Recording: Claude Code transcript compaction can erase the /prepare-build announcement bookend

Observed on run-08 (2026-09-07): the .session breadcrumb correctly pointed at the live transcript, but by extraction time the session had gone through context compaction and the transcript JSONL no longer contained the /prepare-build announcement text ("Run 08 — building in builds/run-08/") — the default opening bookend matched nothing and extract.py sliced from the start of the surviving transcript. The closing bookend (recent text) still matched. Recovered by re-running with --from="Spec fully absorbed", a phrase that survived compaction; the final log covers 138 turns of the build but has lost the allocation/checklist turns that preceded the compaction boundary.

Implication: the post-hoc recording design (CLAUDE.md "Recording is post-hoc") assumes the transcript retains raw turns for the whole build window. Long sessions violate that: compaction can drop any pre-boundary turn, including the opening bookend and early build activity.

Options to consider (next tooling pass):

• /prepare-build writes the announcement text (or a unique token) into evals/run-NN/.session alongside the path, and extract.py falls back to slicing from the earliest surviving turn while WARNING loudly that the opening bookend was lost (today it says "no match — sliced from start" only in stdout).
• Have /prepare-build note a timestamp at allocation; slice by timestamp rather than text.
• Or extract eagerly (run /extract-build-log periodically during long builds) since re-runs are idempotent.

🤖 Generated with Claude Code

Bắt đầu với extract.py và luồng ghi /prepare-build, sau đó đọc hướng dẫn trong CLAUDE.md rằng việc ghi là post-hoc. Tái hiện quá trình trích xuất sau khi transcript được compact bằng kịch bản run-08 và so sánh các tùy chọn boundary hiện có. Được coi là hoàn tất khi các phiên dài không còn âm thầm làm mất ngữ cảnh mở đầu, và quá trình trích xuất báo cáo rõ ràng boundary nào đã được sử dụng khi thiếu bookend ban đầu.