> 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/3.3.2.md).

# 3.3.2

BoxLang AI Module 3.3.2 — Fix for Claude structured output via a synthetic tool-forcing workaround.

**Released:** June 2026

BoxLang AI 3.3.2 is a targeted patch release fixing structured output support for Claude models.

***

## 🪲 Fixed

* **Claude structured output via synthetic tool**: Claude models lack OpenAI-style `response_format`, so structured output was silently unsupported — the schema was never sent and `populateStructuredOutput()` failed parsing the model's prose. Fixed by injecting a synthetic `structured_output` tool (requested schema as `input_schema`), pinning `tool_choice` to it, and routing the returned `tool_use.input` through `populateStructuredOutput()`. Now fails loud with `StructuredOutputError` and an ai-log entry when the forced tool block is absent (max\_tokens truncation, refusal, or `tool_choice` not honored) instead of feeding prose into the JSON populator. ([#198](https://github.com/ortus-boxlang/bx-ai/issues/198))

This fix applies to both the direct Anthropic API and Claude models accessed through AWS Bedrock. No code changes are required — existing `.structuredOutput()` calls against Claude models now work correctly.

***

## 📖 Documentation

* [Structured Output](https://ai.ortusbooks.com/main-components/pipelines/structured-output.md) — `.structuredOutput()` and schema-driven extraction


---

# 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/3.3.2.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.
