hydra-aidirector 1.6.1 → 1.6.2

package/README.md

@@ -1,19 +1,17 @@
 # hydra-aidirector
 
-The official TypeScript SDK for [Hydra](https://hydrai.dev).
+One client. One secret. One AI gateway.
 
-Hydra gives your app one stable AI gateway instead of a pile of provider glue. You send one request. Hydra handles routing, failover, cache behavior, JSON recovery, and operational visibility behind the same API.
+`hydra-aidirector` is the official TypeScript SDK for [Hydra](https://hydrai.dev/docs). It gives your app one clean path for generation, failover chains, structured output, scoped caching, streaming, usage, health, and webhooks without making you glue providers together by hand.
 
 ## Install
 
 ```bash
 bun add hydra-aidirector
-# or
+```
+
+```bash
 npm install hydra-aidirector
-# or
-pnpm add hydra-aidirector
-# or
-yarn add hydra-aidirector
 ```
 
 ## Quick Start
@@ -23,33 +21,34 @@ import { Hydra } from 'hydra-aidirector';
 
 const client = new Hydra({
   secretKey: process.env.HYDRA_SECRET_KEY!, // hyd_sk_...
-  baseUrl: 'https://your-hydra-instance.com',
+  baseUrl: process.env.HYDRA_BASE_URL!,     // https://your-hydra-instance.com
 });
 
 const result = await client.generate({
   chainId: 'support-replies',
-  prompt: 'Write 3 concise onboarding emails as JSON',
+  prompt: 'Return 3 short onboarding emails as JSON.',
 });
 
 if (result.success) {
   console.log(result.data.valid);
+} else {
+  console.error(result.error);
 }
 ```
 
-## What You Get
+## Why Teams Use It
 
+- One typed client for generation, streaming, usage, health, and webhooks.
 - Automatic failover across the models in your chain.
-- JSON extraction and repair when providers return noisy output.
-- User-safe caching with request-level cache controls.
-- Streaming for long responses.
-- Batch generation for parallel prompt execution.
-- Usage, health, and webhook management from the same client.
+- Structured output recovery when providers return noisy JSON.
+- Cache controls that let you keep shared prompts fast and sensitive prompts private.
+- One request trail to inspect when latency, cost, or provider behavior starts drifting.
 
-## Generation Modes
+## How Generation Works
 
-Hydra uses the optimized 3-step flow by default for simple requests. That keeps the fast path cheap and responsive.
+Hydra uses the optimized 3-step flow by default for simple requests. That path keeps the fast lane lean by moving the long model call out of the request path that fronts your app.
 
-When you ask for features that require the full server pipeline, the SDK automatically falls back to the legacy endpoint. That includes:
+When a request needs the full server pipeline, the SDK automatically falls back to the legacy endpoint. That includes:
 
 - `schema`
 - `noCache`
@@ -58,7 +57,7 @@ When you ask for features that require the full server pipeline, the SDK automat
 - `strictJson`
 - `maxRetries`
 
-You can also force the legacy endpoint yourself:
+You can also force the legacy path yourself:
 
 ```ts
 await client.generate({
@@ -70,12 +69,12 @@ await client.generate({
 
 ## Structured Output
 
-Use `schema` when you want validated JSON back:
+Use `schema` when the response shape matters:
 
 ```ts
 const result = await client.generate({
   chainId: 'invoice-parser',
-  prompt: 'Extract invoice fields',
+  prompt: 'Extract the invoice fields.',
   schema: {
     invoiceNumber: 'string',
     amount: 'number',
@@ -85,38 +84,38 @@ const result = await client.generate({
 });
 ```
 
-If the provider returns malformed JSON, Hydra will still try to recover it before the request fails.
+If the provider comes back with malformed JSON, Hydra will still try to recover the payload before the request fails.
 
 ## Cache Control
 
-Use request-level cache controls when the prompt should behave differently from the default path:
+Use request-level cache controls when freshness or privacy matters:
 
 ```ts
 await client.generate({
   chainId: 'account-summary',
-  prompt: 'Summarize this customer account',
+  prompt: 'Summarize this customer account.',
   cacheScope: 'user',
 });
 
 await client.generate({
   chainId: 'pricing-faq',
-  prompt: 'Return the current pricing summary',
+  prompt: 'Return the current pricing summary.',
   cacheScope: 'global',
 });
 
 await client.generate({
   chainId: 'one-off',
-  prompt: 'Generate a fresh variant',
+  prompt: 'Generate a fresh variant.',
   noCache: true,
 });
 ```
 
-You can also tune cache matching:
+Tune cache matching when you want better reuse:
 
 ```ts
 await client.generate({
   chainId: 'reporting',
-  prompt: 'Generate the weekly report',
+  prompt: 'Generate the weekly report.',
   cacheQuality: 'HIGH',
 });
 ```
@@ -129,7 +128,7 @@ Stream parsed objects as they arrive:
 await client.generateStream(
   {
     chainId: 'catalog-generator',
-    prompt: 'Generate 50 product blurbs as JSON',
+    prompt: 'Generate 50 product blurbs as JSON.',
   },
   {
     onObject: (object, index) => {
@@ -159,9 +158,9 @@ const batch = await client.generateBatch('catalog-generator', [
 console.log(batch.summary);
 ```
 
-## Files
+## File Attachments
 
-Send file attachments as base64:
+Send files as base64 and let Hydra handle the processing path:
 
 ```ts
 import fs from 'node:fs';
@@ -170,7 +169,7 @@ const file = fs.readFileSync('report.pdf');
 
 const result = await client.generate({
   chainId: 'document-analysis',
-  prompt: 'Summarize this report',
+  prompt: 'Summarize this report.',
   files: [
     {
       data: file.toString('base64'),
@@ -181,7 +180,7 @@ const result = await client.generate({
 });
 ```
 
-## Usage and Health
+## Usage And Health
 
 Get normalized usage metrics:
 
@@ -200,7 +199,7 @@ Basic health:
 
 ```ts
 const health = await client.health();
-console.log(health.ok, health.latencyMs);
+console.log(health.ok, health.latencyMs, health.version);
 ```
 
 Detailed health requires an admin key:
@@ -242,7 +241,7 @@ setTimeout(() => controller.abort(), 5000);
 
 await client.generate({
   chainId: 'long-job',
-  prompt: 'Generate a long report',
+  prompt: 'Generate a long report.',
   signal: controller.signal,
 });
 ```
@@ -261,11 +260,11 @@ import {
 try {
   await client.generate({
     chainId: 'support-replies',
-    prompt: 'Write a response',
+    prompt: 'Write a response.',
   });
 } catch (error) {
   if (error instanceof AuthenticationError) {
-    console.error('The Hydra secret key is invalid.');
+    console.error('Your Hydra secret key is invalid.');
   } else if (error instanceof QuotaExceededError) {
     console.error(error.tier, error.used, error.limit);
   } else if (error instanceof RateLimitError) {
@@ -297,8 +296,15 @@ try {
 ## Requirements
 
 - Node.js 18+
+- Bun 1.0+ or another runtime with `fetch`
 - TypeScript 5+ for typed projects
 
+## Get Started
+
+- Docs: [hydrai.dev/docs](https://hydrai.dev/docs)
+- Dashboard: [hydrai.dev/signin](https://hydrai.dev/signin)
+- Contact: [hydrai.dev/contact](https://hydrai.dev/contact)
+
 ## License
 
 MIT

package/dist/index.d.mts

@@ -15,7 +15,7 @@ interface HydraConfig {
     /**
      * API base URL
      * @default 'http://localhost:3000' in development
-     * @example 'https://api.hydrai.dev'
+     * @example 'https://your-hydra-instance.com'
      */
     baseUrl?: string;
     /**
@@ -698,7 +698,7 @@ interface WebhookConfig {
  *
  * const client = new Hydra({
  *   secretKey: process.env.HYDRA_SECRET_KEY!,
- *   baseUrl: 'https://api.hydrai.dev',
+ *   baseUrl: 'https://your-hydra-instance.com',
  * });
  *
  * const result = await client.generate({

package/dist/index.d.ts

@@ -15,7 +15,7 @@ interface HydraConfig {
     /**
      * API base URL
      * @default 'http://localhost:3000' in development
-     * @example 'https://api.hydrai.dev'
+     * @example 'https://your-hydra-instance.com'
      */
     baseUrl?: string;
     /**
@@ -698,7 +698,7 @@ interface WebhookConfig {
  *
  * const client = new Hydra({
  *   secretKey: process.env.HYDRA_SECRET_KEY!,
- *   baseUrl: 'https://api.hydrai.dev',
+ *   baseUrl: 'https://your-hydra-instance.com',
  * });
  *
  * const result = await client.generate({

package/package.json

@@ -1,7 +1,7 @@
 {
     "name": "hydra-aidirector",
-    "version": "1.6.1",
-    "description": "Official TypeScript SDK for Hydra - Intelligent AI API Gateway with automatic failover, caching, and JSON extraction",
+    "version": "1.6.2",
+    "description": "Official TypeScript SDK for Hydra. Generate, stream, fail over models, control cache scope, and manage AI operations from one client.",
     "main": "./dist/index.js",
     "module": "./dist/index.mjs",
     "types": "./dist/index.d.ts",
@@ -38,6 +38,7 @@
     },
     "keywords": [
         "ai",
+        "ai-sdk",
         "api",
         "gateway",
         "gemini",
@@ -49,6 +50,10 @@
         "typescript",
         "json",
         "cache",
+        "structured-output",
+        "streaming",
+        "webhooks",
+        "observability",
         "hmac"
     ],
     "author": {
@@ -56,13 +61,9 @@
         "url": "https://hydrai.dev"
     },
     "license": "MIT",
-    "homepage": "https://hydrai.dev",
+    "homepage": "https://hydrai.dev/docs",
     "bugs": {
-        "url": "https://github.com/hydrai/client/issues"
-    },
-    "repository": {
-        "type": "git",
-        "url": "git+https://github.com/hydrai/client.git"
+        "url": "https://hydrai.dev/contact"
     },
     "publishConfig": {
         "access": "public",