@juspay/neurolink 9.27.0 → 9.28.1

package/CHANGELOG.md

@@ -1,3 +1,15 @@
+## [9.28.1](https://github.com/juspay/neurolink/compare/v9.28.0...v9.28.1) (2026-03-18)
+
+### Bug Fixes
+
+- **(docs):** comprehensive documentation audit, code example fixes, and model updates ([f294ff2](https://github.com/juspay/neurolink/commit/f294ff2eef71a09e271c5dc536a9d00d97cfd5e5))
+
+## [9.28.0](https://github.com/juspay/neurolink/compare/v9.27.0...v9.28.0) (2026-03-18)
+
+### Features
+
+- **(mcp):** add MCP enhancement modules with routing, caching, batching, and wire into core SDK ([ee8a0b8](https://github.com/juspay/neurolink/commit/ee8a0b8e5e33dcafe44d33944bf9ff99ef59701a))
+
 ## [9.27.0](https://github.com/juspay/neurolink/compare/v9.26.2...v9.27.0) (2026-03-18)
 
 ### Features

package/README.md

@@ -9,11 +9,14 @@ generated (LLM providers: the neurons) to where they are needed (connectors: the
 ```typescript
 import { NeuroLink } from "@juspay/neurolink";
 
-const pipe = new NeuroLink({ defaultProvider: "anthropic" });
+const pipe = new NeuroLink();
 
 // Everything is a stream
-for await (const token of pipe.stream({ prompt: "Hello" })) {
-  process.stdout.write(token);
+const result = await pipe.stream({ input: { text: "Hello" } });
+for await (const chunk of result.stream) {
+  if ("content" in chunk) {
+    process.stdout.write(chunk.content);
+  }
 }
 ```
 
@@ -37,15 +40,20 @@ Extracted from production systems at Juspay and battle-tested at enterprise scal
 
 ## What's New (Q1 2026)
 
-| Feature                             | Version | Description                                                                                                                                                   | Guide                                                         |
-| ----------------------------------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------- |
-| **External TracerProvider Support** | v8.43.0 | Integrate NeuroLink with existing OpenTelemetry instrumentation. Prevents duplicate registration conflicts.                                                   | [Observability Guide](docs/features/observability.md)         |
-| **Server Adapters**                 | v8.43.0 | Multi-framework HTTP server with Hono, Express, Fastify, Koa support. Full CLI for server management with foreground/background modes.                        | [Server Adapters Guide](docs/guides/server-adapters/index.md) |
-| **Title Generation Events**         | v8.38.0 | Emit `conversation:titleGenerated` event when conversation title is generated. Supports custom title prompts via `NEUROLINK_TITLE_PROMPT`.                    | [Conversation Memory Guide](docs/conversation-memory.md)      |
-| **Video Generation with Veo**       | v8.32.0 | Video generation using Veo 3.1 (`veo-3.1`). Realistic video generation with many parameter options                                                            | [Video Generation Guide](docs/features/video-generation.md)   |
-| **Image Generation with Gemini**    | v8.31.0 | Native image generation using Gemini 2.0 Flash Experimental (`imagen-3.0-generate-002`). High-quality image synthesis directly from Google AI.                | [Image Generation Guide](docs/image-generation-streaming.md)  |
-| **RAG with generate()/stream()**    | v9.2.0  | Pass `rag: { files }` to generate/stream for automatic document chunking, embedding, and AI-powered search. 10 chunking strategies, hybrid search, reranking. | [RAG Guide](docs/features/rag.md)                             |
-| **HTTP/Streamable HTTP Transport**  | v8.29.0 | Connect to remote MCP servers via HTTP with authentication headers, automatic retry with exponential backoff, and configurable rate limiting.                 | [HTTP Transport Guide](docs/mcp-http-transport.md)            |
+| Feature                             | Version | Description                                                                                                                                                   | Guide                                                                 |
+| ----------------------------------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------- |
+| **MCP Enhancements**                | v9.16.0 | Advanced MCP features: tool routing, result caching, request batching, annotations, elicitation, custom server base, multi-server management                  | [MCP Enhancements Guide](docs/features/mcp-enhancements.md)           |
+| **Memory**                          | v9.12.0 | Per-user condensed memory that persists across conversations. LLM-powered condensation with S3, Redis, or SQLite backends.                                    | [Memory Guide](docs/features/memory.md)                               |
+| **Context Window Management**       | v9.2.0  | 4-stage compaction pipeline with auto-detection, budget gate at 80% usage, per-provider token estimation                                                      | [Context Compaction Guide](docs/features/context-compaction.md)       |
+| **Tool Execution Control**          | v9.3.0  | `prepareStep` and `toolChoice` support for per-step tool enforcement in multi-step agentic loops. API-level control over tool calls.                          | [API Reference](docs/api/type-aliases/GenerateOptions.md#preparestep) |
+| **File Processor System**           | v9.1.0  | 17+ file type processors with ProcessorRegistry, security sanitization, SVG text injection                                                                    | [File Processors Guide](docs/features/file-processors.md)             |
+| **RAG with generate()/stream()**    | v9.2.0  | Pass `rag: { files }` to generate/stream for automatic document chunking, embedding, and AI-powered search. 10 chunking strategies, hybrid search, reranking. | [RAG Guide](docs/features/rag.md)                                     |
+| **External TracerProvider Support** | v8.43.0 | Integrate NeuroLink with existing OpenTelemetry instrumentation. Prevents duplicate registration conflicts.                                                   | [Observability Guide](docs/features/observability.md)                 |
+| **Server Adapters**                 | v8.43.0 | Multi-framework HTTP server with Hono, Express, Fastify, Koa support. Full CLI for server management with foreground/background modes.                        | [Server Adapters Guide](docs/guides/server-adapters/index.md)         |
+| **Title Generation Events**         | v8.38.0 | Emit `conversation:titleGenerated` event when conversation title is generated. Supports custom title prompts via `NEUROLINK_TITLE_PROMPT`.                    | [Conversation Memory Guide](docs/conversation-memory.md)              |
+| **Video Generation with Veo**       | v8.32.0 | Video generation using Veo 3.1 (`veo-3.1`). Realistic video generation with many parameter options                                                            | [Video Generation Guide](docs/features/video-generation.md)           |
+| **Image Generation with Gemini**    | v8.31.0 | Native image generation using Gemini 2.0 Flash Experimental (`imagen-3.0-generate-002`). High-quality image synthesis directly from Google AI.                | [Image Generation Guide](docs/image-generation-streaming.md)          |
+| **HTTP/Streamable HTTP Transport**  | v8.29.0 | Connect to remote MCP servers via HTTP with authentication headers, automatic retry with exponential backoff, and configurable rate limiting.                 | [HTTP Transport Guide](docs/mcp-http-transport.md)                    |
 
 - **Memory** – Per-user condensed memory that persists across all conversations. Automatically retrieves and stores memory on each `generate()`/`stream()` call. Supports S3, Redis, and SQLite storage with LLM-powered condensation. → [Memory Guide](docs/features/memory.md)
 - **External TracerProvider Support** – Integrate NeuroLink with applications that already have OpenTelemetry instrumentation. Supports auto-detection and manual configuration. → [Observability Guide](docs/features/observability.md)
@@ -69,15 +77,17 @@ Extracted from production systems at Juspay and battle-tested at enterprise scal
 - **Human-in-the-loop workflows** – Pause generation for user approval/input before tool execution. → [HITL Guide](docs/features/hitl.md)
 - **Guardrails middleware** – Block PII, profanity, and unsafe content with built-in filtering. → [Guardrails Guide](docs/features/guardrails.md)
 - **Context summarization** – Automatic conversation compression for long-running sessions. → [Summarization Guide](docs/context-summarization.md)
+- **MCP Enhancements** – 14 production-grade modules: tool routing (6 strategies), result caching (LRU/FIFO/LFU), request batching, tool annotations with auto-inference, middleware chain, elicitation protocol, multi-server management, and more. → [MCP Enhancements Guide](docs/features/mcp-enhancements.md)
 - **Redis conversation export** – Export full session history as JSON for analytics and debugging. → [History Guide](docs/features/conversation-history.md)
 
 ```typescript
 // Image Generation with Gemini (v8.31.0)
-const image = await neurolink.generateImage({
-  prompt: "A futuristic cityscape",
+const image = await neurolink.generate({
+  input: { text: "A futuristic cityscape" },
   provider: "google-ai",
   model: "imagen-3.0-generate-002",
 });
+console.log(image.imageOutput?.base64); // Base64-encoded image
 
 // HTTP Transport for Remote MCP (v8.29.0)
 await neurolink.addExternalMCPServer("remote-tools", {
@@ -233,6 +243,50 @@ const result = await neurolink.generate({
 
 ---
 
+### 🔌 MCP Enhancements
+
+**Production-grade MCP capabilities** for managing tool calls at scale across multi-server environments:
+
+| Module                        | Purpose                                                    |
+| ----------------------------- | ---------------------------------------------------------- |
+| **Tool Router**               | Intelligent routing across servers with 6 strategies       |
+| **Tool Cache**                | Result caching with LRU, FIFO, and LFU eviction            |
+| **Request Batcher**           | Automatic batching of tool calls for throughput            |
+| **Tool Annotations**          | Safety metadata and behavior hints for MCP tools           |
+| **Tool Converter**            | Bidirectional conversion between NeuroLink and MCP formats |
+| **Elicitation Protocol**      | Interactive user input during tool execution (HITL)        |
+| **Multi-Server Manager**      | Load balancing and failover across server groups           |
+| **MCP Server Base**           | Abstract base class for building custom MCP servers        |
+| **Enhanced Tool Discovery**   | Advanced search and filtering across servers               |
+| **Agent & Workflow Exposure** | Expose agents and workflows as MCP tools                   |
+| **Server Capabilities**       | Resource and prompt management per MCP spec                |
+| **Registry Client**           | Discover and connect to MCP servers from registries        |
+| **Tool Integration**          | End-to-end tool lifecycle with middleware chain            |
+| **Elicitation Manager**       | Manages elicitation flows with validation and timeouts     |
+
+```typescript
+import { ToolRouter, ToolCache, RequestBatcher } from "@juspay/neurolink";
+
+// Route tool calls across multiple MCP servers
+const router = new ToolRouter({
+  strategy: "capability-based",
+  servers: [
+    { name: "github", url: "https://mcp-github.example.com" },
+    { name: "db", url: "https://mcp-postgres.example.com" },
+  ],
+});
+
+// Cache repeated tool results (LRU, FIFO, or LFU)
+const cache = new ToolCache({ strategy: "lru", maxSize: 500, ttl: 60_000 });
+
+// Batch concurrent tool calls for throughput
+const batcher = new RequestBatcher({ maxBatchSize: 10, maxWaitMs: 50 });
+```
+
+**[📖 MCP Enhancements Guide](docs/features/mcp-enhancements.md)** - Full reference for all 14 modules
+
+---
+
 ### 💻 Developer Experience Features
 
 **SDK-First Design** with TypeScript, IntelliSense, and type safety:
@@ -348,27 +402,25 @@ import { NeuroLink } from "@juspay/neurolink";
 const neurolink = new NeuroLink({
   conversationMemory: {
     enabled: true,
-    store: "redis", // Automatically uses REDIS_URL
-    ttl: 86400, // 24-hour session expiration
+    enableSummarization: true,
   },
 });
 
-// Or explicit configuration
+// Or explicit Redis configuration
 const neurolinkExplicit = new NeuroLink({
   conversationMemory: {
     enabled: true,
-    store: "redis",
-    redis: {
+    redisConfig: {
       host: "redis.example.com",
       port: 6379,
       password: process.env.REDIS_PASSWORD,
-      tls: true, // Enable for production
+      ttl: 86400, // 24-hour session expiration (seconds)
     },
   },
 });
 
-// Export conversation for analytics
-const history = await neurolink.exportConversation({ format: "json" });
+// Retrieve conversation history for analytics
+const history = await neurolink.getConversationHistory("session-id");
 await saveToDataWarehouse(history);
 ```
 
@@ -555,7 +607,6 @@ import { NeuroLink } from "@juspay/neurolink";
 const neurolink = new NeuroLink({
   conversationMemory: {
     enabled: true,
-    store: "redis",
   },
   enableOrchestration: true,
 });
@@ -583,7 +634,7 @@ console.log(result.evaluation?.overallScore);
 
 // RAG: Ask questions about your documents
 const answer = await neurolink.generate({
-  prompt: "What are the main architectural decisions?",
+  input: { text: "What are the main architectural decisions?" },
   rag: {
     files: ["./docs/architecture.md", "./docs/decisions.md"],
     strategy: "markdown",
@@ -607,7 +658,9 @@ const result = await neurolink.generate({
   },
   provider: "vertex",
   model: "gemini-3-flash-preview",
-  thinkingLevel: "medium", // Options: "minimal", "low", "medium", "high"
+  thinkingConfig: {
+    thinkingLevel: "medium", // Options: "minimal", "low", "medium", "high"
+  },
 });
 
 console.log(result.content);

package/dist/adapters/providerImageAdapter.js

@@ -62,7 +62,12 @@ function normalizeVisionProvider(provider) {
  */
 const VISION_CAPABILITIES = {
     openai: [
-        // GPT-5.2 family (released Dec 11, 2025) - Latest flagship models
+        // GPT-5.4 family (released Mar 2026) - Latest flagship models
+        "gpt-5.4",
+        "gpt-5.4-mini",
+        "gpt-5.4-nano",
+        "gpt-5.4-pro",
+        // GPT-5.2 family (released Dec 11, 2025)
         "gpt-5.2",
         "gpt-5.2-chat-latest",
         "gpt-5.2-pro",
@@ -118,6 +123,9 @@ const VISION_CAPABILITIES = {
         "gemini-pro-vision",
     ],
     anthropic: [
+        // Claude 4.6 Series (February 2026)
+        "claude-opus-4-6",
+        "claude-sonnet-4-6",
         // Claude 4.5 Series (September-November 2025)
         "claude-sonnet-4-5",
         "claude-sonnet-4-5-20250929",

package/dist/cli/commands/config.d.ts

@@ -247,8 +247,8 @@ declare const ConfigSchema: z.ZodObject<{
         enableEvaluationByDefault: z.ZodDefault<z.ZodBoolean>;
     }, "strip", z.ZodTypeAny, {
         temperature: number;
-        outputFormat: "text" | "json" | "yaml";
         enableLogging: boolean;
+        outputFormat: "text" | "json" | "yaml";
         enableCaching: boolean;
         cacheStrategy: "memory" | "redis" | "file";
         enableAnalyticsByDefault: boolean;
@@ -258,8 +258,8 @@ declare const ConfigSchema: z.ZodObject<{
     }, {
         temperature?: number | undefined;
         maxTokens?: number | undefined;
-        outputFormat?: "text" | "json" | "yaml" | undefined;
         enableLogging?: boolean | undefined;
+        outputFormat?: "text" | "json" | "yaml" | undefined;
         enableCaching?: boolean | undefined;
         cacheStrategy?: "memory" | "redis" | "file" | undefined;
         defaultEvaluationDomain?: string | undefined;
@@ -509,8 +509,8 @@ declare const ConfigSchema: z.ZodObject<{
     profiles: Record<string, any>;
     preferences: {
         temperature: number;
-        outputFormat: "text" | "json" | "yaml";
         enableLogging: boolean;
+        outputFormat: "text" | "json" | "yaml";
         enableCaching: boolean;
         cacheStrategy: "memory" | "redis" | "file";
         enableAnalyticsByDefault: boolean;
@@ -608,8 +608,8 @@ declare const ConfigSchema: z.ZodObject<{
     preferences?: {
         temperature?: number | undefined;
         maxTokens?: number | undefined;
-        outputFormat?: "text" | "json" | "yaml" | undefined;
         enableLogging?: boolean | undefined;
+        outputFormat?: "text" | "json" | "yaml" | undefined;
         enableCaching?: boolean | undefined;
         cacheStrategy?: "memory" | "redis" | "file" | undefined;
         defaultEvaluationDomain?: string | undefined;

package/dist/cli/commands/mcp.d.ts

@@ -2,6 +2,13 @@
  * MCP CLI Commands for NeuroLink
  * Implements comprehensive MCP server management commands
  * Part of Phase 4.2 - MCP CLI Commands
+ *
+ * Enhanced in Phase 8.39.0 with:
+ * - neurolink mcp servers - List all MCP servers
+ * - neurolink mcp tools - List all available tools
+ * - neurolink mcp discover - Enhanced tool discovery
+ * - neurolink mcp create-server - Scaffold a new MCP server
+ * - neurolink mcp annotate - Add/update tool annotations
  */
 import type { CommandModule } from "yargs";
 /**
@@ -76,4 +83,84 @@ export declare class MCPCommandFactory {
      * Discover servers from VS Code configuration
      */
     private static discoverFromVSCode;
+    /**
+     * Build options for servers command
+     */
+    private static buildServersOptions;
+    /**
+     * Build options for tools command
+     */
+    private static buildToolsOptions;
+    /**
+     * Build options for discover tools command
+     */
+    private static buildDiscoverToolsOptions;
+    /**
+     * Build options for create-server command
+     */
+    private static buildCreateServerOptions;
+    /**
+     * Execute servers command
+     */
+    private static executeServers;
+    /**
+     * Execute tools command
+     */
+    private static executeTools;
+    /**
+     * Execute discover tools command
+     */
+    private static executeDiscoverTools;
+    /**
+     * Execute create-server command
+     */
+    private static executeCreateServer;
+    /**
+     * Generate TypeScript MCP server
+     */
+    private static generateTypeScriptServer;
+    /**
+     * Generate Python MCP server
+     */
+    private static generatePythonServer;
+    /**
+     * Generate basic JavaScript MCP server
+     */
+    private static generateBasicServer;
+    /**
+     * Infer tool category from name and description
+     */
+    private static inferToolCategory;
+    /**
+     * Create the registry subcommand
+     */
+    static createRegistryCommand(): CommandModule;
+    /**
+     * Execute registry search
+     */
+    private static executeRegistrySearch;
+    /**
+     * Execute registry list
+     */
+    private static executeRegistryList;
+    /**
+     * Execute registry info
+     */
+    private static executeRegistryInfo;
+    /**
+     * Execute registry categories
+     */
+    private static executeRegistryCategories;
+    /**
+     * Execute registry popular
+     */
+    private static executeRegistryPopular;
+    /**
+     * Build options for annotate command
+     */
+    private static buildAnnotateOptions;
+    /**
+     * Execute annotate command
+     */
+    private static executeAnnotate;
 }