Commit graph

2 commits

Author SHA1 Message Date
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
a39ec56620 Docs: domain assignment guide, migration runbook, blast radius
- domain-assignment.md: algorithm walkthrough (pass 1/2/3), status values,
  CLI command reference, dashboard review guide
- migration-runbook.md: step-by-step deploy with pre-deploy backups,
  8 STOP pause points for operator verification, staged push rollout,
  quarantined --reprocess-missing procedure, 5 rollback procedures
- deploy-blast-radius.md: per-step risk reference with worst case,
  detection signals, rollback procedures, and risk tiers

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-28 00:06:49 +00:00