Joseph Doherty
76 lines
2.5 KiB
Python
76 lines
2.5 KiB
Python
"""Cross-chat search service (T93, Phase 4).
|
|
|
|
FTS5-based search across ALL owners and ALL chats. Used by the
|
|
top-bar search UX (T100) for "where did I last see this character
|
|
mention X?" queries. NO witness filter -- this is intentionally a
|
|
power-user surface that surfaces memories across POVs.
|
|
|
|
Mirrors the FTS5 access pattern of ``chat.state.memory.search_memories``
|
|
but drops both the ``owner_id = ?`` and the per-witness predicates so a
|
|
single query can sweep every chat in the database. The composite
|
|
re-rank is also dropped: callers want raw BM25 ordering for the
|
|
"highest match strength wins" semantics expected of a global search box.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from sqlite3 import Connection
|
|
|
|
|
|
def search_all_memories(
|
|
conn: Connection,
|
|
*,
|
|
query: str,
|
|
k: int = 20,
|
|
) -> list[dict]:
|
|
"""Search FTS5 across all owners and chats.
|
|
|
|
Returns rows with ``{memory_id, owner_id, chat_id, scene_id,
|
|
pov_summary, significance, ts, fts_rank}``, sorted by FTS5 BM25
|
|
rank ascending (lower rank = stronger match, surfaced first).
|
|
|
|
The ``memories`` table has no ``ts`` column; we expose ``created_at``
|
|
(the projector-side row insertion timestamp) under that key so the
|
|
UI does not have to know the storage name.
|
|
|
|
An empty / whitespace-only ``query`` short-circuits to ``[]`` to
|
|
avoid an FTS5 ``MATCH ''`` syntax error and to keep the top-bar
|
|
"no input yet" state from triggering a full-table scan.
|
|
"""
|
|
if not query or not query.strip():
|
|
return []
|
|
|
|
# FTS5 MATCH against the same ``memories_fts`` virtual table that
|
|
# backs ``state.memory.search_memories``; the JOIN pulls metadata
|
|
# from the content table because the FTS index only stores
|
|
# ``pov_summary``. ORDER BY rank ASC because BM25 in FTS5 returns
|
|
# negative scores where lower is better.
|
|
rows = conn.execute(
|
|
"SELECT m.id, m.owner_id, m.chat_id, m.scene_id, "
|
|
" m.pov_summary, m.significance, m.created_at, "
|
|
" memories_fts.rank "
|
|
"FROM memories_fts "
|
|
"JOIN memories m ON m.id = memories_fts.rowid "
|
|
"WHERE memories_fts MATCH ? "
|
|
"ORDER BY memories_fts.rank ASC "
|
|
"LIMIT ?",
|
|
(query.strip(), k),
|
|
).fetchall()
|
|
|
|
return [
|
|
{
|
|
"memory_id": r[0],
|
|
"owner_id": r[1],
|
|
"chat_id": r[2],
|
|
"scene_id": r[3],
|
|
"pov_summary": r[4],
|
|
"significance": r[5],
|
|
"ts": r[6],
|
|
"fts_rank": r[7],
|
|
}
|
|
for r in rows
|
|
]
|
|
|
|
|
|
__all__ = ["search_all_memories"]
|