feat(openrouter): implement missing Rerank component for existing partner package

### Submission checklist - [x] This is a feature request, not a bug report or usage question. - [x] I added a clear and descriptive title that summarizes the feature request. - [x] I used the GitHub search to find a similar feature request and didn't find it. - [x] I checked the LangChain documentation and API reference to see if this feature already exists. - [x] This is not related to the langchain-community package. ### Package (Required) - [ ] langchain - [ ] langchain-openai - [ ] langchain-anthropic - [ ] langchain-classic - [ ] langchain-core - [ ] langchain-model-profiles - [ ] langchain-tests - [ ] langchain-text-splitters - [ ] langchain-chroma - [ ] langchain-deepseek - [ ] langchain-exa - [ ] langchain-fireworks - [ ] langchain-groq - [ ] langchain-huggingface - [ ] langchain-mistralai - [ ] langchain-nomic - [ ] langchain-ollama - [x] langchain-openrouter - [ ] langchain-perplexity - [ ] langchain-qdrant - [ ] langchain-xai - [ ] Other / not sure / general ### Feature Description I would like LangChain to support native document reranking capabilities within the existing `libs/partners/openrouter` partner package. This feature would allow users to instantiate an `OpenRouterRerank` class inheriting directly from `langchain_core.documents.BaseDocumentCompressor`, providing a streamlined, official way to condense and re-order context documents within retrieval pipelines via OpenRouter's API endpoints. ### Use Case I'm trying to build an application that utilizes a unified Retrieval-Augmented Generation (RAG) architecture relying completely on OpenRouter endpoints for both context generation and document context compression. Currently, I have to work around this by pulling in alternative third-party vendor libraries or general-purpose OpenAI custom cross-encoder wrappers just to handle document reranking, which forces an unnecessary fragmentation of integrations and API configurations. This feature would help me/users to cleanly implement localized document…