@hebo-ai/gateway 0.9.4 → 0.10.0

package/README.md

@@ -12,9 +12,9 @@ Learn more in our blog post: [Yet Another AI Gateway?](https://hebo.ai/blog/2601
 
 ## 🍌 Features
 
-- 🌐 OpenAI-compatible /chat/completions, /embeddings & /models endpoints.
-- 🔄 /responses endpoint implementing the Open Responses API (stateless).
-- 💬 /conversations endpoint built on top of the Responses API.
+- 🌐 OpenAI-compatible `/chat/completions`, `/embeddings` & `/models` endpoints.
+- 💬 Open Responses `/responses` endpoint (stateless), including /conversations.
+- 🗨️ Anthropic-compatible `/messages` endpoint.
 - 🔌 Integrate into your existing Hono, Elysia, Next.js & TanStack apps.
 - 🧩 Provider registry compatible with Vercel AI SDK providers.
 - 🧭 Canonical model IDs and parameter naming across providers.
@@ -40,7 +40,7 @@ bun install @hebo-ai/gateway
 - Runtime Support
   - [Vercel Edge](#vercel-edge) | [Cloudflare Workers](#cloudflare-workers) | [Deno Deploy](#deno-deploy) | [AWS Lambda](#aws-lambda)
 - Endpoints
-  - [/chat/completions](#chatcompletions) | [/embeddings](#embeddings) | [/models](#models) | [/responses](#responses) | [/conversations](#conversations)
+  - [/chat/completions](#chatcompletions) | [/embeddings](#embeddings) | [/models](#models) | [/responses](#responses) | [/messages](#messages) | [/conversations](#conversations)
 - OpenAI Extensions
   - [Reasoning](#reasoning) | [Service Tier](#service-tier) | [Prompt Caching](#prompt-caching) | [Compressed Requests](#compressed-requests)
 - Advanced Usage
@@ -584,7 +584,7 @@ export const handler = awsLambdaEventHandler({
 
 ## 🚀 Endpoints
 
-Hebo Gateway provides several OpenAI-compatible and standard-based endpoints.
+Hebo Gateway provides OpenAI-, OpenResponses- and Anthropic-compatible endpoints.
 
 ### `/chat/completions`
 
@@ -665,6 +665,19 @@ It supports:
 - **`include`**: Selective response fields (e.g., `logprobs`, `reasoning.encrypted_content`, and tool-specific outputs).
 - **`stream_options.include_obfuscation`**: Normalizing payload sizes to mitigate side-channel attacks.
 
+### `/messages`
+
+Hebo Gateway provides a `/messages` endpoint compatible with the [Anthropic Messages API](https://docs.anthropic.com/en/api/messages).
+
+Official documentation: [Anthropic Messages API Reference](https://docs.anthropic.com/en/api/messages)
+
+It supports:
+
+- The same models, providers, hooks, and extensions as `/chat/completions`.
+- Anthropic Messages API request/response format.
+- Streaming responses.
+- Tool use and multimodal inputs.
+
 ### `/conversations`
 
 Hebo Gateway provides a dedicated `/conversations` endpoint for managing persistent conversation state. It is designed as an extension of the [OpenAI Conversations API](https://developers.openai.com/api/reference/resources/conversations/methods/create) and supports standard CRUD operations alongside advanced listing with metadata filtering.
@@ -792,10 +805,9 @@ Provider behavior:
 - **Google Gemini**: maps `cached_content` to Gemini `cachedContent`.
 - **Amazon Nova (Bedrock)**: maps `cache_control` to Bedrock `cachePoints` and inserts an automatic cache point on a stable prefix when none is provided.
 
-
 ### Compressed Requests
 
-The gateway supports gzip and deflate compressed request bodies via the Web Compression Streams API. The `maxBodySize` option controls the maximum *decompressed* body size for these compressed requests, protecting against gzip bombs and oversized payloads.
+The gateway supports gzip and deflate compressed request bodies via the Web Compression Streams API. The `maxBodySize` option controls the maximum _decompressed_ body size for these compressed requests, protecting against gzip bombs and oversized payloads.
 
 ```ts
 import { gateway } from "@hebo-ai/gateway";
@@ -811,7 +823,7 @@ const gw = gateway({
 Compressed requests that exceed this limit after decompression receive an HTTP `413 Payload Too Large` response. Unsupported `Content-Encoding` values return HTTP `415 Unsupported Media Type`.
 
 > [!IMPORTANT]
-> **Plain (uncompressed) request body size limits** are *not* enforced by the gateway — they should be configured at the framework or server level. The gateway only enforces `maxBodySize` on decompressed output, since the framework cannot know the decompressed size ahead of time.
+> **Plain (uncompressed) request body size limits** are _not_ enforced by the gateway — they should be configured at the framework or server level. The gateway only enforces `maxBodySize` on decompressed output, since the framework cannot know the decompressed size ahead of time.
 >
 > Framework-level configuration examples:
 >
@@ -1122,10 +1134,9 @@ Non-streaming versions are available via `toChatCompletionsResponse`. Equivalent
 > [!TIP]
 > Since Zod v4.3 you can generate a JSON Schema from any zod object by calling `z.toJSONSchema(...)`. This is useful for producing OpenAPI documentation from the same source of truth.
 
-
 ### Request Body Size
 
-The gateway supports gzip and deflate compressed request bodies via the Web Compression Streams API. The `maxBodySize` option controls the maximum *decompressed* body size for these compressed requests, protecting against gzip bombs and oversized payloads.
+The gateway supports gzip and deflate compressed request bodies via the Web Compression Streams API. The `maxBodySize` option controls the maximum _decompressed_ body size for these compressed requests, protecting against gzip bombs and oversized payloads.
 
 ```ts
 import { gateway } from "@hebo-ai/gateway";
@@ -1141,7 +1152,7 @@ const gw = gateway({
 Compressed requests that exceed this limit after decompression receive an HTTP `413 Payload Too Large` response. Unsupported `Content-Encoding` values return HTTP `415 Unsupported Media Type`.
 
 > [!IMPORTANT]
-> **Plain (uncompressed) request body size limits** are *not* enforced by the gateway — they should be configured at the framework or server level. The gateway only enforces `maxBodySize` on decompressed output, since the framework cannot know the decompressed size ahead of time.
+> **Plain (uncompressed) request body size limits** are _not_ enforced by the gateway — they should be configured at the framework or server level. The gateway only enforces `maxBodySize` on decompressed output, since the framework cannot know the decompressed size ahead of time.
 >
 > Framework-level configuration examples:
 >
@@ -1150,4 +1161,4 @@ Compressed requests that exceed this limit after decompression receive an HTTP `
 > - **Hono** — [`bodyLimit` middleware](https://hono.dev/docs/middleware/builtin/body-limit): `app.use(bodyLimit({ maxSize: 10 * 1024 * 1024 }))`
 > - **Express** — [`express.json({ limit: '10mb' })`](https://expressjs.com/en/api.html#express.json)
 > - **Fastify** — [`fastify({ bodyLimit: 10485760 })`](https://fastify.dev/docs/latest/Reference/Server/#bodylimit)
-> - **Node.js `http`** — [`server.maxRequestSize`](https://nodejs.org/api/http.html) (v22.6+), or use a reverse proxy like nginx (`client_max_body_size 10m`)
+> - **Node.js `http`** — [`server.maxRequestSize`](https://nodejs.org/api/http.html) (v22.6+), or use a reverse proxy like nginx (`client_max_body_size 10m`)