Fix people double-count + duplicate-queue explosion (v0.1.0:51)
Root cause: grid contacts (fundraising_contacts) are the SAME people as the contacts table (the app syncs them by name/email), but resolution matched grid rows by (name + investor-canon) where the two sides derive the investor key from different tables that rarely line up — so nearly every grid contact minted a duplicate person (715 + ~692 ≈ 1406), and the duplicate finder then flagged each twin against its real self (~676 candidates). Fix (entity_resolution.py): - Grid pass matches a grid contact to its existing contacts-table person by PROVABLE keys only (exact email, else exact name within the same investor) and records membership; on a miss it MINTS NOTHING (the old else-branch mint was the double-count source, and guessing by name across firms risks binding two different same-named people). - Targeted, audited cleanup soft-deletes leftover grid-only "twins" (person rows with no 'contacts' link) and superseded pre-:48 'lp'/'organization' rows, guarded so any row carrying enrichment/human data is never dropped (guardrail #3); the tombstoned ids are logged to interaction_log (guardrail #5). - _upsert_entity clears deleted_at on conflict so a re-emitted id is un-tombstoned (no permanent burial); fuzzy-merge losers stay buried via _redirect. entity_merge.py / server.py: the duplicate queue + pending count now filter to candidates whose both sides are still live, so self-healed twins drop out. Verified: offline reproduction test (backend/ingest/test_entity_resolution.py, 10/10) reproduces the 1406-style doubling and proves it collapses; no regression on the synthetic dev set; two adversarial review passes. Known pre-existing identity-key weaknesses (same name+firm+no email collision; shared role inbox over-link) are unchanged by this fix and will be resolved structurally by the contact_id link in the grid/contacts unification. Run "Build search index" after upgrading to recompute the canonical layer. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Keysat
@@ -31,8 +31,16 @@ def _log(c, actor_id, action, target_id, payload):
|
||||
|
||||
def list_candidates(db, status="pending"):
|
||||
c = _conn(db)
|
||||
# Only surface candidates whose BOTH sides are still live canonical entities.
|
||||
# When entity resolution self-heals (a grid "twin" matched back, so its
|
||||
# duplicate entity is soft-deleted), the candidate that paired them becomes
|
||||
# moot — hide it instead of asking a human to adjudicate a tombstone.
|
||||
rows = [dict(r) for r in c.execute(
|
||||
"SELECT * FROM entity_merge_candidates WHERE status=? ORDER BY confidence DESC, created_at DESC", (status,))]
|
||||
"""SELECT mc.* FROM entity_merge_candidates mc
|
||||
JOIN canonical_entities a ON a.id = mc.entity_a AND a.deleted_at IS NULL
|
||||
JOIN canonical_entities b ON b.id = mc.entity_b AND b.deleted_at IS NULL
|
||||
WHERE mc.status=?
|
||||
ORDER BY mc.confidence DESC, mc.created_at DESC""", (status,))]
|
||||
c.close()
|
||||
return {"candidates": rows, "count": len(rows)}
|
||||
|
||||
|
||||
@@ -90,6 +90,12 @@ def _upsert_entity(conn, eid, kind, display_name, primary_email):
|
||||
display_name = excluded.display_name,
|
||||
primary_email = COALESCE(excluded.primary_email, canonical_entities.primary_email),
|
||||
entity_kind = excluded.entity_kind,
|
||||
-- Re-emitting a deterministic id means the entity is live again, so
|
||||
-- clear any prior tombstone (e.g. a stale-cleanup soft-delete from a
|
||||
-- run when the source row was briefly absent). Fuzzy-merge losers are
|
||||
-- redirected away by _redirect and never re-upserted, so this never
|
||||
-- resurrects a merged-away entity.
|
||||
deleted_at = NULL,
|
||||
updated_at = excluded.updated_at
|
||||
""",
|
||||
(eid, kind, display_name, primary_email or None, _now(), _now()),
|
||||
@@ -221,12 +227,21 @@ def resolve_people(conn, org_canon_by_orgid, org_canon_by_fundinv, merge_map=Non
|
||||
email = norm_email(r["email"])
|
||||
name_norm = norm_text(r["full_name"] or "")
|
||||
inv_canon = org_canon_by_fundinv.get(r["investor_id"])
|
||||
# Match the grid contact to its contacts-table person by PROVABLE keys only:
|
||||
# exact email, else exact name within the SAME canonical investor. The app
|
||||
# keeps the grid and the contacts table in sync (_upsert_contact_from_
|
||||
# fundraising), so a grid contact IS an existing contact-person, never a new
|
||||
# one. On a confident match, record the membership. On a miss we deliberately
|
||||
# do NOT mint a person: the old else-branch mint is exactly what produced the
|
||||
# people double-count (a grid row whose (name, investor) key didn't line up
|
||||
# with its contact minted a duplicate), and guessing by name across firms
|
||||
# risks binding two different same-named people. Unresolved grid rows are
|
||||
# left for the explicit contact_id link planned in the grid/contacts
|
||||
# unification — honest separation: never merge or mint on a guess.
|
||||
cid = (by_email.get(email) if email else None) or by_name_inv.get((name_norm, inv_canon or ""))
|
||||
if cid:
|
||||
_link(conn, cid, "fundraising_contacts", r["id"], email or name_norm, "grid_assoc", 0.9)
|
||||
_member_of(conn, cid, inv_canon)
|
||||
else:
|
||||
_person(r["full_name"] or "", email, inv_canon, "fundraising_contacts", r["id"])
|
||||
|
||||
# lp_profiles -> the person entity of its contact
|
||||
for r in conn.execute("SELECT id, contact_id FROM lp_profiles WHERE deleted_at IS NULL"):
|
||||
@@ -270,17 +285,56 @@ def run(db_path: str):
|
||||
conn.commit()
|
||||
person_meta = resolve_people(conn, org_by_oid, org_by_inv, merge_map)
|
||||
conn.commit()
|
||||
|
||||
live = "deleted_at IS NULL"
|
||||
|
||||
# ── Clean up stale derived rows (soft-delete only; guardrail #3) ──
|
||||
# Two UNAMBIGUOUS classes of obsolete entity_resolution-owned rows, tombstoned
|
||||
# ONLY when they carry no human/enrichment data so nothing a partner entered is
|
||||
# ever dropped:
|
||||
# (a) PERSON rows with no 'contacts' source link. Real people come from the
|
||||
# contacts table (pass 1); a person linked only from the grid is a leftover
|
||||
# "twin" minted by the pre-fix else-branch — the source of the 1406
|
||||
# double-count. (Narrow + safe: a contact whose canonical id merely
|
||||
# *changed* still keeps a 'contacts' link, so it is never caught here.)
|
||||
# (b) Rows under the superseded pre-:48 kinds 'lp'/'organization' (the model
|
||||
# is now investor | person), left live by old upsert-only runs.
|
||||
# We list the ids first and log them (guardrail #5: the soft-delete is
|
||||
# reviewable/undoable), then tombstone + audit in ONE transaction.
|
||||
nodata = ("thesis_fit IS NULL AND segment IS NULL AND accreditation_status IS NULL "
|
||||
"AND qp_status IS NULL AND warmth_score IS NULL AND owner_id IS NULL "
|
||||
"AND last_touch_at IS NULL AND notes IS NULL")
|
||||
stale = [r["id"] for r in conn.execute(f"""
|
||||
SELECT id FROM canonical_entities c
|
||||
WHERE {live} AND source='entity_resolution' AND {nodata}
|
||||
AND ( (entity_kind='person' AND NOT EXISTS (
|
||||
SELECT 1 FROM entity_links l
|
||||
WHERE l.canonical_id = c.id AND l.source_model = 'contacts'))
|
||||
OR entity_kind IN ('lp', 'organization') )
|
||||
""")]
|
||||
for sid in stale:
|
||||
conn.execute("UPDATE canonical_entities SET deleted_at=?, updated_at=? WHERE id=?", (_now(), _now(), sid))
|
||||
if stale:
|
||||
conn.execute(
|
||||
"""INSERT INTO interaction_log
|
||||
(id, ts, actor_type, actor_id, action, target_type, target_id, payload, source, created_at)
|
||||
VALUES (?, ?, 'system', 'entity_resolver', 'entity.stale_tombstoned', 'canonical_entities', NULL, ?, 'ingest', ?)""",
|
||||
(str(uuid.uuid4()), _now(), json.dumps({"count": len(stale), "ids": stale}), _now()),
|
||||
)
|
||||
pruned = len(stale)
|
||||
conn.commit()
|
||||
|
||||
candidates = find_fuzzy_candidates(person_meta)
|
||||
|
||||
# Counts report LIVE entities (deleted_at IS NULL); fuzzy-merged losers are
|
||||
# soft-deleted tombstones (guardrail #3) and excluded.
|
||||
live = "deleted_at IS NULL"
|
||||
# Counts report LIVE entities (deleted_at IS NULL); fuzzy-merged losers and
|
||||
# tombstoned stale rows are soft-deleted (guardrail #3) and excluded.
|
||||
counts = {
|
||||
"canonical_total": conn.execute(f"SELECT COUNT(*) FROM canonical_entities WHERE {live}").fetchone()[0],
|
||||
"investor": conn.execute(f"SELECT COUNT(*) FROM canonical_entities WHERE entity_kind='investor' AND {live}").fetchone()[0],
|
||||
"person": conn.execute(f"SELECT COUNT(*) FROM canonical_entities WHERE entity_kind='person' AND {live}").fetchone()[0],
|
||||
"links": conn.execute("SELECT COUNT(*) FROM entity_links").fetchone()[0],
|
||||
"fuzzy_candidates": len(candidates),
|
||||
"pruned_stale": pruned,
|
||||
}
|
||||
|
||||
conn.execute(
|
||||
|
||||
@@ -0,0 +1,190 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Offline regression test for the grid-contact double-count fix (safe version).
|
||||
|
||||
Reproduces the real-data condition that made PEOPLE (RESOLVED) ≈ contacts +
|
||||
grid-contacts (the ~1406 bug): grid contacts (fundraising_contacts) with no email
|
||||
and contacts with no organization, so the (name, investor) keys never coincide and
|
||||
every grid row used to mint its own duplicate person.
|
||||
|
||||
Asserts the SAFE fix:
|
||||
1. a grid contact with a matching email links back to its contact (no new person),
|
||||
2. a grid contact whose contact shares the same investor links back by name,
|
||||
3. a grid contact that can't be PROVABLY matched mints NOTHING (no duplicate
|
||||
person, no cross-firm name guess) — the count stays correct,
|
||||
4. targeted cleanup soft-deletes a stale grid-only "twin" (person with no
|
||||
contacts link) and a superseded 'lp'/'organization' row, with no enrichment,
|
||||
5. cleanup PRESERVES a grid-only person that carries enrichment (guardrail #3),
|
||||
6. a re-emitted id is UN-tombstoned (no permanent burial),
|
||||
7. re-running is idempotent.
|
||||
|
||||
Pure stdlib + SQLite; never calls Spark/Qwen (er.run is deterministic-only).
|
||||
Run: cd backend/ingest && python3 test_entity_resolution.py
|
||||
"""
|
||||
import os
|
||||
import sqlite3
|
||||
import sys
|
||||
import tempfile
|
||||
|
||||
import entity_resolution as er
|
||||
|
||||
SCHEMA = """
|
||||
CREATE TABLE canonical_entities (
|
||||
id TEXT PRIMARY KEY, entity_kind TEXT NOT NULL, display_name TEXT NOT NULL,
|
||||
primary_email TEXT, thesis_fit TEXT, segment TEXT, accreditation_status TEXT,
|
||||
qp_status TEXT, warmth_score REAL, source TEXT, owner_id TEXT,
|
||||
last_touch_at TEXT, notes TEXT,
|
||||
created_at TEXT DEFAULT (datetime('now')), updated_at TEXT DEFAULT (datetime('now')),
|
||||
deleted_at TEXT
|
||||
);
|
||||
CREATE TABLE entity_links (
|
||||
id TEXT PRIMARY KEY, canonical_id TEXT, source_model TEXT, source_id TEXT,
|
||||
match_value TEXT, match_kind TEXT, confidence REAL, created_at TEXT,
|
||||
UNIQUE(source_model, source_id, match_value)
|
||||
);
|
||||
CREATE TABLE relationship_edges (
|
||||
id TEXT PRIMARY KEY, src_id TEXT, dst_id TEXT, edge_type TEXT, source TEXT,
|
||||
strength REAL, directed INTEGER, first_seen_at TEXT, last_seen_at TEXT,
|
||||
created_at TEXT, updated_at TEXT,
|
||||
UNIQUE(src_id, dst_id, edge_type, source)
|
||||
);
|
||||
CREATE TABLE interaction_log (
|
||||
id TEXT PRIMARY KEY, ts TEXT, actor_type TEXT, actor_id TEXT, action TEXT,
|
||||
target_type TEXT, target_id TEXT, payload TEXT, source TEXT, created_at TEXT
|
||||
);
|
||||
CREATE TABLE contacts (
|
||||
id TEXT PRIMARY KEY, first_name TEXT, last_name TEXT, email TEXT,
|
||||
organization_id TEXT, deleted_at TEXT
|
||||
);
|
||||
CREATE TABLE organizations (id TEXT PRIMARY KEY, name TEXT, email TEXT);
|
||||
CREATE TABLE fundraising_investors (id TEXT PRIMARY KEY, investor_name TEXT);
|
||||
CREATE TABLE fundraising_contacts (id TEXT PRIMARY KEY, full_name TEXT, email TEXT, investor_id TEXT);
|
||||
CREATE TABLE lp_profiles (id TEXT PRIMARY KEY, contact_id TEXT, deleted_at TEXT);
|
||||
"""
|
||||
|
||||
SEEDED = ("per_TWIN", "per_ENR", "lp_OLD")
|
||||
|
||||
|
||||
def seed(db):
|
||||
c = sqlite3.connect(db)
|
||||
c.executescript(SCHEMA)
|
||||
c.execute("INSERT INTO organizations (id, name, email) VALUES ('o1','Acme Capital',NULL)")
|
||||
c.executemany("INSERT INTO contacts (id, first_name, last_name, email, organization_id) VALUES (?,?,?,?,?)", [
|
||||
("c1", "Alice", "Anderson", "alice@x.com", None), # email, no org
|
||||
("c2", "Bob", "Brown", None, None), # no email, no org
|
||||
("c3", "Dave", "Davis", None, "o1"), # no email, org = Acme
|
||||
])
|
||||
c.executemany("INSERT INTO fundraising_investors (id, investor_name) VALUES (?,?)", [
|
||||
("i_acme", "Acme Capital"), ("i_beta", "Beta Family Office"),
|
||||
])
|
||||
c.executemany("INSERT INTO fundraising_contacts (id, full_name, email, investor_id) VALUES (?,?,?,?)", [
|
||||
("g_alice", "Alice Anderson", "alice@x.com", "i_beta"), # -> email match to c1
|
||||
("g_dave", "Dave Davis", None, "i_acme"), # -> name+investor match to c3
|
||||
("g_bob", "Bob Brown", None, "i_beta"), # -> MISS (c2 has no org) -> mint NOTHING
|
||||
("g_carol", "Carol Clark", None, "i_beta"), # -> MISS (no contact) -> mint NOTHING
|
||||
])
|
||||
# Stale grid-only "twin" (person, only a fundraising_contacts link, no enrichment) -> prune
|
||||
c.execute("INSERT INTO canonical_entities (id, entity_kind, display_name, source) VALUES "
|
||||
"('per_TWIN','person','Ghost Twin','entity_resolution')")
|
||||
c.execute("INSERT INTO entity_links (id, canonical_id, source_model, source_id, match_value, match_kind, confidence, created_at) "
|
||||
"VALUES ('l_twin','per_TWIN','fundraising_contacts','gx','ghost','name_org',0.8,'t')")
|
||||
# Grid-only person WITH enrichment -> preserved (guardrail #3)
|
||||
c.execute("INSERT INTO canonical_entities (id, entity_kind, display_name, source, segment) VALUES "
|
||||
"('per_ENR','person','Enriched Orphan','entity_resolution','warm')")
|
||||
c.execute("INSERT INTO entity_links (id, canonical_id, source_model, source_id, match_value, match_kind, confidence, created_at) "
|
||||
"VALUES ('l_enr','per_ENR','fundraising_contacts','gy','enr','name_org',0.8,'t')")
|
||||
# Superseded pre-:48 kind -> prune
|
||||
c.execute("INSERT INTO canonical_entities (id, entity_kind, display_name, source) VALUES "
|
||||
"('lp_OLD','lp','Old LP Row','entity_resolution')")
|
||||
c.commit()
|
||||
c.close()
|
||||
|
||||
|
||||
def resolved_persons(db):
|
||||
c = sqlite3.connect(db)
|
||||
q = "SELECT COUNT(*) FROM canonical_entities WHERE entity_kind='person' AND deleted_at IS NULL AND id NOT IN (?,?,?)"
|
||||
n = c.execute(q, SEEDED).fetchone()[0]
|
||||
c.close()
|
||||
return n
|
||||
|
||||
|
||||
def deleted_at(db, eid):
|
||||
c = sqlite3.connect(db)
|
||||
r = c.execute("SELECT deleted_at FROM canonical_entities WHERE id=?", (eid,)).fetchone()
|
||||
c.close()
|
||||
return r[0] if r else "MISSING"
|
||||
|
||||
|
||||
def grid_match_kinds(db):
|
||||
c = sqlite3.connect(db)
|
||||
rows = dict(c.execute("SELECT match_kind, COUNT(*) FROM entity_links "
|
||||
"WHERE source_model='fundraising_contacts' AND match_kind!='name_org' GROUP BY match_kind").fetchall())
|
||||
c.close()
|
||||
return rows
|
||||
|
||||
|
||||
def minted_from_grid(db):
|
||||
"""Persons minted directly from a grid row (the bug). Should be 0 after the fix."""
|
||||
c = sqlite3.connect(db)
|
||||
n = c.execute("""SELECT COUNT(DISTINCT l.canonical_id) FROM entity_links l
|
||||
JOIN canonical_entities ce ON ce.id=l.canonical_id AND ce.deleted_at IS NULL
|
||||
WHERE l.source_model='fundraising_contacts' AND l.match_kind IN ('name_org','exact_email')
|
||||
AND l.canonical_id NOT IN (?,?,?)""", SEEDED).fetchone()[0]
|
||||
c.close()
|
||||
return n
|
||||
|
||||
|
||||
FAILS = []
|
||||
|
||||
|
||||
def check(cond, msg):
|
||||
print((" PASS " if cond else " FAIL ") + msg)
|
||||
if not cond:
|
||||
FAILS.append(msg)
|
||||
|
||||
|
||||
def main():
|
||||
tmp = tempfile.mkdtemp()
|
||||
db = os.path.join(tmp, "repro.db")
|
||||
seed(db)
|
||||
|
||||
counts1, _ = er.run(db)
|
||||
print(f"Run 1 counts: {counts1}")
|
||||
|
||||
# 3 contacts; grid rows either link back (g_alice, g_dave) or are skipped
|
||||
# (g_bob, g_carol). NO grid row mints a person -> count stays 3, not 5-7.
|
||||
check(resolved_persons(db) == 3, f"resolved persons == 3 (got {resolved_persons(db)}); old double-count would be 5-7")
|
||||
check(minted_from_grid(db) == 0, f"zero persons minted from grid rows (got {minted_from_grid(db)})")
|
||||
|
||||
mk = grid_match_kinds(db)
|
||||
check(mk.get("grid_assoc", 0) == 2, f"two grid contacts matched back via grid_assoc (got {mk.get('grid_assoc',0)})")
|
||||
|
||||
# Targeted cleanup: stale grid-only twin + superseded 'lp' row tombstoned...
|
||||
check(deleted_at(db, "per_TWIN") is not None, "stale grid-only twin 'per_TWIN' tombstoned")
|
||||
check(deleted_at(db, "lp_OLD") is not None, "superseded 'lp' row 'lp_OLD' tombstoned")
|
||||
# ...enriched grid-only person preserved.
|
||||
check(deleted_at(db, "per_ENR") is None, "enriched grid-only person 'per_ENR' PRESERVED (has segment)")
|
||||
check(counts1.get("pruned_stale", 0) == 2, f"exactly 2 stale rows pruned (got {counts1.get('pruned_stale')})")
|
||||
|
||||
# Un-tombstone: soft-delete a real contact-person, then re-run -> it comes back.
|
||||
alice = er._eid("per", "e|alice@x.com")
|
||||
cc = sqlite3.connect(db)
|
||||
cc.execute("UPDATE canonical_entities SET deleted_at='2026-01-01' WHERE id=?", (alice,))
|
||||
cc.commit()
|
||||
cc.close()
|
||||
counts2, _ = er.run(db)
|
||||
print(f"Run 2 counts: {counts2}")
|
||||
check(deleted_at(db, alice) is None, "re-emitted contact-person is UN-tombstoned (no permanent burial)")
|
||||
check(resolved_persons(db) == 3, f"resolved persons stable at 3 on re-run (got {resolved_persons(db)})")
|
||||
check(counts2.get("pruned_stale", 0) == 0, f"nothing re-pruned on idempotent re-run (got {counts2.get('pruned_stale')})")
|
||||
|
||||
print()
|
||||
if FAILS:
|
||||
print(f"FAILED ({len(FAILS)}):")
|
||||
for f in FAILS:
|
||||
print(f" - {f}")
|
||||
sys.exit(1)
|
||||
print("ALL PASS")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
+7
-1
@@ -3517,8 +3517,14 @@ class CRMHandler(BaseHTTPRequestHandler):
|
||||
except Exception:
|
||||
out['recent_activity'] = []
|
||||
try:
|
||||
# Count only candidates whose both sides are still live (mirror the
|
||||
# review queue in entity_merge.list_candidates) — self-healed twins
|
||||
# whose duplicate was soft-deleted no longer count as pending work.
|
||||
out['pending_merge_candidates'] = conn.execute(
|
||||
"SELECT COUNT(*) FROM entity_merge_candidates WHERE status='pending'").fetchone()[0]
|
||||
"""SELECT COUNT(*) FROM entity_merge_candidates mc
|
||||
JOIN canonical_entities a ON a.id=mc.entity_a AND a.deleted_at IS NULL
|
||||
JOIN canonical_entities b ON b.id=mc.entity_b AND b.deleted_at IS NULL
|
||||
WHERE mc.status='pending'""").fetchone()[0]
|
||||
except Exception:
|
||||
out['pending_merge_candidates'] = None
|
||||
out['index_job'] = entity_jobs.get_status() if entity_jobs else None
|
||||
|
||||
Reference in New Issue
Block a user