Errors OpenRouter reports in a 200 response body are stringified rather than classified

### Submission checklist - [x] This is a bug, not a usage question. - [x] I added a clear and descriptive title that summarizes this issue. - [x] I used the GitHub search to find a similar question and didn't find it. - [x] I am sure that this is a bug in LangChain rather than my code. - [x] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package). - [x] This is not related to the langchain-community package. - [x] I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS. ### 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 ### Related Issues / PRs * #39538 — added the standard model exception types this asks for (merged). * #39884 — draft classifying `ChatOpenRouter` errors from **raised SDK exceptions**; its diff does not touch the body-borne sites below, so the two are complementary. * #40362 — the same defect in `langchain-openai`, from a different direction. ### Reproduction Steps / Example Code (Python) ```python import json import threading from http.server import BaseHTTPRequestHandler, HTTPServer from langchain_core.exceptions import ModelError # What OpenRouter sends for an upstream fault: HTTP 200, error in the body. STREAM_CHUNK = { "id": "gen-1", "object": "chat.completion.chunk", "created": 1, "model": "x/y", "choices": [], "error": {"code": 502, "message": "Provider returned error"}, } COMPLETION = { "id": "gen-1", "object": "chat.completion…