Blog

Reasoning-capable models have been usable in BoxLang AI for a while. params passes straight through to the provider body, so params: { thinking: { type: "enabled", budget_tokens: 10000 } } for Claude, or params: { reasoning_effort: "high" } for OpenAI, already reached the API. What never worked was reading the reasoning back. It was parsed out on arrival and silently dropped. In 3.4.0, that's fixed, and it's fixed the same way for every provider.

LLM applications face a class of attack traditional input validation was never built for: prompt injection. An attacker embeds instructions in user input, a retrieved document, a web page your tool fetched, or an MCP result, trying to override your system prompt, exfiltrate data, or hijack a tool call. BoxLang AI 3.4.0 ships four layered, configurable defenses against exactly this, plus one more that's on unconditionally.

You call writeDump() on an ORM entity or a very rich class graph . The browser locks up. Thirty seconds later you get a page with forty thousand rows on it, you scroll for a while, you give up, and you go edit your code to dump a sub-key instead. Or worse, you crash the server.

Everyone knows the datasource password should not be sitting in plain text in a config file. Everyone has also, at some point, shipped exactly that, because the alternative was a pile of environment variable plumbing that nobody wanted to build on a deadline. x

Here's a bug that's easy to miss until it bites someone in production: an agent turn asks for two tool calls at once, both need human approval, and only the first one actually suspends. The second one gets silently skipped. Not rejected, not queued, just gone. That's what happened before 3.4.0, and it's fixed now with batched tool-call approvals.

HumanInTheLoopMiddleware used to do everything itself: decide which tool calls needed approval, present the request, and wait for a decision. In 3.4.0, that logic has been pulled apart into a real subsystem, and the piece developers will feel the most is that a human's "always allow this" now actually means always.

Every serious language has a way to ask "is this even parseable?" without running it. bash -n script.sh. node --check file.js. python -m py_compile. As of 1.17.0, BoxLang has one too.

Every AI agent that touches something real eventually needs a human in the loop. Someone has to approve the delete, confirm the wire transfer, or just say "go ahead" before a tool call runs. The question BoxLang AI 3.4.0 answers is: approve it how? A terminal prompt? A webhook? A Slack button?

BoxLang has always been an extensible language. As of 1.17.0, it is a hierarchically extensible one. Every module ecosystem you have worked in is flat. You declare a list of dependencies and something outside the language, a package manager or a build tool, resolves and downloads and orders them. The language itself has no opinion about the shape of the graph. It sees a list, not a tree.

BoxLang has always been an extensible language. As of 1.17.0, it is a hierarchically extensible one. Modules can now contain other modules; aka Module Inception. Recursively. To any depth. Each nested module gets its own class loader, chained to its parent's, and BoxLang's own ModuleService discovers, registers, activates, and unloads that entire tree itself. No package manager. No build tool. No install ordering. Drop in one artifact and everything it depends on comes with it, already wired up and already isolated. Not only that, you can now package modules into a single jar.