> For the complete documentation index, see [llms.txt](https://ai.ortusbooks.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai.ortusbooks.com/introduction/release-history/3.3.0.md).

# 3.3.0

BoxLang AI Module 3.3.0 — Bedrock tool-use support for Claude models, MCP CORS fix, and housekeeping.

**Released:** May 2026

BoxLang AI 3.3.0 brings AWS Bedrock's Claude models up to feature parity with the direct Anthropic API by adding **native tool/function calling** support, alongside an MCP CORS fix and general housekeeping.

***

## ✨ New Features

### 🪨 BedrockService Tool-Use Support for Claude Models

AWS Bedrock's Claude models now support native tool/function calling, matching the feature set of the direct Anthropic API. ([#190](https://github.com/ortus-boxlang/bx-ai/issues/190))

* `formatToolsForClaude()` converts OpenAI-compatible tool schemas to the Claude-native `input_schema` format.
* `executeBedrockTool()` processes Claude `tool_use` blocks, invokes the registered tool, and appends `tool_result` messages back into the conversation.
* Multi-turn tool conversations are preserved by correctly handling structured content (arrays of `tool_use`/`tool_result` blocks) without flattening them via `toString()`.

```javascript
agent = aiAgent(
    name  : "BedrockToolAgent",
    model : aiModel( "bedrock", { params: { model: "anthropic.claude-3-5-sonnet-20241022-v2:0" } } ),
    tools : [ weatherTool, calcTool ]
)

response = agent.run( "What's 15% of the temperature in Miami?" )
```

***

## 🪲 Fixed

* **MCPRequestProcessor CORS parameter collision**: Renamed the `mcpServer` parameter in `handleCORSPreflight()` to `targetServer` to avoid a case-insensitive name collision with the `MCPServer` import, which caused the stricter BoxLang compiler to reject the file and 500 every MCP request.

***

## 🧠 Updated

* Removed obsolete scheduler test stubs (`DataProcessingScheduler.bx`, `ReportingScheduler.bx`).
* Added Spreadsheet Loader integration documentation to the README.

***

## 📖 Documentation

* [Working with Models](https://ai.ortusbooks.com/advanced/models.md) — Provider configuration, including Bedrock
* [AI Tools (Function Calling)](https://ai.ortusbooks.com/main-components/tools.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://ai.ortusbooks.com/introduction/release-history/3.3.0.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
