |
| Stop reason | metadata.finishReason |
| Trace grouping | metadata.sessionId |
| Capture level used | metadata.privacyLevel |
| Latency in milliseconds | durationMs |
Errors (re-thrown to the caller, recorded with outcome: 'failed') | errorMessage, outcome |
Streaming
Streaming works without setup. Anthropic emits a typed event sequence (message_start, content_block_start, content_block_delta, content_block_stop, message_delta, message_stop); the wrapper’s state machine reacts to the events that drive capture and passes the rest through unchanged.
const stream = await client.messages.create({
model: 'claude-haiku-4-5',
max_tokens: 256,
stream: true,
messages: [{ role: 'user', content: 'count to five' }],
})
for await (const event of stream) {
if (
event.type === 'content_block_delta' &&
event.delta.type === 'text_delta'
) {
process.stdout.write(event.delta.text)
}
}
message_start carries input_tokens plus the two cache fields. Final output_tokens lands on message_delta and merges into the emitted event so the full breakdown is captured.
const response = await client.messages.create({
model: 'claude-haiku-4-5',
max_tokens: 256,
tools: [{
name: 'get_weather',
description: 'Get weather for a city',
input_schema: {
type: 'object',
properties: { location: { type: 'string' } },
required: ['location'],
},
}],
messages: [{ role: 'user', content: "what's the weather in Tokyo?" }],
})
tool_use blocks inside response.content[]. The wrapper flattens them into the same { id, name, arguments } shape @voightxyz/openai produces — dashboards render tool calls from either provider identically. Anthropic’s tool input is a parsed object on the wire; we JSON-stringify it so the captured arguments field is a string (matching the openai package).
On the captured event:
toolExecuted: 'get_weather' — first tool’s namemetadata.toolCalls: [{ id, name, arguments }] — full array
Streaming tool use works the same — input_json_delta.partial_json fragments across content_block_delta events are concatenated per index.
Path-A cache pricing
Anthropic distinguishes two cache operations:
- Cache creation (
cache_creation_input_tokens) — writing context to the cache. Billed at 1.25× input rate.
- Cache read (
cache_read_input_tokens) — reading cached context on subsequent turns. Billed at 0.10× input rate.
Both fields are surfaced on metadata.tokens only when strictly positive. The Voight backend pricing engine applies the multipliers automatically — your spend reflects the real cost, not a flat-rate over-estimate.
Privacy
Three levels apply to prompts, response text, and tool-call arguments. The function name in toolExecuted is treated as a tag (not user content) and survives all levels.
| Level | Prompts | Response text | Tool arguments | toolExecuted (name) |
|---|
minimal | dropped | dropped | dropped | kept |
standard | scrubbed | scrubbed | scrubbed | kept |
full | verbatim | verbatim | verbatim | kept |
How it compares
| Use case | Reach for |
|---|
| Coding agent (Claude Code, Cursor) capturing your dev sessions | Hooks-based SDK |
| Autonomous TS/JS bot you wrote yourself emitting custom events | Library mode |
| Production app calling Anthropic in user-facing flows | This package |
| Production app calling OpenAI | @voightxyz/openai |
| Anything else (Python, Go, Rust) | HTTP API |
voight.log() for your own domain events under the same agent.
Source
Roadmap
- Bedrock and Vertex Anthropic clients
- Batch API (when GA)
See the changelog for shipped releases.
