@revenium/anthropic 1.0.6 → 1.0.8

package/CHANGELOG.md

@@ -2,6 +2,32 @@
 
 All notable changes to this project will be documented in this file.
 
+## [1.0.8] - 2025-11-07
+
+### Fixed
+- Fixed `anthropicApiKey` configuration parameter to honor config value before environment variable
+- Fixed `failSilent=false` configuration to properly propagate tracking errors
+- Fixed `maxRetries=0` handling to allow zero retries when explicitly configured
+
+### Added
+- Added `timeToFirstToken` metric tracking for streaming requests
+- Added custom metadata field preservation beyond standard fields
+- Added website link (www.revenium.ai) to README Support section
+
+### Changed
+- Updated Revenium API base URL from `api.revenium.io` to `api.revenium.ai`
+- Updated Node.js requirement from 16+ to 18+
+- Updated `.gitignore` to exclude `dist/` directory and `.env.test`
+- Excluded `.claude/` directory and `*.log` files from npm package
+- Removed `package-lock.json` from public repository allowlist
+
+## [1.0.7] - 2025-10-25
+
+### Changed
+- Updated all examples to use `claude-haiku-4-5` (validated Anthropic model identifier)
+- Improved examples documentation with getting_started.ts reference
+- Streamlined README by removing OpenRouter section for clarity
+
 ## [1.0.6] - 2025-10-24
 
 ### Added

package/README.md

@@ -3,6 +3,7 @@
 [![npm version](https://img.shields.io/npm/v/@revenium/anthropic.svg)](https://www.npmjs.com/package/@revenium/anthropic)
 [![Node Versions](https://img.shields.io/node/v/@revenium/anthropic.svg)](https://www.npmjs.com/package/@revenium/anthropic)
 [![Documentation](https://img.shields.io/badge/docs-revenium.io-blue)](https://docs.revenium.io)
+[![Website](https://img.shields.io/badge/website-revenium.ai-blue)](https://www.revenium.ai)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
 Automatically track and meter your Anthropic Claude API usage with Revenium. This middleware provides seamless integration with **Anthropic Claude SDK**, requiring minimal code changes and featuring native TypeScript support.
@@ -45,7 +46,7 @@ REVENIUM_METERING_API_KEY="hak_your_revenium_key"
 ANTHROPIC_API_KEY="sk-ant-your_anthropic_key"
 ```
 
-> **Note**: `REVENIUM_METERING_BASE_URL` defaults to `https://api.revenium.io` and doesn't need to be set unless using a different environment.
+> **Note**: `REVENIUM_METERING_BASE_URL` defaults to `https://api.revenium.ai` and doesn't need to be set unless using a different environment.
 
 ### 3. Run Your First Example
 
@@ -132,6 +133,48 @@ Add business context to track usage by organization, user, task type, or custom
 | `agent` | AI agent or bot identifier | Distinguish between multiple AI agents or automation workflows in your system |
 | `responseQualityScore` | Custom quality rating (0.0-1.0) | Track user satisfaction or automated quality metrics for model performance analysis |
 
+**All metadata fields are optional.** Custom fields beyond the standard ones are automatically preserved and sent to Revenium.
+
+**Resources:**
+- [examples/advanced-features.ts](https://github.com/revenium/revenium-middleware-anthropic-node/blob/HEAD/examples/advanced-features.ts) - Working examples
+
+## Metadata Fields
+
+The middleware automatically sends the following fields to Revenium's `/meter/v2/ai/completions` endpoint:
+
+| Field | Type | Source | Description |
+|-------|------|--------|-------------|
+| `stopReason` | string | Anthropic Response | Why completion stopped: "END", "MAX_TOKENS", "STOP_SEQUENCE", "TOOL_USE" |
+| `costType` | string | Fixed | Always "AI" for AI completions |
+| `isStreamed` | boolean | Request Type | Whether response was streamed |
+| `taskType` | string | usageMetadata | Optional task categorization |
+| `agent` | string | usageMetadata | Optional agent identifier |
+| `operationType` | string | Fixed | Always "CHAT" for message completions |
+| `inputTokenCount` | number | Anthropic Usage | Input tokens consumed |
+| `outputTokenCount` | number | Anthropic Usage | Output tokens generated |
+| `reasoningTokenCount` | number | Fixed | Always 0 (Anthropic doesn't report reasoning tokens) |
+| `cacheCreationTokenCount` | number | Anthropic Usage | Tokens used for prompt caching creation |
+| `cacheReadTokenCount` | number | Anthropic Usage | Tokens read from prompt cache |
+| `totalTokenCount` | number | Calculated | Sum of input + output tokens |
+| `organizationId` | string | usageMetadata | Optional organization identifier |
+| `productId` | string | usageMetadata | Optional product identifier |
+| `subscriber` | object | usageMetadata | Optional subscriber info (id, email, credential) |
+| `subscriptionId` | string | usageMetadata | Optional subscription plan identifier |
+| `model` | string | Request | Anthropic model used (e.g., "claude-3-5-haiku-20241022") |
+| `transactionId` | string | Generated | Unique request identifier (UUID) |
+| `responseTime` | string | Timestamp | ISO 8601 timestamp of response completion |
+| `requestDuration` | number | Measured | Total request duration in milliseconds |
+| `provider` | string | Fixed | Always "Anthropic" |
+| `requestTime` | string | Timestamp | ISO 8601 timestamp when request started |
+| `completionStartTime` | string | Timestamp | ISO 8601 timestamp when completion generation started |
+| `timeToFirstToken` | number | Measured | Milliseconds from request start to first token (streaming only) |
+| `traceId` | string | usageMetadata | Optional trace identifier for request correlation |
+| `responseQualityScore` | number | usageMetadata | Optional quality rating (0.0-1.0) |
+| `middlewareSource` | string | Fixed | Always "nodejs" to identify this middleware |
+| Custom Fields | any | usageMetadata | Any additional fields in usageMetadata are preserved |
+
+**Note:** Fields marked as "usageMetadata" come from the optional `usageMetadata` object you pass to `messages.create()`.
+
 **Resources:**
 - [API Reference](https://revenium.readme.io/reference/meter_ai_completion) - Complete metadata field documentation
 
@@ -143,7 +186,7 @@ Add business context to track usage by organization, user, task type, or custom
 | ---------------------------- | -------- | -------------------------- | --------------------------------- |
 | `REVENIUM_METERING_API_KEY`  | Yes      | -                          | Your Revenium API key             |
 | `ANTHROPIC_API_KEY`          | Yes      | -                          | Anthropic Claude API key          |
-| `REVENIUM_METERING_BASE_URL` | No       | `https://api.revenium.io`  | Revenium metering API base URL    |
+| `REVENIUM_METERING_BASE_URL` | No       | `https://api.revenium.ai`  | Revenium metering API base URL    |
 | `REVENIUM_DEBUG`             | No       | `false`                    | Enable debug logging (true/false) |
 
 ### Manual Configuration
@@ -191,14 +234,6 @@ npm install
 npm run build
 ```
 
-### OpenRouter Users
-
-**Note:** Revenium's automatic token cost calculation uses AI model names from the providers themselves (e.g., `claude-sonnet-4-20250514`).
-
-If you are using a service like OpenRouter that changes model names (from `claude-sonnet-4-20250514` to `anthropic/claude-sonnet-4`), automatic cost calculations may not work properly in Revenium (though all other processing will work normally).
-
-Supporting OpenRouter AI model names is something we're working on for the future. If this is critical for your use case, please use the 'provide feedback' button in the Help Center to let us know.
-
 ### Debug Mode
 
 Enable detailed logging to troubleshoot issues:
@@ -242,7 +277,9 @@ The middleware never blocks your application - if Revenium tracking fails, your
 
 ## Documentation
 
-For detailed documentation, visit [docs.revenium.io](https://docs.revenium.io)
+For detailed documentation, visit [docs.revenium.io](https://docs.revenium.io).  
+For contributor lifecycle, validation, and provider metadata, see
+[docs/standardization/README.md](https://github.com/revenium/revenium-middleware-anthropic-node/blob/HEAD/docs/standardization/README.md).
 
 ## Contributing
 
@@ -264,6 +301,7 @@ This project is licensed under the MIT License - see the [LICENSE](https://githu
 
 For issues, feature requests, or contributions:
 
+- **Website**: [www.revenium.ai](https://www.revenium.ai)
 - **GitHub Repository**: [revenium/revenium-middleware-anthropic-node](https://github.com/revenium/revenium-middleware-anthropic-node)
 - **Issues**: [Report bugs or request features](https://github.com/revenium/revenium-middleware-anthropic-node/issues)
 - **Documentation**: [docs.revenium.io](https://docs.revenium.io)

package/dist/cjs/constants.js

@@ -10,7 +10,7 @@ exports.ANTHROPIC_PATTERNS = exports.API_ENDPOINTS = exports.ENV_VARS = exports.
  */
 exports.DEFAULT_CONFIG = {
     /** Default Revenium API base URL */
-    REVENIUM_BASE_URL: 'https://api.revenium.io',
+    REVENIUM_BASE_URL: 'https://api.revenium.ai',
     /** Default API timeout in milliseconds */
     API_TIMEOUT: 5000,
     /** Default maximum retries for failed API calls */

package/dist/cjs/tracking.js

@@ -92,7 +92,7 @@ async function sendReveniumMetrics(data) {
                     duration: data.duration,
                 });
                 return response;
-            }, config.maxRetries || constants_1.DEFAULT_CONFIG.MAX_RETRIES);
+            }, config.maxRetries ?? constants_1.DEFAULT_CONFIG.MAX_RETRIES);
         });
     }
     catch (error) {
@@ -102,8 +102,12 @@ async function sendReveniumMetrics(data) {
             .withDuration(data.duration)
             .build();
         (0, error_handling_1.handleError)(error, logger, errorContext);
-        // Always fail silently for tracking errors to prevent breaking user's application
-        // Tracking errors should never break the user's main application flow
+        // Respect failSilent configuration
+        // By default (failSilent=true), tracking errors don't break the user's application
+        // If failSilent=false, re-throw the error for user handling
+        if (config.failSilent === false) {
+            throw error;
+        }
     }
     finally {
         clearTimeout(timeoutId);
@@ -116,6 +120,20 @@ function buildReveniumPayload(data) {
     const now = new Date().toISOString();
     const requestTime = data.requestTime.toISOString();
     const completionStartTime = data.responseTime.toISOString();
+    // Standard known fields
+    const knownFields = new Set([
+        'taskType', 'agent', 'organizationId', 'productId', 'subscriber',
+        'subscriptionId', 'traceId', 'responseQualityScore'
+    ]);
+    // Extract custom fields (anything NOT in the standard 8 fields)
+    const customFields = {};
+    if (data.metadata) {
+        for (const [key, value] of Object.entries(data.metadata)) {
+            if (!knownFields.has(key)) {
+                customFields[key] = value;
+            }
+        }
+    }
     return {
         stopReason: getStopReason(data.stopReason),
         costType: "AI",
@@ -144,6 +162,7 @@ function buildReveniumPayload(data) {
         traceId: data.metadata?.traceId,
         responseQualityScore: data.metadata?.responseQualityScore, // Fixed: Now sending to Revenium
         middlewareSource: "nodejs",
+        ...customFields, // Preserve any custom metadata fields
     };
 }
 /**
@@ -184,6 +203,12 @@ function trackUsageAsync(trackingData) {
             requestId: trackingData.requestId,
             context: errorContext,
         });
+        // If failSilent=false, propagate the error
+        // Note: Since this is fire-and-forget, the error won't be caught by caller
+        // but it will appear as an unhandled promise rejection
+        if (config.failSilent === false) {
+            throw error;
+        }
     });
 }
 /**

package/dist/cjs/utils/validation.js

@@ -160,17 +160,17 @@ function validateReveniumConfig(config) {
         }
         catch {
             errors.push('reveniumBaseUrl must be a valid URL');
-            suggestions.push('Use format: https://api.revenium.io');
+            suggestions.push('Use format: https://api.revenium.ai');
         }
     }
     // Validate optional Anthropic API key
-    if (!isString(cfg?.anthropicApiKey)) {
+    if (cfg?.anthropicApiKey !== undefined && !isString(cfg?.anthropicApiKey)) {
         errors.push('anthropicApiKey must be a string if provided');
     }
-    else if (cfg?.anthropicApiKey?.trim()?.length === 0) {
+    else if (cfg?.anthropicApiKey !== undefined && cfg?.anthropicApiKey?.trim()?.length === 0) {
         warnings.push('anthropicApiKey is empty - API calls may fail');
     }
-    else if (!cfg?.anthropicApiKey?.startsWith(constants_1.VALIDATION_CONFIG.ANTHROPIC_API_KEY_PREFIX)) {
+    else if (cfg?.anthropicApiKey && !cfg?.anthropicApiKey?.startsWith(constants_1.VALIDATION_CONFIG.ANTHROPIC_API_KEY_PREFIX)) {
         warnings.push(`anthropicApiKey does not start with "${constants_1.VALIDATION_CONFIG.ANTHROPIC_API_KEY_PREFIX}" - verify it is correct`);
     }
     // Validate optional timeout using constants

package/dist/cjs/wrapper.js

@@ -42,9 +42,12 @@ function getMessagesPrototype() {
             return anthropicConstructor?._Messages?.prototype;
         // Method 3: Create a minimal instance with the real API key if available
         // Fallback approach when direct prototype access methods fail
-        const apiKey = process.env.ANTHROPIC_API_KEY;
+        // Check config first, then environment variable
+        const config = (0, config_1.getConfig)();
+        const apiKey = config?.anthropicApiKey ?? process.env.ANTHROPIC_API_KEY;
         if (!apiKey) {
-            throw new error_handling_1.AnthropicPatchingError('Unable to access Anthropic Messages prototype: No API key available and direct prototype access failed');
+            throw new error_handling_1.AnthropicPatchingError('Unable to access Anthropic Messages prototype: No API key available and direct prototype access failed. ' +
+                'Provide ANTHROPIC_API_KEY environment variable or pass anthropicApiKey in config.');
         }
         const minimalInstance = new sdk_1.default({ apiKey });
         const messagesPrototype = Object.getPrototypeOf(minimalInstance.messages);
@@ -155,10 +158,12 @@ async function handleStreamingResponse(stream, context) {
             const endTime = Date.now();
             const responseTime = new Date();
             const duration = endTime - startTime;
+            const timeToFirstToken = firstTokenTime ? firstTokenTime - startTime : undefined;
             logger.debug('Stream completed, extracting usage', {
                 requestId,
                 chunkCount: chunks.length,
-                duration
+                duration,
+                timeToFirstToken
             });
             const usage = (0, tracking_1.extractUsageFromStream)(chunks);
             // Create tracking data
@@ -174,7 +179,8 @@ async function handleStreamingResponse(stream, context) {
                 stopReason: usage.stopReason,
                 metadata,
                 requestTime,
-                responseTime
+                responseTime,
+                timeToFirstToken
             };
             // Track usage asynchronously
             (0, tracking_1.trackUsageAsync)(trackingData);

package/dist/esm/constants.js

@@ -7,7 +7,7 @@
  */
 export const DEFAULT_CONFIG = {
     /** Default Revenium API base URL */
-    REVENIUM_BASE_URL: 'https://api.revenium.io',
+    REVENIUM_BASE_URL: 'https://api.revenium.ai',
     /** Default API timeout in milliseconds */
     API_TIMEOUT: 5000,
     /** Default maximum retries for failed API calls */

package/dist/esm/tracking.js

@@ -83,7 +83,7 @@ export async function sendReveniumMetrics(data) {
                     duration: data.duration,
                 });
                 return response;
-            }, config.maxRetries || DEFAULT_CONFIG.MAX_RETRIES);
+            }, config.maxRetries ?? DEFAULT_CONFIG.MAX_RETRIES);
         });
     }
     catch (error) {
@@ -93,8 +93,12 @@ export async function sendReveniumMetrics(data) {
             .withDuration(data.duration)
             .build();
         handleError(error, logger, errorContext);
-        // Always fail silently for tracking errors to prevent breaking user's application
-        // Tracking errors should never break the user's main application flow
+        // Respect failSilent configuration
+        // By default (failSilent=true), tracking errors don't break the user's application
+        // If failSilent=false, re-throw the error for user handling
+        if (config.failSilent === false) {
+            throw error;
+        }
     }
     finally {
         clearTimeout(timeoutId);
@@ -107,6 +111,20 @@ function buildReveniumPayload(data) {
     const now = new Date().toISOString();
     const requestTime = data.requestTime.toISOString();
     const completionStartTime = data.responseTime.toISOString();
+    // Standard known fields
+    const knownFields = new Set([
+        'taskType', 'agent', 'organizationId', 'productId', 'subscriber',
+        'subscriptionId', 'traceId', 'responseQualityScore'
+    ]);
+    // Extract custom fields (anything NOT in the standard 8 fields)
+    const customFields = {};
+    if (data.metadata) {
+        for (const [key, value] of Object.entries(data.metadata)) {
+            if (!knownFields.has(key)) {
+                customFields[key] = value;
+            }
+        }
+    }
     return {
         stopReason: getStopReason(data.stopReason),
         costType: "AI",
@@ -135,6 +153,7 @@ function buildReveniumPayload(data) {
         traceId: data.metadata?.traceId,
         responseQualityScore: data.metadata?.responseQualityScore, // Fixed: Now sending to Revenium
         middlewareSource: "nodejs",
+        ...customFields, // Preserve any custom metadata fields
     };
 }
 /**
@@ -175,6 +194,12 @@ export function trackUsageAsync(trackingData) {
             requestId: trackingData.requestId,
             context: errorContext,
         });
+        // If failSilent=false, propagate the error
+        // Note: Since this is fire-and-forget, the error won't be caught by caller
+        // but it will appear as an unhandled promise rejection
+        if (config.failSilent === false) {
+            throw error;
+        }
     });
 }
 /**

package/dist/esm/utils/validation.js

@@ -149,17 +149,17 @@ export function validateReveniumConfig(config) {
         }
         catch {
             errors.push('reveniumBaseUrl must be a valid URL');
-            suggestions.push('Use format: https://api.revenium.io');
+            suggestions.push('Use format: https://api.revenium.ai');
         }
     }
     // Validate optional Anthropic API key
-    if (!isString(cfg?.anthropicApiKey)) {
+    if (cfg?.anthropicApiKey !== undefined && !isString(cfg?.anthropicApiKey)) {
         errors.push('anthropicApiKey must be a string if provided');
     }
-    else if (cfg?.anthropicApiKey?.trim()?.length === 0) {
+    else if (cfg?.anthropicApiKey !== undefined && cfg?.anthropicApiKey?.trim()?.length === 0) {
         warnings.push('anthropicApiKey is empty - API calls may fail');
     }
-    else if (!cfg?.anthropicApiKey?.startsWith(VALIDATION_CONFIG.ANTHROPIC_API_KEY_PREFIX)) {
+    else if (cfg?.anthropicApiKey && !cfg?.anthropicApiKey?.startsWith(VALIDATION_CONFIG.ANTHROPIC_API_KEY_PREFIX)) {
         warnings.push(`anthropicApiKey does not start with "${VALIDATION_CONFIG.ANTHROPIC_API_KEY_PREFIX}" - verify it is correct`);
     }
     // Validate optional timeout using constants

package/dist/esm/wrapper.js

@@ -2,7 +2,7 @@
  * Anthropic SDK wrapper with type safety and structured error handling
  */
 import Anthropic from '@anthropic-ai/sdk';
-import { getLogger } from './config.js';
+import { getLogger, getConfig } from './config.js';
 import { trackUsageAsync, extractUsageFromResponse, extractUsageFromStream } from './tracking.js';
 import { validateAnthropicMessageParams, validateUsageMetadata } from './utils/validation.js';
 import { AnthropicPatchingError, RequestProcessingError, StreamProcessingError, createErrorContext, handleError } from './utils/error-handling.js';
@@ -34,9 +34,12 @@ function getMessagesPrototype() {
             return anthropicConstructor?._Messages?.prototype;
         // Method 3: Create a minimal instance with the real API key if available
         // Fallback approach when direct prototype access methods fail
-        const apiKey = process.env.ANTHROPIC_API_KEY;
+        // Check config first, then environment variable
+        const config = getConfig();
+        const apiKey = config?.anthropicApiKey ?? process.env.ANTHROPIC_API_KEY;
         if (!apiKey) {
-            throw new AnthropicPatchingError('Unable to access Anthropic Messages prototype: No API key available and direct prototype access failed');
+            throw new AnthropicPatchingError('Unable to access Anthropic Messages prototype: No API key available and direct prototype access failed. ' +
+                'Provide ANTHROPIC_API_KEY environment variable or pass anthropicApiKey in config.');
         }
         const minimalInstance = new Anthropic({ apiKey });
         const messagesPrototype = Object.getPrototypeOf(minimalInstance.messages);
@@ -147,10 +150,12 @@ async function handleStreamingResponse(stream, context) {
             const endTime = Date.now();
             const responseTime = new Date();
             const duration = endTime - startTime;
+            const timeToFirstToken = firstTokenTime ? firstTokenTime - startTime : undefined;
             logger.debug('Stream completed, extracting usage', {
                 requestId,
                 chunkCount: chunks.length,
-                duration
+                duration,
+                timeToFirstToken
             });
             const usage = extractUsageFromStream(chunks);
             // Create tracking data
@@ -166,7 +171,8 @@ async function handleStreamingResponse(stream, context) {
                 stopReason: usage.stopReason,
                 metadata,
                 requestTime,
-                responseTime
+                responseTime,
+                timeToFirstToken
             };
             // Track usage asynchronously
             trackUsageAsync(trackingData);

package/dist/types/constants.d.ts

@@ -7,7 +7,7 @@
  */
 export declare const DEFAULT_CONFIG: {
     /** Default Revenium API base URL */
-    readonly REVENIUM_BASE_URL: "https://api.revenium.io";
+    readonly REVENIUM_BASE_URL: "https://api.revenium.ai";
     /** Default API timeout in milliseconds */
     readonly API_TIMEOUT: 5000;
     /** Default maximum retries for failed API calls */

package/dist/types/types.d.ts

@@ -51,9 +51,9 @@ export interface Subscriber {
  * @example
  * ```typescript
  * const config: ReveniumConfig = {
- *   reveniumApiKey: 'hak_1234567890abcdef',
- *   reveniumBaseUrl: 'https://api.revenium.io',
- *   anthropicApiKey: 'sk-ant-1234567890abcdef',
+ *   reveniumApiKey: 'hak_your_key_value_here',
+ *   reveniumBaseUrl: 'https://api.revenium.ai',
+ *   anthropicApiKey: 'sk-ant-your_api_key_here',
  *   apiTimeout: 8000,
  *   failSilent: true,
  *   maxRetries: 3

package/examples/README.md

@@ -32,7 +32,7 @@ REVENIUM_METERING_API_KEY=hak_your_revenium_api_key
 ANTHROPIC_API_KEY=sk-ant-your_anthropic_api_key
 
 # Optional
-REVENIUM_METERING_BASE_URL=https://api.revenium.io
+REVENIUM_METERING_BASE_URL=https://api.revenium.ai
 REVENIUM_DEBUG=false
 ```
 
@@ -46,6 +46,7 @@ npm run example:basic
 npm run example:advanced
 
 # Or use tsx directly
+npx tsx examples/getting_started.ts
 npx tsx examples/basic-usage.ts
 npx tsx examples/advanced-features.ts
 ```
@@ -55,12 +56,32 @@ npx tsx examples/advanced-features.ts
 Examples are included in your `node_modules/@revenium/anthropic/examples/` directory:
 
 ```bash
+npx tsx node_modules/@revenium/anthropic/examples/getting_started.ts
 npx tsx node_modules/@revenium/anthropic/examples/basic-usage.ts
 npx tsx node_modules/@revenium/anthropic/examples/advanced-features.ts
 ```
 
 ## Available Examples
 
+### `getting_started.ts` - Simple Entry Point
+
+The simplest example to get you started with Revenium tracking:
+
+- **Minimal setup** - Just import, configure, and start tracking
+- **Complete metadata example** - Shows all 8 optional metadata fields
+- **Ready to customize** - Uncomment the metadata section to add tracking context
+
+**Key Features:**
+
+- Auto-initialization from environment variables
+- Native `usageMetadata` support via module augmentation
+- All metadata fields documented with examples
+- Single API call demonstration
+
+**Perfect for:** First-time users, quick validation, understanding metadata structure
+
+**See the file for complete code examples.**
+
 ### `basic-usage.ts` - Initialization Methods
 
 Demonstrates the three ways to initialize the Revenium middleware:
@@ -116,7 +137,7 @@ Ensure your `tsconfig.json` includes:
 
 ## Requirements
 
-- **Node.js 16+** with TypeScript support
+- **Node.js 18+** with TypeScript support
 - **TypeScript 4.5+** for module augmentation features
 - **Valid Revenium API key** (starts with `hak_`)
 - **Valid Anthropic API key** (starts with `sk-ant-`)

package/examples/advanced-features.ts

@@ -122,7 +122,7 @@ async function demonstrateAdvancedFeatures(): Promise<void> {
     });
 
     const stream1 = await anthropic.messages.create({
-      model: "claude-3-5-sonnet-latest",
+      model: "claude-haiku-4-5",
       max_tokens: 150,
       messages: [
         {
@@ -187,7 +187,7 @@ async function demonstrateAdvancedFeatures(): Promise<void> {
     const now = new Date();
     const trackingData: TrackingData = {
       requestId: `manual_${Date.now()}`,
-      model: "claude-3-5-sonnet-latest",
+      model: "claude-haiku-4-5",
       inputTokens: 25,
       outputTokens: 150,
       duration: 2500,
@@ -245,7 +245,7 @@ async function demonstrateAdvancedFeatures(): Promise<void> {
     } satisfies UsageMetadata;
 
     const stream2 = await anthropic.messages.create({
-      model: "claude-3-5-sonnet-latest",
+      model: "claude-haiku-4-5",
       max_tokens: 100,
       messages: [
         {
@@ -296,7 +296,7 @@ async function demonstrateAdvancedFeatures(): Promise<void> {
     } satisfies UsageMetadata;
 
     const toolStream = await anthropic.messages.create({
-      model: "claude-3-5-sonnet-latest",
+      model: "claude-haiku-4-5",
       max_tokens: 200,
       tools: [
         {
@@ -432,7 +432,7 @@ function checkEnvironment(): void {
     console.error("   REVENIUM_METERING_API_KEY=hak_your_api_key");
     console.error("   ANTHROPIC_API_KEY=sk-ant-your_anthropic_key");
     console.error("\nOptional (uses defaults if not set):");
-    console.error("   REVENIUM_METERING_BASE_URL=https://api.revenium.io");
+    console.error("   REVENIUM_METERING_BASE_URL=https://api.revenium.ai");
     console.error("   REVENIUM_DEBUG=true  # For detailed logging");
     process.exit(1);
   }

package/examples/basic-usage.ts

@@ -52,7 +52,7 @@ async function demonstrateBasicUsage() {
     // Example 1: Basic request without metadata (still tracked automatically)
     console.log("Example 1: Basic request without metadata...");
     const basicResponse = await anthropic.messages.create({
-      model: "claude-3-5-sonnet-latest",
+      model: "claude-haiku-4-5",
       max_tokens: 50,
       messages: [
         { role: "user", content: "What is the capital of France? Be concise." },
@@ -73,7 +73,7 @@ async function demonstrateBasicUsage() {
     // Example 2: Request with rich metadata for enhanced tracking
     console.log("Example 2: Request with rich metadata...");
     const metadataResponse = await anthropic.messages.create({
-      model: "claude-3-5-sonnet-latest",
+      model: "claude-haiku-4-5",
       max_tokens: 80,
       messages: [
         { role: "user", content: "Explain quantum computing in one sentence." },
@@ -146,7 +146,7 @@ async function demonstrateExplicitInitialization() {
     // Now use Anthropic with guaranteed tracking
     const anthropic = new Anthropic();
     const response = await anthropic.messages.create({
-      model: "claude-3-5-sonnet-latest",
+      model: "claude-haiku-4-5",
       max_tokens: 60,
       messages: [
         {
@@ -194,7 +194,7 @@ async function demonstrateManualConfiguration() {
       reveniumApiKey:
         process.env.REVENIUM_METERING_API_KEY || "hak_your_api_key_here",
       reveniumBaseUrl:
-        process.env.REVENIUM_METERING_BASE_URL || "https://api.revenium.io",
+        process.env.REVENIUM_METERING_BASE_URL || "https://api.revenium.ai",
 
       // Optional: Anthropic API key (can also be set in Anthropic client)
       anthropicApiKey: process.env.ANTHROPIC_API_KEY,
@@ -222,7 +222,7 @@ async function demonstrateManualConfiguration() {
     });
 
     const response = await anthropic.messages.create({
-      model: "claude-3-5-sonnet-latest",
+      model: "claude-haiku-4-5",
       max_tokens: 80,
       messages: [
         {
@@ -279,7 +279,7 @@ function checkEnvironment() {
     console.error("   REVENIUM_METERING_API_KEY=hak_your_api_key");
     console.error("   ANTHROPIC_API_KEY=sk-ant-your_anthropic_key");
     console.error("\nOptional (uses defaults if not set):");
-    console.error("   REVENIUM_METERING_BASE_URL=https://api.revenium.io");
+    console.error("   REVENIUM_METERING_BASE_URL=https://api.revenium.ai");
     console.error("   REVENIUM_DEBUG=true  # For detailed logging");
     process.exit(1);
   }

package/examples/getting_started.ts

@@ -8,7 +8,7 @@ async function main() {
 
   // Chat completion with metadata
   const response = await anthropic.messages.create({
-    model: 'claude-3-5-sonnet-latest',
+    model: 'claude-haiku-4-5',
     max_tokens: 2000,
     messages: [
       { role: 'user', content: 'Please verify you are ready to assist me.' }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@revenium/anthropic",
-  "version": "1.0.6",
+  "version": "1.0.8",
   "description": "Transparent TypeScript middleware for automatic Revenium usage tracking with Anthropic Claude AI",
   "main": "dist/cjs/index.js",
   "module": "dist/esm/index.js",
@@ -73,12 +73,15 @@
     "dist/esm/**/*.js",
     "dist/types/**/*.d.ts",
     "examples/**/*",
+    "!examples/.claude/**",
+    "!examples/**/*.log",
+    "!examples/**/*.sh",
     "README.md",
     "CHANGELOG.md",
     "LICENSE"
   ],
   "sideEffects": false,
   "engines": {
-    "node": ">=16.0.0"
+    "node": ">=18.0.0"
   }
 }

package/examples/.claude/settings.local.json

@@ -1,18 +0,0 @@
-{
-  "permissions": {
-    "allow": [
-      "Read(//Users/daithi/git/rev/git/revenium-middleware-anthropic-node/**)",
-      "Bash(npm init:*)",
-      "Bash(npm install:*)",
-      "Bash(cp:*)",
-      "Bash(npx tsx:*)",
-      "WebFetch(domain:revenium.readme.io)",
-      "Bash(tee:*)",
-      "Bash(npm run clean:*)",
-      "Bash(npm run build:*)",
-      "Bash(node -e \"require(''@revenium/anthropic''); console.log(''✅ Option A (Auto-init) - Import works'')\")"
-    ],
-    "deny": [],
-    "ask": []
-  }
-}