IB-WP-0014: archive-list, restore, retention annotation, docs (T03-T05)

Round out IB-WP-0014 with the remaining archive operations and docs.

- restore_archive() and `infospace-bench restore <pkg> --target <dir>` round-trip
  a finalized package's bytes back to disk. Refuses to overwrite a non-empty
  target unless --force. --from <infospace-root> resolves the store location.
- archive-list CLI with --with-retention flag; annotate_retention() opens the
  per-infospace registry and joins each record with its current retention
  state (effective class, expires, holds, eligibility).
- docs/archive-integration.md covers when to archive, the include set,
  retention classes, storage layout, credentials policy, and the explicit
  non-goal that S3/git backends live in artifact-store.
- SCOPE.md cross-links the new doc.
- Workplan flipped to status: done. Full pytest suite: 72 passed.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
2026-05-17 11:46:23 +02:00
parent e343443d77
commit ddefd69f71
8 changed files with 636 additions and 2 deletions

View File

@@ -1,5 +1,6 @@
from __future__ import annotations
import filecmp
from pathlib import Path
import pytest
@@ -8,10 +9,13 @@ import yaml
from infospace_bench import (
ArchiveRecord,
InfospaceError,
RestoredArchive,
add_artifact,
annotate_retention,
archive_infospace,
create_infospace,
list_archives,
restore_archive,
)
from infospace_bench.archive import (
ARCHIVE_INDEX_PATH,
@@ -99,3 +103,96 @@ def test_archive_rejects_empty_include(tmp_path: Path) -> None:
with pytest.raises(InfospaceError) as excinfo:
archive_infospace(root, include=["does-not-exist"])
assert excinfo.value.code == "empty_archive"
def test_restore_archive_round_trips_bytes(tmp_path: Path) -> None:
root = _seed_infospace(tmp_path)
record = archive_infospace(root, note="round trip")
target = tmp_path / "restored"
result = restore_archive(
record.package_id,
target=target,
source_infospace=root,
)
assert isinstance(result, RestoredArchive)
assert result.manifest_digest == record.manifest_digest
assert result.file_count == record.file_count
for rel in result.restored_paths:
original = root / rel
restored = target / rel
assert restored.is_file()
assert filecmp.cmp(original, restored, shallow=False), rel
def test_restore_archive_refuses_non_empty_target(tmp_path: Path) -> None:
root = _seed_infospace(tmp_path)
record = archive_infospace(root)
target = tmp_path / "filled"
target.mkdir()
(target / "existing.txt").write_text("hi", encoding="utf-8")
with pytest.raises(InfospaceError) as excinfo:
restore_archive(
record.package_id,
target=target,
source_infospace=root,
)
assert excinfo.value.code == "restore_target_not_empty"
def test_restore_archive_force_overwrites_non_empty_target(tmp_path: Path) -> None:
root = _seed_infospace(tmp_path)
record = archive_infospace(root)
target = tmp_path / "filled-force"
target.mkdir()
(target / "leftover.txt").write_text("old", encoding="utf-8")
result = restore_archive(
record.package_id,
target=target,
source_infospace=root,
force=True,
)
assert result.file_count == record.file_count
# Pre-existing files that are not in the manifest are left in place.
assert (target / "leftover.txt").read_text(encoding="utf-8") == "old"
def test_restore_archive_requires_store_location(tmp_path: Path) -> None:
with pytest.raises(InfospaceError) as excinfo:
restore_archive("00000000-0000-0000-0000-000000000000", target=tmp_path)
assert excinfo.value.code == "missing_archive_store"
def test_annotate_retention_returns_state_for_each_archive(tmp_path: Path) -> None:
root = _seed_infospace(tmp_path)
first = archive_infospace(root)
second = archive_infospace(root)
archives = list_archives(root)
annotated = annotate_retention(archives, source_infospace=root)
assert [item["archive"]["package_id"] for item in annotated] == [
first.package_id,
second.package_id,
]
for item in annotated:
retention = item["retention"]
assert retention is not None
assert retention["effective_class"] == DEFAULT_RETENTION_CLASS
assert retention["eligible_for_deletion"] is False
def test_annotate_retention_returns_none_when_store_missing(tmp_path: Path) -> None:
root = _seed_infospace(tmp_path)
archive_infospace(root, store_root=tmp_path / "external-store")
archives = list_archives(root)
# Source infospace's store doesn't exist (we overrode store_root)
annotated = annotate_retention(archives, source_infospace=root)
assert annotated[0]["retention"] is None