feat(openrouter/nvidia/nemotron-3.5-lightning): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for openrouter/nvidia/nemotron-3.5-lightning.

---

Note

Low Risk
Additive model metadata only; no runtime logic, auth, or data-handling changes.

Overview
Adds OpenRouter support for nvidia/nemotron-3.5-lightning, a text chat model with thinking enabled, a 262K context window, and prompt caching / structured output features.

^{Reviewed by Cursor Bugbot for commit d8bf879. Bugbot is set up for automated code reviews on this repo. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit d8bf879. Configure here.}

[cursor]

Missing tool-calling feature flags

Medium Severity

features lists json_output, prompt_caching, and structured_output, but omits function_calling and tool_choice. Lightning is an agentic execution model, and sibling OpenRouter Nemotron chat configs declare those tool flags. Without them, consumers of this registry will treat the model as non-tool-capable.

 

^{Reviewed by Cursor Bugbot for commit d8bf879. Configure here.}