marcopanandClaude Opus 4.8
c4d130828f
Implementazione del piano di remediation progressiva sui difetti emersi dall'analisi dell'harness. Tutto verificato: 214 test Python (incl. L0 su Postgres reale), 14 test JS del gate, ruff pulito. Blocco 1 (CRITICA, integrazione gate↔CLI): - phase advance: gate usa --auto + exit 6; reviewer_confirm kind:phase fa advance esplicito che applica i prerequisiti (prima non avanzava per le fasi a conferma umana). - cte plan riceve i --name dal gate (param names); set-question con id posizionale; skill `tht search find`; nuovo comando `tht memory save-one` con dedup hash client-side in save_one_memory. Blocco 2 (D15, stato post-rollback): - campo `phase` su DecisionRecord + effective_decisions phase-aware per i subject "a nome" (cte_approved ecc.); _compute_promotions e finalize sulla vista effective; finalize confronta col piano CTE effettivo, non glob; `decision add --retracts` + comando `decision retract`. Blocco 3 (D7 read-only + D6 manifest): - assert_read_only su tutti e quattro i codepath (direct + REST); - manifest author/summary/updated_at/updated_by/schema_version popolati + helper touch_manifest sulle mutazioni. Blocco 4-5 (D14a/D14b): - decision_min_phase data-driven via `emits:` in workflow.yaml; - formula evidence: status auto, search_formulas, gruppo CLI `tht formula`, `search find --kind formula`, load_evidence_dir salta i .sql.md. Blocco 6 (robustezza): - taskdoc slice promoted_tables + bound enforced; report escaping/bound + rsplit note; filtro kind reader REST/direct; conteggio upserted robusto; guard REST run_query non-list; LSH disallineato -> LshIndexError. Blocco 7 (pulizia): - dead code gate e KIND_TO_TABLE morto rimossi; doc Postgres-only (README + connection.py). Blocco 0 (parziale): test di compatibilità firma gate↔CLI (tests/integration). Rinviati: fake-Pi runtime completo, artifact-gate da disco (#23), parità eligibility REST/direct (#28), unificazione reserved-labels (#30), memory_rejected da deselezione (#33). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
90 lines
2.9 KiB
Python
90 lines
2.9 KiB
Python
import json
|
|
import pickle
|
|
from dataclasses import dataclass
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
from datasketch import MinHash, MinHashLSH
|
|
|
|
from tht.config import LshConfig
|
|
from tht.vendor.thoth_lsh import create_lsh_index, create_minhash
|
|
|
|
|
|
class LshIndexError(Exception):
|
|
pass
|
|
|
|
|
|
@dataclass
|
|
class LshHit:
|
|
table: str
|
|
column: str
|
|
value: str
|
|
score: float
|
|
|
|
|
|
def build_index(
|
|
values: dict[str, dict[str, list[str]]], cfg: LshConfig, verbose: bool = False
|
|
) -> tuple[MinHashLSH, dict[str, tuple[MinHash, str, str, str]]]:
|
|
return create_lsh_index(
|
|
values, signature_size=cfg.signature_size, n_gram=cfg.n_gram,
|
|
threshold=cfg.threshold, verbose=verbose,
|
|
)
|
|
|
|
|
|
def _paths(directory: Path, name: str) -> tuple[Path, Path, Path]:
|
|
return (
|
|
directory / f"{name}_lsh.pkl",
|
|
directory / f"{name}_minhashes.pkl",
|
|
directory / f"{name}_meta.json",
|
|
)
|
|
|
|
|
|
def save_index(lsh, minhashes, cfg: LshConfig, directory: Path, name: str) -> None:
|
|
directory.mkdir(parents=True, exist_ok=True)
|
|
lsh_path, mh_path, meta_path = _paths(directory, name)
|
|
lsh_path.write_bytes(pickle.dumps(lsh))
|
|
mh_path.write_bytes(pickle.dumps(minhashes))
|
|
meta_path.write_text(
|
|
json.dumps(
|
|
{"signature_size": cfg.signature_size, "n_gram": cfg.n_gram,
|
|
"threshold": cfg.threshold, "entries": len(minhashes)},
|
|
indent=2,
|
|
)
|
|
)
|
|
|
|
|
|
def load_index(directory: Path, name: str) -> tuple[Any, Any, dict]:
|
|
lsh_path, mh_path, meta_path = _paths(directory, name)
|
|
if not (lsh_path.exists() and mh_path.exists() and meta_path.exists()):
|
|
raise LshIndexError(
|
|
f"Indice LSH non trovato in {directory} (atteso {name}_lsh.pkl). "
|
|
f"Esegui prima `tht lsh build`."
|
|
)
|
|
lsh = pickle.loads(lsh_path.read_bytes())
|
|
minhashes = pickle.loads(mh_path.read_bytes())
|
|
meta = json.loads(meta_path.read_text())
|
|
return lsh, minhashes, meta
|
|
|
|
|
|
def query_index(lsh, minhashes, keyword: str, meta: dict, top_n: int = 10) -> list[LshHit]:
|
|
"""Query con score: i parametri MinHash vengono dal meta dell'indice, non dalla config.
|
|
|
|
Se i due pickle (`*_lsh.pkl` e `*_minhashes.pkl`) sono disallineati (rigenerati
|
|
separatamente) `lsh.query` puo' restituire chiavi assenti da `minhashes`: si solleva
|
|
LshIndexError azionabile invece di un KeyError opaco."""
|
|
qmh = create_minhash(meta["signature_size"], keyword, meta["n_gram"])
|
|
scored = []
|
|
for key in lsh.query(qmh):
|
|
entry = minhashes.get(key)
|
|
if entry is None:
|
|
raise LshIndexError(
|
|
"Indice LSH disallineato (lsh.pkl e minhashes.pkl non coerenti): "
|
|
"rigenera con `tht lsh build`."
|
|
)
|
|
scored.append((key, qmh.jaccard(entry[0])))
|
|
scored.sort(key=lambda kv: kv[1], reverse=True)
|
|
return [
|
|
LshHit(table=minhashes[k][1], column=minhashes[k][2], value=minhashes[k][3], score=s)
|
|
for k, s in scored[:top_n]
|
|
]
|