Subagent sessions duplicate the full parent transcript and create 10+ GB JSONL files

Codex Desktop on Windows is creating extremely large session files under:

%USERPROFILE%.codex\sessions

In the September session directory, 6 subagent JSONL files consume about 62.8 GB. Each file is approximately 10.4–10.7 GB and references the same parent session.

Investigation shows:

• 1 MB samples taken at 1 GB, 5 GB, and 10 GB offsets are byte-identical across all six files.
• In one representative 10.4 GB file, 273 "compacted" records occupy 10.18 GB (97.8% of the file).
• Most of the duplicated data appears to be image-related parent context.
• Individual compacted JSONL records can reach approximately 92.6 MB.
• The same issue previously produced multiple 8 GB subagent session files.

Expected behavior:
Subagent sessions should reference or deduplicate the parent transcript and store only their own incremental history.

Actual behavior:
Every spawned subagent stores a near-complete copy of the large parent transcript, causing tens of gigabytes of disk usage within a few hours.

Environment:

• Windows
• Codex Desktop
• Bundled Codex CLI: 0.153.0-alpha.5

Start by tracing how spawned subagent sessions persist their JSONL history and inherit the parent transcript; the issue names no files or tests, so locating those entry points is part of the investigation. Done means subagent files retain only incremental history or safely reference shared parent data, without duplicating large compacted records or producing multi-gigabyte files.