Cameron CordesandClaude Opus 5.5
070f20b295
Stored vectors are only searchable with the backend, model, width and prefixes that built them, and nothing enforced that: changing [embedding] (or backend) without reembed_embeddings silently broke similarity search, and the per-row dim check missed same-width model or prefix swaps. - embedding_contract: one row (backend, model, dim, both prefixes). The server checks it once after migrations; the src/bin tools check it on their first embed. No row yet = record the running config. - On a mismatch every embed (embed_many, so queries and documents) fails with a message naming each changed field and the fix. Mixing vector spaces corrupts the corpus for good; refusing only pauses semantic search until the config is put back or the corpus re-embedded. - reembed_embeddings bypasses the guard and records the contract after a full run (all four tables, no --limit, not --dry-run). - A DB error in the check leaves embedding allowed and is logged. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2 lines
31 B
SQL
2 lines
31 B
SQL
DROP TABLE embedding_contract;
|