Summary

• use estimate_request_tokens_rough(...) when updating last_prompt_tokens after context compression
• include tool schema tokens in the post-compression estimate so the next compression cycle is scheduled against the real request size
• add a regression test covering _compress_context() with a large tool schema

Closes #14695

Testing

• python3 -m pytest -o addopts= tests/run_agent/test_context_token_tracking.py