Microservice that wraps headroom-ai as a LiteLLM pre_call guardrail.
Compresses tool outputs and JSON arrays before they reach the LLM
provider using headroom's smart_crusher (JSON dedup + schema compression)
and kompress (prose/log compression). Returns compressed structured_messages
via the generic guardrail API, which required adding structured_messages
support to GenericGuardrailAPIResponse.
