compress-lightreach 1.0.1 → 1.0.3

package/README.md

@@ -1,25 +1,26 @@
 # Compress Light Reach
 
-**Intelligent compression algorithms for LLM prompts that reduce token usage**
+**AI cost management SDK with intelligent model routing, prompt compression, and real-time token tracking**
 
 [![npm version](https://badge.fury.io/js/compress-lightreach.svg)](https://badge.fury.io/js/compress-lightreach)
 [![Node.js 14+](https://img.shields.io/badge/node-14+-blue.svg)](https://nodejs.org/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-Compress Light Reach is a Node.js/TypeScript library that intelligently compresses LLM prompts by replacing repeated substrings with shorter placeholders, significantly reducing token usage and costs while maintaining perfect decompression.
+Compress Light Reach is a Node.js/TypeScript SDK that provides intelligent model routing and prompt compression for LLM applications, reducing token usage and costs while maintaining quality.
 
 ## Features
 
-- **Token-aware compression**: Only replaces substrings >1 token with 1-token placeholders
-- **Dual algorithms**: 
+- **Intelligent Model Routing**: Automatically selects optimal model based on quality requirements (HLE) and available provider keys
+- **Token-aware Compression**: Replaces repeated substrings with shorter placeholders
+- **Dual Algorithms**: 
   - Fast greedy (~99% optimal) for daily use
   - Optimal DP (O(n²)) for critical prompts
 - **Lossless**: Perfect decompression guaranteed
-- **Output compression**: Optional model output compression support
-- **Cloud API**: Uses Light Reach's cloud service for compression
-- **Model-aware**: Optimized for GPT-4, GPT-3.5-turbo, Claude, and more
+- **Output Compression**: Optional model output compression support
+- **Cloud API**: Uses Light Reach's cloud service for compression and routing
+- **Multi-provider Support**: OpenAI, Anthropic, Google, DeepSeek, Moonshot
 - **TypeScript**: Full TypeScript support with type definitions
-- **Intelligent Routing**: Automatic model selection based on quality requirements
+- **BYOK**: Provider API keys managed securely in dashboard (never passed through SDK)
 
 ## Installation
 
@@ -33,12 +34,12 @@ or
 yarn add compress-lightreach
 ```
 
-## Quick Start (v1.0.0)
+## Quick Start
 
 The SDK uses **intelligent model routing** and targets `POST /api/v2/complete`.
 
-- Authenticate with your **LightReach API key** (env var `PCOMPRESLR_API_KEY`)
-- Manage **provider keys** (OpenAI/Anthropic/Google) in the dashboard (BYOK)
+- Authenticate with your **LightReach API key** (env var `PCOMPRESLR_API_KEY` or `LIGHTREACH_API_KEY`)
+- Manage **provider keys** (OpenAI/Anthropic/Google/etc.) in the dashboard (BYOK)
 - System automatically selects optimal model based on your requirements
 
 ```typescript
@@ -51,7 +52,7 @@ const result = await client.complete({
     { role: 'system', content: 'You are a helpful assistant.' },
     { role: 'user', content: 'Explain quantum computing in simple terms.' },
   ],
-  desiredHle: 30,  // Quality preference (0-40, where 40 is SOTA)
+  desired_hle: 30,  // Quality preference (0-40, where 40 is SOTA)
 });
 
 console.log(result.decompressed_response);
@@ -64,14 +65,14 @@ console.log(`Token savings: ${result.compression_stats.token_savings}`);
 ```typescript
 const result = await client.complete({
   messages: [{ role: 'user', content: 'Generate a long report...' }],
-  desiredHle: 25,
-  compressOutput: true,
+  desired_hle: 25,
+  compress_output: true,
 });
 
 console.log(result.decompressed_response);
 ```
 
-### Intelligent Model Routing (v1.0.0)
+### Intelligent Model Routing
 
 The system automatically selects the optimal model based on quality requirements and your available provider keys:
 
@@ -82,14 +83,14 @@ const client = new PcompresslrAPIClient("your-lightreach-api-key");
 
 // Cross-provider optimization: system picks cheapest model meeting your quality bar
 const result = await client.complete({
-  messages: [{role: 'user', content: 'Explain quantum computing'}],
-  desiredHle: 30,  // Quality preference (0-40, where 40 is SOTA)
+  messages: [{ role: 'user', content: 'Explain quantum computing' }],
+  desired_hle: 30,  // Quality preference (0-40, where 40 is SOTA)
 });
 
 // Check what was selected
-console.log(result.routing_info?.selected_model);      // e.g., "gpt-4o-mini"
-console.log(result.routing_info?.selected_provider);   // e.g., "openai"
-console.log(result.routing_info?.model_hle);           // e.g., 32.5
+console.log(result.routing_info?.selected_model);           // e.g., "gpt-4o-mini"
+console.log(result.routing_info?.selected_provider);        // e.g., "openai"
+console.log(result.routing_info?.model_hle);                // e.g., 32.5
 console.log(result.routing_info?.model_price_per_million);  // e.g., 0.15
 ```
 
@@ -100,24 +101,24 @@ Optionally constrain to a specific provider:
 ```typescript
 // Only use OpenAI models, but pick the cheapest one meeting HLE 35
 const result = await client.complete({
-  messages: [{role: 'user', content: 'Write a poem'}],
-  llmProvider: 'openai',  // Optional: constrain to one provider
-  desiredHle: 35,
+  messages: [{ role: 'user', content: 'Write a poem' }],
+  llm_provider: 'openai',  // Optional: constrain to one provider
+  desired_hle: 35,
 });
 ```
 
 ### HLE Cascading with Admin Controls
 
-Admins can set quality **ceilings** via the dashboard (global or per-tag) to control costs. Your `desiredHle` is a preference, but requests will error if they exceed the admin-set ceiling:
+Admins can set quality **ceilings** via the dashboard (global or per-tag) to control costs. Your `desired_hle` is a preference, but requests will error if they exceed the admin-set ceiling:
 
 ```typescript
 // Admin set global HLE ceiling to 30%
 // Requesting above the ceiling will error
 try {
   const result = await client.complete({
-    messages: [{role: 'user', content: 'Process payment'}],
-    desiredHle: 35,  // ❌ ERROR: exceeds ceiling of 30
-    tags: {env: 'production'},
+    messages: [{ role: 'user', content: 'Process payment' }],
+    desired_hle: 35,  // ERROR: exceeds ceiling of 30
+    tags: { env: 'production' },
   });
 } catch (e) {
   console.error(e.message);  // "Requested HLE 35% exceeds workspace maximum of 30%"
@@ -125,9 +126,9 @@ try {
 
 // Correct usage: request within ceiling
 const result = await client.complete({
-  messages: [{role: 'user', content: 'Process payment'}],
-  desiredHle: 25,  // ✅ OK: below ceiling of 30
-  tags: {env: 'production'},
+  messages: [{ role: 'user', content: 'Process payment' }],
+  desired_hle: 25,  // OK: below ceiling of 30
+  tags: { env: 'production' },
 });
 
 // Check if your HLE was lowered by admin ceiling
@@ -138,6 +139,59 @@ if (result.routing_info?.hle_clamped) {
 }
 ```
 
+### With Compression Config
+
+Configure per-role compression settings:
+
+```typescript
+import { PcompresslrAPIClient } from 'compress-lightreach';
+
+const client = new PcompresslrAPIClient("your-lightreach-api-key");
+
+const result = await client.complete({
+  messages: [{ role: 'user', content: 'Hello!' }],
+  desired_hle: 30,
+  compress: true,
+  compress_output: false,
+  compression_config: {
+    compress_system: false,
+    compress_user: true,
+    compress_assistant: false,
+    compress_only_last_n_user: 1,
+  },
+  temperature: 0.7,
+  max_tokens: 1000,
+  tags: { env: 'production' },
+});
+
+console.log(result.decompressed_response);
+console.log(`Model used: ${result.routing_info?.selected_model}`);
+```
+
+
+### Compression Only (No LLM Call)
+
+```typescript
+import { PcompresslrAPIClient } from 'compress-lightreach';
+
+const client = new PcompresslrAPIClient("your-lightreach-api-key");
+
+// Compress text without making an LLM call
+const compressed = await client.compress(
+  "Your text with repeated content here...",
+  "gpt-4",      // Model for tokenization
+  "greedy",     // Algorithm: 'greedy' or 'optimal'
+  { env: 'dev' } // Optional tags
+);
+
+console.log(compressed.llm_format);
+console.log(`Compression ratio: ${compressed.compression_ratio}`);
+
+// Decompress later
+const decompressed = await client.decompress(compressed.llm_format);
+console.log(decompressed.decompressed);
+```
+
 ### Command Line Interface
 
 ```bash
@@ -145,7 +199,6 @@ if (result.routing_info?.hle_clamped) {
 export PCOMPRESLR_API_KEY=your-api-key
 
 # Compress a prompt
-# Run the CLI directly (the published binary name is `pcompresslr`)
 npx pcompresslr "Your prompt with repeated text here..."
 
 # Use optimal algorithm only
@@ -161,67 +214,189 @@ npx pcompresslr "Your prompt here" --greedy-only
 
 Main API client for intelligent model routing and compression.
 
-#### Constructor Parameters
+#### Constructor
 
-- `apiKey` (string, optional): LightReach API key (or use `PCOMPRESLR_API_KEY` env var).
-- `apiUrl` (string, optional): Override base API URL (advanced/testing).
-- `timeout` (number): Request timeout in milliseconds (default: 120000).
+```typescript
+new PcompresslrAPIClient(apiKey?: string, apiUrl?: string, timeout?: number)
+```
+
+**Parameters:**
+- `apiKey` (string, optional): LightReach API key. Falls back to `LIGHTREACH_API_KEY` or `PCOMPRESLR_API_KEY` env vars.
+- `apiUrl` (string, optional): Override base API URL. Falls back to `PCOMPRESLR_API_URL` env var. Default: `https://api.compress.lightreach.io`
+- `timeout` (number, optional): Request timeout in milliseconds. Default: `120000` (2 minutes)
 
 #### Methods
 
-##### `complete(request)`
+##### `complete(request: CompleteV2Request): Promise<CompleteResponse>`
 
 Messages-first completion with intelligent routing (POST `/api/v2/complete`).
 
-**Parameters (CompleteV2Request):**
-- `messages` (required): Conversation history as array of objects with `role` and `content`
-- `llmProvider` (optional): Provider constraint (`'openai'`, `'anthropic'`, `'google'`, etc.). Omit for cross-provider optimization.
-- `desiredHle` (optional): Quality preference (0-40, where 40 is SOTA). Must not exceed admin's global/tag-level ceilings (request will error if it does).
-- `tags` (optional): Object of tags for cost attribution and tag-level HLE ceilings
-- `compress` (optional): Whether to compress messages (default: `true`)
-- `compressOutput` (optional): Whether to request compressed output from LLM (default: `false`)
-- `algorithm` (optional): Compression algorithm (`'greedy'` or `'optimal'`, default: `'greedy'`)
-- `temperature` (optional): LLM temperature parameter
-- `maxTokens` (optional): Maximum tokens to generate
-- `compressionConfig` (optional): Per-role compression settings
-- `maxHistoryMessages` (optional): Limit conversation history length
-
-**Response (CompleteResponse) includes:**
-- `decompressed_response`: Final decompressed LLM response
-- `routing_info`: Details about model selection:
-  - `selected_model`: Model chosen by system
-  - `selected_provider`: Provider chosen by system
-  - `model_hle`: HLE score of selected model
-  - `effective_hle`: Effective HLE after applying admin ceilings (min of desired/tag/global)
-  - `hle_source`: `'request'`, `'tag'`, `'global'`, or `'none'`
-  - `hle_clamped`: `true` if admin ceiling lowered your `desiredHle`
-- `compression_stats`: Token savings statistics
-- `llm_stats`: Token usage from the LLM
-- `warnings`: Array of any warnings (including HLE ceiling notifications)
-
-##### `compress(prompt, model, algorithm, tags)`
+**Request Parameters (`CompleteV2Request`):**
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `messages` | `Message[]` | required | Conversation history with `role` and `content` |
+| `llm_provider` | `'openai' \| 'anthropic' \| 'google' \| 'deepseek' \| 'moonshot'` | — | Optional provider constraint. Omit for cross-provider optimization |
+| `desired_hle` | `number` | — | Quality preference (0-40, where 40 is SOTA). Must not exceed admin ceilings |
+| `compress` | `boolean` | `true` | Whether to compress messages |
+| `compress_output` | `boolean` | `false` | Whether to request compressed output from LLM |
+| `algorithm` | `'greedy' \| 'optimal'` | `'greedy'` | Compression algorithm |
+| `compression_config` | `object` | — | Per-role compression settings (see below) |
+| `temperature` | `number` | — | LLM temperature parameter |
+| `max_tokens` | `number` | — | Maximum tokens to generate |
+| `tags` | `Record<string, string>` | — | Tags for cost attribution and tag-level HLE ceilings |
+| `max_history_messages` | `number` | — | Limit conversation history length |
+
+**`compression_config` options:**
+
+```typescript
+{
+  compress_system?: boolean;         // default: false
+  compress_user?: boolean;           // default: true
+  compress_assistant?: boolean;      // default: false
+  compress_only_last_n_user?: number | null;  // default: 1
+}
+```
+
+**Response (`CompleteResponse`):**
+
+```typescript
+{
+  decompressed_response: string;     // Final decompressed LLM response
+  compression_stats: {
+    original_size_chars: number;
+    compressed_size_chars: number;
+    original_tokens: number;
+    compressed_tokens: number;
+    compression_ratio: number;
+    token_savings: number;
+    token_savings_percent: number;
+    processing_time_ms?: number;
+  };
+  llm_stats: {
+    prompt_tokens: number;
+    completion_tokens: number;
+    total_tokens: number;
+  };
+  routing_info?: {
+    selected_model: string;          // Model chosen by system
+    selected_provider: string;       // Provider chosen by system
+    selected_model_id: string;
+    model_hle: number;               // HLE score of selected model
+    model_price_per_million: number;
+    requested_hle: number | null;
+    effective_hle: number | null;    // Effective HLE after admin ceilings
+    hle_source: 'request' | 'tag' | 'global' | 'none';
+    hle_clamped: boolean;            // true if admin ceiling lowered your desired_hle
+  };
+  warnings?: string[];
+  
+  // Convenience aliases
+  text?: string;                     // Alias for decompressed_response
+  tokens_saved?: number;             // Alias for compression_stats.token_savings
+  tokens_used?: number;              // Alias for llm_stats.total_tokens
+  compression_ratio?: number;        // Alias for compression_stats.compression_ratio
+}
+```
+
+##### `compress(prompt, model?, algorithm?, tags?): Promise<CompressResponse>`
 
 Compression-only (POST `/api/v1/compress`).
 
-##### `decompress(llmFormat)`
+**Parameters:**
+- `prompt` (string, required): Text to compress
+- `model` (string, optional): Model for tokenization. Default: `'gpt-4'`
+- `algorithm` (`'greedy' | 'optimal'`, optional): Compression algorithm. Default: `'greedy'`
+- `tags` (`Record<string, string>`, optional): Tags for attribution
+
+**Response (`CompressResponse`):**
+
+```typescript
+{
+  compressed: string;
+  dictionary: Record<string, string>;
+  llm_format: string;
+  compression_ratio: number;
+  original_size: number;
+  compressed_size: number;
+  processing_time_ms: number;
+  algorithm: string;
+}
+```
+
+##### `decompress(llmFormat): Promise<DecompressResponse>`
 
 Decompress an LLM-formatted compressed prompt (POST `/api/v1/decompress`).
 
-##### `healthCheck()`
+**Parameters:**
+- `llmFormat` (string, required): The `llm_format` string from a compress response
+
+**Response (`DecompressResponse`):**
+
+```typescript
+{
+  decompressed: string;
+  processing_time_ms: number;
+}
+```
+
+##### `healthCheck(): Promise<HealthCheckResponse>`
 
 Check API health status (GET `/health`).
 
+**Response:**
+
+```typescript
+{
+  status: string;
+  version?: string;
+}
+```
+
+
+### Message Types
+
+```typescript
+type MessageRole = 'system' | 'developer' | 'user' | 'assistant';
+
+interface Message {
+  role: MessageRole;
+  content: string;
+}
+```
+
 ### Environment Variables
 
-- `PCOMPRESLR_API_KEY` (or `LIGHTREACH_API_KEY`): Your LightReach API key.
-- `PCOMPRESLR_API_URL`: Override the API base URL (advanced/testing).
+| Variable | Description |
+|----------|-------------|
+| `PCOMPRESLR_API_KEY` | Your LightReach API key (primary) |
+| `LIGHTREACH_API_KEY` | Your LightReach API key (alternative) |
+| `PCOMPRESLR_API_URL` | Override the API base URL (advanced/testing) |
 
 ### Exceptions
 
-- `APIKeyError`: Raised when API key is invalid or missing
-- `RateLimitError`: Raised when rate limit is exceeded
-- `APIRequestError`: Raised for general API errors (including routing failures)
-- `PcompresslrAPIError`: Base exception class
+| Exception | Description |
+|-----------|-------------|
+| `PcompresslrAPIError` | Base exception class |
+| `APIKeyError` | Invalid or missing API key |
+| `RateLimitError` | Rate limit exceeded |
+| `APIRequestError` | General API errors (including routing failures) |
+
+```typescript
+import { APIKeyError, RateLimitError, APIRequestError } from 'compress-lightreach';
+
+try {
+  const result = await client.complete({ messages: [...] });
+} catch (error) {
+  if (error instanceof APIKeyError) {
+    console.error('Invalid API key');
+  } else if (error instanceof RateLimitError) {
+    console.error('Rate limited, please retry later');
+  } else if (error instanceof APIRequestError) {
+    console.error('API error:', error.message);
+  }
+}
+```
 
 ## How It Works
 
@@ -237,7 +412,7 @@ The library:
 
 ## Examples
 
-### Example 1: Using Complete Method (Recommended)
+### Example 1: Complete with Compression
 
 ```typescript
 import { PcompresslrAPIClient } from 'compress-lightreach';
@@ -250,10 +425,9 @@ Write a story about a dog. The dog is very friendly.
 Write a story about a bird. The bird is very friendly.
 `;
 
-// One call handles compression, LLM request, and decompression
 const result = await client.complete({
   messages: [{ role: "user", content: prompt }],
-  desiredHle: 30,
+  desired_hle: 30,
 });
 
 console.log(result.decompressed_response);
@@ -262,22 +436,46 @@ console.log(`Token savings: ${result.compression_stats.token_savings} tokens`);
 console.log(`Compression ratio: ${(result.compression_stats.compression_ratio * 100).toFixed(2)}%`);
 ```
 
-### Example 2: Complete with Output Compression
+### Example 2: Output Compression
 
 ```typescript
 import { PcompresslrAPIClient } from 'compress-lightreach';
 
 const client = new PcompresslrAPIClient("your-lightreach-api-key");
 
-// Complete with output compression - response is automatically decompressed
 const result = await client.complete({
   messages: [{ role: "user", content: "Generate a long report with repeated sections..." }],
-  desiredHle: 35,
-  compressOutput: true
+  desired_hle: 35,
+  compress_output: true,
 });
+
 console.log(result.decompressed_response);
 ```
 
+### Example 3: Multi-turn Conversation
+
+```typescript
+import { PcompresslrAPIClient } from 'compress-lightreach';
+
+const client = new PcompresslrAPIClient("your-lightreach-api-key");
+
+const result = await client.complete({
+  messages: [
+    { role: "system", content: "You are a helpful coding assistant." },
+    { role: "user", content: "How do I read a file in Python?" },
+    { role: "assistant", content: "You can use open() with a context manager..." },
+    { role: "user", content: "How about writing to a file?" },
+  ],
+  desired_hle: 30,
+  compression_config: {
+    compress_system: false,
+    compress_user: true,
+    compress_assistant: false,
+    compress_only_last_n_user: 2,  // Only compress last 2 user messages
+  },
+});
+```
+
 ## Getting an API Key
 
 To use Compress Light Reach, you need an API key from [compress.lightreach.io](https://compress.lightreach.io).
@@ -289,7 +487,7 @@ To use Compress Light Reach, you need an API key from [compress.lightreach.io](h
 
 ## Security & Privacy
 
-**BYOK model:** Provider keys (OpenAI/Anthropic/Google) are managed in the dashboard and **never passed through this SDK**. The SDK only uses your LightReach API key for authentication with the service.
+**BYOK model:** Provider keys (OpenAI/Anthropic/Google/etc.) are managed in the dashboard and **never passed through this SDK**. The SDK only uses your LightReach API key for authentication with the service.
 
 ## Requirements
 
@@ -298,7 +496,7 @@ To use Compress Light Reach, you need an API key from [compress.lightreach.io](h
 
 ## License
 
-MIT License - see [LICENSE](../LICENSE) file for details.
+MIT License - see [LICENSE](./LICENSE) file for details.
 
 ## Support
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "compress-lightreach",
-  "version": "1.0.1",
+  "version": "1.0.3",
   "description": "AI cost management SDK with intelligent model routing, prompt compression, and real-time token tracking",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",