Using compaction causes Anthropic's API to fail when agent invoked with print_mode="messages" or when streaming with stream_mode="messages"

### 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 _No response_ ### Reproduction Steps / Example Code (Python) ```python import anthropic from langchain.agents import create_agent from langchain_anthropic import ChatAnthropic from langchain_core.messages import HumanMessage model = ChatAnthropic( model="claude-sonnet-4-6", betas=["compact-2026-01-12"], max_tokens=8000, context_management={ "edits": [ { "type": "compact_20260112", "trigger": {"type": "input_tokens", "value": 50000}, } ] }, ) agent = create_agent( model=model, ) client = anthropic.Anthropic() SYSTEM_MESSAGE = "You are a helpful assistant that answers questions thoroughly and in great detail." FILLER_PARAGRAPH = FILLER_PARAGRAPH = ( "Brand24 is a social listening and media monitoring platform that helps busines…