feat: add reasoning guardrail connector (NVIDIA-NeMo#1565)

* add reasoning guardrail connector

Signed-off-by: Makesh Sreedhar <makeshn@nvidia.com>

* update reasoning guardrail prompt

Signed-off-by: Makesh Sreedhar <makeshn@nvidia.com>

* feat(content_safety): add reasoning_enabled to prompt ctx

Include the `reasoning_enabled` flag from the content safety config in
the context passed to both input and output content safety check
prompts.
This enables prompt templates to conditionally adjust behavior based on
the reasoning setting. Removes redundant config exposure in
LLMTaskManager's default context.

* revert streamers.py change

* test(content_safety): add Nemotron reasoning parser tests

* Revert "revert streamers.py change"

This reverts commit e916dd4.

* fix: add type ignore for streamer import

* minor updates to docs, example

Signed-off-by: Makesh Sreedhar <makeshn@nvidia.com>

---------

Signed-off-by: Makesh Sreedhar <makeshn@nvidia.com>
Co-authored-by: Pouyanpi <13303554+Pouyanpi@users.noreply.github.com>

Author: makeshn

docs/getting-started/tutorials/index.md

@@ -25,6 +25,13 @@ This section contains tutorials that help you get started with the NeMo Guardrai
 Check text inputs and outputs for harmful content using Nemotron Content Safety NIM.
 :::
 
+:::{grid-item-card} Enforce Custom Safety and Dialogue Policies
+:link: nemotron-content-safety-reasoning-deployment
+:link-type: doc
+
+Enforce customizable content safety and dialogue policies for your use-case by using our reasoning guard model Nemotron-Content-Safety-Reasoning-4B.
+:::
+
 :::{grid-item-card} Restrict Topics
 :link: nemoguard-topiccontrol-deployment
 :link-type: doc
@@ -53,6 +60,7 @@ Add safety checks to images and text using a vision model as LLM-as-a-Judge.
 :maxdepth: 2
 
 Check Harmful Content <nemotron-safety-guard-deployment>
+Content Safety Reasoning <nemotron-content-safety-reasoning-deployment>
 Restrict Topics <nemoguard-topiccontrol-deployment>
 Detect Jailbreak Attempts <nemoguard-jailbreakdetect-deployment>
 Add Multimodal Content Safety <multimodal>