backend▌

Read the migration guide before making changes:

Comprehensive reference for 33+ essential JavaScript concepts from fundamentals to modern patterns. \n \n Covers core language features including primitive types, type coercion, scope, closures, and the this keyword with practical examples \n Explains asynchronous patterns: callbacks, Promises, async/await, and the event loop with execution order details \n Includes functional programming concepts like higher-order functions, pure functions, map/filter/reduce, currying, and composition \n Addres

Store and manage API response test fixtures for provider parsing validation. \n \n Fixtures are organized in __fixtures__ subfolders within provider packages, using naming conventions documented in existing examples \n Supports two testing patterns: generateText (log raw response to console and copy into fixture) and streamText (use includeRawChunks and saveRawChunks helper to capture streaming chunks) \n Recommends storing true provider responses unless size constraints require semantic-preserv

Read the migration guide before making changes:

Unified authentication and patterns for building integrations across 11 Google Workspace APIs. \n \n Covers OAuth 2.0 (user context) and service account (server-to-server) authentication with domain-wide delegation support \n Includes rate limit handling, exponential backoff strategies, and per-user/per-project quota reference for Gmail, Calendar, Drive, Sheets, and other APIs \n Provides batch request patterns (up to 100–1000 requests per batch) and Cloudflare Workers configuration for token st

Read the setup guide before making changes:

You are a Python expert specializing in modern Python 3.12+ development with cutting-edge tools and practices from the 2024/2025 ecosystem.

Multimodal AI with Gemini 2.5 and 3 models, supporting text, images, video, audio, PDFs, function calling, thinking mode, and real-time web grounding. \n \n Supports three deployment approaches: Node.js SDK (@google/genai), fetch-based REST API for edge runtimes, and chat helpers for multi-turn conversations \n Handles multimodal inputs (images, video, audio, PDFs) with 1,048,576 token context window; thinking mode enabled by default for enhanced reasoning quality \n Includes function calling wi

Complete reference for OpenAI's stateless APIs including Chat Completions, embeddings, images, audio, and moderation. \n \n Supports GPT-5 series (with reasoning_effort control), GPT-4o multimodal, o3 reasoning models, and legacy GPT-4 variants; streaming, function calling, and structured JSON outputs included \n Embeddings API for RAG with custom dimensions (256–3072), DALL-E 3 image generation, Whisper transcription, and TTS with 11 voices \n Batch API for 50% cost savings on large-scale proce

Use the Google Sheets API via direct curl calls to read, write, and manage spreadsheet data.