ai-sdk-provider-env 0.2.0 → 0.4.0

package/README.md

@@ -1,60 +1,38 @@
-> [中文](./README_zh.md)
+> [For AI agent (llms.txt)](./llms.txt) | [中文](./README_zh.md)
 
 # ai-sdk-provider-env
 
-A dynamic, environment-variable-driven provider for [Vercel AI SDK](https://sdk.vercel.ai/). Resolves AI provider configuration from env var conventions at runtime, so you can switch models without touching code.
+Environment-variable-driven provider for [Vercel AI SDK](https://sdk.vercel.ai/). Switch AI providers and models without code changes.
 
 [![npm version](https://img.shields.io/npm/v/ai-sdk-provider-env)](https://www.npmjs.com/package/ai-sdk-provider-env)
 [![license](https://img.shields.io/npm/l/ai-sdk-provider-env)](./LICENSE)
 
-## Motivation
-
-Using multiple AI providers with Vercel AI SDK means importing each SDK, configuring API keys and base URLs, and wiring everything together — per provider, per project. Switching providers requires code changes.
-
-`ai-sdk-provider-env` eliminates this boilerplate. Define provider configurations through environment variables, resolve them at runtime. Add a new provider by setting env vars, switch models by changing a string — no code changes needed.
-
-## Features
-
-- Resolve provider config (base URL, API key, compatibility mode) from environment variables automatically
-- Built-in presets for popular providers, so you only need to set an API key
-- Supports OpenAI, Anthropic, Google Gemini, and any OpenAI-compatible API
-- Implements `ProviderV3`, plugs directly into `createProviderRegistry`
-- Provider instances are cached, no redundant initialization
-- Fully customizable: custom fetch, env-based headers, custom separator, code-based configs
-
-## Installation
+## Quick Start
 
 ```bash
 pnpm add ai-sdk-provider-env
 ```
 
-Install provider SDKs as needed:
-
 ```bash
-pnpm add @ai-sdk/openai            # for OpenAI
-pnpm add @ai-sdk/anthropic         # for Anthropic
-pnpm add @ai-sdk/google            # for Google AI Studio (Gemini)
-pnpm add @ai-sdk/openai-compatible # for generic OpenAI-compatible APIs
+# .env
+OPENAI_API_KEY=sk-xxx
 ```
 
-## Quick Start
-
 ```ts
-import { createProviderRegistry, generateText } from 'ai'
+import { generateText } from 'ai'
 import { envProvider } from 'ai-sdk-provider-env'
 
-const registry = createProviderRegistry({
-  env: envProvider(),
-})
-
-// Use a preset: only API_KEY is required
-// OPENAI_API_KEY=sk-xxx  (OPENAI_PRESET=openai is optional — auto-detected)
-const model = registry.languageModel('env:openai/gpt-4o')
+const provider = envProvider()
 
-const { text } = await generateText({ model, prompt: 'Hello!' })
+const { text } = await generateText({
+  model: provider.languageModel('openai/gpt-4o'),
+  prompt: 'Hello!',
+})
 ```
 
-Any env var prefix is a config set. Two endpoints? Two prefixes, zero code changes:
+The config set name `openai` auto-matches the built-in preset — only an API key is needed.
+
+Any [valid](#environment-variables) env var prefix becomes a config set. Two endpoints, zero code changes:
 
 ```bash
 # .env
@@ -66,235 +44,86 @@ SMART_API_KEY=key-smart
 ```
 
 ```ts
-const draft = await generateText({
-  model: registry.languageModel('env:fast/llama-3-8b'),
-  prompt: 'Write a story',
-})
-
-const review = await generateText({
-  model: registry.languageModel('env:smart/gpt-4o'),
-  prompt: `Review this: ${draft.text}`,
-})
+provider.languageModel('fast/llama-3-8b')
+provider.languageModel('smart/gpt-4o')
 ```
 
-## Environment Variable Convention
+## Environment Variables
 
-The model ID format is `{configSet}/{modelId}`. The config set name maps to an env var prefix (uppercased).
-
-With the default separator `_`, a config set reads these variables (`[MYAI]` = your config set name, uppercased):
-
-| Variable | Required | Description |
-|---|---|---|
-| `[MYAI]_API_KEY` | Yes | API key |
-| `[MYAI]_BASE_URL` | Yes (unless preset is set or auto-detected) | API base URL |
-| `[MYAI]_PRESET` | No | Built-in preset name (e.g. `openai`) |
-| `[MYAI]_COMPATIBLE` | No | Compatibility mode (default: `openai-compatible`) |
-| `[MYAI]_HEADERS` | No | Custom HTTP headers (JSON format) |
+Model ID format: `{configSet}/{modelId}`. The config set maps to an uppercased env var prefix.
 
-When `PRESET` is set, `BASE_URL` and `COMPATIBLE` become optional and fall back to the preset's values.
-
-**Compatibility modes:**
-
-| Value | Behavior |
-|---|---|
-| `openai` | Uses `@ai-sdk/openai` |
-| `anthropic` | Uses `@ai-sdk/anthropic` |
-| `gemini` | Uses `@ai-sdk/google` |
-| `openai-compatible` | Uses `@ai-sdk/openai-compatible` with the config set name as the provider name (default) |
-
-## Built-in Presets
-
-| Preset name | Base URL | Compatible |
-|---|---|---|
-| `openai` | `https://api.openai.com/v1` | `openai` |
-| `anthropic` | `https://api.anthropic.com` | `anthropic` |
-| `google` | `https://generativelanguage.googleapis.com/v1beta` | `gemini` |
-| `deepseek` | `https://api.deepseek.com` | `openai-compatible` |
-| `zhipu` | `https://open.bigmodel.cn/api/paas/v4` | `openai-compatible` |
-| `groq` | `https://api.groq.com/openai/v1` | `openai-compatible` |
-| `together` | `https://api.together.xyz/v1` | `openai-compatible` |
-| `fireworks` | `https://api.fireworks.ai/inference/v1` | `openai-compatible` |
-| `mistral` | `https://api.mistral.ai/v1` | `openai-compatible` |
-| `moonshot` | `https://api.moonshot.cn/v1` | `openai-compatible` |
-| `perplexity` | `https://api.perplexity.ai` | `openai-compatible` |
-| `openrouter` | `https://openrouter.ai/api/v1` | `openai-compatible` |
-| `siliconflow` | `https://api.siliconflow.cn/v1` | `openai-compatible` |
-
-## Preset Auto-Detect
-
-`presetAutoDetect` is enabled by default. When the config set name exactly matches a built-in preset name, the preset is applied automatically — no `_PRESET` env var needed. Only an API key is required:
+Config set names must match `[A-Za-z_][A-Za-z0-9_-]*` — ASCII letters, digits, underscores, and hyphens. **Hyphens are automatically normalized to underscores** for env var lookup:
 
 ```bash
-# OPENROUTER_API_KEY is all you need
-OPENROUTER_API_KEY=sk-or-xxx
-```
-
-```ts
-const provider = envProvider()
-
-// Works — openrouter preset auto-detected from config set name
-const model = provider.languageModel('openrouter/some-model')
+# Config set "my-api" → reads MY_API_* env vars
+MY_API_BASE_URL=https://api.example.com/v1
+MY_API_API_KEY=sk-xxx
 ```
 
-Explicit `_PRESET` and `_BASE_URL` env vars always take precedence over auto-detect. To disable this behavior:
-
 ```ts
-envProvider({ presetAutoDetect: false })
+provider.languageModel('my-api/some-model')  // reads MY_API_* env vars
+provider.languageModel('my_api/some-model')  // same env vars
 ```
 
-## API Reference
-
-### `envProvider(options?)`
-
-Returns a `ProviderV3` instance.
-
-```ts
-import { envProvider } from 'ai-sdk-provider-env'
-
-const provider = envProvider(options)
-```
-
-**Options** (`EnvProviderOptions`):
-
-| Option | Type | Default | Description |
-|---|---|---|---|
-| `separator` | `string` | `'_'` | Separator between the prefix and the variable name |
-| `configs` | `Record<string, ConfigSetEntry>` | `undefined` | Explicit config sets (takes precedence over env vars) |
-| `defaults` | `EnvProviderDefaults` | `undefined` | Global defaults applied to all providers (can be overridden per config set) |
-| `presetAutoDetect` | `boolean` | `true` | Auto-apply a built-in preset when the config set name matches. Set to `false` to require explicit `_PRESET` configuration. |
-
-**`EnvProviderDefaults`:**
-
-| Option | Type | Default | Description |
-|---|---|---|---|
-| `fetch` | `typeof globalThis.fetch` | `undefined` | Custom fetch implementation passed to all created providers |
-| `headers` | `Record<string, string>` | `undefined` | Default HTTP headers for all providers (overridden by config-set headers) |
-
-**`ConfigSetEntry`:**
+> For config set names outside these rules (e.g. Unicode, dots), use the [`configs` option](./docs/advanced.md#code-based-configs) instead.
 
-```ts
-interface ConfigSetEntry {
-  apiKey: string
-  preset?: string
-  baseURL?: string
-  compatible?: 'openai' | 'anthropic' | 'gemini' | 'openai-compatible' // default: 'openai-compatible'
-  headers?: Record<string, string>
-}
-```
-
-**Model ID format:**
-
-```
-{configSet}/{modelId}
-```
-
-Examples: `openai/gpt-4o`, `anthropic/claude-sonnet-4-20250514`, `myapi/some-model`.
-
-## Advanced Usage
-
-### Custom separator
-
-If single underscores conflict with your naming scheme, use double underscores or any other string:
-
-```ts
-const provider = envProvider({ separator: '__' })
-
-// Now reads: OPENAI__BASE_URL, OPENAI__API_KEY, OPENAI__PRESET, OPENAI__COMPATIBLE
-```
-
-### Code-based configs
-
-Skip env vars entirely and pass config directly. This takes the highest precedence:
-
-```ts
-const provider = envProvider({
-  configs: {
-    openai: {
-      baseURL: 'https://api.openai.com/v1',
-      apiKey: process.env.OPENAI_KEY!,
-      compatible: 'openai',
-    },
-    claude: {
-      baseURL: 'https://api.anthropic.com',
-      apiKey: process.env.ANTHROPIC_KEY!,
-      compatible: 'anthropic',
-    },
-    deepseek: {
-      preset: 'deepseek',
-      apiKey: process.env.DEEPSEEK_KEY!,
-    },
-  },
-})
-
-const model = provider.languageModel('openai/gpt-4o')
-```
-
-### Custom fetch
-
-Pass a custom fetch implementation to all providers. Useful for proxies, logging, or test mocks:
+| Variable | Required | Description |
+|---|---|---|
+| `{PREFIX}_API_KEY` | Yes | API key |
+| `{PREFIX}_BASE_URL` | Unless preset matches | API base URL |
+| `{PREFIX}_PRESET` | No | Built-in preset name (e.g. `openai`) |
+| `{PREFIX}_COMPATIBLE` | No | `openai` · `anthropic` · `gemini` · `openai-compatible` (default) |
+| `{PREFIX}_HEADERS` | No | Custom HTTP headers (JSON) |
 
-```ts
-const provider = envProvider({ defaults: { fetch: myCustomFetch } })
-```
+When `_PRESET` is set or [auto-detected](#built-in-presets), `_BASE_URL` and `_COMPATIBLE` fall back to preset defaults.
 
-### Default headers
+### Compatibility modes
 
-Set HTTP headers that apply to all providers. Per-config-set headers (from env vars or code configs) override defaults with the same key:
+| Value | SDK | Fallback |
+|---|---|---|
+| `openai` | `@ai-sdk/openai` | `@ai-sdk/openai-compatible` if not installed |
+| `anthropic` | `@ai-sdk/anthropic` | None |
+| `gemini` | `@ai-sdk/google` | None |
+| `openai-compatible` | `@ai-sdk/openai-compatible` (default) | — |
 
-```ts
-const provider = envProvider({
-  defaults: {
-    headers: { 'X-App-Name': 'my-app', 'X-Request-Source': 'server' },
-  },
-})
-```
+Install provider SDKs as needed: `pnpm add @ai-sdk/openai @ai-sdk/anthropic @ai-sdk/google`
 
-### Custom headers via env vars
+## Built-in Presets
 
-Set per-config-set HTTP headers using the `HEADERS` env var. The value must be valid JSON:
+When the config set name matches a preset, it auto-applies — only `_API_KEY` is needed:
 
 ```bash
-OPENAI_HEADERS={"X-Custom":"value","X-Request-Source":"my-app"}
+DEEPSEEK_API_KEY=sk-xxx          # config set "deepseek" matches the preset
 ```
 
-These headers are merged into every request made by that config set's provider. When combined with `defaults.headers`, config-set headers take precedence for the same key.
-
-### Using with `createProviderRegistry`
-
-`envProvider()` implements `ProviderV3`, so it works directly with `createProviderRegistry`:
-
 ```ts
-import { createProviderRegistry, generateText } from 'ai'
-import { envProvider } from 'ai-sdk-provider-env'
-
-const registry = createProviderRegistry({
-  env: envProvider(),
-})
-
-// Language model
-const model = registry.languageModel('env:openai/gpt-4o')
-
-// Embedding model
-const embedder = registry.embeddingModel('env:openai/text-embedding-3-small')
-
-// Image model
-const imageModel = registry.imageModel('env:openai/dall-e-3')
-
-const { text } = await generateText({
-  model,
-  prompt: 'Hello!',
-})
+provider.languageModel('deepseek/deepseek-chat')   // just works
 ```
 
-The model ID format inside the registry is `{registryKey}:{configSet}/{modelId}`. With the setup above, `env:openai/gpt-4o` means config set `openai`, model `gpt-4o`.
+| Preset | Base URL | Compatible |
+|---|---|---|
+| `openai` | `https://api.openai.com/v1` | `openai` |
+| `anthropic` | `https://api.anthropic.com` | `anthropic` |
+| `google` | `https://generativelanguage.googleapis.com/v1beta` | `gemini` |
+| `deepseek` | `https://api.deepseek.com` | `openai-compatible` |
+| `groq` | `https://api.groq.com/openai/v1` | `openai-compatible` |
+| `together` | `https://api.together.xyz/v1` | `openai-compatible` |
+| `fireworks` | `https://api.fireworks.ai/inference/v1` | `openai-compatible` |
+| `mistral` | `https://api.mistral.ai/v1` | `openai-compatible` |
+| `moonshot` | `https://api.moonshot.ai/v1` | `openai-compatible` |
+| `moonshot-china` | `https://api.moonshot.cn/v1` | `openai-compatible` |
+| `perplexity` | `https://api.perplexity.ai` | `openai-compatible` |
+| `openrouter` | `https://openrouter.ai/api/v1` | `openai-compatible` |
+| `siliconflow` | `https://api.siliconflow.com/v1` | `openai-compatible` |
+| `siliconflow-china` | `https://api.siliconflow.cn/v1` | `openai-compatible` |
+| `xai` | `https://api.x.ai/v1` | `openai-compatible` |
+| `zai` | `https://api.z.ai/api/paas/v4` | `openai-compatible` |
+| `zhipu` | `https://open.bigmodel.cn/api/paas/v4` | `openai-compatible` |
 
-You can also mount multiple providers side by side:
+To disable auto-detection: `envProvider({ presetAutoDetect: false })`. See [Advanced Usage](./docs/advanced.md#preset-auto-detect) for details.
 
-```ts
-import { createOpenAI } from '@ai-sdk/openai'
+## Documentation
 
-const registry = createProviderRegistry({
-  env: envProvider(),
-  openai: createOpenAI({ apiKey: process.env.OPENAI_API_KEY }),
-})
-```
+- **[API Reference](./docs/api-reference.md)** — `envProvider()` options, types, model ID format
+- **[Advanced Usage](./docs/advanced.md)** — Code-based configs, custom fetch/headers, custom separator, provider registry
+- **[Bundler Usage](./docs/bundler.md)** — For `bun build`, `vite build`, and other bundlers