@posthog/ai/dist/openai/index.cjs.map

PostHog Node.js AI integrations

{"version":3,"file":"index.cjs","sources":["../../src/typeGuards.ts","../../src/sanitization.ts","../../src/utils.ts","../../src/openai/utils.ts","../../src/openai/index.ts"],"sourcesContent":["// Type guards for safer type checking\n\nexport const isString = (value: unknown): value is string => {\n  return typeof value === 'string'\n}\n\nexport const isObject = (value: unknown): value is Record<string, unknown> => {\n  return value !== null && typeof value === 'object' && !Array.isArray(value)\n}\n","import { isString, isObject } from './typeGuards'\n\nconst REDACTED_IMAGE_PLACEHOLDER = '[base64 image redacted]'\n\n// ============================================\n// Multimodal Feature Toggle\n// ============================================\n\nconst isMultimodalEnabled = (): boolean => {\n  const val = process.env._INTERNAL_LLMA_MULTIMODAL || ''\n  return val.toLowerCase() === 'true' || val === '1' || val.toLowerCase() === 'yes'\n}\n\n// ============================================\n// Base64 Detection Helpers\n// ============================================\n\nconst isBase64DataUrl = (str: string): boolean => {\n  return /^data:([^;]+);base64,/.test(str)\n}\n\nconst isValidUrl = (str: string): boolean => {\n  try {\n    new URL(str)\n    return true\n  } catch {\n    // Not an absolute URL, check if it's a relative URL or path\n    return str.startsWith('/') || str.startsWith('./') || str.startsWith('../')\n  }\n}\n\nconst isRawBase64 = (str: string): boolean => {\n  // Skip if it's a valid URL or path\n  if (isValidUrl(str)) {\n    return false\n  }\n\n  // Check if it's a valid base64 string\n  // Base64 images are typically at least a few hundred chars, but we'll be conservative\n  return str.length > 20 && /^[A-Za-z0-9+/]+=*$/.test(str)\n}\n\nexport function redactBase64DataUrl(str: string): string\nexport function redactBase64DataUrl(str: unknown): unknown\nexport function redactBase64DataUrl(str: unknown): unknown {\n  if (isMultimodalEnabled()) return str\n  if (!isString(str)) return str\n\n  // Check for data URL format\n  if (isBase64DataUrl(str)) {\n    return REDACTED_IMAGE_PLACEHOLDER\n  }\n\n  // Check for raw base64 (Vercel sends raw base64 for inline images)\n  if (isRawBase64(str)) {\n    return REDACTED_IMAGE_PLACEHOLDER\n  }\n\n  return str\n}\n\n// ============================================\n// Common Message Processing\n// ============================================\n\ntype ContentTransformer = (item: unknown) => unknown\n\nconst processMessages = (messages: unknown, transformContent: ContentTransformer): unknown => {\n  if (!messages) return messages\n\n  const processContent = (content: unknown): unknown => {\n    if (typeof content === 'string') return content\n\n    if (!content) return content\n\n    if (Array.isArray(content)) {\n      return content.map(transformContent)\n    }\n\n    // Handle single object content\n    return transformContent(content)\n  }\n\n  const processMessage = (msg: unknown): unknown => {\n    if (!isObject(msg) || !('content' in msg)) return msg\n    return { ...msg, content: processContent(msg.content) }\n  }\n\n  // Handle both arrays and single messages\n  if (Array.isArray(messages)) {\n    return messages.map(processMessage)\n  }\n\n  return processMessage(messages)\n}\n\n// ============================================\n// Provider-Specific Image Sanitizers\n// ============================================\n\nconst sanitizeOpenAIImage = (item: unknown): unknown => {\n  if (!isObject(item)) return item\n\n  // Handle image_url format\n  if (item.type === 'image_url' && 'image_url' in item && isObject(item.image_url) && 'url' in item.image_url) {\n    return {\n      ...item,\n      image_url: {\n        ...item.image_url,\n        url: redactBase64DataUrl(item.image_url.url),\n      },\n    }\n  }\n\n  // Handle audio format\n  if (item.type === 'audio' && 'data' in item) {\n    if (isMultimodalEnabled()) return item\n    return { ...item, data: REDACTED_IMAGE_PLACEHOLDER }\n  }\n\n  return item\n}\n\nconst sanitizeOpenAIResponseImage = (item: unknown): unknown => {\n  if (!isObject(item)) return item\n\n  // Handle input_image format\n  if (item.type === 'input_image' && 'image_url' in item) {\n    return {\n      ...item,\n      image_url: redactBase64DataUrl(item.image_url),\n    }\n  }\n\n  return item\n}\n\nconst sanitizeAnthropicImage = (item: unknown): unknown => {\n  if (isMultimodalEnabled()) return item\n  if (!isObject(item)) return item\n\n  // Handle Anthropic's image and document formats (same structure, different type field)\n  if (\n    (item.type === 'image' || item.type === 'document') &&\n    'source' in item &&\n    isObject(item.source) &&\n    item.source.type === 'base64' &&\n    'data' in item.source\n  ) {\n    return {\n      ...item,\n      source: {\n        ...item.source,\n        data: REDACTED_IMAGE_PLACEHOLDER,\n      },\n    }\n  }\n\n  return item\n}\n\nconst sanitizeGeminiPart = (part: unknown): unknown => {\n  if (isMultimodalEnabled()) return part\n  if (!isObject(part)) return part\n\n  // Handle Gemini's inline data format (images, audio, PDFs all use inlineData)\n  if ('inlineData' in part && isObject(part.inlineData) && 'data' in part.inlineData) {\n    return {\n      ...part,\n      inlineData: {\n        ...part.inlineData,\n        data: REDACTED_IMAGE_PLACEHOLDER,\n      },\n    }\n  }\n\n  return part\n}\n\nconst processGeminiItem = (item: unknown): unknown => {\n  if (!isObject(item)) return item\n\n  // If it has parts, process them\n  if ('parts' in item && item.parts) {\n    const parts = Array.isArray(item.parts) ? item.parts.map(sanitizeGeminiPart) : sanitizeGeminiPart(item.parts)\n\n    return { ...item, parts }\n  }\n\n  return item\n}\n\nconst sanitizeLangChainImage = (item: unknown): unknown => {\n  if (!isObject(item)) return item\n\n  // OpenAI style\n  if (item.type === 'image_url' && 'image_url' in item && isObject(item.image_url) && 'url' in item.image_url) {\n    return {\n      ...item,\n      image_url: {\n        ...item.image_url,\n        url: redactBase64DataUrl(item.image_url.url),\n      },\n    }\n  }\n\n  // Direct image with data field\n  if (item.type === 'image' && 'data' in item) {\n    return { ...item, data: redactBase64DataUrl(item.data) }\n  }\n\n  // Anthropic style\n  if (item.type === 'image' && 'source' in item && isObject(item.source) && 'data' in item.source) {\n    if (isMultimodalEnabled()) return item\n    return {\n      ...item,\n      source: {\n        ...item.source,\n        data: redactBase64DataUrl(item.source.data),\n      },\n    }\n  }\n\n  // Google style\n  if (item.type === 'media' && 'data' in item) {\n    return { ...item, data: redactBase64DataUrl(item.data) }\n  }\n\n  return item\n}\n\n// Export individual sanitizers for tree-shaking\nexport const sanitizeOpenAI = (data: unknown): unknown => {\n  return processMessages(data, sanitizeOpenAIImage)\n}\n\nexport const sanitizeOpenAIResponse = (data: unknown): unknown => {\n  return processMessages(data, sanitizeOpenAIResponseImage)\n}\n\nexport const sanitizeAnthropic = (data: unknown): unknown => {\n  return processMessages(data, sanitizeAnthropicImage)\n}\n\nexport const sanitizeGemini = (data: unknown): unknown => {\n  // Gemini has a different structure with 'parts' directly on items instead of 'content'\n  // So we need custom processing instead of using processMessages\n  if (!data) return data\n\n  if (Array.isArray(data)) {\n    return data.map(processGeminiItem)\n  }\n\n  return processGeminiItem(data)\n}\n\nexport const sanitizeLangChain = (data: unknown): unknown => {\n  return processMessages(data, sanitizeLangChainImage)\n}\n","import { EventMessage, PostHog } from 'posthog-node'\nimport OpenAIOrignal from 'openai'\nimport AnthropicOriginal from '@anthropic-ai/sdk'\nimport type { ChatCompletionTool } from 'openai/resources/chat/completions'\nimport type { ResponseCreateParamsWithTools } from 'openai/lib/ResponsesParser'\nimport type { Tool as GeminiTool } from '@google/genai'\nimport type { FormattedMessage, FormattedContent, TokenUsage } from './types'\nimport { version } from '../package.json'\nimport { v4 as uuidv4 } from 'uuid'\nimport { isString } from './typeGuards'\nimport { uuidv7, ErrorTracking as CoreErrorTracking } from '@posthog/core'\nimport { redactBase64DataUrl } from './sanitization'\n\ntype ChatCompletionCreateParamsBase = OpenAIOrignal.Chat.Completions.ChatCompletionCreateParams\ntype MessageCreateParams = AnthropicOriginal.Messages.MessageCreateParams\ntype ResponseCreateParams = OpenAIOrignal.Responses.ResponseCreateParams\ntype EmbeddingCreateParams = OpenAIOrignal.EmbeddingCreateParams\ntype TranscriptionCreateParams = OpenAIOrignal.Audio.Transcriptions.TranscriptionCreateParams\ntype AnthropicTool = AnthropicOriginal.Tool\n\n// limit large outputs by truncating to 200kb (approx 200k bytes)\nexport const MAX_OUTPUT_SIZE = 200000\nconst STRING_FORMAT = 'utf8'\n\n/**\n * Safely converts content to a string, preserving structure for objects/arrays.\n * - If content is already a string, returns it as-is\n * - If content is an object or array, stringifies it with JSON.stringify to preserve structure\n * - Otherwise, converts to string with String()\n *\n * This prevents the \"[object Object]\" bug when objects are naively converted to strings.\n *\n * @param content - The content to convert to a string\n * @returns A string representation that preserves structure for complex types\n */\nexport function toContentString(content: unknown): string {\n  if (typeof content === 'string') {\n    return content\n  }\n  if (content !== undefined && content !== null && typeof content === 'object') {\n    try {\n      return JSON.stringify(content)\n    } catch {\n      // Fallback for circular refs, BigInt, or objects with throwing toJSON\n      return String(content)\n    }\n  }\n  return String(content)\n}\n\nexport interface MonitoringEventPropertiesWithDefaults {\n  distinctId?: string\n  traceId: string\n  properties?: Record<string, any>\n  privacyMode: boolean\n  groups?: Record<string, any>\n  modelOverride?: string\n  providerOverride?: string\n  costOverride?: CostOverride\n  captureImmediate?: boolean\n}\n\nexport type MonitoringEventProperties = Partial<MonitoringEventPropertiesWithDefaults>\n\nexport type MonitoringParams = {\n  [K in keyof MonitoringEventProperties as `posthog${Capitalize<string & K>}`]: MonitoringEventProperties[K]\n}\n\nexport interface CostOverride {\n  inputCost: number\n  outputCost: number\n}\n\nexport const getModelParams = (\n  params:\n    | ((\n        | ChatCompletionCreateParamsBase\n        | MessageCreateParams\n        | ResponseCreateParams\n        | ResponseCreateParamsWithTools\n        | EmbeddingCreateParams\n        | TranscriptionCreateParams\n      ) &\n        MonitoringParams)\n    | null\n): Record<string, any> => {\n  if (!params) {\n    return {}\n  }\n  const modelParams: Record<string, any> = {}\n  const paramKeys = [\n    'temperature',\n    'max_tokens',\n    'max_completion_tokens',\n    'top_p',\n    'frequency_penalty',\n    'presence_penalty',\n    'n',\n    'stop',\n    'stream',\n    'streaming',\n    'language',\n    'response_format',\n    'timestamp_granularities',\n  ] as const\n\n  for (const key of paramKeys) {\n    if (key in params && (params as any)[key] !== undefined) {\n      modelParams[key] = (params as any)[key]\n    }\n  }\n  return modelParams\n}\n\n/**\n * Helper to format responses (non-streaming) for consumption\n */\nexport const formatResponse = (response: any, provider: string): FormattedMessage[] => {\n  if (!response) {\n    return []\n  }\n  if (provider === 'anthropic') {\n    return formatResponseAnthropic(response)\n  } else if (provider === 'openai') {\n    return formatResponseOpenAI(response)\n  } else if (provider === 'gemini') {\n    return formatResponseGemini(response)\n  }\n  return []\n}\n\nexport const formatResponseAnthropic = (response: any): FormattedMessage[] => {\n  const output: FormattedMessage[] = []\n  const content: FormattedContent = []\n\n  for (const choice of response.content ?? []) {\n    if (choice?.type === 'text' && choice?.text) {\n      content.push({ type: 'text', text: choice.text })\n    } else if (choice?.type === 'tool_use' && choice?.name && choice?.id) {\n      content.push({\n        type: 'function',\n        id: choice.id,\n        function: {\n          name: choice.name,\n          arguments: choice.input || {},\n        },\n      })\n    }\n  }\n\n  if (content.length > 0) {\n    output.push({\n      role: 'assistant',\n      content,\n    })\n  }\n\n  return output\n}\n\nexport const formatResponseOpenAI = (response: any): FormattedMessage[] => {\n  const output: FormattedMessage[] = []\n\n  if (response.choices) {\n    for (const choice of response.choices) {\n      const content: FormattedContent = []\n      let role = 'assistant'\n\n      if (choice.message) {\n        if (choice.message.role) {\n          role = choice.message.role\n        }\n\n        if (choice.message.content) {\n          content.push({ type: 'text', text: choice.message.content })\n        }\n\n        if (choice.message.tool_calls) {\n          for (const toolCall of choice.message.tool_calls) {\n            content.push({\n              type: 'function',\n              id: toolCall.id,\n              function: {\n                name: toolCall.function.name,\n                arguments: toolCall.function.arguments,\n              },\n            })\n          }\n        }\n\n        // Handle audio output (gpt-4o-audio-preview)\n        if (choice.message.audio) {\n          content.push({\n            type: 'audio',\n            ...choice.message.audio,\n          })\n        }\n      }\n\n      if (content.length > 0) {\n        output.push({\n          role,\n          content,\n        })\n      }\n    }\n  }\n\n  // Handle Responses API format\n  if (response.output) {\n    const content: FormattedContent = []\n    let role = 'assistant'\n\n    for (const item of response.output) {\n      if (item.type === 'message') {\n        role = item.role\n\n        if (item.content && Array.isArray(item.content)) {\n          for (const contentItem of item.content) {\n            if (contentItem.type === 'output_text' && contentItem.text) {\n              content.push({ type: 'text', text: contentItem.text })\n            } else if (contentItem.text) {\n              content.push({ type: 'text', text: contentItem.text })\n            } else if (contentItem.type === 'input_image' && contentItem.image_url) {\n              content.push({\n                type: 'image',\n                image: contentItem.image_url,\n              })\n            }\n          }\n        } else if (item.content) {\n          content.push({ type: 'text', text: String(item.content) })\n        }\n      } else if (item.type === 'function_call') {\n        content.push({\n          type: 'function',\n          id: item.call_id || item.id || '',\n          function: {\n            name: item.name,\n            arguments: item.arguments || {},\n          },\n        })\n      }\n    }\n\n    if (content.length > 0) {\n      output.push({\n        role,\n        content,\n      })\n    }\n  }\n\n  return output\n}\n\nexport const formatResponseGemini = (response: any): FormattedMessage[] => {\n  const output: FormattedMessage[] = []\n\n  if (response.candidates && Array.isArray(response.candidates)) {\n    for (const candidate of response.candidates) {\n      if (candidate.content && candidate.content.parts) {\n        const content: FormattedContent = []\n\n        for (const part of candidate.content.parts) {\n          if (part.text) {\n            content.push({ type: 'text', text: part.text })\n          } else if (part.functionCall) {\n            content.push({\n              type: 'function',\n              function: {\n                name: part.functionCall.name,\n                arguments: part.functionCall.args,\n              },\n            })\n          } else if (part.inlineData) {\n            // Handle audio/media inline data\n            const mimeType = part.inlineData.mimeType || 'audio/pcm'\n            let data = part.inlineData.data\n\n            // Handle binary data (Uint8Array/Buffer -> base64)\n            if (data instanceof Uint8Array) {\n              if (typeof Buffer !== 'undefined') {\n                data = Buffer.from(data).toString('base64')\n              } else {\n                let binary = ''\n                for (let i = 0; i < data.length; i++) {\n                  binary += String.fromCharCode(data[i])\n                }\n                data = btoa(binary)\n              }\n            }\n\n            // Sanitize base64 data for images and other large inline data\n            data = redactBase64DataUrl(data)\n\n            content.push({\n              type: 'audio',\n              mime_type: mimeType,\n              data: data,\n            })\n          }\n        }\n\n        if (content.length > 0) {\n          output.push({\n            role: 'assistant',\n            content,\n          })\n        }\n      } else if (candidate.text) {\n        output.push({\n          role: 'assistant',\n          content: [{ type: 'text', text: candidate.text }],\n        })\n      }\n    }\n  } else if (response.text) {\n    output.push({\n      role: 'assistant',\n      content: [{ type: 'text', text: response.text }],\n    })\n  }\n\n  return output\n}\n\nexport const mergeSystemPrompt = (params: MessageCreateParams & MonitoringParams, provider: string): any => {\n  if (provider == 'anthropic') {\n    const messages = params.messages || []\n    if (!(params as any).system) {\n      return messages\n    }\n    const systemMessage = (params as any).system\n    return [{ role: 'system', content: systemMessage }, ...messages]\n  }\n  return params.messages\n}\n\nexport const withPrivacyMode = (client: PostHog, privacyMode: boolean, input: any): any => {\n  return (client as any).privacy_mode || privacyMode ? null : input\n}\n\nfunction toSafeString(input: unknown): string {\n  if (input === undefined || input === null) {\n    return ''\n  }\n  if (typeof input === 'string') {\n    return input\n  }\n  try {\n    return JSON.stringify(input)\n  } catch {\n    console.warn('Failed to stringify input', input)\n    return ''\n  }\n}\n\nexport const truncate = (input: unknown): string => {\n  const str = toSafeString(input)\n  if (str === '') {\n    return ''\n  }\n\n  // Check if we need to truncate and ensure STRING_FORMAT is respected\n  const encoder = new TextEncoder()\n  const buffer = encoder.encode(str)\n  if (buffer.length <= MAX_OUTPUT_SIZE) {\n    // Ensure STRING_FORMAT is respected\n    return new TextDecoder(STRING_FORMAT).decode(buffer)\n  }\n\n  // Truncate the buffer and ensure a valid string is returned\n  const truncatedBuffer = buffer.slice(0, MAX_OUTPUT_SIZE)\n  // fatal: false means we get U+FFFD at the end if truncation broke the encoding\n  const decoder = new TextDecoder(STRING_FORMAT, { fatal: false })\n  let truncatedStr = decoder.decode(truncatedBuffer)\n  if (truncatedStr.endsWith('\\uFFFD')) {\n    truncatedStr = truncatedStr.slice(0, -1)\n  }\n  return `${truncatedStr}... [truncated]`\n}\n\n/**\n * Calculate web search count from raw API response.\n *\n * Uses a two-tier detection strategy:\n * Priority 1 (Exact Count): Count actual web search calls when available\n * Priority 2 (Binary Detection): Return 1 if web search indicators are present, 0 otherwise\n *\n * @param result - Raw API response from any provider (OpenAI, Perplexity, OpenRouter, Gemini, etc.)\n * @returns Number of web searches performed (exact count or binary 1/0)\n */\nexport function calculateWebSearchCount(result: unknown): number {\n  if (!result || typeof result !== 'object') {\n    return 0\n  }\n\n  // Priority 1: Exact Count\n  // Check for OpenAI Responses API web_search_call items\n  if ('output' in result && Array.isArray(result.output)) {\n    let count = 0\n\n    for (const item of result.output) {\n      if (typeof item === 'object' && item !== null && 'type' in item && item.type === 'web_search_call') {\n        count++\n      }\n    }\n\n    if (count > 0) {\n      return count\n    }\n  }\n\n  // Priority 2: Binary Detection (1 or 0)\n\n  // Check for citations at root level (Perplexity)\n  if ('citations' in result && Array.isArray(result.citations) && result.citations.length > 0) {\n    return 1\n  }\n\n  // Check for search_results at root level (Perplexity via OpenRouter)\n  if ('search_results' in result && Array.isArray(result.search_results) && result.search_results.length > 0) {\n    return 1\n  }\n\n  // Check for usage.search_context_size (Perplexity via OpenRouter)\n  if ('usage' in result && typeof result.usage === 'object' && result.usage !== null) {\n    if ('search_context_size' in result.usage && result.usage.search_context_size) {\n      return 1\n    }\n  }\n\n  // Check for annotations with url_citation in choices[].message or choices[].delta (OpenAI/Perplexity)\n  if ('choices' in result && Array.isArray(result.choices)) {\n    for (const choice of result.choices) {\n      if (typeof choice === 'object' && choice !== null) {\n        // Check both message (non-streaming) and delta (streaming) for annotations\n        const content = ('message' in choice ? choice.message : null) || ('delta' in choice ? choice.delta : null)\n\n        if (typeof content === 'object' && content !== null && 'annotations' in content) {\n          const annotations = content.annotations\n\n          if (Array.isArray(annotations)) {\n            const hasUrlCitation = annotations.some((ann: unknown) => {\n              return typeof ann === 'object' && ann !== null && 'type' in ann && ann.type === 'url_citation'\n            })\n\n            if (hasUrlCitation) {\n              return 1\n            }\n          }\n        }\n      }\n    }\n  }\n\n  // Check for annotations in output[].content[] (OpenAI Responses API)\n  if ('output' in result && Array.isArray(result.output)) {\n    for (const item of result.output) {\n      if (typeof item === 'object' && item !== null && 'content' in item) {\n        const content = item.content\n\n        if (Array.isArray(content)) {\n          for (const contentItem of content) {\n            if (typeof contentItem === 'object' && contentItem !== null && 'annotations' in contentItem) {\n              const annotations = contentItem.annotations\n\n              if (Array.isArray(annotations)) {\n                const hasUrlCitation = annotations.some((ann: unknown) => {\n                  return typeof ann === 'object' && ann !== null && 'type' in ann && ann.type === 'url_citation'\n                })\n\n                if (hasUrlCitation) {\n                  return 1\n                }\n              }\n            }\n          }\n        }\n      }\n    }\n  }\n\n  // Check for grounding_metadata (Gemini)\n  if ('candidates' in result && Array.isArray(result.candidates)) {\n    for (const candidate of result.candidates) {\n      if (\n        typeof candidate === 'object' &&\n        candidate !== null &&\n        'grounding_metadata' in candidate &&\n        candidate.grounding_metadata\n      ) {\n        return 1\n      }\n    }\n  }\n\n  return 0\n}\n\n/**\n * Extract available tool calls from the request parameters.\n * These are the tools provided to the LLM, not the tool calls in the response.\n */\nexport const extractAvailableToolCalls = (\n  provider: string,\n  params: any\n): ChatCompletionTool[] | AnthropicTool[] | GeminiTool[] | null => {\n  if (provider === 'anthropic') {\n    if (params.tools) {\n      return params.tools\n    }\n\n    return null\n  } else if (provider === 'gemini') {\n    if (params.config && params.config.tools) {\n      return params.config.tools\n    }\n\n    return null\n  } else if (provider === 'openai') {\n    if (params.tools) {\n      return params.tools\n    }\n\n    return null\n  } else if (provider === 'vercel') {\n    if (params.tools) {\n      return params.tools\n    }\n\n    return null\n  }\n\n  return null\n}\n\nexport enum AIEvent {\n  Generation = '$ai_generation',\n  Embedding = '$ai_embedding',\n}\n\nexport type SendEventToPosthogParams = {\n  client: PostHog\n  eventType?: AIEvent\n  distinctId?: string\n  traceId: string\n  model?: string\n  provider: string\n  input: any\n  output: any\n  latency: number\n  timeToFirstToken?: number\n  baseURL: string\n  httpStatus: number\n  usage?: TokenUsage\n  params: (\n    | ChatCompletionCreateParamsBase\n    | MessageCreateParams\n    | ResponseCreateParams\n    | ResponseCreateParamsWithTools\n    | EmbeddingCreateParams\n    | TranscriptionCreateParams\n  ) &\n    MonitoringParams\n  error?: unknown\n  exceptionId?: string\n  tools?: ChatCompletionTool[] | AnthropicTool[] | GeminiTool[] | null\n  captureImmediate?: boolean\n}\n\nfunction sanitizeValues(obj: any): any {\n  if (obj === undefined || obj === null) {\n    return obj\n  }\n  const jsonSafe = JSON.parse(JSON.stringify(obj))\n  if (typeof jsonSafe === 'string') {\n    // Sanitize lone surrogates by round-tripping through UTF-8\n    return new TextDecoder().decode(new TextEncoder().encode(jsonSafe))\n  } else if (Array.isArray(jsonSafe)) {\n    return jsonSafe.map(sanitizeValues)\n  } else if (jsonSafe && typeof jsonSafe === 'object') {\n    return Object.fromEntries(Object.entries(jsonSafe).map(([k, v]) => [k, sanitizeValues(v)]))\n  }\n  return jsonSafe\n}\n\nconst POSTHOG_PARAMS_MAP: Record<keyof MonitoringParams, string> = {\n  posthogDistinctId: 'distinctId',\n  posthogTraceId: 'traceId',\n  posthogProperties: 'properties',\n  posthogPrivacyMode: 'privacyMode',\n  posthogGroups: 'groups',\n  posthogModelOverride: 'modelOverride',\n  posthogProviderOverride: 'providerOverride',\n  posthogCostOverride: 'costOverride',\n  posthogCaptureImmediate: 'captureImmediate',\n}\n\nexport function extractPosthogParams<T>(body: T & MonitoringParams): {\n  providerParams: T\n  posthogParams: MonitoringEventPropertiesWithDefaults\n} {\n  const providerParams: Record<string, unknown> = {}\n  const posthogParams: Record<string, unknown> = {}\n\n  for (const [key, value] of Object.entries(body)) {\n    if (POSTHOG_PARAMS_MAP[key as keyof MonitoringParams]) {\n      posthogParams[POSTHOG_PARAMS_MAP[key as keyof MonitoringParams]] = value\n    } else if (key.startsWith('posthog')) {\n      console.warn(`Unknown Posthog parameter ${key}`)\n    } else {\n      providerParams[key] = value\n    }\n  }\n\n  return {\n    providerParams: providerParams as T,\n    posthogParams: addDefaults(posthogParams),\n  }\n}\n\nfunction addDefaults(params: MonitoringEventProperties): MonitoringEventPropertiesWithDefaults {\n  return {\n    ...params,\n    privacyMode: params.privacyMode ?? false,\n    traceId: params.traceId ?? uuidv4(),\n  }\n}\n\nexport const sendEventWithErrorToPosthog = async ({\n  client,\n  traceId,\n  error,\n  ...args\n}: Omit<SendEventToPosthogParams, 'error' | 'httpStatus'> &\n  Required<Pick<SendEventToPosthogParams, 'error'>>): Promise<unknown> => {\n  const httpStatus =\n    error && typeof error === 'object' && 'status' in error ? ((error as { status?: number }).status ?? 500) : 500\n\n  const properties = { client, traceId, httpStatus, error: JSON.stringify(error), ...args }\n  const enrichedError = error as CoreErrorTracking.PreviouslyCapturedError\n\n  if (client.options?.enableExceptionAutocapture) {\n    // assign a uuid that can be used to link the trace and exception events\n    const exceptionId = uuidv7()\n    client.captureException(error, undefined, { $ai_trace_id: traceId }, exceptionId)\n    enrichedError.__posthog_previously_captured_error = true\n    properties.exceptionId = exceptionId\n  }\n\n  await sendEventToPosthog(properties)\n\n  return enrichedError\n}\n\nexport const sendEventToPosthog = async ({\n  client,\n  eventType = AIEvent.Generation,\n  distinctId,\n  traceId,\n  model,\n  provider,\n  input,\n  output,\n  latency,\n  timeToFirstToken,\n  baseURL,\n  params,\n  httpStatus = 200,\n  usage = {},\n  error,\n  exceptionId,\n  tools,\n  captureImmediate = false,\n}: SendEventToPosthogParams): Promise<void> => {\n  if (!client.capture) {\n    return Promise.resolve()\n  }\n  // sanitize input and output for UTF-8 validity\n  const safeInput = sanitizeValues(input)\n  const safeOutput = sanitizeValues(output)\n  const safeError = sanitizeValues(error)\n\n  let errorData = {}\n  if (error) {\n    errorData = {\n      $ai_is_error: true,\n      $ai_error: safeError,\n      $exception_event_id: exceptionId,\n    }\n  }\n  let costOverrideData = {}\n  if (params.posthogCostOverride) {\n    const inputCostUSD = (params.posthogCostOverride.inputCost ?? 0) * (usage.inputTokens ?? 0)\n    const outputCostUSD = (params.posthogCostOverride.outputCost ?? 0) * (usage.outputTokens ?? 0)\n    costOverrideData = {\n      $ai_input_cost_usd: inputCostUSD,\n      $ai_output_cost_usd: outputCostUSD,\n      $ai_total_cost_usd: inputCostUSD + outputCostUSD,\n    }\n  }\n\n  const additionalTokenValues = {\n    ...(usage.reasoningTokens ? { $ai_reasoning_tokens: usage.reasoningTokens } : {}),\n    ...(usage.cacheReadInputTokens ? { $ai_cache_read_input_tokens: usage.cacheReadInputTokens } : {}),\n    ...(usage.cacheCreationInputTokens ? { $ai_cache_creation_input_tokens: usage.cacheCreationInputTokens } : {}),\n    ...(usage.webSearchCount ? { $ai_web_search_count: usage.webSearchCount } : {}),\n    ...(usage.rawUsage ? { $ai_usage: usage.rawUsage } : {}),\n  }\n\n  const properties = {\n    $ai_lib: 'posthog-ai',\n    $ai_lib_version: version,\n    $ai_provider: params.posthogProviderOverride ?? provider,\n    $ai_model: params.posthogModelOverride ?? model,\n    $ai_model_parameters: getModelParams(params),\n    $ai_input: withPrivacyMode(client, params.posthogPrivacyMode ?? false, safeInput),\n    $ai_output_choices: withPrivacyMode(client, params.posthogPrivacyMode ?? false, safeOutput),\n    $ai_http_status: httpStatus,\n    $ai_input_tokens: usage.inputTokens ?? 0,\n    ...(usage.outputTokens !== undefined ? { $ai_output_tokens: usage.outputTokens } : {}),\n    ...additionalTokenValues,\n    $ai_latency: latency,\n    ...(timeToFirstToken !== undefined ? { $ai_time_to_first_token: timeToFirstToken } : {}),\n    $ai_trace_id: traceId,\n    $ai_base_url: baseURL,\n    ...params.posthogProperties,\n    ...(distinctId ? {} : { $process_person_profile: false }),\n    ...(tools ? { $ai_tools: tools } : {}),\n    ...errorData,\n    ...costOverrideData,\n  }\n\n  const event: EventMessage = {\n    distinctId: distinctId ?? traceId,\n    event: eventType,\n    properties,\n    groups: params.posthogGroups,\n  }\n\n  if (captureImmediate) {\n    // await capture promise to send single event in serverless environments\n    await client.captureImmediate(event)\n  } else {\n    client.capture(event)\n  }\n\n  return Promise.resolve()\n}\n\nexport function formatOpenAIResponsesInput(input: unknown, instructions?: string | null): FormattedMessage[] {\n  const messages: FormattedMessage[] = []\n\n  if (instructions) {\n    messages.push({\n      role: 'system',\n      content: instructions,\n    })\n  }\n\n  if (Array.isArray(input)) {\n    for (const item of input) {\n      if (typeof item === 'string') {\n        messages.push({ role: 'user', content: item })\n      } else if (item && typeof item === 'object') {\n        const obj = item as Record<string, unknown>\n        const role = isString(obj.role) ? obj.role : 'user'\n\n        // Handle content properly - preserve structure for objects/arrays\n        const content = obj.content ?? obj.text ?? item\n        messages.push({ role, content: toContentString(content) })\n      } else {\n        messages.push({ role: 'user', content: toContentString(item) })\n      }\n    }\n  } else if (typeof input === 'string') {\n    messages.push({ role: 'user', content: input })\n  } else if (input) {\n    messages.push({ role: 'user', content: toContentString(input) })\n  }\n\n  return messages\n}\n","import type OpenAI from 'openai'\n\n/**\n * Checks if a ResponseStreamEvent chunk represents the first token/content from the model.\n * This includes various content types like text, reasoning, audio, and refusals.\n */\nexport function isResponseTokenChunk(chunk: OpenAI.Responses.ResponseStreamEvent): boolean {\n  return (\n    chunk.type === 'response.output_item.added' ||\n    chunk.type === 'response.content_part.added' ||\n    chunk.type === 'response.output_text.delta' ||\n    chunk.type === 'response.reasoning_text.delta' ||\n    chunk.type === 'response.reasoning_summary_text.delta' ||\n    chunk.type === 'response.audio.delta' ||\n    chunk.type === 'response.audio.transcript.delta' ||\n    chunk.type === 'response.refusal.delta'\n  )\n}\n","import { OpenAI as OpenAIOrignal, ClientOptions } from 'openai'\nimport { PostHog } from 'posthog-node'\nimport {\n  formatResponseOpenAI,\n  MonitoringParams,\n  sendEventToPosthog,\n  extractAvailableToolCalls,\n  withPrivacyMode,\n  AIEvent,\n  formatOpenAIResponsesInput,\n  calculateWebSearchCount,\n  sendEventWithErrorToPosthog,\n} from '../utils'\nimport type { APIPromise } from 'openai'\nimport type { Stream } from 'openai/streaming'\nimport type { ParsedResponse } from 'openai/resources/responses/responses'\nimport type { ResponseCreateParamsWithTools, ExtractParsedContentFromParams } from 'openai/lib/ResponsesParser'\nimport type { FormattedMessage, FormattedContent, FormattedFunctionCall } from '../types'\nimport { sanitizeOpenAI, sanitizeOpenAIResponse } from '../sanitization'\nimport { extractPosthogParams } from '../utils'\nimport { isResponseTokenChunk } from './utils'\n\nconst Chat = OpenAIOrignal.Chat\nconst Completions = Chat.Completions\nconst Responses = OpenAIOrignal.Responses\nconst Embeddings = OpenAIOrignal.Embeddings\nconst Audio = OpenAIOrignal.Audio\nconst Transcriptions = OpenAIOrignal.Audio.Transcriptions\n\ntype ChatCompletion = OpenAIOrignal.ChatCompletion\ntype ChatCompletionChunk = OpenAIOrignal.ChatCompletionChunk\ntype ChatCompletionCreateParamsBase = OpenAIOrignal.Chat.Completions.ChatCompletionCreateParams\ntype ChatCompletionCreateParamsNonStreaming = OpenAIOrignal.Chat.Completions.ChatCompletionCreateParamsNonStreaming\ntype ChatCompletionCreateParamsStreaming = OpenAIOrignal.Chat.Completions.ChatCompletionCreateParamsStreaming\ntype ResponsesCreateParamsBase = OpenAIOrignal.Responses.ResponseCreateParams\ntype ResponsesCreateParamsNonStreaming = OpenAIOrignal.Responses.ResponseCreateParamsNonStreaming\ntype ResponsesCreateParamsStreaming = OpenAIOrignal.Responses.ResponseCreateParamsStreaming\ntype CreateEmbeddingResponse = OpenAIOrignal.CreateEmbeddingResponse\ntype EmbeddingCreateParams = OpenAIOrignal.EmbeddingCreateParams\n\ninterface MonitoringOpenAIConfig extends ClientOptions {\n  apiKey: string\n  posthog: PostHog\n  baseURL?: string\n}\n\ntype RequestOptions = Record<string, unknown>\n\nexport class PostHogOpenAI extends OpenAIOrignal {\n  private readonly phClient: PostHog\n  public chat: WrappedChat\n  public responses: WrappedResponses\n  public embeddings: WrappedEmbeddings\n  public audio: WrappedAudio\n\n  constructor(config: MonitoringOpenAIConfig) {\n    const { posthog, ...openAIConfig } = config\n    super(openAIConfig)\n    this.phClient = posthog\n    this.chat = new WrappedChat(this, this.phClient)\n    this.responses = new WrappedResponses(this, this.phClient)\n    this.embeddings = new WrappedEmbeddings(this, this.phClient)\n    this.audio = new WrappedAudio(this, this.phClient)\n  }\n}\n\nexport class WrappedChat extends Chat {\n  constructor(parentClient: PostHogOpenAI, phClient: PostHog) {\n    super(parentClient)\n    this.completions = new WrappedCompletions(parentClient, phClient)\n  }\n\n  public completions: WrappedCompletions\n}\n\nexport class WrappedCompletions extends Completions {\n  private readonly phClient: PostHog\n  private readonly baseURL: string\n\n  constructor(client: OpenAIOrignal, phClient: PostHog) {\n    super(client)\n    this.phClient = phClient\n    this.baseURL = client.baseURL\n  }\n\n  // --- Overload #1: Non-streaming\n  public create(\n    body: ChatCompletionCreateParamsNonStreaming & MonitoringParams,\n    options?: RequestOptions\n  ): APIPromise<ChatCompletion>\n\n  // --- Overload #2: Streaming\n  public create(\n    body: ChatCompletionCreateParamsStreaming & MonitoringParams,\n    options?: RequestOptions\n  ): APIPromise<Stream<ChatCompletionChunk>>\n\n  // --- Overload #3: Generic base\n  public create(\n    body: ChatCompletionCreateParamsBase & MonitoringParams,\n    options?: RequestOptions\n  ): APIPromise<ChatCompletion | Stream<ChatCompletionChunk>>\n\n  // --- Implementation Signature\n  public create(\n    body: ChatCompletionCreateParamsBase & MonitoringParams,\n    options?: RequestOptions\n  ): APIPromise<ChatCompletion | Stream<ChatCompletionChunk>> {\n    const { providerParams: openAIParams, posthogParams } = extractPosthogParams(body)\n    const startTime = Date.now()\n\n    const parentPromise = super.create(openAIParams, options)\n\n    if (openAIParams.stream) {\n      return parentPromise.then((value) => {\n        if ('tee' in value) {\n          const [stream1, stream2] = value.tee()\n          ;(async () => {\n            try {\n              const contentBlocks: FormattedContent = []\n              let accumulatedContent = ''\n              let modelFromResponse: string | undefined\n              let firstTokenTime: number | undefined\n              let usage: {\n                inputTokens?: number\n                outputTokens?: number\n                reasoningTokens?: number\n                cacheReadInputTokens?: number\n                webSearchCount?: number\n              } = {\n                inputTokens: 0,\n                outputTokens: 0,\n                webSearchCount: 0,\n              }\n\n              // Map to track in-progress tool calls\n              const toolCallsInProgress = new Map<\n                number,\n                {\n                  id: string\n                  name: string\n                  arguments: string\n                }\n              >()\n              let rawUsageData: unknown\n\n              for await (const chunk of stream1) {\n                // Extract model from chunk (Chat Completions chunks have model field)\n                if (!modelFromResponse && chunk.model) {\n                  modelFromResponse = chunk.model\n                }\n\n                const choice = chunk?.choices?.[0]\n\n                const chunkWebSearchCount = calculateWebSearchCount(chunk)\n                if (chunkWebSearchCount > 0 && chunkWebSearchCount > (usage.webSearchCount ?? 0)) {\n                  usage.webSearchCount = chunkWebSearchCount\n                }\n\n                // Handle text content\n                const deltaContent = choice?.delta?.content\n                if (deltaContent) {\n                  if (firstTokenTime === undefined) {\n                    firstTokenTime = Date.now()\n                  }\n                  accumulatedContent += deltaContent\n                }\n\n                // Handle tool calls\n                const deltaToolCalls = choice?.delta?.tool_calls\n                if (deltaToolCalls && Array.isArray(deltaToolCalls)) {\n                  if (firstTokenTime === undefined) {\n                    firstTokenTime = Date.now()\n                  }\n                  for (const toolCall of deltaToolCalls) {\n                    const index = toolCall.index\n\n                    if (index !== undefined) {\n                      if (!toolCallsInProgress.has(index)) {\n                        // New tool call\n                        toolCallsInProgress.set(index, {\n                          id: toolCall.id || '',\n                          name: toolCall.function?.name || '',\n                          arguments: '',\n                        })\n                      }\n\n                      const inProgressCall = toolCallsInProgress.get(index)\n                      if (inProgressCall) {\n                        // Update tool call data\n                        if (toolCall.id) {\n                          inProgressCall.id = toolCall.id\n                        }\n                        if (toolCall.function?.name) {\n                          inProgressCall.name = toolCall.function.name\n                        }\n                        if (toolCall.function?.arguments) {\n                          inProgressCall.arguments += toolCall.function.arguments\n                        }\n                      }\n                    }\n                  }\n                }\n\n                // Handle usage information\n                if (chunk.usage) {\n                  rawUsageData = chunk.usage\n                  usage = {\n                    ...usage,\n                    inputTokens: chunk.usage.prompt_tokens ?? 0,\n                    outputTokens: chunk.usage.completion_tokens ?? 0,\n                    reasoningTokens: chunk.usage.completion_tokens_details?.reasoning_tokens ?? 0,\n                    cacheReadInputTokens: chunk.usage.prompt_tokens_details?.cached_tokens ?? 0,\n                  }\n                }\n              }\n\n              // Build final content blocks\n              if (accumulatedContent) {\n                contentBlocks.push({ type: 'text', text: accumulatedContent })\n              }\n\n              // Add completed tool calls to content blocks\n              for (const toolCall of toolCallsInProgress.values()) {\n                if (toolCall.name) {\n                  contentBlocks.push({\n                    type: 'function',\n                    id: toolCall.id,\n                    function: {\n                      name: toolCall.name,\n                      arguments: toolCall.arguments,\n                    },\n                  } as FormattedFunctionCall)\n                }\n              }\n\n              // Format output to match non-streaming version\n              const formattedOutput: FormattedMessage[] =\n                contentBlocks.length > 0\n                  ? [\n                      {\n                        role: 'assistant',\n                        content: contentBlocks,\n                      },\n                    ]\n                  : [\n                      {\n                        role: 'assistant',\n                        content: [{ type: 'text', text: '' }],\n                      },\n                    ]\n\n              const latency = (Date.now() - startTime) / 1000\n              const timeToFirstToken = firstTokenTime !== undefined ? (firstTokenTime - startTime) / 1000 : undefined\n              const availableTools = extractAvailableToolCalls('openai', openAIParams)\n              await sendEventToPosthog({\n                client: this.phClient,\n                ...posthogParams,\n                model: openAIParams.model ?? modelFromResponse,\n                provider: 'openai',\n                input: sanitizeOpenAI(openAIParams.messages),\n                output: formattedOutput,\n                latency,\n                timeToFirstToken,\n                baseURL: this.baseURL,\n                params: body,\n                httpStatus: 200,\n                usage: {\n                  inputTokens: usage.inputTokens,\n                  outputTokens: usage.outputTokens,\n                  reasoningTokens: usage.reasoningTokens,\n                  cacheReadInputTokens: usage.cacheReadInputTokens,\n                  webSearchCount: usage.webSearchCount,\n                  rawUsage: rawUsageData,\n                },\n                tools: availableTools,\n              })\n            } catch (error: unknown) {\n              const enrichedError = await sendEventWithErrorToPosthog({\n                client: this.phClient,\n                ...posthogParams,\n                model: openAIParams.model,\n                provider: 'openai',\n                input: sanitizeOpenAI(openAIParams.messages),\n                output: [],\n                latency: 0,\n                baseURL: this.baseURL,\n                params: body,\n                usage: { inputTokens: 0, outputTokens: 0 },\n                error,\n              })\n              throw enrichedError\n            }\n          })()\n\n          // Return the other stream to the user\n          return stream2\n        }\n        return value\n      }) as APIPromise<Stream<ChatCompletionChunk>>\n    } else {\n      const wrappedPromise = parentPromise.then(\n        async (result) => {\n          if ('choices' in result) {\n            const latency = (Date.now() - startTime) / 1000\n            const availableTools = extractAvailableToolCalls('openai', openAIParams)\n            const formattedOutput = formatResponseOpenAI(result)\n            await sendEventToPosthog({\n              client: this.phClient,\n              ...posthogParams,\n              model: openAIParams.model ?? result.model,\n              provider: 'openai',\n              input: sanitizeOpenAI(openAIParams.messages),\n              output: formattedOutput,\n              latency,\n              baseURL: this.baseURL,\n              params: body,\n              httpStatus: 200,\n              usage: {\n                inputTokens: result.usage?.prompt_tokens ?? 0,\n                outputTokens: result.usage?.completion_tokens ?? 0,\n                reasoningTokens: result.usage?.completion_tokens_details?.reasoning_tokens ?? 0,\n                cacheReadInputTokens: result.usage?.prompt_tokens_details?.cached_tokens ?? 0,\n                webSearchCount: calculateWebSearchCount(result),\n                rawUsage: result.usage,\n              },\n              tools: availableTools,\n            })\n          }\n          return result\n        },\n        async (error: unknown) => {\n          const httpStatus =\n            error && typeof error === 'object' && 'status' in error\n              ? ((error as { status?: number }).status ?? 500)\n              : 500\n\n          await sendEventToPosthog({\n            client: this.phClient,\n            ...posthogParams,\n            model: openAIParams.model,\n            provider: 'openai',\n            input: sanitizeOpenAI(openAIParams.messages),\n            output: [],\n            latency: 0,\n            baseURL: this.baseURL,\n            params: body,\n            httpStatus,\n            usage: {\n              inputTokens: 0,\n              outputTokens: 0,\n            },\n            error: JSON.stringify(error),\n          })\n          throw error\n        }\n      ) as APIPromise<ChatCompletion>\n\n      return wrappedPromise\n    }\n  }\n}\n\nexport class WrappedResponses extends Responses {\n  private readonly phClient: PostHog\n  private readonly baseURL: string\n\n  constructor(client: OpenAIOrignal, phClient: PostHog) {\n    super(client)\n    this.phClient = phClient\n    this.baseURL = client.baseURL\n  }\n\n  // --- Overload #1: Non-streaming\n  public create(\n    body: ResponsesCreateParamsNonStreaming & MonitoringParams,\n    options?: RequestOptions\n  ): APIPromise<OpenAIOrignal.Responses.Response>\n\n  // --- Overload #2: Streaming\n  public create(\n    body: ResponsesCreateParamsStreaming & MonitoringParams,\n    options?: RequestOptions\n  ): APIPromise<Stream<OpenAIOrignal.Responses.ResponseStreamEvent>>\n\n  // --- Overload #3: Generic base\n  public create(\n    body: ResponsesCreateParamsBase & MonitoringParams,\n    options?: RequestOptions\n  ): APIPromise<OpenAIOrignal.Responses.Response | Stream<OpenAIOrignal.Responses.ResponseStreamEvent>>\n\n  // --- Implementation Signature\n  public create(\n    body: ResponsesCreateParamsBase & MonitoringParams,\n    options?: RequestOptions\n  ): APIPromise<OpenAIOrignal.Responses.Response | Stream<OpenAIOrignal.Responses.ResponseStreamEvent>> {\n    const { providerParams: openAIParams, posthogParams } = extractPosthogParams(body)\n    const startTime = Date.now()\n\n    const parentPromise = super.create(openAIParams, options)\n\n    if (openAIParams.stream) {\n      return parentPromise.then((value) => {\n        if ('tee' in value && typeof value.tee === 'function') {\n          const [stream1, stream2] = value.tee()\n          ;(async () => {\n            try {\n              let finalContent: unknown[] = []\n              let modelFromResponse: string | undefined\n              let firstTokenTime: number | undefined\n              let usage: {\n                inputTokens?: number\n                outputTokens?: number\n                reasoningTokens?: number\n                cacheReadInputTokens?: number\n                webSearchCount?: number\n              } = {\n                inputTokens: 0,\n                outputTokens: 0,\n                webSearchCount: 0,\n              }\n              let rawUsageData: unknown\n\n              for await (const chunk of stream1) {\n                // Track first token time on content delta events\n                if (firstTokenTime === undefined && isResponseTokenChunk(chunk)) {\n                  firstTokenTime = Date.now()\n                }\n\n                if ('response' in chunk && chunk.response) {\n                  // Extract model from response object in chunk (for stored prompts)\n                  if (!modelFromResponse && chunk.response.model) {\n                    modelFromResponse = chunk.response.model\n                  }\n\n                  const chunkWebSearchCount = calculateWebSearchCount(chunk.response)\n                  if (chunkWebSearchCount > 0 && chunkWebSearchCount > (usage.webSearchCount ?? 0)) {\n                    usage.webSearchCount