core: add focused diagnostics for remote compaction overflows (#11133)

## Summary
- add targeted remote-compaction failure diagnostics in compact_remote
logging
- log the specific values needed to explain overflow timing:
  - last_api_response_total_tokens
  - estimated_tokens_of_items_added_since_last_successful_api_response
  - estimated_bytes_of_items_added_since_last_successful_api_response
  - failing_compaction_request_body_bytes
- simplify breakdown naming and remove
last_api_response_total_bytes_estimate (it was an approximation and not
useful for debugging)

## Why
When compaction fails with context_length_exceeded, we need concrete,
low-ambiguity numbers that map directly to:
1) what the API most recently reported, and
2) what local history added since then.

This keeps the failure logs actionable without adding broad, noisy
metrics.

## Testing
- just fmt
- cargo test -p codex-core

codex-rs/core/src/context_manager/mod.rs

@@ -2,5 +2,7 @@ mod history;
 mod normalize;
 
 pub(crate) use history::ContextManager;
+pub(crate) use history::TotalTokenUsageBreakdown;
+pub(crate) use history::estimate_response_item_model_visible_bytes;
 pub(crate) use history::is_codex_generated_item;
 pub(crate) use history::is_user_turn_boundary;