@semiont/inference 0.3.4 → 0.3.5

package/dist/index.d.ts

@@ -1,4 +1,4 @@
-import { Logger, InferenceServiceConfig } from '@semiont/core';
+import { Logger } from '@semiont/core';
 
 interface InferenceResponse {
     text: string;
@@ -32,11 +32,6 @@ interface InferenceClientConfig {
     baseURL?: string;
 }
 declare function createInferenceClient(config: InferenceClientConfig, logger?: Logger): InferenceClient;
-declare function getInferenceClient(inferenceConfig: InferenceServiceConfig, logger?: Logger): Promise<InferenceClient>;
-/**
- * Get the configured model name
- */
-declare function getInferenceModel(inferenceConfig: InferenceServiceConfig): string;
 
 declare class AnthropicInferenceClient implements InferenceClient {
     private client;
@@ -72,4 +67,4 @@ declare class MockInferenceClient implements InferenceClient {
     setResponses(responses: string[], stopReasons?: string[]): void;
 }
 
-export { AnthropicInferenceClient, type InferenceClient, type InferenceClientConfig, type InferenceClientType, type InferenceResponse, MockInferenceClient, OllamaInferenceClient, createInferenceClient, getInferenceClient, getInferenceModel };
+export { AnthropicInferenceClient, type InferenceClient, type InferenceClientConfig, type InferenceClientType, type InferenceResponse, MockInferenceClient, OllamaInferenceClient, createInferenceClient };

package/dist/index.js

@@ -156,46 +156,6 @@ function createInferenceClient(config, logger) {
       throw new Error(`Unsupported inference client type: ${config.type}`);
   }
 }
-function evaluateEnvVar(value) {
-  if (!value) return void 0;
-  return value.replace(/\$\{([^}]+)\}/g, (match, varName) => {
-    const envValue = process.env[varName];
-    if (!envValue) {
-      throw new Error(`Environment variable ${varName} is not set. Referenced in configuration as ${match}`);
-    }
-    return envValue;
-  });
-}
-async function getInferenceClient(inferenceConfig, logger) {
-  if (!inferenceConfig.model) {
-    throw new Error("services.inference.model is required in environment config");
-  }
-  const clientConfig = {
-    type: inferenceConfig.type,
-    apiKey: evaluateEnvVar(inferenceConfig.apiKey),
-    model: inferenceConfig.model,
-    endpoint: inferenceConfig.endpoint,
-    baseURL: inferenceConfig.baseURL
-  };
-  logger?.info("Loading inference client configuration", {
-    type: clientConfig.type,
-    model: clientConfig.model,
-    endpoint: clientConfig.endpoint,
-    hasApiKey: !!clientConfig.apiKey
-  });
-  const client = createInferenceClient(clientConfig, logger);
-  logger?.info("Inference client initialized", {
-    type: inferenceConfig.type,
-    model: inferenceConfig.model
-  });
-  return client;
-}
-function getInferenceModel(inferenceConfig) {
-  if (!inferenceConfig.model) {
-    throw new Error("Inference model not configured! Set it in your environment configuration.");
-  }
-  return inferenceConfig.model;
-}
 
 // src/implementations/mock.ts
 var MockInferenceClient = class {
@@ -235,8 +195,6 @@ export {
   AnthropicInferenceClient,
   MockInferenceClient,
   OllamaInferenceClient,
-  createInferenceClient,
-  getInferenceClient,
-  getInferenceModel
+  createInferenceClient
 };
 //# sourceMappingURL=index.js.map

package/dist/index.js.map

@@ -1 +1 @@
-{"version":3,"sources":["../src/implementations/anthropic.ts","../src/implementations/ollama.ts","../src/factory.ts","../src/implementations/mock.ts"],"sourcesContent":["// Anthropic Claude implementation of InferenceClient interface\n\nimport Anthropic from '@anthropic-ai/sdk';\nimport type { Logger } from '@semiont/core';\nimport { InferenceClient, InferenceResponse } from '../interface.js';\n\nexport class AnthropicInferenceClient implements InferenceClient {\n  private client: Anthropic;\n  private model: string;\n  private logger?: Logger;\n\n  constructor(apiKey: string, model: string, baseURL?: string, logger?: Logger) {\n    this.client = new Anthropic({\n      apiKey,\n      baseURL: baseURL || 'https://api.anthropic.com',\n    });\n    this.model = model;\n    this.logger = logger;\n  }\n\n  async generateText(prompt: string, maxTokens: number, temperature: number): Promise<string> {\n    const response = await this.generateTextWithMetadata(prompt, maxTokens, temperature);\n    return response.text;\n  }\n\n  async generateTextWithMetadata(prompt: string, maxTokens: number, temperature: number): Promise<InferenceResponse> {\n    this.logger?.debug('Generating text with inference client', {\n      model: this.model,\n      promptLength: prompt.length,\n      maxTokens,\n      temperature\n    });\n\n    const response = await this.client.messages.create({\n      model: this.model,\n      max_tokens: maxTokens,\n      temperature,\n      messages: [\n        {\n          role: 'user',\n          content: prompt\n        }\n      ]\n    });\n\n    this.logger?.debug('Inference response received', {\n      model: this.model,\n      contentBlocks: response.content.length,\n      stopReason: response.stop_reason\n    });\n\n    const textContent = response.content.find(c => c.type === 'text');\n\n    if (!textContent || textContent.type !== 'text') {\n      this.logger?.error('No text content in inference response', {\n        model: this.model,\n        contentTypes: response.content.map(c => c.type)\n      });\n      throw new Error('No text content in inference response');\n    }\n\n    this.logger?.info('Text generation completed', {\n      model: this.model,\n      textLength: textContent.text.length,\n      stopReason: response.stop_reason\n    });\n\n    return {\n      text: textContent.text,\n      stopReason: response.stop_reason || 'unknown'\n    };\n  }\n}\n","// Ollama implementation of InferenceClient interface\n// Uses native Ollama HTTP API (no SDK dependency)\n\nimport type { Logger } from '@semiont/core';\nimport { InferenceClient, InferenceResponse } from '../interface.js';\n\ninterface OllamaGenerateResponse {\n  response: string;\n  done: boolean;\n  done_reason?: string;\n}\n\nexport class OllamaInferenceClient implements InferenceClient {\n  private baseURL: string;\n  private model: string;\n  private logger?: Logger;\n\n  constructor(model: string, baseURL?: string, logger?: Logger) {\n    this.baseURL = (baseURL || 'http://localhost:11434').replace(/\\/+$/, '');\n    this.model = model;\n    this.logger = logger;\n  }\n\n  async generateText(prompt: string, maxTokens: number, temperature: number): Promise<string> {\n    const response = await this.generateTextWithMetadata(prompt, maxTokens, temperature);\n    return response.text;\n  }\n\n  async generateTextWithMetadata(prompt: string, maxTokens: number, temperature: number): Promise<InferenceResponse> {\n    this.logger?.debug('Generating text with Ollama', {\n      model: this.model,\n      promptLength: prompt.length,\n      maxTokens,\n      temperature\n    });\n\n    const url = `${this.baseURL}/api/generate`;\n\n    const res = await fetch(url, {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify({\n        model: this.model,\n        prompt,\n        stream: false,\n        options: {\n          num_predict: maxTokens,\n          temperature,\n        },\n      }),\n    });\n\n    if (!res.ok) {\n      const body = await res.text();\n      this.logger?.error('Ollama API error', {\n        model: this.model,\n        status: res.status,\n        body,\n      });\n      throw new Error(`Ollama API error (${res.status}): ${body}`);\n    }\n\n    const data = await res.json() as OllamaGenerateResponse;\n\n    if (!data.response) {\n      this.logger?.error('Empty response from Ollama', { model: this.model });\n      throw new Error('Empty response from Ollama');\n    }\n\n    const stopReason = mapStopReason(data.done_reason);\n\n    this.logger?.info('Text generation completed', {\n      model: this.model,\n      textLength: data.response.length,\n      stopReason,\n    });\n\n    return {\n      text: data.response,\n      stopReason,\n    };\n  }\n}\n\nfunction mapStopReason(doneReason: string | undefined): string {\n  switch (doneReason) {\n    case 'stop': return 'end_turn';\n    case 'length': return 'max_tokens';\n    default: return doneReason || 'unknown';\n  }\n}\n","// Factory for creating inference client instances based on configuration\n\nimport type { InferenceServiceConfig, Logger } from '@semiont/core';\nimport { InferenceClient } from './interface.js';\nimport { AnthropicInferenceClient } from './implementations/anthropic.js';\nimport { OllamaInferenceClient } from './implementations/ollama.js';\n\nexport type InferenceClientType = 'anthropic' | 'ollama';\n\nexport interface InferenceClientConfig {\n  type: InferenceClientType;\n  apiKey?: string;\n  model: string;\n  endpoint?: string;\n  baseURL?: string;\n}\n\nexport function createInferenceClient(config: InferenceClientConfig, logger?: Logger): InferenceClient {\n  switch (config.type) {\n    case 'anthropic': {\n      if (!config.apiKey || config.apiKey.trim() === '') {\n        throw new Error('apiKey is required for Anthropic inference client');\n      }\n      return new AnthropicInferenceClient(\n        config.apiKey,\n        config.model,\n        config.endpoint || config.baseURL,\n        logger\n      );\n    }\n\n    case 'ollama': {\n      return new OllamaInferenceClient(\n        config.model,\n        config.endpoint || config.baseURL,\n        logger\n      );\n    }\n\n    default:\n      throw new Error(`Unsupported inference client type: ${config.type}`);\n  }\n}\n\n// Helper function to evaluate environment variable placeholders\nfunction evaluateEnvVar(value: string | undefined): string | undefined {\n  if (!value) return undefined;\n\n  // Replace ${VAR_NAME} with actual environment variable value\n  return value.replace(/\\$\\{([^}]+)\\}/g, (match, varName) => {\n    const envValue = process.env[varName];\n    if (!envValue) {\n      throw new Error(`Environment variable ${varName} is not set. Referenced in configuration as ${match}`);\n    }\n    return envValue;\n  });\n}\n\nexport async function getInferenceClient(inferenceConfig: InferenceServiceConfig, logger?: Logger): Promise<InferenceClient> {\n  if (!inferenceConfig.model) {\n    throw new Error('services.inference.model is required in environment config');\n  }\n\n  const clientConfig: InferenceClientConfig = {\n    type: inferenceConfig.type as InferenceClientType,\n    apiKey: evaluateEnvVar(inferenceConfig.apiKey),\n    model: inferenceConfig.model,\n    endpoint: inferenceConfig.endpoint,\n    baseURL: inferenceConfig.baseURL,\n  };\n\n  logger?.info('Loading inference client configuration', {\n    type: clientConfig.type,\n    model: clientConfig.model,\n    endpoint: clientConfig.endpoint,\n    hasApiKey: !!clientConfig.apiKey\n  });\n\n  const client = createInferenceClient(clientConfig, logger);\n\n  logger?.info('Inference client initialized', {\n    type: inferenceConfig.type,\n    model: inferenceConfig.model\n  });\n  return client;\n}\n\n/**\n * Get the configured model name\n */\nexport function getInferenceModel(inferenceConfig: InferenceServiceConfig): string {\n  if (!inferenceConfig.model) {\n    throw new Error('Inference model not configured! Set it in your environment configuration.');\n  }\n  return inferenceConfig.model;\n}\n\n","// Mock implementation of InferenceClient for testing\n\nimport { InferenceClient, InferenceResponse } from '../interface.js';\n\nexport class MockInferenceClient implements InferenceClient {\n  private responses: string[] = [];\n  private responseIndex: number = 0;\n  private stopReasons: string[] = [];\n  public calls: Array<{ prompt: string; maxTokens: number; temperature: number }> = [];\n\n  constructor(responses: string[] = ['Mock response'], stopReasons?: string[]) {\n    this.responses = responses;\n    this.stopReasons = stopReasons || responses.map(() => 'end_turn');\n  }\n\n  async generateText(prompt: string, maxTokens: number, temperature: number): Promise<string> {\n    const response = await this.generateTextWithMetadata(prompt, maxTokens, temperature);\n    return response.text;\n  }\n\n  async generateTextWithMetadata(prompt: string, maxTokens: number, temperature: number): Promise<InferenceResponse> {\n    this.calls.push({ prompt, maxTokens, temperature });\n\n    const text = this.responses[this.responseIndex];\n    const stopReason = this.stopReasons[this.responseIndex] || 'end_turn';\n\n    if (this.responseIndex < this.responses.length - 1) {\n      this.responseIndex++;\n    }\n\n    return { text, stopReason };\n  }\n\n  // Test helper methods\n  reset(): void {\n    this.calls = [];\n    this.responseIndex = 0;\n  }\n\n  setResponses(responses: string[], stopReasons?: string[]): void {\n    this.responses = responses;\n    this.stopReasons = stopReasons || responses.map(() => 'end_turn');\n    this.responseIndex = 0;\n  }\n}\n"],"mappings":";AAEA,OAAO,eAAe;AAIf,IAAM,2BAAN,MAA0D;AAAA,EACvD;AAAA,EACA;AAAA,EACA;AAAA,EAER,YAAY,QAAgB,OAAe,SAAkB,QAAiB;AAC5E,SAAK,SAAS,IAAI,UAAU;AAAA,MAC1B;AAAA,MACA,SAAS,WAAW;AAAA,IACtB,CAAC;AACD,SAAK,QAAQ;AACb,SAAK,SAAS;AAAA,EAChB;AAAA,EAEA,MAAM,aAAa,QAAgB,WAAmB,aAAsC;AAC1F,UAAM,WAAW,MAAM,KAAK,yBAAyB,QAAQ,WAAW,WAAW;AACnF,WAAO,SAAS;AAAA,EAClB;AAAA,EAEA,MAAM,yBAAyB,QAAgB,WAAmB,aAAiD;AACjH,SAAK,QAAQ,MAAM,yCAAyC;AAAA,MAC1D,OAAO,KAAK;AAAA,MACZ,cAAc,OAAO;AAAA,MACrB;AAAA,MACA;AAAA,IACF,CAAC;AAED,UAAM,WAAW,MAAM,KAAK,OAAO,SAAS,OAAO;AAAA,MACjD,OAAO,KAAK;AAAA,MACZ,YAAY;AAAA,MACZ;AAAA,MACA,UAAU;AAAA,QACR;AAAA,UACE,MAAM;AAAA,UACN,SAAS;AAAA,QACX;AAAA,MACF;AAAA,IACF,CAAC;AAED,SAAK,QAAQ,MAAM,+BAA+B;AAAA,MAChD,OAAO,KAAK;AAAA,MACZ,eAAe,SAAS,QAAQ;AAAA,MAChC,YAAY,SAAS;AAAA,IACvB,CAAC;AAED,UAAM,cAAc,SAAS,QAAQ,KAAK,OAAK,EAAE,SAAS,MAAM;AAEhE,QAAI,CAAC,eAAe,YAAY,SAAS,QAAQ;AAC/C,WAAK,QAAQ,MAAM,yCAAyC;AAAA,QAC1D,OAAO,KAAK;AAAA,QACZ,cAAc,SAAS,QAAQ,IAAI,OAAK,EAAE,IAAI;AAAA,MAChD,CAAC;AACD,YAAM,IAAI,MAAM,uCAAuC;AAAA,IACzD;AAEA,SAAK,QAAQ,KAAK,6BAA6B;AAAA,MAC7C,OAAO,KAAK;AAAA,MACZ,YAAY,YAAY,KAAK;AAAA,MAC7B,YAAY,SAAS;AAAA,IACvB,CAAC;AAED,WAAO;AAAA,MACL,MAAM,YAAY;AAAA,MAClB,YAAY,SAAS,eAAe;AAAA,IACtC;AAAA,EACF;AACF;;;AC5DO,IAAM,wBAAN,MAAuD;AAAA,EACpD;AAAA,EACA;AAAA,EACA;AAAA,EAER,YAAY,OAAe,SAAkB,QAAiB;AAC5D,SAAK,WAAW,WAAW,0BAA0B,QAAQ,QAAQ,EAAE;AACvE,SAAK,QAAQ;AACb,SAAK,SAAS;AAAA,EAChB;AAAA,EAEA,MAAM,aAAa,QAAgB,WAAmB,aAAsC;AAC1F,UAAM,WAAW,MAAM,KAAK,yBAAyB,QAAQ,WAAW,WAAW;AACnF,WAAO,SAAS;AAAA,EAClB;AAAA,EAEA,MAAM,yBAAyB,QAAgB,WAAmB,aAAiD;AACjH,SAAK,QAAQ,MAAM,+BAA+B;AAAA,MAChD,OAAO,KAAK;AAAA,MACZ,cAAc,OAAO;AAAA,MACrB;AAAA,MACA;AAAA,IACF,CAAC;AAED,UAAM,MAAM,GAAG,KAAK,OAAO;AAE3B,UAAM,MAAM,MAAM,MAAM,KAAK;AAAA,MAC3B,QAAQ;AAAA,MACR,SAAS,EAAE,gBAAgB,mBAAmB;AAAA,MAC9C,MAAM,KAAK,UAAU;AAAA,QACnB,OAAO,KAAK;AAAA,QACZ;AAAA,QACA,QAAQ;AAAA,QACR,SAAS;AAAA,UACP,aAAa;AAAA,UACb;AAAA,QACF;AAAA,MACF,CAAC;AAAA,IACH,CAAC;AAED,QAAI,CAAC,IAAI,IAAI;AACX,YAAM,OAAO,MAAM,IAAI,KAAK;AAC5B,WAAK,QAAQ,MAAM,oBAAoB;AAAA,QACrC,OAAO,KAAK;AAAA,QACZ,QAAQ,IAAI;AAAA,QACZ;AAAA,MACF,CAAC;AACD,YAAM,IAAI,MAAM,qBAAqB,IAAI,MAAM,MAAM,IAAI,EAAE;AAAA,IAC7D;AAEA,UAAM,OAAO,MAAM,IAAI,KAAK;AAE5B,QAAI,CAAC,KAAK,UAAU;AAClB,WAAK,QAAQ,MAAM,8BAA8B,EAAE,OAAO,KAAK,MAAM,CAAC;AACtE,YAAM,IAAI,MAAM,4BAA4B;AAAA,IAC9C;AAEA,UAAM,aAAa,cAAc,KAAK,WAAW;AAEjD,SAAK,QAAQ,KAAK,6BAA6B;AAAA,MAC7C,OAAO,KAAK;AAAA,MACZ,YAAY,KAAK,SAAS;AAAA,MAC1B;AAAA,IACF,CAAC;AAED,WAAO;AAAA,MACL,MAAM,KAAK;AAAA,MACX;AAAA,IACF;AAAA,EACF;AACF;AAEA,SAAS,cAAc,YAAwC;AAC7D,UAAQ,YAAY;AAAA,IAClB,KAAK;AAAQ,aAAO;AAAA,IACpB,KAAK;AAAU,aAAO;AAAA,IACtB;AAAS,aAAO,cAAc;AAAA,EAChC;AACF;;;ACzEO,SAAS,sBAAsB,QAA+B,QAAkC;AACrG,UAAQ,OAAO,MAAM;AAAA,IACnB,KAAK,aAAa;AAChB,UAAI,CAAC,OAAO,UAAU,OAAO,OAAO,KAAK,MAAM,IAAI;AACjD,cAAM,IAAI,MAAM,mDAAmD;AAAA,MACrE;AACA,aAAO,IAAI;AAAA,QACT,OAAO;AAAA,QACP,OAAO;AAAA,QACP,OAAO,YAAY,OAAO;AAAA,QAC1B;AAAA,MACF;AAAA,IACF;AAAA,IAEA,KAAK,UAAU;AACb,aAAO,IAAI;AAAA,QACT,OAAO;AAAA,QACP,OAAO,YAAY,OAAO;AAAA,QAC1B;AAAA,MACF;AAAA,IACF;AAAA,IAEA;AACE,YAAM,IAAI,MAAM,sCAAsC,OAAO,IAAI,EAAE;AAAA,EACvE;AACF;AAGA,SAAS,eAAe,OAA+C;AACrE,MAAI,CAAC,MAAO,QAAO;AAGnB,SAAO,MAAM,QAAQ,kBAAkB,CAAC,OAAO,YAAY;AACzD,UAAM,WAAW,QAAQ,IAAI,OAAO;AACpC,QAAI,CAAC,UAAU;AACb,YAAM,IAAI,MAAM,wBAAwB,OAAO,+CAA+C,KAAK,EAAE;AAAA,IACvG;AACA,WAAO;AAAA,EACT,CAAC;AACH;AAEA,eAAsB,mBAAmB,iBAAyC,QAA2C;AAC3H,MAAI,CAAC,gBAAgB,OAAO;AAC1B,UAAM,IAAI,MAAM,4DAA4D;AAAA,EAC9E;AAEA,QAAM,eAAsC;AAAA,IAC1C,MAAM,gBAAgB;AAAA,IACtB,QAAQ,eAAe,gBAAgB,MAAM;AAAA,IAC7C,OAAO,gBAAgB;AAAA,IACvB,UAAU,gBAAgB;AAAA,IAC1B,SAAS,gBAAgB;AAAA,EAC3B;AAEA,UAAQ,KAAK,0CAA0C;AAAA,IACrD,MAAM,aAAa;AAAA,IACnB,OAAO,aAAa;AAAA,IACpB,UAAU,aAAa;AAAA,IACvB,WAAW,CAAC,CAAC,aAAa;AAAA,EAC5B,CAAC;AAED,QAAM,SAAS,sBAAsB,cAAc,MAAM;AAEzD,UAAQ,KAAK,gCAAgC;AAAA,IAC3C,MAAM,gBAAgB;AAAA,IACtB,OAAO,gBAAgB;AAAA,EACzB,CAAC;AACD,SAAO;AACT;AAKO,SAAS,kBAAkB,iBAAiD;AACjF,MAAI,CAAC,gBAAgB,OAAO;AAC1B,UAAM,IAAI,MAAM,2EAA2E;AAAA,EAC7F;AACA,SAAO,gBAAgB;AACzB;;;AC3FO,IAAM,sBAAN,MAAqD;AAAA,EAClD,YAAsB,CAAC;AAAA,EACvB,gBAAwB;AAAA,EACxB,cAAwB,CAAC;AAAA,EAC1B,QAA2E,CAAC;AAAA,EAEnF,YAAY,YAAsB,CAAC,eAAe,GAAG,aAAwB;AAC3E,SAAK,YAAY;AACjB,SAAK,cAAc,eAAe,UAAU,IAAI,MAAM,UAAU;AAAA,EAClE;AAAA,EAEA,MAAM,aAAa,QAAgB,WAAmB,aAAsC;AAC1F,UAAM,WAAW,MAAM,KAAK,yBAAyB,QAAQ,WAAW,WAAW;AACnF,WAAO,SAAS;AAAA,EAClB;AAAA,EAEA,MAAM,yBAAyB,QAAgB,WAAmB,aAAiD;AACjH,SAAK,MAAM,KAAK,EAAE,QAAQ,WAAW,YAAY,CAAC;AAElD,UAAM,OAAO,KAAK,UAAU,KAAK,aAAa;AAC9C,UAAM,aAAa,KAAK,YAAY,KAAK,aAAa,KAAK;AAE3D,QAAI,KAAK,gBAAgB,KAAK,UAAU,SAAS,GAAG;AAClD,WAAK;AAAA,IACP;AAEA,WAAO,EAAE,MAAM,WAAW;AAAA,EAC5B;AAAA;AAAA,EAGA,QAAc;AACZ,SAAK,QAAQ,CAAC;AACd,SAAK,gBAAgB;AAAA,EACvB;AAAA,EAEA,aAAa,WAAqB,aAA8B;AAC9D,SAAK,YAAY;AACjB,SAAK,cAAc,eAAe,UAAU,IAAI,MAAM,UAAU;AAChE,SAAK,gBAAgB;AAAA,EACvB;AACF;","names":[]}
+{"version":3,"sources":["../src/implementations/anthropic.ts","../src/implementations/ollama.ts","../src/factory.ts","../src/implementations/mock.ts"],"sourcesContent":["// Anthropic Claude implementation of InferenceClient interface\n\nimport Anthropic from '@anthropic-ai/sdk';\nimport type { Logger } from '@semiont/core';\nimport { InferenceClient, InferenceResponse } from '../interface.js';\n\nexport class AnthropicInferenceClient implements InferenceClient {\n  private client: Anthropic;\n  private model: string;\n  private logger?: Logger;\n\n  constructor(apiKey: string, model: string, baseURL?: string, logger?: Logger) {\n    this.client = new Anthropic({\n      apiKey,\n      baseURL: baseURL || 'https://api.anthropic.com',\n    });\n    this.model = model;\n    this.logger = logger;\n  }\n\n  async generateText(prompt: string, maxTokens: number, temperature: number): Promise<string> {\n    const response = await this.generateTextWithMetadata(prompt, maxTokens, temperature);\n    return response.text;\n  }\n\n  async generateTextWithMetadata(prompt: string, maxTokens: number, temperature: number): Promise<InferenceResponse> {\n    this.logger?.debug('Generating text with inference client', {\n      model: this.model,\n      promptLength: prompt.length,\n      maxTokens,\n      temperature\n    });\n\n    const response = await this.client.messages.create({\n      model: this.model,\n      max_tokens: maxTokens,\n      temperature,\n      messages: [\n        {\n          role: 'user',\n          content: prompt\n        }\n      ]\n    });\n\n    this.logger?.debug('Inference response received', {\n      model: this.model,\n      contentBlocks: response.content.length,\n      stopReason: response.stop_reason\n    });\n\n    const textContent = response.content.find(c => c.type === 'text');\n\n    if (!textContent || textContent.type !== 'text') {\n      this.logger?.error('No text content in inference response', {\n        model: this.model,\n        contentTypes: response.content.map(c => c.type)\n      });\n      throw new Error('No text content in inference response');\n    }\n\n    this.logger?.info('Text generation completed', {\n      model: this.model,\n      textLength: textContent.text.length,\n      stopReason: response.stop_reason\n    });\n\n    return {\n      text: textContent.text,\n      stopReason: response.stop_reason || 'unknown'\n    };\n  }\n}\n","// Ollama implementation of InferenceClient interface\n// Uses native Ollama HTTP API (no SDK dependency)\n\nimport type { Logger } from '@semiont/core';\nimport { InferenceClient, InferenceResponse } from '../interface.js';\n\ninterface OllamaGenerateResponse {\n  response: string;\n  done: boolean;\n  done_reason?: string;\n}\n\nexport class OllamaInferenceClient implements InferenceClient {\n  private baseURL: string;\n  private model: string;\n  private logger?: Logger;\n\n  constructor(model: string, baseURL?: string, logger?: Logger) {\n    this.baseURL = (baseURL || 'http://localhost:11434').replace(/\\/+$/, '');\n    this.model = model;\n    this.logger = logger;\n  }\n\n  async generateText(prompt: string, maxTokens: number, temperature: number): Promise<string> {\n    const response = await this.generateTextWithMetadata(prompt, maxTokens, temperature);\n    return response.text;\n  }\n\n  async generateTextWithMetadata(prompt: string, maxTokens: number, temperature: number): Promise<InferenceResponse> {\n    this.logger?.debug('Generating text with Ollama', {\n      model: this.model,\n      promptLength: prompt.length,\n      maxTokens,\n      temperature\n    });\n\n    const url = `${this.baseURL}/api/generate`;\n\n    const res = await fetch(url, {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify({\n        model: this.model,\n        prompt,\n        stream: false,\n        options: {\n          num_predict: maxTokens,\n          temperature,\n        },\n      }),\n    });\n\n    if (!res.ok) {\n      const body = await res.text();\n      this.logger?.error('Ollama API error', {\n        model: this.model,\n        status: res.status,\n        body,\n      });\n      throw new Error(`Ollama API error (${res.status}): ${body}`);\n    }\n\n    const data = await res.json() as OllamaGenerateResponse;\n\n    if (!data.response) {\n      this.logger?.error('Empty response from Ollama', { model: this.model });\n      throw new Error('Empty response from Ollama');\n    }\n\n    const stopReason = mapStopReason(data.done_reason);\n\n    this.logger?.info('Text generation completed', {\n      model: this.model,\n      textLength: data.response.length,\n      stopReason,\n    });\n\n    return {\n      text: data.response,\n      stopReason,\n    };\n  }\n}\n\nfunction mapStopReason(doneReason: string | undefined): string {\n  switch (doneReason) {\n    case 'stop': return 'end_turn';\n    case 'length': return 'max_tokens';\n    default: return doneReason || 'unknown';\n  }\n}\n","// Factory for creating inference client instances based on configuration\n\nimport type { Logger } from '@semiont/core';\nimport { InferenceClient } from './interface.js';\nimport { AnthropicInferenceClient } from './implementations/anthropic.js';\nimport { OllamaInferenceClient } from './implementations/ollama.js';\n\nexport type InferenceClientType = 'anthropic' | 'ollama';\n\nexport interface InferenceClientConfig {\n  type: InferenceClientType;\n  apiKey?: string;\n  model: string;\n  endpoint?: string;\n  baseURL?: string;\n}\n\nexport function createInferenceClient(config: InferenceClientConfig, logger?: Logger): InferenceClient {\n  switch (config.type) {\n    case 'anthropic': {\n      if (!config.apiKey || config.apiKey.trim() === '') {\n        throw new Error('apiKey is required for Anthropic inference client');\n      }\n      return new AnthropicInferenceClient(\n        config.apiKey,\n        config.model,\n        config.endpoint || config.baseURL,\n        logger\n      );\n    }\n\n    case 'ollama': {\n      return new OllamaInferenceClient(\n        config.model,\n        config.endpoint || config.baseURL,\n        logger\n      );\n    }\n\n    default:\n      throw new Error(`Unsupported inference client type: ${config.type}`);\n  }\n}\n","// Mock implementation of InferenceClient for testing\n\nimport { InferenceClient, InferenceResponse } from '../interface.js';\n\nexport class MockInferenceClient implements InferenceClient {\n  private responses: string[] = [];\n  private responseIndex: number = 0;\n  private stopReasons: string[] = [];\n  public calls: Array<{ prompt: string; maxTokens: number; temperature: number }> = [];\n\n  constructor(responses: string[] = ['Mock response'], stopReasons?: string[]) {\n    this.responses = responses;\n    this.stopReasons = stopReasons || responses.map(() => 'end_turn');\n  }\n\n  async generateText(prompt: string, maxTokens: number, temperature: number): Promise<string> {\n    const response = await this.generateTextWithMetadata(prompt, maxTokens, temperature);\n    return response.text;\n  }\n\n  async generateTextWithMetadata(prompt: string, maxTokens: number, temperature: number): Promise<InferenceResponse> {\n    this.calls.push({ prompt, maxTokens, temperature });\n\n    const text = this.responses[this.responseIndex];\n    const stopReason = this.stopReasons[this.responseIndex] || 'end_turn';\n\n    if (this.responseIndex < this.responses.length - 1) {\n      this.responseIndex++;\n    }\n\n    return { text, stopReason };\n  }\n\n  // Test helper methods\n  reset(): void {\n    this.calls = [];\n    this.responseIndex = 0;\n  }\n\n  setResponses(responses: string[], stopReasons?: string[]): void {\n    this.responses = responses;\n    this.stopReasons = stopReasons || responses.map(() => 'end_turn');\n    this.responseIndex = 0;\n  }\n}\n"],"mappings":";AAEA,OAAO,eAAe;AAIf,IAAM,2BAAN,MAA0D;AAAA,EACvD;AAAA,EACA;AAAA,EACA;AAAA,EAER,YAAY,QAAgB,OAAe,SAAkB,QAAiB;AAC5E,SAAK,SAAS,IAAI,UAAU;AAAA,MAC1B;AAAA,MACA,SAAS,WAAW;AAAA,IACtB,CAAC;AACD,SAAK,QAAQ;AACb,SAAK,SAAS;AAAA,EAChB;AAAA,EAEA,MAAM,aAAa,QAAgB,WAAmB,aAAsC;AAC1F,UAAM,WAAW,MAAM,KAAK,yBAAyB,QAAQ,WAAW,WAAW;AACnF,WAAO,SAAS;AAAA,EAClB;AAAA,EAEA,MAAM,yBAAyB,QAAgB,WAAmB,aAAiD;AACjH,SAAK,QAAQ,MAAM,yCAAyC;AAAA,MAC1D,OAAO,KAAK;AAAA,MACZ,cAAc,OAAO;AAAA,MACrB;AAAA,MACA;AAAA,IACF,CAAC;AAED,UAAM,WAAW,MAAM,KAAK,OAAO,SAAS,OAAO;AAAA,MACjD,OAAO,KAAK;AAAA,MACZ,YAAY;AAAA,MACZ;AAAA,MACA,UAAU;AAAA,QACR;AAAA,UACE,MAAM;AAAA,UACN,SAAS;AAAA,QACX;AAAA,MACF;AAAA,IACF,CAAC;AAED,SAAK,QAAQ,MAAM,+BAA+B;AAAA,MAChD,OAAO,KAAK;AAAA,MACZ,eAAe,SAAS,QAAQ;AAAA,MAChC,YAAY,SAAS;AAAA,IACvB,CAAC;AAED,UAAM,cAAc,SAAS,QAAQ,KAAK,OAAK,EAAE,SAAS,MAAM;AAEhE,QAAI,CAAC,eAAe,YAAY,SAAS,QAAQ;AAC/C,WAAK,QAAQ,MAAM,yCAAyC;AAAA,QAC1D,OAAO,KAAK;AAAA,QACZ,cAAc,SAAS,QAAQ,IAAI,OAAK,EAAE,IAAI;AAAA,MAChD,CAAC;AACD,YAAM,IAAI,MAAM,uCAAuC;AAAA,IACzD;AAEA,SAAK,QAAQ,KAAK,6BAA6B;AAAA,MAC7C,OAAO,KAAK;AAAA,MACZ,YAAY,YAAY,KAAK;AAAA,MAC7B,YAAY,SAAS;AAAA,IACvB,CAAC;AAED,WAAO;AAAA,MACL,MAAM,YAAY;AAAA,MAClB,YAAY,SAAS,eAAe;AAAA,IACtC;AAAA,EACF;AACF;;;AC5DO,IAAM,wBAAN,MAAuD;AAAA,EACpD;AAAA,EACA;AAAA,EACA;AAAA,EAER,YAAY,OAAe,SAAkB,QAAiB;AAC5D,SAAK,WAAW,WAAW,0BAA0B,QAAQ,QAAQ,EAAE;AACvE,SAAK,QAAQ;AACb,SAAK,SAAS;AAAA,EAChB;AAAA,EAEA,MAAM,aAAa,QAAgB,WAAmB,aAAsC;AAC1F,UAAM,WAAW,MAAM,KAAK,yBAAyB,QAAQ,WAAW,WAAW;AACnF,WAAO,SAAS;AAAA,EAClB;AAAA,EAEA,MAAM,yBAAyB,QAAgB,WAAmB,aAAiD;AACjH,SAAK,QAAQ,MAAM,+BAA+B;AAAA,MAChD,OAAO,KAAK;AAAA,MACZ,cAAc,OAAO;AAAA,MACrB;AAAA,MACA;AAAA,IACF,CAAC;AAED,UAAM,MAAM,GAAG,KAAK,OAAO;AAE3B,UAAM,MAAM,MAAM,MAAM,KAAK;AAAA,MAC3B,QAAQ;AAAA,MACR,SAAS,EAAE,gBAAgB,mBAAmB;AAAA,MAC9C,MAAM,KAAK,UAAU;AAAA,QACnB,OAAO,KAAK;AAAA,QACZ;AAAA,QACA,QAAQ;AAAA,QACR,SAAS;AAAA,UACP,aAAa;AAAA,UACb;AAAA,QACF;AAAA,MACF,CAAC;AAAA,IACH,CAAC;AAED,QAAI,CAAC,IAAI,IAAI;AACX,YAAM,OAAO,MAAM,IAAI,KAAK;AAC5B,WAAK,QAAQ,MAAM,oBAAoB;AAAA,QACrC,OAAO,KAAK;AAAA,QACZ,QAAQ,IAAI;AAAA,QACZ;AAAA,MACF,CAAC;AACD,YAAM,IAAI,MAAM,qBAAqB,IAAI,MAAM,MAAM,IAAI,EAAE;AAAA,IAC7D;AAEA,UAAM,OAAO,MAAM,IAAI,KAAK;AAE5B,QAAI,CAAC,KAAK,UAAU;AAClB,WAAK,QAAQ,MAAM,8BAA8B,EAAE,OAAO,KAAK,MAAM,CAAC;AACtE,YAAM,IAAI,MAAM,4BAA4B;AAAA,IAC9C;AAEA,UAAM,aAAa,cAAc,KAAK,WAAW;AAEjD,SAAK,QAAQ,KAAK,6BAA6B;AAAA,MAC7C,OAAO,KAAK;AAAA,MACZ,YAAY,KAAK,SAAS;AAAA,MAC1B;AAAA,IACF,CAAC;AAED,WAAO;AAAA,MACL,MAAM,KAAK;AAAA,MACX;AAAA,IACF;AAAA,EACF;AACF;AAEA,SAAS,cAAc,YAAwC;AAC7D,UAAQ,YAAY;AAAA,IAClB,KAAK;AAAQ,aAAO;AAAA,IACpB,KAAK;AAAU,aAAO;AAAA,IACtB;AAAS,aAAO,cAAc;AAAA,EAChC;AACF;;;ACzEO,SAAS,sBAAsB,QAA+B,QAAkC;AACrG,UAAQ,OAAO,MAAM;AAAA,IACnB,KAAK,aAAa;AAChB,UAAI,CAAC,OAAO,UAAU,OAAO,OAAO,KAAK,MAAM,IAAI;AACjD,cAAM,IAAI,MAAM,mDAAmD;AAAA,MACrE;AACA,aAAO,IAAI;AAAA,QACT,OAAO;AAAA,QACP,OAAO;AAAA,QACP,OAAO,YAAY,OAAO;AAAA,QAC1B;AAAA,MACF;AAAA,IACF;AAAA,IAEA,KAAK,UAAU;AACb,aAAO,IAAI;AAAA,QACT,OAAO;AAAA,QACP,OAAO,YAAY,OAAO;AAAA,QAC1B;AAAA,MACF;AAAA,IACF;AAAA,IAEA;AACE,YAAM,IAAI,MAAM,sCAAsC,OAAO,IAAI,EAAE;AAAA,EACvE;AACF;;;ACtCO,IAAM,sBAAN,MAAqD;AAAA,EAClD,YAAsB,CAAC;AAAA,EACvB,gBAAwB;AAAA,EACxB,cAAwB,CAAC;AAAA,EAC1B,QAA2E,CAAC;AAAA,EAEnF,YAAY,YAAsB,CAAC,eAAe,GAAG,aAAwB;AAC3E,SAAK,YAAY;AACjB,SAAK,cAAc,eAAe,UAAU,IAAI,MAAM,UAAU;AAAA,EAClE;AAAA,EAEA,MAAM,aAAa,QAAgB,WAAmB,aAAsC;AAC1F,UAAM,WAAW,MAAM,KAAK,yBAAyB,QAAQ,WAAW,WAAW;AACnF,WAAO,SAAS;AAAA,EAClB;AAAA,EAEA,MAAM,yBAAyB,QAAgB,WAAmB,aAAiD;AACjH,SAAK,MAAM,KAAK,EAAE,QAAQ,WAAW,YAAY,CAAC;AAElD,UAAM,OAAO,KAAK,UAAU,KAAK,aAAa;AAC9C,UAAM,aAAa,KAAK,YAAY,KAAK,aAAa,KAAK;AAE3D,QAAI,KAAK,gBAAgB,KAAK,UAAU,SAAS,GAAG;AAClD,WAAK;AAAA,IACP;AAEA,WAAO,EAAE,MAAM,WAAW;AAAA,EAC5B;AAAA;AAAA,EAGA,QAAc;AACZ,SAAK,QAAQ,CAAC;AACd,SAAK,gBAAgB;AAAA,EACvB;AAAA,EAEA,aAAa,WAAqB,aAA8B;AAC9D,SAAK,YAAY;AACjB,SAAK,cAAc,eAAe,UAAU,IAAI,MAAM,UAAU;AAChE,SAAK,gBAAgB;AAAA,EACvB;AACF;","names":[]}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@semiont/inference",
-  "version": "0.3.4",
+  "version": "0.3.5",
   "type": "module",
   "description": "AI inference capabilities for entity extraction, text generation, and resource creation",
   "main": "./dist/index.js",
@@ -26,13 +26,14 @@
   "dependencies": {
     "@anthropic-ai/sdk": "^0.63.0",
     "@semiont/api-client": "*",
-    "@semiont/core": "*"
+    "@semiont/core": "*",
+    "@vitest/ui": "4.0.18"
   },
   "devDependencies": {
-    "@vitest/coverage-v8": "^4.1.0",
+    "@vitest/coverage-v8": "^4.0.18",
     "tsup": "^8.0.1",
     "typescript": "^5.6.3",
-    "vitest": "^4.1.0"
+    "vitest": "^4.0.18"
   },
   "publishConfig": {
     "access": "public"