arborist/tests/test_reclassify.py
russell@unturf.com 01a4390693
verify: layered strategies + entity policies, rename VISUAL → UNGROUNDED
- aborist/qa/verify.py: three strategies tried in sequence. quote uses
  sequential pairing (1st & 2nd `"`, 3rd & 4th, ...) which eliminates
  the phantom inter-pair captures regex pairing produced on adjacent
  quote pairs like `"title" prose "quote"`. span checks bullet/sentence
  lines verbatim. entity matches multi-word proper nouns; gated by
  policy ∈ {strict, hybrid, drop, proximity}. Default proximity
  promotes to STRICT only when N=3 verified entities cluster within
  W=300 chars in source — separates structural grounding (cast list,
  infobox) from incidental mention (scattered plot summary).

- aborist/store.py: schema CHECK now `('STRICT','HYBRID','UNGROUNDED')`.
  Migration helper rebuilds legacy `('STRICT','HYBRID','VISUAL')`
  tables via temp-table copy, translating VISUAL → UNGROUNDED in the
  SELECT. Idempotent — DDL inspection skips the rebuild on already-
  migrated DBs.

- aborist/cli.py: new `aborist reclassify` re-runs the verifier
  against existing live records under the current entity policy; no
  LLM calls. --compare runs all four policies side-by-side, --dry-run
  reports transitions without writing. Cold-source records skipped.
  One providence_reclassify audit event per changed row.

- AuditMode.UNGROUNDED replaces VISUAL across search backend, FTS5,
  test fixtures, CLAUDE.md. The substrate (Merkle-AGI) name was
  about FOR-style visualization; in the RAG layer the semantic is
  "no recoverable grounding," so the label now says that.

DEFAULT_QUERY_POLICY gains entity_policy + entity_proximity_n +
entity_proximity_window so any tuning folds into governance_policy_hash
and invalidates cache cleanly.
2026-04-28 16:58:31 -04:00

215 lines
6.7 KiB
Python

"""`aborist reclassify` — re-runs the verifier against live providence records.
Covers:
- Stale UNGROUNDED records become STRICT/HYBRID/etc when the new verifier
finds grounding via span/entity paths.
- Already-correct records stay unchanged.
- Cold-source records (where any source doc has no hot chunks) are
skipped — we cannot reclassify without context.
- --dry-run reports transitions without writing.
- Each changed record writes one 'providence_reclassify' audit event.
"""
from __future__ import annotations
import argparse
import json
from typing import Iterator
from aborist.cli import _cmd_reclassify
from aborist.document import Document
from aborist.ingest import ingest_source
from aborist.qa import query
from aborist.qa.client import StubClient
from aborist.source import Source
from aborist.store import connect
class _FakeSource(Source):
source_type = "test"
def __init__(self, docs):
self.docs = docs
def iter_documents(self) -> Iterator[Document]:
yield from self.docs
def _doc(uri, content):
return Document(uri=uri, content=content, source_type="test", title=uri)
def _build_corpus_and_query(tmp_path, answer_text):
"""Ingest one doc, run a query with `answer_text` from a stub client,
return (qa_db, main_db, cache_key, conn-factory)."""
main_db = tmp_path / "corpus.db"
qa_db = tmp_path / "qa.db"
conn = connect(main_db)
try:
ingest_source(
conn,
_FakeSource([
_doc(
"test://matrix",
"Keanu Reeves stars as Thomas A. Anderson. "
"Laurence Fishburne plays Morpheus. "
"Carrie-Anne Moss plays Trinity. "
"Hugo Weaving plays Agent Smith.",
)
]),
)
finally:
conn.close()
client = StubClient(answer=answer_text)
result = query(
question="who stars in The Matrix?",
qa_db=qa_db,
chat_client=client,
model_id="test-model",
single_db=main_db,
top_k=1,
)
return qa_db, main_db, result["cache_key"]
def _make_args(qa_db, dry_run=False, limit=0, entity_policy=None, compare=False):
return argparse.Namespace(
qa_db=str(qa_db),
global_shards_dir=None,
dry_run=dry_run,
limit=limit,
entity_policy=entity_policy,
compare=compare,
)
def test_reclassify_promotes_stale_visual_via_entity_path(tmp_path, capsys):
"""Stub answer with no quotes but verbatim entity names. The query
persists UNGROUNDED/none if the verifier ran first; we then mutate the
row to simulate an OLDER record (pre-layered-verifier), and reclassify."""
answer = (
"The cast includes Keanu Reeves, Laurence Fishburne, "
"Carrie-Anne Moss, and Hugo Weaving."
)
qa_db, _, ckey = _build_corpus_and_query(tmp_path, answer)
# Force the row into a stale state: UNGROUNDED/none/0 — what the old
# quote-only verifier would have written.
conn = connect(qa_db)
try:
conn.execute(
"UPDATE providence_cache SET audit_mode='UNGROUNDED', "
" verifier_method='none', n_quotes=0, n_verified=0, "
" unverified_quotes=NULL "
"WHERE cache_key = ?",
(ckey,),
)
finally:
conn.close()
rc = _cmd_reclassify(_make_args(qa_db))
assert rc == 0
out = json.loads(capsys.readouterr().out)
assert out["examined"] == 1
assert out["changed"] == 1
assert out["skipped_cold"] == 0
# Row reflects the new verdict.
conn = connect(qa_db)
try:
row = conn.execute(
"SELECT audit_mode, verifier_method, n_verified FROM providence_cache "
"WHERE cache_key = ?",
(ckey,),
).fetchone()
assert row["audit_mode"] in ("STRICT", "HYBRID")
assert row["verifier_method"] == "entity"
assert row["n_verified"] >= 3
# Audit event recorded.
last = conn.execute(
"SELECT event_type FROM audit_events ORDER BY seq DESC LIMIT 1"
).fetchone()
assert last["event_type"] == "providence_reclassify"
finally:
conn.close()
def test_reclassify_unchanged_when_already_correct(tmp_path, capsys):
"""Re-running reclassify on a correctly-labeled record is a no-op."""
answer = (
"The cast includes Keanu Reeves, Laurence Fishburne, "
"Carrie-Anne Moss, and Hugo Weaving."
)
qa_db, _, _ = _build_corpus_and_query(tmp_path, answer)
# First pass classifies correctly via the entity path. Reclassify
# should report unchanged.
rc = _cmd_reclassify(_make_args(qa_db))
assert rc == 0
out = json.loads(capsys.readouterr().out)
assert out["examined"] == 1
assert out["unchanged"] == 1
assert out["changed"] == 0
def test_reclassify_dry_run_does_not_write(tmp_path, capsys):
"""--dry-run reports transitions but leaves the row untouched."""
answer = (
"The cast includes Keanu Reeves, Laurence Fishburne, "
"Carrie-Anne Moss, and Hugo Weaving."
)
qa_db, _, ckey = _build_corpus_and_query(tmp_path, answer)
# Force stale state.
conn = connect(qa_db)
try:
conn.execute(
"UPDATE providence_cache SET audit_mode='UNGROUNDED', "
" verifier_method='none', n_quotes=0, n_verified=0 "
"WHERE cache_key = ?",
(ckey,),
)
finally:
conn.close()
rc = _cmd_reclassify(_make_args(qa_db, dry_run=True))
assert rc == 0
out = json.loads(capsys.readouterr().out)
assert out["dry_run"] is True
assert out["changed"] == 1
# Row was NOT updated.
conn = connect(qa_db)
try:
row = conn.execute(
"SELECT audit_mode, verifier_method FROM providence_cache "
"WHERE cache_key = ?",
(ckey,),
).fetchone()
assert row["audit_mode"] == "UNGROUNDED"
assert row["verifier_method"] == "none"
finally:
conn.close()
def test_reclassify_skips_cold_source(tmp_path, capsys):
"""If the source doc's chunks are cold (content NULL), the loader
returns None and we cannot reclassify — record is skipped."""
answer = "Keanu Reeves stars in this film."
qa_db, main_db, ckey = _build_corpus_and_query(tmp_path, answer)
# Evict all chunks of the source doc to cold. Loader will return None.
conn = connect(main_db)
try:
conn.execute("UPDATE chunks SET content = NULL, tier = 'cold'")
finally:
conn.close()
rc = _cmd_reclassify(_make_args(qa_db))
assert rc == 0
out = json.loads(capsys.readouterr().out)
assert out["examined"] == 1
assert out["skipped_cold"] == 1
assert out["changed"] == 0