arborist/tests/test_reclassify.py
russell@unturf.com 8d6961fcc1
aborist/arborist
modified:   .gitlab-ci.yml
	modified:   bench/qa_questions.txt
	modified:   bench/qa_sweep.py
	modified:   bench/run.sh
	modified:   docs/TICKETS.md
	modified:   docs/_source/README.md
	modified:   docs/_source/_ext/makefile_targets.py
	modified:   docs/_source/api/cli.rst
	modified:   docs/_source/api/distill.rst
	modified:   docs/_source/api/mesh.rst
	modified:   docs/_source/api/qa.rst
	modified:   docs/_source/api/retrieval.rst
	modified:   docs/_source/api/storage.rst
	modified:   docs/_source/api/substrate.rst
	modified:   docs/_source/concepts.rst
	modified:   docs/_source/conf.py
	modified:   docs/_source/cookbook.rst
	modified:   docs/_source/index.rst
	modified:   docs/_source/license.rst
	modified:   docs/_source/quickstart.rst
	modified:   docs/bench-maxing.md
	modified:   docs/benchmarks.md
	modified:   docs/cti-architecture.md
	modified:   docs/diagrams/aborist-modules.dot
	modified:   docs/diagrams/aborist-modules.svg
	modified:   docs/diagrams/mesh-data-flow.dot
	modified:   docs/diagrams/mesh-epoch-lifecycle.dot
	modified:   docs/diagrams/mesh-epoch-lifecycle.svg
	modified:   docs/diagrams/mesh-group-decisions.dot
	modified:   docs/diagrams/mesh-group-decisions.svg
	modified:   docs/diagrams/mesh-identity-stack.dot
	modified:   docs/diagrams/mesh-secret-envelope.dot
	modified:   docs/mesh.md
	modified:   docs/qa-modes-bench.md
	modified:   docs/seven-point-program.md
	modified:   docs/tickets/ticket-000001-retrieval-keywords-audit-gap.md
	modified:   docs/tickets/ticket-000002-reference-frame-polarity-contract.md
	modified:   docs/tickets/ticket-000003-anchor-class-warrant.md
	modified:   docs/tickets/ticket-000005-label-ladder-migration.md
	modified:   docs/tickets/ticket-000006-bench-emergent-findings.md
	modified:   docs/tickets/ticket-000007-query-layer-hyphen-fold.md
	modified:   docs/tickets/ticket-000008-broad-quantifier-preflight-guard.md
	modified:   docs/tickets/ticket-000009-quantifier-preflight-dag-binding.md
	modified:   docs/tickets/ticket-000010-metacognition-preflight-guard.md
	modified:   docs/tickets/ticket-000011-soft-preflight-hint-sidecar.md
	modified:   scripts/backfill_concepts.py
	modified:   scripts/bench_emergent.py
	modified:   tests/crawler/test_async_web_fetcher.py
	modified:   tests/crawler/test_bridge.py
	modified:   tests/crawler/test_web_fetch.py
	modified:   tests/test_bench_qa_sweep.py
	modified:   tests/test_burn.py
	modified:   tests/test_burn_doc.py
	modified:   tests/test_claim_lattice.py
	modified:   tests/test_cli_render.py
	modified:   tests/test_compress.py
	modified:   tests/test_concepts.py
	modified:   tests/test_dag.py
	modified:   tests/test_directives.py
	modified:   tests/test_distill.py
	modified:   tests/test_distill_recursive.py
	modified:   tests/test_evict.py
	modified:   tests/test_frame.py
	modified:   tests/test_grok_source.py
	modified:   tests/test_html_source.py
	modified:   tests/test_ingest.py
	modified:   tests/test_inspect.py
	modified:   tests/test_journal.py
	modified:   tests/test_keys.py
	modified:   tests/test_llm_context_base.py
	modified:   tests/test_merkle.py
	modified:   tests/test_mesh.py
	modified:   tests/test_mesh_aead.py
	modified:   tests/test_mesh_chain.py
	modified:   tests/test_mesh_cli.py
	modified:   tests/test_mesh_cli_pull.py
	modified:   tests/test_mesh_wire.py
	modified:   tests/test_mesh_wire_e2e.py
	modified:   tests/test_metacognition.py
	modified:   tests/test_migration_audit_mode.py
	modified:   tests/test_providence_source.py
	modified:   tests/test_qa.py
	modified:   tests/test_qa_quality_live.py
	modified:   tests/test_quantifier_caps.py
	modified:   tests/test_quantifier_classifier.py
	modified:   tests/test_quantifier_phase4.py
	modified:   tests/test_quantifier_reminder.py
	modified:   tests/test_query.py
	modified:   tests/test_reclassify.py
	modified:   tests/test_repair.py
	modified:   tests/test_resume.py
	modified:   tests/test_snapshot.py
	modified:   tests/test_soft_preflight.py
	modified:   tests/test_tfidf.py
	modified:   tests/test_vcs_source.py
	modified:   tests/test_verify.py
	modified:   tests/test_verify_json.py
	modified:   tests/test_versioned_ingest.py
	modified:   tests/test_warrant.py
	modified:   tests/test_wikipedia_old.py
	modified:   tests/test_wikipedia_xml.py
	modified:   tests/test_wikitext.py
2026-05-07 09:31:49 -04:00

215 lines
6.7 KiB
Python

"""`arborist 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 arborist.cli import _cmd_reclassify
from arborist.document import Document
from arborist.ingest import ingest_source
from arborist.qa import query
from arborist.qa.client import StubClient
from arborist.source import Source
from arborist.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