@juspay/neurolink 4.2.0 → 5.1.0

package/CHANGELOG.md

@@ -1,9 +1,54 @@
-# [4.2.0](https://github.com/juspay/neurolink/compare/v4.1.1...v4.2.0) (2025-07-11)
+# [5.1.0](https://github.com/juspay/neurolink/compare/v5.0.0...v5.1.0) (2025-07-13)
+
+
+### Features
+
+* **core:** complete unified multimodal AI platform architecture with generate/stream unification ([846e409](https://github.com/juspay/neurolink/commit/846e409a4a77024ddee9961c9b5049bc99f8335e))
+
+# [5.0.0](https://github.com/juspay/neurolink/compare/v4.2.0...v5.0.0) (2025-07-11)
+
+
+* refactor(cli)!: remove agent-generate command, unify CLI to single generate command ([9c034b7](https://github.com/juspay/neurolink/commit/9c034b7b5a8df3b861fccae0e617c5aa4c85a903))
+
+
+### Bug Fixes
 
+* **scripts:** update docs:generate to use docs:validate instead of removed docs:sync ([3277bab](https://github.com/juspay/neurolink/commit/3277bab3eb1cec24a60fe28bf3897fce63d83d3a))
+
+
+### BREAKING CHANGES
+
+* agent-generate command has been removed
+
+The agent-generate command has been completely removed from the CLI. All 
+functionality is now available through the enhanced generate command with 
+tools enabled by default.
+
+### Changes Made:
+- Delete src/cli/commands/agent-generate.ts command implementation
+- Remove agent-generate import and registration from src/cli/index.ts
+- Update docs/CLI-GUIDE.md to remove agent-generate documentation
+- Update memory-bank documentation files to reflect unified approach
+- Remove agent-generate test cases from scripts/corrected-functionality-test.js
+
+### Migration Guide:
+- Replace `neurolink agent-generate "prompt"` with `neurolink generate "prompt"`
+- Tools are enabled by default in generate command
+- Use `--disable-tools` flag if tool-calling is not desired
+- All previous agent-generate functionality available in generate command
+
+### Technical Impact:
+- Simplified CLI interface with single text generation command
+- Reduced codebase complexity and maintenance overhead
+- Enhanced generate command provides all tool-calling capabilities
+- Zero breaking changes to core functionality
+- Clean TypeScript compilation and documentation consistency
+
+# [4.2.0](https://github.com/juspay/neurolink/compare/v4.1.1...v4.2.0) (2025-07-11)
 
 ### Features
 
-* **mcp:** comprehensive MCP system enhancements with timeout management ([1d35b5e](https://github.com/juspay/neurolink/commit/1d35b5e12d03ce60bcdf0608749a1b99e8565567))
+- **mcp:** comprehensive MCP system enhancements with timeout management ([1d35b5e](https://github.com/juspay/neurolink/commit/1d35b5e12d03ce60bcdf0608749a1b99e8565567))
 
 ## [4.1.1](https://github.com/juspay/neurolink/compare/v4.1.0...v4.1.1) (2025-07-10)
 

package/README.md

@@ -17,53 +17,6 @@
 - **📊 Advanced Telemetry** - Optional OpenTelemetry monitoring with zero overhead when disabled
 - **💬 Enhanced Chat Services** - Dual-mode SSE + WebSocket support for enterprise applications
 - **🏗️ Enterprise Architecture** - Production-ready scaling with connection pooling and optimization
-
-## 🏗️ Enterprise Configuration Management
-
-### **✨ NEW: Automatic Backup System**
-
-```bash
-# All config changes create automatic backups
-npm run config:update
-# ✅ Backup created: .neurolink.backups/neurolink-config-2025-01-07T10-30-00.js
-
-# Auto-restore on failures
-npm run config:validate
-# ✅ Config validated with suggestions and warnings
-```
-
-### **✨ NEW: Industry-Standard Interfaces**
-
-```typescript
-// Modern camelCase interfaces with rich context
-interface ExecutionContext {
-  sessionId?: string;
-  userId?: string;
-  aiProvider?: string;
-  permissions?: string[];
-  cacheOptions?: CacheOptions;
-  fallbackOptions?: FallbackOptions;
-  metadata?: Record<string, unknown>;
-}
-
-// Optional methods for maximum flexibility
-interface McpRegistry {
-  registerServer?(
-    serverId: string,
-    config?: unknown,
-    context?: ExecutionContext,
-  ): Promise<void>;
-  executeTool?<T>(
-    toolName: string,
-    args?: unknown,
-    context?: ExecutionContext,
-  ): Promise<T>;
-  listTools?(context?: ExecutionContext): Promise<ToolInfo[]>;
-}
-```
-
-### **Enterprise Features**
-
 - **🔄 Automatic Backup/Restore** - Timestamped backups with hash verification
 - **✅ Config Validation** - Comprehensive validation with suggestions
 - **🏗️ Factory-First MCP** - Lighthouse-compatible architecture (99% compatible)
@@ -71,6 +24,19 @@ interface McpRegistry {
 - **⚡ Performance** - Tool execution <1ms, pipeline execution ~22ms
 - **🛡️ Error Recovery** - Graceful failures with auto-restore
 
+## ✅ LATEST UPDATE: Stream Function Migration Complete (2025-01-12)
+
+**NeuroLink now uses `stream()` as the primary streaming function with future-ready multi-modal interface.**
+
+- ✅ **New Primary Streaming**: `stream()` with multi-modal ready interface
+- ✅ **Enhanced Generation**: `generate()` as primary generation function
+- ✅ **Factory Enhanced**: Better provider management across all methods
+- ✅ **Zero Breaking Changes**: All existing code continues working (backward compatibility)
+
+> **Enhanced API**: NeuroLink uses `stream()` and `generate()` as primary functions with multi-modal ready interfaces and improved factory patterns.
+
+---
+
 ## 🚀 Quick Start
 
 ### Install & Run (2 minutes)
@@ -83,7 +49,11 @@ export GOOGLE_AI_API_KEY="AIza-your-google-ai-api-key"
 npx @juspay/neurolink generate "Hello, AI"
 npx @juspay/neurolink gen "Hello, AI"        # Shortest form
 
-# 🆕 NEW: AI Enhancement Features
+# ✨ Primary Method (generate) - Recommended
+npx @juspay/neurolink generate "Explain AI" --provider google-ai
+npx @juspay/neurolink gen "Write code" --provider openai       # Shortest form
+
+# 🆕 AI Enhancement Features
 npx @juspay/neurolink generate "Explain AI" --enable-analytics --debug
 npx @juspay/neurolink generate "Write code" --enable-evaluation --debug
 npx @juspay/neurolink generate "Help me" --context '{"userId":"123"}' --debug
@@ -99,13 +69,21 @@ npm install @juspay/neurolink
 ### Basic Usage
 
 ```typescript
-import { createBestAIProvider } from "@juspay/neurolink";
+import { NeuroLink } from "@juspay/neurolink";
 
-// Auto-selects best available provider
+// NEW: Primary method (recommended)
+const neurolink = new NeuroLink();
+const result = await neurolink.generate({
+  input: { text: "Write a haiku about programming" },
+  provider: "google-ai",
+  timeout: "30s", // Optional: Set custom timeout (default: 30s)
+});
+// Alternative: Auto-selects best available provider
+import { createBestAIProvider } from "@juspay/neurolink";
 const provider = createBestAIProvider();
-const result = await provider.generateText({
+const providerResult = await provider.generate({
   prompt: "Write a haiku about programming",
-  timeout: "30s", // Optional: Set custom timeout (default: 30s)
+  timeout: "30s",
 });
 
 console.log(result.text);
@@ -118,7 +96,7 @@ Method aliases that match CLI command names:
 
 ```typescript
 // All three methods are equivalent:
-const result1 = await provider.generateText({ prompt: "Hello" }); // Original
+const result1 = await provider.generate({ prompt: "Hello" }); // Original
 const result2 = await provider.generate({ prompt: "Hello" }); // Matches CLI 'generate'
 const result3 = await provider.gen({ prompt: "Hello" }); // Matches CLI 'gen'
 
@@ -126,7 +104,7 @@ const result3 = await provider.gen({ prompt: "Hello" }); // Matches CLI 'gen'
 const provider = createBestAIProvider();
 
 // Detailed method name
-const story = await provider.generateText({
+const story = await provider.generate({
   prompt: "Write a short story about AI",
   maxTokens: 200,
 });
@@ -162,10 +140,10 @@ import { NeuroLink } from "@juspay/neurolink";
 const neurolink = new NeuroLink();
 
 // Basic usage
-const result = await neurolink.generateText("Write a story");
+const result = await neurolink.generate("Write a story");
 
 // With enhancements (NEW!)
-const enhancedResult = await neurolink.generateText({
+const enhancedResult = await neurolink.generate({
   prompt: "Write a business proposal",
   enableAnalytics: true, // Get usage & cost data
   enableEvaluation: true, // Get AI quality scores
@@ -189,7 +167,7 @@ const enhancedContext = createEnhancedContext(
   {
     domain: "Business development",
     role: "Business proposal assistant",
-    toolsUsed: ["generate-text", "analytics-helper"],
+    toolsUsed: ["generate", "analytics-helper"],
     conversationHistory: [
       { role: "user", content: "I need help with our Q1 business plan" },
       {
@@ -273,7 +251,7 @@ console.log("Version:", status.version);
 
 // All AI operations are now automatically monitored
 const provider = await createBestAIProvider();
-const result = await provider.generateText({
+const result = await provider.generate({
   prompt: "Generate business report",
 });
 // Telemetry automatically tracks: response time, token usage, cost, errors
@@ -426,7 +404,20 @@ export const POST: RequestHandler = async ({ request }) => {
   const provider = createBestAIProvider();
 
   try {
-    const result = await provider.streamText({
+    // NEW: Primary streaming method (recommended)
+    const result = await provider.stream({
+      input: { text: message },
+      timeout: "2m", // 2 minutes for streaming
+    });
+
+    // Process stream
+    for await (const chunk of result.stream) {
+      // Handle streaming content
+      console.log(chunk.content);
+    }
+
+    // LEGACY: Backward compatibility (still works)
+    const legacyResult = await provider.stream({ input: { text:
       prompt: message,
       timeout: "2m", // 2 minutes for streaming
     });
@@ -444,7 +435,7 @@ export async function POST(request: NextRequest) {
   const { prompt } = await request.json();
   const provider = createBestAIProvider();
 
-  const result = await provider.generateText({
+  const result = await provider.generate({
     prompt,
     timeout: process.env.AI_TIMEOUT || "30s", // Configurable timeout
   });

package/dist/chat/sse-handler.js

@@ -42,14 +42,15 @@ export class SSEChatHandler {
                     data: { type: "start", sessionId, messageId: userMessage.id },
                 });
                 // Generate AI response with streaming
-                const aiResponse = await this.provider.streamText({
-                    prompt: message,
+                const aiResponse = await this.provider.stream({
+                    input: { text: message },
                     temperature: options.temperature,
                     maxTokens: options.maxTokens,
                     systemPrompt: options.systemPrompt,
                 });
-                if (aiResponse?.textStream) {
-                    const reader = aiResponse.textStream.getReader();
+                if (aiResponse?.stream) {
+                    // Convert async iterable to readable stream
+                    const reader = aiResponse.stream;
                     let fullResponse = "";
                     try {
                         while (true) {

package/dist/chat/websocket-chat-handler.js

@@ -60,12 +60,12 @@ export class WebSocketChatHandler extends SSEChatHandler {
                 latencyTarget: 200,
             });
             // Generate AI response
-            const result = await this.provider.generateText({
+            const result = await this.provider.generate({
                 prompt: request.prompt,
                 temperature: request.options?.temperature,
                 maxTokens: request.options?.maxTokens,
             });
-            if (!result || !result.text) {
+            if (!result || !result.content) {
                 throw new Error("Invalid AI response");
             }
             // Send response via WebSocket
@@ -75,7 +75,7 @@ export class WebSocketChatHandler extends SSEChatHandler {
                 connectionId,
                 timestamp: Date.now(),
                 data: {
-                    text: result.text,
+                    text: result.content,
                     sessionId: request.sessionId,
                     metadata: {
                         provider: this.provider.constructor.name,
@@ -98,12 +98,12 @@ export class WebSocketChatHandler extends SSEChatHandler {
     async handleGroupChat(roomId, request) {
         try {
             // Process AI request
-            const result = await this.provider.generateText({
+            const result = await this.provider.generate({
                 prompt: request.prompt,
                 temperature: request.options?.temperature,
                 maxTokens: request.options?.maxTokens,
             });
-            if (!result || !result.text) {
+            if (!result || !result.content) {
                 throw new Error("Invalid AI response");
             }
             // Broadcast to room
@@ -113,7 +113,7 @@ export class WebSocketChatHandler extends SSEChatHandler {
                 connectionId: "system",
                 timestamp: Date.now(),
                 data: {
-                    text: result.text,
+                    text: result.content,
                     sessionId: request.sessionId,
                     userId: request.userId,
                     isGroupMessage: true,
@@ -136,11 +136,11 @@ export class WebSocketChatHandler extends SSEChatHandler {
             const channelId = randomUUID();
             const channel = this.wsServer.createStreamingChannel(connectionId, channelId);
             // Generate response
-            const result = await this.provider.generateText({
+            const result = await this.provider.generate({
                 prompt: request.prompt,
                 ...request.options,
             });
-            if (!result || !result.text) {
+            if (!result || !result.content) {
                 throw new Error("Invalid AI response");
             }
             // Send complete response
@@ -150,7 +150,7 @@ export class WebSocketChatHandler extends SSEChatHandler {
                 connectionId,
                 timestamp: Date.now(),
                 data: {
-                    text: result.text,
+                    text: result.content,
                     isStreamingComplete: true,
                     channelId,
                 },

package/dist/cli/commands/mcp.js

@@ -891,7 +891,7 @@ export function addMCPCommands(yargs) {
             type: "boolean",
             description: "Disable fallback to other sources",
         })
-            .example('$0 mcp run generate-text --params \'{"prompt": "Hello world"}\'', "Run tool with fallback")
+            .example('$0 mcp run generate --params \'{"prompt": "Hello world"}\'', "Run tool with fallback")
             .example('$0 mcp run read_file --params \'{"path": "README.md"}\' --source manual', "Prefer manual config"), async (argv) => {
             console.log(chalk.blue(`🚀 Executing tool: ${argv.tool}`));
             const spinner = ora("Initializing NeuroLink MCP...").start();

package/dist/cli/commands/ollama.js

@@ -53,7 +53,7 @@ async function pullModelHandler(argv) {
     try {
         execSync(`ollama pull ${model}`, { stdio: "inherit" });
         console.log(chalk.green(`\n✅ Successfully downloaded ${model}`));
-        console.log(chalk.blue(`\nTest it with: npx @juspay/neurolink generate-text "Hello!" --provider ollama --model ${model}`));
+        console.log(chalk.blue(`\nTest it with: npx @juspay/neurolink generate "Hello!" --provider ollama --model ${model}`));
     }
     catch (error) {
         console.error(chalk.red(`\n❌ Failed to download ${model}`));
@@ -322,9 +322,9 @@ async function setupHandler() {
     console.log(chalk.blue("Next steps:"));
     console.log("1. List models: " + chalk.gray("neurolink ollama list-models"));
     console.log("2. Generate text: " +
-        chalk.gray('neurolink generate-text "Hello!" --provider ollama'));
+        chalk.gray('neurolink generate "Hello!" --provider ollama'));
     console.log("3. Use specific model: " +
-        chalk.gray('neurolink generate-text "Hello!" --provider ollama --model codellama'));
+        chalk.gray('neurolink generate "Hello!" --provider ollama --model codellama'));
     console.log(chalk.gray("\nFor more information, see: https://docs.neurolink.ai/providers/ollama"));
 }
 export default addOllamaCommands;

package/dist/cli/factories/command-factory.d.ts

@@ -0,0 +1,14 @@
+import type { CommandModule } from "yargs";
+/**
+ * CLI Command Factory for generate commands
+ */
+export declare class CLICommandFactory {
+    /**
+     * Create the new primary 'generate' command
+     */
+    static createGenerateCommand(): CommandModule;
+    /**
+     * Execute the generate command
+     */
+    private static executeGenerate;
+}

package/dist/cli/factories/command-factory.js

@@ -0,0 +1,129 @@
+import { NeuroLink } from "../../lib/neurolink.js";
+import ora from "ora";
+import chalk from "chalk";
+/**
+ * CLI Command Factory for generate commands
+ */
+export class CLICommandFactory {
+    /**
+     * Create the new primary 'generate' command
+     */
+    static createGenerateCommand() {
+        return {
+            command: "generate <input>",
+            describe: "Generate content using AI (primary command)",
+            builder: (yargs) => {
+                return yargs
+                    .positional("input", {
+                    describe: "Text input for generation",
+                    type: "string",
+                })
+                    .option("provider", {
+                    describe: "AI provider to use",
+                    type: "string",
+                    choices: [
+                        "google-ai",
+                        "vertex",
+                        "openai",
+                        "anthropic",
+                        "bedrock",
+                        "azure",
+                        "huggingface",
+                        "ollama",
+                        "mistral",
+                    ],
+                    default: "google-ai",
+                })
+                    .option("model", {
+                    describe: "Specific model to use",
+                    type: "string",
+                })
+                    .option("temperature", {
+                    describe: "Temperature (0-1)",
+                    type: "number",
+                })
+                    .option("max-tokens", {
+                    describe: "Maximum tokens",
+                    type: "number",
+                })
+                    .option("system-prompt", {
+                    describe: "System prompt",
+                    type: "string",
+                })
+                    .option("timeout", {
+                    describe: "Timeout (e.g., 30s, 2m)",
+                    type: "string",
+                })
+                    .option("disable-tools", {
+                    describe: "Disable MCP tools",
+                    type: "boolean",
+                    default: false,
+                })
+                    .option("enable-analytics", {
+                    describe: "Enable usage analytics",
+                    type: "boolean",
+                    default: false,
+                })
+                    .option("enable-evaluation", {
+                    describe: "Enable AI quality evaluation",
+                    type: "boolean",
+                    default: false,
+                })
+                    .option("output-format", {
+                    describe: "Output format",
+                    type: "string",
+                    choices: ["text", "structured", "json"],
+                    default: "text",
+                })
+                    .option("debug", {
+                    describe: "Enable debug output",
+                    type: "boolean",
+                    default: false,
+                });
+            },
+            handler: async (argv) => await CLICommandFactory.executeGenerate(argv),
+        };
+    }
+    /**
+     * Execute the generate command
+     */
+    static async executeGenerate(argv) {
+        const spinner = ora("Generating content...").start();
+        try {
+            const sdk = new NeuroLink();
+            const result = await sdk.generate({
+                input: { text: argv.input },
+                output: { format: argv.outputFormat },
+                provider: argv.provider,
+                model: argv.model,
+                temperature: argv.temperature,
+                maxTokens: argv.maxTokens,
+                systemPrompt: argv.systemPrompt,
+                timeout: argv.timeout,
+                enableAnalytics: argv.enableAnalytics,
+                enableEvaluation: argv.enableEvaluation,
+            });
+            spinner.succeed("Content generated successfully!");
+            console.log("\n" + chalk.cyan("Generated Content:"));
+            console.log(result.content);
+            if (argv.debug) {
+                console.log("\n" + chalk.yellow("Debug Information:"));
+                console.log("Provider:", result.provider);
+                console.log("Model:", result.model);
+                if (result.analytics) {
+                    console.log("Analytics:", JSON.stringify(result.analytics, null, 2));
+                }
+                if (result.evaluation) {
+                    console.log("Evaluation:", JSON.stringify(result.evaluation, null, 2));
+                }
+            }
+            // Exit successfully
+            process.exit(0);
+        }
+        catch (error) {
+            spinner.fail("Generation failed");
+            console.error(chalk.red("Error:"), error);
+            process.exit(1);
+        }
+    }
+}