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/truncate.rs

@@ -304,6 +304,14 @@ pub(crate) fn approx_tokens_from_byte_count(bytes: usize) -> u64 {
         / (APPROX_BYTES_PER_TOKEN as u64)
 }
 
+pub(crate) fn approx_tokens_from_byte_count_i64(bytes: i64) -> i64 {
+    if bytes <= 0 {
+        return 0;
+    }
+    let bytes = usize::try_from(bytes).unwrap_or(usize::MAX);
+    i64::try_from(approx_tokens_from_byte_count(bytes)).unwrap_or(i64::MAX)
+}
+
 #[cfg(test)]
 mod tests {