feat(embeddings): per-chunk rows — schema, write path, version-aware backfill (#280 steps 2+3)
note_embeddings becomes one row per chunk: PK (note_id, chunk_index), plus chunk_text (what this vector actually encodes) and chunker_version. Migration 0077 clears the table — embeddings are derived (0067 precedent) and the old whole-document rows are indistinguishable from single-chunk notes, so the startup backfill regenerates the corpus at the new shape. The backfill is now version-aware: a future shape change is a CHUNKER_VERSION bump that re-embeds exactly the stale notes, not another wipe. upsert_note_embedding takes (title, body) and chunks internally — one path for the write path, the recurrence spawn and the backfill. The recurrence spawn's own embed call is deleted outright: create_note already embeds via embed_note (#2056), so the spawn was a second copy of the rule. An emptied record now CLEARS its stale vectors instead of leaving them findable. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01UaYUaouG9jjhATyuxCKrQs
This commit is contained in:
@@ -29,18 +29,25 @@ def test_embed_note_uses_the_OWNER_not_the_caller():
|
||||
upsert.assert_called_once()
|
||||
assert upsert.call_args.args[0] == 5
|
||||
assert upsert.call_args.args[1] == 42 # owner, never the caller
|
||||
assert upsert.call_args.args[2] == "T\nB"
|
||||
# Title and body travel separately since #280 — chunking happens inside
|
||||
# upsert_note_embedding, the one path every writer shares.
|
||||
assert upsert.call_args.args[2] == "T"
|
||||
assert upsert.call_args.args[3] == "B"
|
||||
|
||||
|
||||
def test_embed_note_skips_a_record_with_no_text():
|
||||
"""An empty embedding is worse than none — it is a row that matches nothing
|
||||
and hides the fact that the record was never indexed."""
|
||||
def test_embed_note_hands_even_an_empty_record_to_the_one_path():
|
||||
"""The empty-record decision moved INTO upsert_note_embedding (#280): an
|
||||
emptied record must have its stale vectors CLEARED, not merely skipped —
|
||||
so embed_note schedules the call unconditionally rather than deciding
|
||||
here. The clearing behaviour itself is pinned in test_chunking.py."""
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
note = MagicMock(id=5, user_id=42, title="", body="")
|
||||
with patch("asyncio.create_task") as create_task:
|
||||
with patch("scribe.services.embeddings.upsert_note_embedding") as upsert, \
|
||||
patch("asyncio.create_task") as create_task:
|
||||
notes_svc.embed_note(note)
|
||||
assert not create_task.called
|
||||
assert create_task.called
|
||||
upsert.assert_called_once()
|
||||
|
||||
|
||||
def test_embed_note_without_a_running_loop_is_not_an_error():
|
||||
|
||||
Reference in New Issue
Block a user