// Use when calling OpenAI Chat Completions through Fetcher, configuring OpenAI or ChatClient, sending streaming or non-streaming chat completion requests, adding interceptors, using completion result extractors, or handling OpenAI client errors.
| name | fetcher-openai-client |
| description | Use when calling OpenAI Chat Completions through Fetcher, configuring OpenAI or ChatClient, sending streaming or non-streaming chat completion requests, adding interceptors, using completion result extractors, or handling OpenAI client errors. |
OpenAI, ChatClient, chat completions, streaming completions, or completion result extractors.@ahoo-wang/fetcher-openai package rather than general OpenAI platform usage.OpenAI entry point before using ChatClient directly.references/api.md for class APIs, type shapes, streaming examples, and error handling patterns.fetcher-llm-streaming covers the stream mechanics.references/api.md: Detailed package API, examples, and edge-case guidance. Load it only when the task needs OpenAI and ChatClient APIs, chat completion types, streaming and non-streaming examples, interceptors, and error handling snippets.Use when implementing CoSec authentication with Fetcher, including CoSecConfigurer, JWT token lifecycle, token storage, refresh handling, device ID storage, multi-tenant space resolution, resource attribution, authorization headers, and 401 or 403 error handling.
Use when creating declarative TypeScript API service classes with fetcher-decorator, including @api, HTTP method decorators, path/query/header/body/request parameters, result extractors, lifecycle hooks, inheritance, and reflect-metadata setup.
Use when implementing typed event buses, serial or parallel event execution, BroadcastChannel or storage-based cross-tab messaging, handler priority, once handlers, name generation, or event synchronization across browser contexts.
Use when setting up the core Fetcher HTTP client, NamedFetcher, fetcherRegistrar, HTTP methods, path and query parameters, interceptors, timeouts, result extractors, request lifecycle, status validation, or URL templates.
Use when consuming Server-Sent Events, LLM token streams, OpenAI-style streaming chat responses, Fetcher eventstream helpers, response prototype extensions, stream termination detection, result extractors, or ReadableStream async iteration.
Use when generating type-safe Fetcher API clients from OpenAPI 3.x specs, including fetcher-generator CLI usage, CodeGenerator API, GeneratorConfiguration, parse and generation pipeline, model generation, client generation, barrel exports, and Wow CQRS generation support.