feat(mnemosyne): add by_date_range and temporal_neighbors query methods
Some checks failed
CI / test (pull_request) Failing after 9s
CI / validate (pull_request) Failing after 14s
Review Approval Gate / verify-review (pull_request) Failing after 2s

Implements two new temporal query methods on MnemosyneArchive:
- by_date_range(start, end): returns entries whose created_at falls within
  an ISO datetime range (inclusive, timezone-naive inputs treated as UTC)
- temporal_neighbors(entry_id, window_days=7): returns entries created
  within N days of a given anchor entry, excluding the anchor itself

Both methods return results sorted by created_at ascending and handle
edge cases: empty archive, single entry, timezone-naive dates, boundary
dates, and missing entry IDs (temporal_neighbors raises KeyError).

Adds CLI subcommands:
- mnemosyne timeline <start> <end>
- mnemosyne neighbors <entry_id> [--days N]

Tests cover: empty results, boundary inclusivity, timezone handling,
window sizing, sort order, and error cases.

Fixes #1244

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Alexander Whitestone
2026-04-11 21:00:36 -04:00
parent a14bf80631
commit f00ad12c49
3 changed files with 294 additions and 2 deletions

View File

@@ -7,7 +7,7 @@ and provides query interfaces for retrieving connected knowledge.
from __future__ import annotations
import json
from datetime import datetime, timezone
from datetime import datetime, timedelta, timezone
from pathlib import Path
from typing import Optional
@@ -651,6 +651,68 @@ class MnemosyneArchive:
self._save()
return entry
@staticmethod
def _parse_dt(dt_str: str) -> datetime:
"""Parse an ISO datetime string. Assumes UTC if no timezone is specified."""
dt = datetime.fromisoformat(dt_str)
if dt.tzinfo is None:
dt = dt.replace(tzinfo=timezone.utc)
return dt
def by_date_range(self, start: str, end: str) -> list[ArchiveEntry]:
"""Return entries whose ``created_at`` falls within [start, end] (inclusive).
Args:
start: ISO datetime string for the range start (e.g. "2024-01-01" or
"2024-01-01T00:00:00Z"). Timezone-naive strings are treated as UTC.
end: ISO datetime string for the range end. Timezone-naive strings are
treated as UTC.
Returns:
List of ArchiveEntry sorted by ``created_at`` ascending.
"""
start_dt = self._parse_dt(start)
end_dt = self._parse_dt(end)
results = []
for entry in self._entries.values():
entry_dt = self._parse_dt(entry.created_at)
if start_dt <= entry_dt <= end_dt:
results.append(entry)
results.sort(key=lambda e: e.created_at)
return results
def temporal_neighbors(self, entry_id: str, window_days: int = 7) -> list[ArchiveEntry]:
"""Return entries created within ``window_days`` of a given entry.
The reference entry itself is excluded from results.
Args:
entry_id: ID of the anchor entry.
window_days: Number of days around the anchor's ``created_at`` to search.
Returns:
List of ArchiveEntry sorted by ``created_at`` ascending.
Raises:
KeyError: If ``entry_id`` does not exist in the archive.
"""
anchor = self._entries.get(entry_id)
if anchor is None:
raise KeyError(entry_id)
anchor_dt = self._parse_dt(anchor.created_at)
delta = timedelta(days=window_days)
window_start = anchor_dt - delta
window_end = anchor_dt + delta
results = []
for entry in self._entries.values():
if entry.id == entry_id:
continue
entry_dt = self._parse_dt(entry.created_at)
if window_start <= entry_dt <= window_end:
results.append(entry)
results.sort(key=lambda e: e.created_at)
return results
def rebuild_links(self, threshold: Optional[float] = None) -> int:
"""Recompute all links from scratch.

View File

@@ -3,7 +3,8 @@
Provides: mnemosyne ingest, mnemosyne search, mnemosyne link, mnemosyne stats,
mnemosyne topics, mnemosyne remove, mnemosyne export,
mnemosyne clusters, mnemosyne hubs, mnemosyne bridges, mnemosyne rebuild,
mnemosyne tag, mnemosyne untag, mnemosyne retag
mnemosyne tag, mnemosyne untag, mnemosyne retag,
mnemosyne timeline, mnemosyne neighbors
"""
from __future__ import annotations
@@ -180,6 +181,38 @@ def cmd_retag(args):
print(f" Topics: {', '.join(entry.topics) if entry.topics else '(none)'}")
def cmd_timeline(args):
archive = MnemosyneArchive()
try:
results = archive.by_date_range(args.start, args.end)
except ValueError as e:
print(f"Invalid date format: {e}")
sys.exit(1)
if not results:
print("No entries found in that date range.")
return
for entry in results:
print(f"[{entry.id[:8]}] {entry.created_at[:10]} {entry.title}")
print(f" Topics: {', '.join(entry.topics) if entry.topics else '(none)'}")
print()
def cmd_neighbors(args):
archive = MnemosyneArchive()
try:
results = archive.temporal_neighbors(args.entry_id, window_days=args.days)
except KeyError:
print(f"Entry not found: {args.entry_id}")
sys.exit(1)
if not results:
print("No temporal neighbors found.")
return
for entry in results:
print(f"[{entry.id[:8]}] {entry.created_at[:10]} {entry.title}")
print(f" Topics: {', '.join(entry.topics) if entry.topics else '(none)'}")
print()
def main():
parser = argparse.ArgumentParser(prog="mnemosyne", description="The Living Holographic Archive")
sub = parser.add_subparsers(dest="command")
@@ -233,6 +266,14 @@ def main():
rt.add_argument("entry_id", help="Entry ID")
rt.add_argument("tags", help="Comma-separated new tag list")
tl = sub.add_parser("timeline", help="Show entries within an ISO date range")
tl.add_argument("start", help="Start datetime (ISO format, e.g. 2024-01-01 or 2024-01-01T00:00:00Z)")
tl.add_argument("end", help="End datetime (ISO format)")
nb = sub.add_parser("neighbors", help="Show entries temporally near a given entry")
nb.add_argument("entry_id", help="Anchor entry ID")
nb.add_argument("--days", type=int, default=7, help="Window in days (default: 7)")
args = parser.parse_args()
if not args.command:
parser.print_help()
@@ -253,6 +294,8 @@ def main():
"tag": cmd_tag,
"untag": cmd_untag,
"retag": cmd_retag,
"timeline": cmd_timeline,
"neighbors": cmd_neighbors,
}
dispatch[args.command](args)

View File

@@ -2,6 +2,7 @@
import json
import tempfile
from datetime import datetime, timezone, timedelta
from pathlib import Path
from nexus.mnemosyne.entry import ArchiveEntry
@@ -666,3 +667,189 @@ def test_update_entry_no_change_no_crash():
e = ingest_event(archive, title="T", content="c")
result = archive.update_entry(e.id)
assert result.title == "T"
# --- by_date_range tests ---
def _make_entry_at(archive: MnemosyneArchive, title: str, dt: datetime) -> ArchiveEntry:
"""Helper: ingest an entry and backdate its created_at."""
e = ingest_event(archive, title=title, content=title)
e.created_at = dt.isoformat()
archive._save()
return e
def test_by_date_range_empty_archive():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
results = archive.by_date_range("2024-01-01", "2024-12-31")
assert results == []
def test_by_date_range_returns_matching_entries():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
jan = datetime(2024, 1, 15, tzinfo=timezone.utc)
mar = datetime(2024, 3, 10, tzinfo=timezone.utc)
jun = datetime(2024, 6, 1, tzinfo=timezone.utc)
e1 = _make_entry_at(archive, "Jan entry", jan)
e2 = _make_entry_at(archive, "Mar entry", mar)
e3 = _make_entry_at(archive, "Jun entry", jun)
results = archive.by_date_range("2024-01-01", "2024-04-01")
ids = {e.id for e in results}
assert e1.id in ids
assert e2.id in ids
assert e3.id not in ids
def test_by_date_range_boundary_inclusive():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
exact = datetime(2024, 3, 1, tzinfo=timezone.utc)
e = _make_entry_at(archive, "Exact boundary", exact)
results = archive.by_date_range("2024-03-01T00:00:00+00:00", "2024-03-01T00:00:00+00:00")
assert len(results) == 1
assert results[0].id == e.id
def test_by_date_range_no_results():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
jan = datetime(2024, 1, 15, tzinfo=timezone.utc)
_make_entry_at(archive, "Jan entry", jan)
results = archive.by_date_range("2023-01-01", "2023-12-31")
assert results == []
def test_by_date_range_timezone_naive_treated_as_utc():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
dt = datetime(2024, 6, 15, tzinfo=timezone.utc)
e = _make_entry_at(archive, "Summer", dt)
# Timezone-naive start/end should still match
results = archive.by_date_range("2024-06-01", "2024-07-01")
assert any(r.id == e.id for r in results)
def test_by_date_range_sorted_ascending():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
dates = [
datetime(2024, 3, 5, tzinfo=timezone.utc),
datetime(2024, 1, 10, tzinfo=timezone.utc),
datetime(2024, 2, 20, tzinfo=timezone.utc),
]
for i, dt in enumerate(dates):
_make_entry_at(archive, f"Entry {i}", dt)
results = archive.by_date_range("2024-01-01", "2024-12-31")
assert len(results) == 3
assert results[0].created_at < results[1].created_at < results[2].created_at
def test_by_date_range_single_entry_archive():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
dt = datetime(2024, 5, 1, tzinfo=timezone.utc)
e = _make_entry_at(archive, "Only", dt)
assert archive.by_date_range("2024-01-01", "2024-12-31") == [e]
assert archive.by_date_range("2025-01-01", "2025-12-31") == []
# --- temporal_neighbors tests ---
def test_temporal_neighbors_empty_archive():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
e = ingest_event(archive, title="Lone", content="c")
results = archive.temporal_neighbors(e.id, window_days=7)
assert results == []
def test_temporal_neighbors_missing_entry_raises():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
try:
archive.temporal_neighbors("nonexistent-id")
assert False, "Expected KeyError"
except KeyError:
pass
def test_temporal_neighbors_returns_within_window():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
anchor_dt = datetime(2024, 4, 10, tzinfo=timezone.utc)
near_dt = datetime(2024, 4, 14, tzinfo=timezone.utc) # +4 days — within 7
far_dt = datetime(2024, 4, 20, tzinfo=timezone.utc) # +10 days — outside 7
anchor = _make_entry_at(archive, "Anchor", anchor_dt)
near = _make_entry_at(archive, "Near", near_dt)
far = _make_entry_at(archive, "Far", far_dt)
results = archive.temporal_neighbors(anchor.id, window_days=7)
ids = {e.id for e in results}
assert near.id in ids
assert far.id not in ids
assert anchor.id not in ids
def test_temporal_neighbors_excludes_anchor():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
dt = datetime(2024, 4, 10, tzinfo=timezone.utc)
anchor = _make_entry_at(archive, "Anchor", dt)
same = _make_entry_at(archive, "Same day", dt)
results = archive.temporal_neighbors(anchor.id, window_days=0)
ids = {e.id for e in results}
assert anchor.id not in ids
assert same.id in ids
def test_temporal_neighbors_custom_window():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
anchor_dt = datetime(2024, 4, 10, tzinfo=timezone.utc)
within_3 = datetime(2024, 4, 12, tzinfo=timezone.utc) # +2 days
outside_3 = datetime(2024, 4, 15, tzinfo=timezone.utc) # +5 days
anchor = _make_entry_at(archive, "Anchor", anchor_dt)
e_near = _make_entry_at(archive, "Near", within_3)
e_far = _make_entry_at(archive, "Far", outside_3)
results = archive.temporal_neighbors(anchor.id, window_days=3)
ids = {e.id for e in results}
assert e_near.id in ids
assert e_far.id not in ids
def test_temporal_neighbors_sorted_ascending():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
anchor_dt = datetime(2024, 6, 15, tzinfo=timezone.utc)
anchor = _make_entry_at(archive, "Anchor", anchor_dt)
for offset in [5, 1, 3]:
_make_entry_at(archive, f"Offset {offset}", anchor_dt + timedelta(days=offset))
results = archive.temporal_neighbors(anchor.id, window_days=7)
assert len(results) == 3
assert results[0].created_at < results[1].created_at < results[2].created_at
def test_temporal_neighbors_boundary_inclusive():
with tempfile.TemporaryDirectory() as tmp:
archive = MnemosyneArchive(archive_path=Path(tmp) / "a.json")
anchor_dt = datetime(2024, 6, 15, tzinfo=timezone.utc)
boundary_dt = anchor_dt + timedelta(days=7) # exactly at window edge
anchor = _make_entry_at(archive, "Anchor", anchor_dt)
boundary = _make_entry_at(archive, "Boundary", boundary_dt)
results = archive.temporal_neighbors(anchor.id, window_days=7)
assert any(r.id == boundary.id for r in results)