sync: auto-sync from GURU-5070 at 2026-06-11 08:33:19

Author: Mike Swanson
Machine: GURU-5070
Timestamp: 2026-06-11 08:33:19
This commit is contained in:
2026-06-11 08:33:32 -07:00
parent d0f90d4023
commit 25d2cf5148

View File

@@ -494,7 +494,10 @@ def cluster_overlaps(mems: list[Memory], threshold: float = 0.34):
slug_prefix[fi] == slug_prefix[fj] slug_prefix[fi] == slug_prefix[fj]
and len(slug_prefix[fi].split("_")) >= 2 and len(slug_prefix[fi].split("_")) >= 2
) )
if sim >= threshold or same_prefix: # same_prefix alone over-flags coincidental first-word collisions
# (feedback_no_*, feedback_client_*, reference_rmm_* with ~0 content
# overlap). Require a little real similarity for a prefix-only match.
if sim >= threshold or (same_prefix and sim >= 0.12):
# Don't flag intentional current/archive splits (X + X_history): # Don't flag intentional current/archive splits (X + X_history):
# deliberately separate files, cross-linked in frontmatter, not dupes. # deliberately separate files, cross-linked in frontmatter, not dupes.
si, sj = slug_of[fi], slug_of[fj] si, sj = slug_of[fi], slug_of[fj]