`ChatAnthropic(stream_usage=False)` also drops `stop_reason`, `stop_sequence` and `model_name` from `response_metadata`, not just usage metadata

### 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 - [x] 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 - [ ] langchain-openrouter - [ ] langchain-perplexity - [ ] langchain-qdrant - [ ] langchain-xai - [ ] Other / not sure / general ### Related Issues / PRs #39333 is the same class of defect in `langchain-openrouter` (a `stream_usage` flag suppressing provider metadata that is unrelated to usage) and was fixed in #39338. ### Reproduction Steps / Example Code (Python) ```python # Self-contained: no API key and no network needed. Only the transport is # stubbed; the whole `_stream` / `_generate` path runs unmodified. from unittest.mock import patch from anthropic.types import ( Message, MessageDeltaUsage, RawContentBlockDeltaEvent, RawMessageDeltaEvent, RawMessageStartEvent, TextBlock, TextDelta, Usage, ) from anthropic.types.raw_message_delta_event import Delta from langchain_anthropic import ChatAnthropic MODEL = "claude-sonnet-4-5-20250929" # A response that was cut off by `max_tokens`, i.e. `stop_reason="max_tokens"`. non_streaming_response = …