> This page is for version v0.25.0.
> For other versions, use one of these documentation indexes:
> - Latest (default): https://docs.nvidia.com/nemo/guardrails/latest/llms.txt
> - v0.25.0: https://docs.nvidia.com/nemo/guardrails/v0.25.0/llms.txt
> - v0.24.1: https://docs.nvidia.com/nemo/guardrails/v0.24.1/llms.txt
> - v0.24.0: https://docs.nvidia.com/nemo/guardrails/v0.24.0/llms.txt
> - v0.23.0: https://docs.nvidia.com/nemo/guardrails/v0.23.0/llms.txt
> - v0.22.0: https://docs.nvidia.com/nemo/guardrails/v0.22.0/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/guardrails/llms.txt.

# Release Notes

> Review new features, breaking changes, and fixed issues for each release.

The following sections summarize and highlight the changes for the current release.
For a complete record of changes in a release, refer to the
[CHANGELOG.md](https://github.com/NVIDIA-NeMo/Guardrails/blob/develop/CHANGELOG.md) in the GitHub repository.

---

## 0.25.0

Version 0.25.0 expands input, output, and tool checks. It also changes Python
requirements and deprecates the `LLMRails` engine and Colang runtimes.

### Key Features

New integrations and rails extend checks to model requests, tool calls, and languages.

* The experimental [NeMo Guardrails Gateway](/nemo/guardrails/v0.25.0/run-guardrailed-inference/using-gateway)
  applies input and output rails to supported OpenAI Chat Completions and
  Responses requests. It inspects one user text input and one assistant text
  output and supports both buffered and streaming responses.
* The [hooks server](/nemo/guardrails/v0.25.0/run-guardrailed-inference/using-hooks-server/overview)
  checks tool calls before Claude Code, Codex, or NeMo Relay executes them.
  You can allow or block tools by name and check their arguments before execution.
* With `IORails`, you can run [per-tool checks](/nemo/guardrails/v0.25.0/configure-guardrails/guardrail-catalog/tool-calling)
  on arguments and results using regular expressions, Common Expression Language
  (CEL) expressions, or a large language model (LLM) judge.
* The `/v1/checks` endpoint can run per-tool checks independently of generation.
  It reports which tools violated a policy in `tool_violations`.
* The [Language Detector](/nemo/guardrails/v0.25.0/configure-guardrails/guardrail-catalog/language-detector)
  input rail can allow or block messages by language and return a localized
  refusal.
* The library restores input and output moderation with
  [Zscaler AI Guard](/nemo/guardrails/v0.25.0/configure-guardrails/guardrail-catalog/third-party/zscaler-aiguard).

### Breaking Changes

Existing applications can require environment, streaming, or error-handling updates.

* **Python support.** Upgrade Python 3.10 environments to Python 3.11, 3.12,
  or 3.13 before installing this release. Refer to [Installation](/nemo/guardrails/v0.25.0/get-started/installation-guide).
* **Event-loop patching.** If your application enables automatic event-loop
  patching, install `nemoguardrails[nest-asyncio]`. In an application or
  notebook with a running event loop, you can use `await rails.generate_async(...)`.
* **Streaming tool calls.** Python consumers of `IORails` streams now receive
  completed tool calls as `ToolCallChunk` objects. To update a stream consumer:

  1. Read completed calls from `chunk.tool_calls`.
  2. Handle text chunks separately.
* **Jailbreak detection.** The model-based rail rejects messages longer than
  2,048 tokens, including special tokens. If a detector is unavailable or returns
  an invalid result, the request stops with an internal error. To update an
  application that uses this rail:

  1. Keep each message within the token limit.
  2. Ensure the `tokenizers` package is installed for input validation.
  3. Enforce blocked results when using check-only APIs.

  Refer to [Jailbreak Protection](/nemo/guardrails/v0.25.0/configure-guardrails/guardrail-catalog/jailbreak-protection).

### Deprecations

The following engines, runtimes, and configuration names remain available but are deprecated.

* The `LLMRails` engine and the Colang 1.0 and 2.x runtimes are deprecated.
  Removal is planned no earlier than 0.27.0. Before migrating:

  1. Review engine coverage in [Migrating to 0.25](/nemo/guardrails/v0.25.0/reference/0-25), especially
     for dialog flows or a Colang 2.x application.
  2. Use `Guardrails(config)` to run supported configurations on `IORails`.

* The `tool_output` and `tool_input` names remain available as deprecated aliases.
  To update rail configuration and generation options:

  1. Rename `tool_output` to `tool_call`.
  2. Rename `tool_input` to `tool_result`.

### Fixes and Enhancements

Streaming errors, injection handling, and configuration validation have the following updates.

* When the API server encounters a rail execution failure during streaming,
  it sends a terminal server-sent error event. Clients can distinguish a failed
  check from a completed response.
* Injection detection rechecks the text after removing a match and blocks the
  request if it cannot safely remove all matches.
* Configuration loading validates model references in global and per-tool rails.
* Configuration loading suggests supported names when it encounters an unknown
  configuration key.

## Previous Releases

Release-specific documentation preserves the notes for earlier versions.

* [0.24.1](/nemo/guardrails/v0.24.1/about-nemo-guardrails-library/release-notes)
* [0.24.0](/nemo/guardrails/v0.24.0/about-nemo-guardrails-library/release-notes)
* [0.23.0](/nemo/guardrails/v0.23.0/about-nemo-guardrails-library/release-notes)
* [0.22.0](/nemo/guardrails/v0.22.0/about-nemo-guardrails-library/release-notes)
* [0.21.0](https://archive.docs.nvidia.com/nemo/guardrails/0.21.0/index.html)
* [0.20.0](https://archive.docs.nvidia.com/nemo/guardrails/0.20.0/index.html)
* [0.19.0](https://archive.docs.nvidia.com/nemo/guardrails/0.19.0/index.html)
* [0.18.0](https://archive.docs.nvidia.com/nemo/guardrails/0.18.0/index.html)
* [0.17.0](https://archive.docs.nvidia.com/nemo/guardrails/0.17.0/index.html)
* [0.16.0](https://archive.docs.nvidia.com/nemo/guardrails/0.16.0/index.html)
* [0.15.0](https://archive.docs.nvidia.com/nemo/guardrails/0.15.0/index.html)
* [0.14.1](https://archive.docs.nvidia.com/nemo/guardrails/0.14.1/index.html)