Matt 3b37d96c4d Switch domain assignment to Qdrant as source of truth ... Replace on-disk concept file reads with Qdrant payload queries for domain assignment. This unlocks assignment for ~10,120 items that had missing or legacy-only concept files on disk while Qdrant held the correct 18-domain taxonomy data. Changes: - domain_assigner.py: Replace _count_concept_domains (disk) with _count_domains_from_qdrant and _count_domains_from_qdrant_batch (Qdrant scroll queries). Add _get_qdrant_client helper. Remove pass 3 defensive re-run (Qdrant reads are consistent). Add no_concepts terminal status for zero-vector documents. - embedder.py: Post-embed hook passes existing qdrant client to compute_assignment, avoiding a second connection. - recon.py: Backfill creates one QdrantClient for the batch. SQL filter includes existing needs_reprocess items. Dry-run reports no_concepts as separate bucket. --reprocess-missing removes concept-dir deletion step (no longer reads from disk). - docs/domain-assignment.md: Algorithm references Qdrant, documents no_concepts status, removes pass 3 description. Dry-run results: 20,453 assigned, 1,392 tied, 298 no_concepts, 0 needs_reprocess, 0 errors (previously 10,416 needs_reprocess). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-04-28 03:59:06 +00:00
..
deploy-blast-radius.md	Docs: domain assignment guide, migration runbook, blast radius	2026-04-28 00:06:49 +00:00
domain-assignment.md	Switch domain assignment to Qdrant as source of truth	2026-04-28 03:59:06 +00:00
migration-runbook.md	Fix: correct Contabo concept backup path in docs (/opt/backups/recon/concepts/)	2026-04-28 01:42:05 +00:00