utils-reclaim-stale-snapshots

name

utils-reclaim-stale-snapshots

description

Reclaim idle Daytona SNAPSHOTS org-wide to free space under the 60-snapshot cap, using scripts/daytona/daytona_snapshot_manager.py. Deletes only harbor__ per- environment snapshots idle past the standing threshold GT'd in .agents/projects/daytona/daytona.md — NEVER the shared base/template images (daytonaio/sandbox:*, daytona-*, windows-*), which do not rebuild-on-demand. Use when a datagen/eval launch hits SnapshotCapExceeded, when a monitor sweep finds the cap full, or as routine cap hygiene. This is the org-wide RECLAIM tool; to shrink a SINGLE dataset's unique-environment count instead, use datagen-reduce-dataset-snapshots. Snapshots are a DIFFERENT resource from sandboxes (for sandbox cleanup use utils-cleanup-stale-sandboxes).

utils-reclaim-stale-snapshots

Free Daytona snapshot quota by deleting idle harbor__<hash>__snapshot environments under the hard cap of 60.

Why this is safe (and what it must never touch)

Harbor builds one snapshot per task-environment hash (harbor__<hash>__snapshot). auto_snapshot rebuilds a deleted idle snapshot on demand.

The base/template images (daytonaio/sandbox:*, daytona-gpu, daytona-medium/large/small, windows-*) are shared and do not rebuild on demand. Keep --name-prefix harbor__ so only Harbor snapshots are eligible.

For snapshots, state=active means built and available. Staleness uses last_used_at, falling back to created_at; live-job environments remain below the idle threshold.

Which org

Datagen/eval pre-build uses the cli org and DAYTONA_API_KEY. RL uses the separate DAYTONA_RL_API_KEY org.

How to run

Always , then delete.