Files
ten31-database/backend/migrations/0003_entity_merge_review.sql
T
Keysat cd3cca725c Phase 1: dual approval default, web-UI index jobs + merge review queue, thesis v2
- Dual sign-off is now the default (thesis_required_approvals defaults to 2).
- Entity-merge review queue (migration 0003): the fuzzy/Qwen tier no longer
  auto-merges — it writes CANDIDATES (entity_merge_candidates) with a same/different
  suggestion + confidence + reason for a human to approve (merge) or reject (keep
  separate). entity_merge.py applies/rejects (durable via entity_merges, soft-delete,
  repoint links+edges); decided pairs aren't re-surfaced.
- entity_jobs.py: UI-triggered background index jobs (rebuild/update/find-duplicates)
  as subprocesses with a one-at-a-time lock; status in /api/system/status.
- server.py: /api/index/{rebuild,update}, /api/entities/find-duplicates,
  /api/entities/merge-candidates [+ /{id} decide] — admin-gated.
- docs/thesis-seed-v2.md: concrete, plain-English rewrite per Grant's feedback.

Backend verified end-to-end on synthetic data (candidate gen -> approve/reject).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-05 11:14:12 -05:00

26 lines
1.3 KiB
SQL

-- Phase 1 — entity-merge review queue.
--
-- ADDITIVE/REVERSIBLE. The fuzzy (local-Qwen) tier no longer auto-merges; it
-- writes CANDIDATES here for a human to approve (same entity -> merge) or reject
-- (different entities -> keep separate), surfaced in the CRM web UI. Approved
-- candidates apply the merge and are recorded in entity_merges (durable);
-- rejected pairs are remembered so they are not re-surfaced.
CREATE TABLE IF NOT EXISTS entity_merge_candidates (
id TEXT PRIMARY KEY,
entity_a TEXT NOT NULL, -- survivor (kept) canonical id
entity_b TEXT NOT NULL, -- would be merged INTO entity_a
name_a TEXT, name_b TEXT,
email_a TEXT, email_b TEXT,
context TEXT, -- firm / surname context for the reviewer
verdict TEXT, -- 'same' | 'different' (local-Qwen suggestion)
confidence REAL,
reason TEXT, -- Qwen's reasoning (why it thinks same/different)
status TEXT NOT NULL DEFAULT 'pending', -- pending | approved | rejected
decided_by TEXT, -- users.id of the partner who decided
decided_at TEXT,
created_at TEXT DEFAULT (datetime('now')),
UNIQUE(entity_a, entity_b)
);
CREATE INDEX IF NOT EXISTS idx_merge_candidates_status ON entity_merge_candidates(status);