primellm 0.1.0 → 1.0.0

package/README.md

@@ -1,198 +1,97 @@
-# PrimeLLM JavaScript SDK
+# PrimeLLM CLI
 
-Official JavaScript/TypeScript SDK for the PrimeLLM unified AI API.
+> Configure Claude Code and Codex to use PrimeLLM as the backend
 
-PrimeLLM lets you access multiple AI models (GPT-5.1, Claude, Gemini) through a single, simple API. This SDK makes it easy to call PrimeLLM from JavaScript or TypeScript.
+A production-grade CLI installer that configures AI coding tools to use PrimeLLM's unified API.
 
-## Installation
-
-### Local Development (Not on npm yet)
+## Quick Start
 
 ```bash
-cd js-sdk
-npm install
-npm run build
+npx primellm
 ```
 
-### Future npm Usage (Coming Soon)
+## Features
 
-```bash
-npm install primellm
-```
-
-## Quick Start
+- 🎨 **Beautiful UI** - ASCII art banner and progress indicators
+- 🔍 **System Detection** - Automatically detects OS, shell, and Node version
+- 🛠 **Tool Selection** - Choose between Claude Code or Codex
+- 📦 **Smart Installation** - Only installs tools if not already present
+- 🔑 **Secure API Key Flow** - Masked input with validation
+- 📁 **Flexible Scope** - System-level or project-level configuration
 
-```javascript
-import PrimeLLMClient from "primellm";
-
-// Create a client with your API key
-const client = new PrimeLLMClient({
-  apiKey: "primellm_live_XXX", // Get from https://primellm.in/dashboard
-});
-
-// Send a chat message
-const response = await client.chat({
-  model: "gpt-5.1",
-  messages: [
-    { role: "system", content: "You are a helpful assistant." },
-    { role: "user", content: "What is TypeScript?" },
-  ],
-});
-
-// Access the response
-console.log(response.choices[0].message.content);
-console.log("Tokens used:", response.usage.total_tokens);
-console.log("Credits left:", response.credits.remaining);
-```
+## Supported Tools
 
-## Available Models
+| Tool | Package | Command |
+|------|---------|---------|
+| Claude Code | `@anthropic-ai/claude-code` | `claude` |
+| Codex | `@openai/codex` | `codex` |
 
-| Model | Description |
-|-------|-------------|
-| `gpt-5.1` | Latest GPT model (default) |
-| `claude-sonnet-4.5` | Claude Sonnet 4.5 |
-| `gemini-3.0` | Gemini 3.0 |
+## Usage
 
-## API Reference
+### Interactive Mode
 
-### Creating a Client
+Simply run the CLI and follow the prompts:
 
-```typescript
-const client = new PrimeLLMClient({
-  apiKey: "primellm_live_XXX",  // Required
-  baseURL: "https://api.primellm.in",  // Optional, this is the default
-  timeoutMs: 60000,  // Optional, 60 seconds default
-});
+```bash
+npx primellm
 ```
 
-### client.chat(request)
+### What it Does
 
-Send a chat completion request to `/v1/chat`. This is the recommended method.
-
-```javascript
-const response = await client.chat({
-  model: "gpt-5.1",
-  messages: [
-    { role: "user", content: "Hello!" }
-  ],
-  temperature: 0.7,  // Optional
-  max_tokens: 1000,  // Optional
-});
-```
+1. **Detects your system** - Shows OS, shell, and Node version
+2. **Asks which tool** - Claude Code or Codex
+3. **Checks installation** - Skips install if already present
+4. **Gets your API key** - Opens browser if you need to create one
+5. **Configures the tool** - Writes config with PrimeLLM backend
 
-**Response:**
-```javascript
-{
-  id: "chatcmpl_xxx",
-  model: "gpt-5.1",
-  choices: [{
-    index: 0,
-    message: { role: "assistant", content: "..." },
-    finish_reason: "stop"
-  }],
-  usage: {
-    prompt_tokens: 10,
-    completion_tokens: 20,
-    total_tokens: 30
-  },
-  credits: {
-    remaining: 149.99,
-    cost: 0.00006
-  }
-}
-```
+## Configuration
 
-### client.completions(request)
+### System-level (recommended)
 
-Same as `chat()`, but uses the `/v1/chat/completions` endpoint.
-Use this for OpenAI API path compatibility.
+Applies to all projects. Config stored in:
+- Claude Code: `~/.claude/config.json`
+- Codex: `~/.codex/config.json`
 
-```javascript
-const response = await client.completions({
-  model: "claude-sonnet-4.5",
-  messages: [{ role: "user", content: "Hello!" }],
-});
-```
+### Project-level
 
-### client.generate(request)
+Applies to current project only. Config stored in:
+- Claude Code: `./.claude/config.json`
+- Codex: `./.codex/config.json`
 
-Legacy endpoint using `/generate`. Returns a simpler response format.
+## API Key
 
-```javascript
-const response = await client.generate({
-  model: "gpt-5.1",
-  messages: [{ role: "user", content: "Hello!" }],
-});
+Your PrimeLLM API key:
+- Must start with `primellm_`
+- Can be created at: https://primellm.in/dashboard/api-keys
 
-// Response format is different:
-console.log(response.reply);  // The AI's response
-console.log(response.tokens_used);  // Total tokens
-console.log(response.credits_remaining);  // Credits left
-```
+## Requirements
 
-## Examples
+- Node.js >= 18.0.0
+- npm or npx
 
-Run the included examples:
+## Development
 
 ```bash
-cd js-sdk
-npm install
-npm run build
-
-# Edit examples to add your API key, then:
-node ./examples/chat-basic.mjs
-node ./examples/completions-basic.mjs
-node ./examples/generate-basic.mjs
-```
-
-## Understanding the Response
-
-- **model**: Which AI model generated the response
-- **messages**: The conversation, including the AI's reply
-- **usage**: Token counts (how much "text" was processed)
-  - `prompt_tokens`: Your input
-  - `completion_tokens`: AI's output
-  - `total_tokens`: Total
-- **credits**: Your PrimeLLM account balance
-  - `remaining`: Credits left
-  - `cost`: Cost of this request
-
-## TypeScript Support
-
-This SDK is written in TypeScript and includes full type definitions.
-
-```typescript
-import { PrimeLLMClient, ChatRequest, ChatResponse } from "primellm";
+# Clone the repo
+git clone https://github.com/rishuuu-codesss/primellm-backend.git
+cd primellm-backend/primellm-cli
 
-const client = new PrimeLLMClient({ apiKey: "..." });
-
-const request: ChatRequest = {
-  model: "gpt-5.1",
-  messages: [{ role: "user", content: "Hello!" }],
-};
+# Install dependencies
+npm install
 
-const response: ChatResponse = await client.chat(request);
-```
+# Run in development
+npm run dev
 
-## Error Handling
-
-```javascript
-try {
-  const response = await client.chat({
-    model: "gpt-5.1",
-    messages: [{ role: "user", content: "Hello!" }],
-  });
-} catch (error) {
-  console.error("API Error:", error.message);
-  // Example: "PrimeLLM API error: 401 Unauthorized - Invalid API key"
-}
+# Build
+npm run build
 ```
 
-## Notes
-
-- **Streaming**: Not yet supported. Calling `streamChat()` will throw an error.
-- **Publishing**: This SDK will be published to npm as `primellm` in a future release.
-
 ## License
 
 MIT
+
+## Links
+
+- [PrimeLLM Website](https://primellm.in)
+- [API Documentation](https://primellm.in/docs)
+- [Dashboard](https://primellm.in/dashboard)

package/dist/index.d.ts

@@ -1,124 +1,3 @@
-/**
- * PrimeLLM JavaScript SDK - Main Client
- *
- * This is the main SDK file. Developers import this to talk to PrimeLLM
- * from JavaScript or TypeScript.
- *
- * Example usage:
- *
- *   import { PrimeLLMClient } from "primellm";
- *
- *   const client = new PrimeLLMClient({ apiKey: "primellm_live_XXX" });
- *
- *   const response = await client.chat({
- *     model: "gpt-5.1",
- *     messages: [{ role: "user", content: "Hello!" }],
- *   });
- *
- *   console.log(response.choices[0].message.content);
- */
-import { ChatRequest, ChatResponse, GenerateRequest, GenerateResponse, PrimeLLMClientOptions } from "./types.js";
-export * from "./types.js";
-/**
- * PrimeLLM API Client
- *
- * This class handles all communication with the PrimeLLM API.
- * It provides methods for chat, completions, and the legacy generate endpoint.
- */
-export declare class PrimeLLMClient {
-    private apiKey;
-    private baseURL;
-    private timeoutMs;
-    /**
-     * Create a new PrimeLLM client.
-     *
-     * @param options - Configuration options
-     * @param options.apiKey - Your PrimeLLM API key (required)
-     * @param options.baseURL - API base URL (default: "https://api.primellm.in")
-     * @param options.timeoutMs - Request timeout in ms (default: 60000)
-     *
-     * @example
-     * const client = new PrimeLLMClient({
-     *   apiKey: "primellm_live_XXX",
-     * });
-     */
-    constructor(options: PrimeLLMClientOptions);
-    /**
-     * Internal helper to make API requests.
-     * Handles authentication, JSON parsing, and error handling.
-     */
-    private request;
-    /**
-     * Send a chat completion request using /v1/chat endpoint.
-     *
-     * This is the recommended method for most use cases.
-     * Returns an OpenAI-compatible response format.
-     *
-     * @param request - The chat request with model and messages
-     * @returns The chat response with choices, usage, and credits
-     *
-     * @example
-     * const response = await client.chat({
-     *   model: "gpt-5.1",
-     *   messages: [
-     *     { role: "system", content: "You are a helpful assistant." },
-     *     { role: "user", content: "What is TypeScript?" },
-     *   ],
-     * });
-     * console.log(response.choices[0].message.content);
-     */
-    chat(request: ChatRequest): Promise<ChatResponse>;
-    /**
-     * Send a chat completion request using /v1/chat/completions endpoint.
-     *
-     * This is an alternative endpoint that also returns OpenAI-compatible format.
-     * Use this if you need compatibility with OpenAI's exact endpoint path.
-     *
-     * @param request - The chat request with model and messages
-     * @returns The chat response with choices, usage, and credits
-     */
-    completions(request: ChatRequest): Promise<ChatResponse>;
-    /**
-     * Send a request to the legacy /generate endpoint.
-     *
-     * This endpoint returns a different response format than chat().
-     * Use chat() for new projects; this is for backwards compatibility.
-     *
-     * @param request - The generate request with model and messages
-     * @returns The generate response with reply, tokens_used, cost
-     *
-     * @example
-     * const response = await client.generate({
-     *   model: "gpt-5.1",
-     *   messages: [{ role: "user", content: "Hello!" }],
-     * });
-     * console.log(response.reply);
-     */
-    generate(request: GenerateRequest): Promise<GenerateResponse>;
-    /**
-     * Stream a chat completion response.
-     *
-     * ⚠️ NOT IMPLEMENTED YET - Backend streaming support coming soon.
-     *
-     * @throws Error always - streaming not supported in this version
-     */
-    streamChat(_request: ChatRequest): AsyncGenerator<ChatResponse, void, unknown>;
-    /**
-     * Stream a completions response.
-     *
-     * ⚠️ NOT IMPLEMENTED YET - Backend streaming support coming soon.
-     *
-     * @throws Error always - streaming not supported in this version
-     */
-    streamCompletions(_request: ChatRequest): AsyncGenerator<ChatResponse, void, unknown>;
-    /**
-     * Stream a generate response.
-     *
-     * ⚠️ NOT IMPLEMENTED YET - Backend streaming support coming soon.
-     *
-     * @throws Error always - streaming not supported in this version
-     */
-    streamGenerate(_request: GenerateRequest): AsyncGenerator<GenerateResponse, void, unknown>;
-}
-export default PrimeLLMClient;
+#!/usr/bin/env node
+export {};
 //# sourceMappingURL=index.d.ts.map

package/dist/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAEH,OAAO,EACH,WAAW,EACX,YAAY,EACZ,eAAe,EACf,gBAAgB,EAChB,qBAAqB,EACxB,MAAM,YAAY,CAAC;AAGpB,cAAc,YAAY,CAAC;AAE3B;;;;;GAKG;AACH,qBAAa,cAAc;IACvB,OAAO,CAAC,MAAM,CAAS;IACvB,OAAO,CAAC,OAAO,CAAS;IACxB,OAAO,CAAC,SAAS,CAAS;IAE1B;;;;;;;;;;;;OAYG;gBACS,OAAO,EAAE,qBAAqB;IAS1C;;;OAGG;YACW,OAAO;IAsCrB;;;;;;;;;;;;;;;;;;OAkBG;IACG,IAAI,CAAC,OAAO,EAAE,WAAW,GAAG,OAAO,CAAC,YAAY,CAAC;IAIvD;;;;;;;;OAQG;IACG,WAAW,CAAC,OAAO,EAAE,WAAW,GAAG,OAAO,CAAC,YAAY,CAAC;IAI9D;;;;;;;;;;;;;;;OAeG;IACG,QAAQ,CAAC,OAAO,EAAE,eAAe,GAAG,OAAO,CAAC,gBAAgB,CAAC;IAQnE;;;;;;OAMG;IACI,UAAU,CACb,QAAQ,EAAE,WAAW,GACtB,cAAc,CAAC,YAAY,EAAE,IAAI,EAAE,OAAO,CAAC;IAQ9C;;;;;;OAMG;IACI,iBAAiB,CACpB,QAAQ,EAAE,WAAW,GACtB,cAAc,CAAC,YAAY,EAAE,IAAI,EAAE,OAAO,CAAC;IAO9C;;;;;;OAMG;IACI,cAAc,CACjB,QAAQ,EAAE,eAAe,GAC1B,cAAc,CAAC,gBAAgB,EAAE,IAAI,EAAE,OAAO,CAAC;CAMrD;AAGD,eAAe,cAAc,CAAC"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":""}