adaptive-memory-multi-model-router 2.2.6 → 2.2.7

package/dist/sdk.js

@@ -5,127 +5,118 @@
  * Clean wrapper class providing a better DX than raw exports.
  *
  * Usage:
- *   import { A3MRouter } from 'adaptive-memory-multi-model-router/sdk';
- *
+ *   const { A3MRouter } = require('adaptive-memory-multi-model-router/sdk');
  *   const router = new A3MRouter();
- *
- *   // Route a query (no execution, just model selection)
  *   const decision = router.route("What is 2+2?");
  *   console.log(decision.model, decision.tier, decision.cost);
- *
- *   // Start the OpenAI-compatible proxy server
- *   const proxyURL = await router.serve(8787);
- *
- *   // Use with any OpenAI SDK
- *   import OpenAI from 'openai';
- *   const client = new OpenAI({ baseURL: router.proxyURL });
- *   const response = await client.chat.completions.create({
- *     model: 'auto',
- *     messages: [{ role: 'user', content: 'Hello' }]
- *   });
  */
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.A3MRouter = void 0;
-exports.createSDK = createSDK;
-const advancedRouter_1 = require("./routing/advancedRouter");
-const proxyServer_1 = require("./server/proxyServer");
+
+const advancedRouter = require("./routing/advancedRouter");
+const proxyServer = require("./server/proxyServer");
+
 // ============================================================
 // A3MRouter SDK Class
 // ============================================================
+
 class A3MRouter {
-    config;
-    _proxyURL = null;
-    constructor(config = {}) {
-        this.config = config;
-    }
-    /**
-     * Route a query — returns model selection without executing it.
-     *
-     * @param query - The user prompt to route
-     * @returns Routing decision with model, tier, cost, complexity
-     */
-    route(query) {
-        const features = (0, advancedRouter_1.extractQueryFeatures)(query);
-        const result = (0, advancedRouter_1.routeQuery)(query, this.config.providers);
-        return {
-            model: result.primary_model || 'unknown',
-            tier: this.classifyTier(features.complexity),
-            cost: result.estimated_cost || 0,
-            complexity: features.complexity,
-            reasoning: result.reasoning || '',
-            fallbackModels: result.fallback_models || [],
-            isFree: (result.estimated_cost || 0) === 0,
-            isExpert: features.complexity >= 0.65,
-        };
-    }
-    /**
-     * Route multiple queries in batch.
-     *
-     * @param queries - Array of user prompts
-     * @returns Array of routing decisions
-     */
-    routeBatch(queries) {
-        (0, advancedRouter_1.routeBatch)(queries); // warm the internal cache
-        return queries.map((q) => this.route(q));
-    }
-    /**
-     * Get model recommendation for a task description.
-     *
-     * @param task - Task description (e.g. "code generation", "summarization")
-     * @returns Routing decision
-     */
-    recommend(task) {
-        (0, advancedRouter_1.recommendForTask)(task);
-        return this.route(task);
-    }
-    /**
-     * Start the OpenAI-compatible proxy server.
-     *
-     * @param port - Port to listen on (default: 8787)
-     * @returns The proxy base URL (e.g. "http://localhost:8787/v1")
-     */
-    async serve(port = 8787) {
-        (0, proxyServer_1.createProxyServer)(port);
-        this._proxyURL = `http://localhost:${port}/v1`;
-        return this._proxyURL;
-    }
-    /**
-     * Get the proxy URL. Available after serve() is called,
-     * otherwise returns the default.
-     */
-    get proxyURL() {
-        return this._proxyURL || 'http://localhost:8787/v1';
-    }
-    /**
-     * Extract features from a query for debugging or analysis.
-     *
-     * @param query - The user prompt to analyze
-     * @returns Detailed feature breakdown
-     */
-    analyze(query) {
-        return (0, advancedRouter_1.extractQueryFeatures)(query);
-    }
-    /**
-     * Classify a complexity score into a named tier.
-     */
-    classifyTier(complexity) {
-        if (complexity < 0.20)
-            return 'free';
-        if (complexity < 0.45)
-            return 'cheap';
-        if (complexity < 0.65)
-            return 'mid';
-        return 'premium';
-    }
+  constructor(config = {}) {
+    this.config = config;
+    this._proxyURL = null;
+  }
+
+  /**
+   * Route a query — returns model selection without executing it.
+   *
+   * @param {string} query - The user prompt to route
+   * @returns {object} Routing decision with model, tier, cost, complexity
+   */
+  route(query) {
+    const features = advancedRouter.extractQueryFeatures(query);
+    const result = advancedRouter.routeQuery(query, this.config.providers);
+
+    return {
+      model: result.primary_model || 'unknown',
+      tier: this.classifyTier(features.complexity),
+      cost: result.estimated_cost || 0,
+      complexity: features.complexity,
+      reasoning: result.reasoning || '',
+      fallbackModels: result.fallback_models || [],
+      isFree: (result.estimated_cost || 0) === 0,
+      isExpert: features.complexity >= 0.65,
+    };
+  }
+
+  /**
+   * Route multiple queries in batch.
+   *
+   * @param {string[]} queries - Array of user prompts
+   * @returns {object[]} Array of routing decisions
+   */
+  routeBatch(queries) {
+    advancedRouter.routeBatch(queries); // warm the internal cache
+    return queries.map((q) => this.route(q));
+  }
+
+  /**
+   * Get model recommendation for a task description.
+   *
+   * @param {string} task - Task description
+   * @returns {object} Routing decision
+   */
+  recommend(task) {
+    advancedRouter.recommendForTask(task);
+    return this.route(task);
+  }
+
+  /**
+   * Start the OpenAI-compatible proxy server.
+   *
+   * @param {number} port - Port to listen on (default: 8787)
+   * @returns {Promise<string>} The proxy base URL
+   */
+  async serve(port = 8787) {
+    proxyServer.createProxyServer(port);
+    this._proxyURL = `http://localhost:${port}/v1`;
+    return this._proxyURL;
+  }
+
+  /**
+   * Get the proxy URL. Available after serve() is called.
+   */
+  get proxyURL() {
+    return this._proxyURL || 'http://localhost:8787/v1';
+  }
+
+  /**
+   * Extract features from a query for debugging or analysis.
+   *
+   * @param {string} query - The user prompt to analyze
+   * @returns {object} Detailed feature breakdown
+   */
+  analyze(query) {
+    return advancedRouter.extractQueryFeatures(query);
+  }
+
+  /**
+   * Classify a complexity score into a named tier.
+   */
+  classifyTier(complexity) {
+    if (complexity < 0.20) return 'free';
+    if (complexity < 0.45) return 'cheap';
+    if (complexity < 0.65) return 'mid';
+    return 'premium';
+  }
 }
-exports.A3MRouter = A3MRouter;
+
 /**
  * Convenience: create an A3MRouter instance.
  *
- * @param config - Optional configuration
- * @returns Configured A3MRouter instance
+ * @param {object} config - Optional configuration
+ * @returns {A3MRouter} Configured instance
  */
 function createSDK(config) {
-    return new A3MRouter(config);
+  return new A3MRouter(config);
 }
-//# sourceMappingURL=sdk.js.map
+
+module.exports = { A3MRouter, createSDK };
+module.exports.default = A3MRouter;

package/dist/security/guardrails.d.ts

@@ -74,4 +74,3 @@ export declare class GuardrailEngine {
 }
 export declare function createGuardrails(config?: Partial<GuardrailConfig>): GuardrailEngine;
 export {};
-//# sourceMappingURL=guardrails.d.ts.map

package/dist/server/dashboard.d.ts

@@ -56,4 +56,3 @@ export declare function registerProvider(id: string, name: string): void;
  */
 export declare function handleDashboardRequest(req: http.IncomingMessage, res: http.ServerResponse): boolean;
 export declare function getDashboardHTML(): string;
-//# sourceMappingURL=dashboard.d.ts.map

package/dist/server/modelMapper.d.ts

@@ -41,4 +41,3 @@ export declare function listAvailableModels(): Array<{
     created: number;
     owned_by: string;
 }>;
-//# sourceMappingURL=modelMapper.d.ts.map

package/dist/server/proxyServer.d.ts

@@ -39,4 +39,3 @@ declare const costTracker: any;
 export declare function createProxyServer(port?: number): http.Server;
 export { CostTracker, costTracker, requestLogs };
 export default createProxyServer;
-//# sourceMappingURL=proxyServer.d.ts.map

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "adaptive-memory-multi-model-router",
-  "version": "2.2.6",
+  "version": "2.2.7",
   "shortName": "A3M Router",
   "displayName": "A3M Router - Adaptive Memory Multi-Model Router",
   "description": "LLM router & AI gateway with 99.5% routing accuracy — supports 47 providers including DeepSeek, Kimi (Moonshot), Qwen, Zhipu GLM, Yi, Baichuan, MiniMax, StepFun. Zero ML, 19.5KB. Multi-signal routing, semantic cache, guardrails, cost analytics. MIT. TypeScript SDK + Python SDK + OpenAI proxy.",
@@ -53,142 +53,6 @@
     }
   },
   "keywords": [
-    "adaptive-router",
-    "agent",
-    "agent-framework",
-    "ai-agent-tools",
-    "ai-assistant",
-    "ai-discoverability",
-    "ai-routing",
-    "airtable",
-    "amplitude",
-    "api-gateway",
-    "asana",
-    "automation",
-    "autonomous-agents",
-    "aws-bedrock",
-    "batch-processing",
-    "bitbucket",
-    "circuit-breaker",
-    "claude-code",
-    "cli",
-    "cloud",
-    "code-generation",
-    "cohere",
-    "content-filtering",
-    "copilot",
-    "cost-analytics",
-    "datadog",
-    "deepinfra",
-    "developer-experience",
-    "developer-tools",
-    "devops",
-    "discord",
-    "dropbox",
-    "dx",
-    "edge-computing",
-    "embedding",
-    "enterprise",
-    "fallback",
-    "fine-tuning",
-    "fireworks",
-    "gemini",
-    "generative-engine-optimization",
-    "geo",
-    "github",
-    "gitlab",
-    "gmail",
-    "google",
-    "google-calendar",
-    "gpt-4",
-    "graphql",
-    "high-availability",
-    "hubspot",
-    "huggingface",
-    "inference",
-    "input-validation",
-    "intent-mapping",
-    "intercom",
-    "javascript",
-    "jira",
-    "latency-optimization",
-    "linear",
-    "llamaindex",
-    "llm-intent",
-    "llm-tools",
-    "llmlingua",
-    "load-balancing",
-    "logging",
-    "machine-learning",
-    "mailchimp",
-    "mcp",
-    "medusa",
-    "memory-tree",
-    "middleware",
-    "mixpanel",
-    "monitoring",
-    "multi-model",
-    "natural-language-processing",
-    "netlify",
-    "nodejs",
-    "notion",
-    "npm",
-    "observability",
-    "open-source",
-    "orchestration",
-    "parallel-execution",
-    "performance",
-    "perplexity",
-    "pii-detection",
-    "pinecone",
-    "posthog",
-    "prefix-caching",
-    "production",
-    "prompt-engineering",
-    "prompt-injection",
-    "provider-registry",
-    "proxy",
-    "proxy-server",
-    "python",
-    "radix-attention",
-    "rag",
-    "rate-limiting",
-    "real-time",
-    "rest-api",
-    "retrieval-augmented-generation",
-    "retry",
-    "route-quality",
-    "routellm",
-    "router",
-    "s3",
-    "salesforce",
-    "sanitization",
-    "scalability",
-    "sdk",
-    "security",
-    "segment",
-    "sendgrid",
-    "sentry",
-    "serverless",
-    "shopify",
-    "slack",
-    "speculative-decoding",
-    "streaming",
-    "stripe",
-    "telegram",
-    "testing",
-    "together-ai",
-    "token-compression",
-    "tools",
-    "tracing",
-    "transformer",
-    "trello",
-    "typescript",
-    "vector-database",
-    "vercel",
-    "websocket",
-    "xai",
-    "zendesk",
     "llm-proxy",
     "claude",
     "ai",
@@ -271,191 +135,7 @@
     "semantic-cache",
     "langchain",
     "ai-guardrails",
-    "chatbot",
-    "a3m",
-    "a3m-router",
-    "adaptive",
-    "memory-based",
-    "multi-model-router",
-    "memory-based-router",
-    "treequest",
-    "parallel-ai",
-    "agent-orchestration",
-    "multi-agent",
-    "parallel",
-    "cost-tracking",
-    "cache",
-    "caching",
-    "exponential-backoff",
-    "mcts",
-    "monte-carlo-tree-search",
-    "workflow-optimization",
-    "hierarchical-planning",
-    "halo",
-    "episodic-memory",
-    "semantic-memory",
-    "agent-memory",
-    "python-bindings",
-    "pypi",
-    "autogen",
-    "crewai",
-    "transformers",
-    "agent-codegen",
-    "ai-coding",
-    "zai",
-    "llama",
-    "ai-agents",
-    "memory-based-llm-router",
-    "multi-llm-router",
-    "llm-memory-router",
-    "adaptive-llm-router",
-    "intelligent-router",
-    "intelligent-llm-router",
-    "learning-router",
-    "contextual-router",
-    "context-aware-router",
-    "task-aware-router",
-    "memory-augmented",
-    "memory-augmented-llm",
-    "episodic-memory-router",
-    "semantic-memory-router",
-    "task-memory",
-    "cross-context-memory",
-    "context-compression",
-    "ison-format",
-    "message-truncation",
-    "context-management",
-    "local-llm",
-    "lmstudio",
-    "local-model",
-    "privacy-llm",
-    "priority-queue",
-    "token-counting",
-    "cost-estimation",
-    "cost-prediction",
-    "intelligent-failover",
-    "kv-cache",
-    "pagedattention",
-    "kv-cache-quantization",
-    "streamingllm",
-    "multimodel-orchestration",
-    "multi-agent-debate",
-    "self-consistency",
-    "tensor-parallelism",
-    "continuous-batching",
-    "arxiv",
-    "research-backed",
-    "icml",
-    "neurips",
-    "iclr",
-    "pi-extension",
-    "pi",
-    "pi-package",
-    "pi-coding-agent",
-    "pi-agent",
-    "agent-discoverable",
-    "ai-native",
-    "01-ai",
-    "01ai",
-    "128k上下文",
-    "ai-gateway-cn",
-    "ai路由",
-    "aliyun",
-    "baichuan-ai",
-    "baichuan2",
-    "baichuan2-flash",
-    "baiducloud",
-    "chinese-ai-proxy",
-    "chinese-api-gateway",
-    "chinese-chatgpt",
-    "chinese-language-model",
-    "chinese-llm-proxy",
-    "chinese-models",
-    "chinese-nlp",
-    "chinesellm",
-    "chinesellm-routing",
-    "deepseek-ai",
-    "deepseek-api",
-    "deepseek-chat",
-    "deepseek-coder",
-    "deepseek-reasoner",
-    "embedding-model",
-    "glm-4",
-    "glm-4-air",
-    "glm-4-flash",
-    "glm-4-long",
-    "glm-4-plus",
-    "huawei-cloud",
-    "langchain-cn",
-    "lingyi",
-    "lingyi-wanwu",
-    "llamaindex-cn",
-    "llm-gateway-cn",
-    "long-context-model",
-    "minimax-ai",
-    "minimax-api",
-    "minimax-chat",
-    "minimax-turbo",
-    "moonshot-ai",
-    "moonshot-v1",
-    "moonshot-v1-128k",
-    "moonshot-v1-32k",
-    "moonshot-v1-8k",
-    "multimodal",
-    "qianwen",
-    "qwen-long",
-    "qwen-max",
-    "qwen-plus",
-    "qwen-turbo",
-    "qwen2",
-    "qwen3",
-    "step-1",
-    "step-1v",
-    "step-2",
-    "tencentcloud",
-    "tongji",
-    "tongyi",
-    "tongyi-qianwen",
-    "vision-model",
-    "volcengine",
-    "wu-yuan",
-    "wuyuan",
-    "yi-ai",
-    "yi-large",
-    "yi-lightning",
-    "yi-medium",
-    "zai-glm",
-    "zai-glm-4",
-    "zhipu-ai",
-    "中国ai",
-    "中国大模型",
-    "中文chatgpt",
-    "中文embedding",
-    "中文langchain",
-    "中文llamaindex",
-    "中文nlp",
-    "中文seo",
-    "中文多模态",
-    "中文大模型",
-    "中文搜索引擎优化",
-    "中文模型",
-    "华为云",
-    "向量化",
-    "国产ai",
-    "国产大模型",
-    "多模型路由",
-    "多模态",
-    "大模型路由",
-    "字节ai",
-    "智能路由",
-    "火山引擎",
-    "百度ai",
-    "百度云",
-    "腾讯ai",
-    "腾讯云",
-    "长上下文",
-    "阿里ai",
-    "阿里云"
+    "chatbot"
   ],
   "author": "Das-rebel <subho@example.com>",
   "license": "MIT",
@@ -471,8 +151,7 @@
     "test": "node test.js && node test/provider-test.js",
     "test:providers": "node test/provider-test.js",
     "benchmark": "node test/benchmark.js",
-    "benchmark:verbose": "node test/benchmark.js --verbose",
-    "build": "tsc"
+    "benchmark:verbose": "node test/benchmark.js --verbose"
   },
   "engines": {
     "node": ">=18.0.0"
@@ -490,7 +169,6 @@
   },
   "devDependencies": {
     "@types/node": "^25.8.0",
-    "tsx": "^4.22.3",
     "typescript": "^6.0.3"
   }
 }