refactor(memory): own solved-question lifecycle (#24)

This commit is contained in:
2026-08-24 01:23:39 +02:00
parent 93fe0d733b
commit 4a654de84a
13 changed files with 511 additions and 201 deletions
+1 -1
View File
@@ -1015,7 +1015,7 @@ search` (Phase 2) reuse:
(ledger detail `seq:<n>`) so it is never re-proposed. `tht memory promote`/`save-one` were
added to the gate's anti-bypass FORBIDDEN list (model must go through the gate tool).
- **Solved-question exemplars.** New vector kind `solved_question` reusing the existing
`memory` pgvector table (no server-side DDL); `harness/tht/solved.py` does a one-row
`memory` pgvector table (no server-side DDL); `harness/tht/memory/solved.py` does a one-row
upsert keyed by a hash of question+SQL. CLI: `tht memory solved-index` / `solved-search`.
`tht session finalize` auto-indexes the pair (best-effort: green line on upsert, cyan
"già aggiornata" on dedup no-op, yellow warning + the recovery command