drip-billing（点滴计费）

Drip Billing Integration

Track usage and costs for AI agents, LLM calls, tool invocations, and any metered workload.

When to Use This Skill

• Recording LLM usage quantities (for example total tokens per call)
• Tracking tool/function call costs
• Logging agent execution traces
• Metering API requests for billing
• Attributing costs to customers or workflows

Security & Data Privacy

Key scoping (least privilege):

• Use pk_ (public) keys for usage tracking, customer management, and billing. This is sufficient for all skill operations.
• Only use sk_ (secret) keys if you need admin operations: webhook management, API key rotation, or feature flags.
• Public keys (pk_) cannot manage webhooks, rotate API keys, or toggle feature flags — this limits blast radius if the key is compromised.

Metadata safety:

• Include only minimal non-sensitive operational context in metadata.
• Never include PII, secrets, passwords, API keys, raw user prompts, model outputs, or full request/response bodies.
• Use a strict allowlist and redaction policy before telemetry writes.
• Prefer hashes/IDs (for example queryHash) instead of raw user text.

What data is transmitted:

• Usage quantities (meter name + numeric value)
• Customer identifiers
• Run lifecycle events (start/end, status, duration)
• Sanitized metadata you explicitly provide (model family, tool name, status code, latency, hashed IDs)

What is NOT transmitted:

• Raw prompts, completions, or model outputs
• Environment variables or secrets
• File contents or source code

Installation

npm install @drip-sdk/node

Environment Setup

# Recommended: public key — sufficient for all usage tracking and billing
export DRIP_API_KEY=pk_live_...

# Only if you need admin operations (webhooks, key management, feature flags):
# export DRIP_API_KEY=sk_live_...

Telemetry Safety Contract

• Send only metadata needed for billing and diagnostics.
• Do not send raw prompts, raw model outputs, raw query text, full request/response bodies, or credentials.
• Prefer stable identifiers and hashes (for example queryHash) over raw user content.
• Emit telemetry only to a trusted DRIP_BASE_URL.

Quick Start

1. Initialize the SDK

import { Drip } from '@drip-sdk/node';

// Reads DRIP_API_KEY from environment automatically (pk_live_... recommended)
const drip = new Drip({
  apiKey: process.env.DRIP_API_KEY
});

2. Track Usage (Simple)

await drip.trackUsage({
  customerId: 'customer_123',
  meter: 'llm_tokens',
  quantity: 1500,
  // metadata is optional — only include operational context, never PII or secrets
  metadata: { model: 'gpt-4' }
});

3. Record Agent Runs (Complete Execution)

await drip.recordRun({
  customerId: 'cus_123',
  workflow: 'research-agent',
  events: [
    { eventType: 'llm.call', model: 'gpt-4', quantity: 1700, units: 'tokens' },
    { eventType: 'tool.call', name: 'web-search', duration: 1500 },
    { eventType: 'llm.call', model: 'gpt-4', quantity: 1000, units: 'tokens' },
  ],
  status: 'COMPLETED',
});

4. Streaming Execution (Real-Time)

// Start the run
const run = await drip.startRun({
  customerId: 'cus_123',
  workflowSlug: 'document-processor',
});

// Log each step as it happens
await drip.emitEvent({
  runId: run.id,
  eventType: 'llm.call',
  model: 'gpt-4',
  quantity: 1700,
  units: 'tokens',
});

await drip.emitEvent({
  runId: run.id,
  eventType: 'tool.call',
  name: 'web-search',
  duration: 1500,
});

// Complete the run
await drip.endRun(run.id, { status: 'COMPLETED' });

Event Types

Common Patterns

Wrap Tool Calls

async function trackedToolCall<T>(runId: string, toolName: string, fn: () => Promise<T>): Promise<T> {
  const start = Date.now();
  try {
    const result = await fn();
    await drip.emitEvent({
      runId,
      eventType: 'tool.call',
      name: toolName,
      duration: Date.now() - start,
      status: 'success',
    });
    return result;
  } catch (error: unknown) {
    const message = error instanceof Error ? error.message : 'Unknown error';
    await drip.emitEvent({
      runId,
      eventType: 'tool.call',
      name: toolName,
      duration: Date.now() - start,
      status: 'error',
      // Only include the error message — never include stack traces, env vars, or user data
      metadata: { error: message },
    });
    throw error;
  }
}

LangChain Auto-Tracking

import { DripCallbackHandler } from '@drip-sdk/node/langchain';

const handler = new DripCallbackHandler({
  drip,
  customerId: 'cus_123',
  workflow: 'research-agent',
});

// All LLM calls and tool usage automatically tracked
const result = await agent.invoke(
  { input: 'Research the latest AI news' },
  { callbacks: [handler] }
);

API Reference

See references/API.md for complete SDK documentation.