feat(compact): complete remaining issue #30 items

[crstrn13]

Summary

Completes the remaining work items from #30:

• Use previous_usage for token estimation — should_compact() checks the stored usage.total_tokens from the rehydrated response before falling back to local tiktoken counting
• Configurable summary prefix — summary_prefix config option (default: [Previous conversation summary]) carried through to compaction items and both translation paths
• Hide compaction items from input_items API — normalize_input_items() filters out {"type": "compaction"} items so clients never see internal state
• Persist compaction as a stored response — after summarization, the compacted response is written back to the response store with the compaction item in its input
• Explicit compact endpoint — POST /v1/responses/{id}/compact triggers compaction on a previously stored response

Test plan

• cargo test -p praxis-ai-apis — new unit tests for all 5 items
• cargo test -p praxis-ai-filters — no regressions in filter tests
• make lint passes
• Manual test with example config against a real inference backend