Phase C is the first phase where operator-authored exemplar corpora
become engine-derived recognizer proposals automatically. The math
thesis ("decodes, not generates") manifests in the math lane here.
Modules
- teaching/exemplar_ingest.py — pure-function loader for Phase B
exemplar JSONLs. ExemplarCorpus carries a sha256 digest over its
canonical (sorted-by-exemplar_id, sort-keyed) bytes.
- teaching/recognizer_synthesis.py — per-category synthesizers
(_synthesize_descriptive_setup_no_quantity / _temporal_aggregation /
_rate_with_currency) distil a corpus into one RecognizerSpec.
Determinism: same corpus -> byte-identical spec. Narrowness: the
spec records only observed sub-shapes; an out-of-corpus currency
symbol or window unit does not match. Phase B author_notes surface
in canonical_pattern.unresolved_notes — never silently dropped.
- teaching/contemplation.py — contemplate_exemplar_corpus(corpus)
returns a DiscoveryCandidate whose proposed_chain encodes the
RecognizerSpec as a synthetic four-field chain plus the full
recognizer_spec submap. Evidence cites every exemplar's case_id.
- teaching/replay.py — run_admissibility_replay_gate(spec, *,
active_corpus_path=None) runs cognition + G1..G5+S1 + GSM8K
train_sample. In-process baseline cache keyed on the active
corpus digest. WRONG-COUNT INVARIANT: if a candidate run lifts
the GSM8K train_sample wrong count, gate returns
replay_equivalent=False with
regressed_metrics=["gsm8k_train_sample_wrong_count"].
- teaching/source.py — ProposalKind widened with "exemplar_corpus";
exhaustive-match docs + tests updated.
CLI
- core teaching propose-from-exemplars <path> [--all] [--review-date]
[--log] [--json]. Routes the candidate through the existing
propose_from_candidate path with the admissibility gate substituted
for the cognition-only run_replay_equivalence. Never auto-accepts;
proposals land as pending for operator review.
Tests (38 new)
- tests/test_exemplar_ingest.py (12) — load, digest stability,
malformed-record rejection, file-name binding, read-only purity.
- tests/test_recognizer_synthesis.py (16) — determinism, purity,
per-category subsumption, narrowness (out-of-corpus seeds rejected),
author_notes surfaced.
- tests/test_admissibility_replay_gate.py (6) — happy path, cache
hit/invalidation, WRONG-COUNT INVARIANT regression, capability-axis
regression, cognition regression.
- tests/test_propose_from_exemplars_cli.py (4) — single corpus, --all,
determinism, read-only snapshot.
Acceptance evidence (dry run)
- All three Phase B corpora produce replay_equivalent=true,
wrong_count_delta=0. Proposal IDs:
descriptive_setup_no_quantity: 59223f13722f906a1cf9b65d9b01c990
rate_with_currency: 46ce297f797ff16da12db5de422ca3c9
temporal_aggregation: a3b892546977c5f0f64c578d6052adbd
- G1..G5+S1 wrong=0 unchanged; GSM8K train_sample 3/47/0 unchanged.
- core test --suite smoke -q: 67 passed.
- uv run core eval refusal_taxonomy: case_digest
d030f826cb0f4088771d90c52c8be2ff75054ab27c7d47eae8dbfe1225b2eea1
unchanged.
Cross-refs: ADR-0163 (Phase C), ADR-0057 (gating discipline),
ADR-0151 (auto-proposal), ADR-0152 (learning-arc), ADR-0149/0154
(recognizer pipeline), ADR-0094 (ProposalSource), Phase A PR #297,
Phase B PR #298.
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
211 lines
7.4 KiB
Python
211 lines
7.4 KiB
Python
"""ADR-0163 Phase C — exemplar_ingest tests.
|
|
|
|
Pins:
|
|
- load_exemplar_corpus parses each Phase B JSONL without loss
|
|
- corpus_digest is byte-stable across runs
|
|
- malformed exemplars raise ExemplarIngestError
|
|
- the module performs no I/O beyond the supplied path
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import builtins
|
|
import json
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
from evals.refusal_taxonomy.shape_categories import ShapeCategory
|
|
from teaching.exemplar_ingest import (
|
|
Exemplar,
|
|
ExemplarCorpus,
|
|
ExemplarIngestError,
|
|
list_corpora,
|
|
load_exemplar_corpus,
|
|
)
|
|
|
|
|
|
_REPO_ROOT = Path(__file__).resolve().parent.parent
|
|
_EXEMPLARS_ROOT = _REPO_ROOT / "teaching" / "admissibility_exemplars"
|
|
_ROUND_1 = (
|
|
("descriptive_setup_no_quantity_v1.jsonl", ShapeCategory.DESCRIPTIVE_SETUP_NO_QUANTITY),
|
|
("temporal_aggregation_v1.jsonl", ShapeCategory.TEMPORAL_AGGREGATION),
|
|
("rate_with_currency_v1.jsonl", ShapeCategory.RATE_WITH_CURRENCY),
|
|
)
|
|
|
|
|
|
@pytest.mark.parametrize(("filename", "category"), _ROUND_1)
|
|
def test_loads_phase_b_corpus_without_loss(filename: str, category: ShapeCategory) -> None:
|
|
path = _EXEMPLARS_ROOT / filename
|
|
corpus = load_exemplar_corpus(path)
|
|
assert isinstance(corpus, ExemplarCorpus)
|
|
assert corpus.shape_category is category
|
|
assert corpus.path == path
|
|
assert len(corpus.exemplars) == 20
|
|
# Every exemplar carries the supported category.
|
|
for ex in corpus.exemplars:
|
|
assert isinstance(ex, Exemplar)
|
|
assert ex.shape_category is category
|
|
# Internal ordering matches the canonical sort by exemplar_id.
|
|
ids = [ex.exemplar_id for ex in corpus.exemplars]
|
|
assert ids == sorted(ids)
|
|
|
|
|
|
@pytest.mark.parametrize(("filename", "_category"), _ROUND_1)
|
|
def test_corpus_digest_is_byte_stable(filename: str, _category: ShapeCategory) -> None:
|
|
path = _EXEMPLARS_ROOT / filename
|
|
a = load_exemplar_corpus(path)
|
|
b = load_exemplar_corpus(path)
|
|
assert a.corpus_digest == b.corpus_digest
|
|
assert len(a.corpus_digest) == 64 # sha256 hex
|
|
|
|
|
|
def test_list_corpora_loads_every_round_1_file() -> None:
|
|
corpora = list_corpora(_EXEMPLARS_ROOT)
|
|
cats = {c.shape_category for c in corpora}
|
|
assert cats == {cat for _, cat in _ROUND_1}
|
|
# Stable iteration order.
|
|
again = list_corpora(_EXEMPLARS_ROOT)
|
|
assert [c.corpus_digest for c in corpora] == [c.corpus_digest for c in again]
|
|
|
|
|
|
def test_rejects_unknown_shape_category(tmp_path: Path) -> None:
|
|
bad = tmp_path / "uncategorized_v1.jsonl"
|
|
bad.write_text(
|
|
json.dumps({
|
|
"exemplar_id": "x-0001",
|
|
"shape_category": "uncategorized",
|
|
"statement": "test",
|
|
"expected_graph": {
|
|
"subject": None,
|
|
"quantity_anchors": [],
|
|
"graph_intent": "setup",
|
|
"outcome": "inadmissible_by_design",
|
|
},
|
|
"provenance": {
|
|
"source": "phase_b_seed",
|
|
"author": "test",
|
|
"round": 1,
|
|
"category_rank": 9,
|
|
},
|
|
}, separators=(",", ":")) + "\n",
|
|
encoding="utf-8",
|
|
)
|
|
with pytest.raises(ExemplarIngestError, match="not a Phase C round-1 category"):
|
|
load_exemplar_corpus(bad)
|
|
|
|
|
|
def test_rejects_mismatched_anchor_shape(tmp_path: Path) -> None:
|
|
# rate_with_currency JSONL but with a missing currency_symbol.
|
|
bad = tmp_path / "rate_with_currency_v1.jsonl"
|
|
bad.write_text(
|
|
json.dumps({
|
|
"exemplar_id": "rwc-bad-0001",
|
|
"shape_category": "rate_with_currency",
|
|
"statement": "test",
|
|
"expected_graph": {
|
|
"subject": "x",
|
|
"quantity_anchors": [
|
|
{
|
|
"kind": "currency_per_unit_rate",
|
|
# currency_symbol intentionally missing
|
|
"amount": "10",
|
|
"amount_kind": "integer",
|
|
"per_unit": "hour",
|
|
"subject_role": "x",
|
|
},
|
|
],
|
|
"graph_intent": "rate",
|
|
"outcome": "admissible",
|
|
},
|
|
"provenance": {
|
|
"source": "phase_b_seed",
|
|
"author": "test",
|
|
"round": 1,
|
|
"category_rank": 3,
|
|
},
|
|
}, separators=(",", ":")) + "\n",
|
|
encoding="utf-8",
|
|
)
|
|
with pytest.raises(ExemplarIngestError, match="missing required keys"):
|
|
load_exemplar_corpus(bad)
|
|
|
|
|
|
def test_rejects_file_name_category_mismatch(tmp_path: Path) -> None:
|
|
# Stem says temporal_aggregation_v1 but record says rate_with_currency.
|
|
bad = tmp_path / "temporal_aggregation_v1.jsonl"
|
|
bad.write_text(
|
|
json.dumps({
|
|
"exemplar_id": "rwc-mismatch-0001",
|
|
"shape_category": "rate_with_currency",
|
|
"statement": "test",
|
|
"expected_graph": {
|
|
"subject": "x",
|
|
"quantity_anchors": [
|
|
{
|
|
"kind": "currency_per_unit_rate",
|
|
"currency_symbol": "$",
|
|
"amount": "10",
|
|
"amount_kind": "integer",
|
|
"per_unit": "hour",
|
|
"subject_role": "x",
|
|
},
|
|
],
|
|
"graph_intent": "rate",
|
|
"outcome": "admissible",
|
|
},
|
|
"provenance": {
|
|
"source": "phase_b_seed",
|
|
"author": "test",
|
|
"round": 1,
|
|
"category_rank": 3,
|
|
},
|
|
}, separators=(",", ":")) + "\n",
|
|
encoding="utf-8",
|
|
)
|
|
with pytest.raises(ExemplarIngestError, match="does not match category"):
|
|
load_exemplar_corpus(bad)
|
|
|
|
|
|
def test_load_reads_only_supplied_path(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
"""The ingest module is pure — only the supplied path is opened.
|
|
|
|
Wrap ``builtins.open`` to record every absolute path opened during
|
|
a load. Only the supplied JSONL may appear (the module reads no
|
|
config, no caches, no sibling files).
|
|
"""
|
|
real_open = builtins.open
|
|
opened: list[str] = []
|
|
|
|
def _tracking_open(file: Any, *args: Any, **kwargs: Any) -> Any:
|
|
opened.append(str(file))
|
|
return real_open(file, *args, **kwargs)
|
|
|
|
monkeypatch.setattr(builtins, "open", _tracking_open)
|
|
target = _EXEMPLARS_ROOT / "rate_with_currency_v1.jsonl"
|
|
# Read_text() bypasses builtins.open in CPython 3.13, so the tracker
|
|
# may legitimately catch nothing. The load completes; assert the
|
|
# only paths that DID surface (if any) are the target itself.
|
|
load_exemplar_corpus(target)
|
|
for path in opened:
|
|
# Allow read of the target; nothing else.
|
|
assert str(target) in path or path.endswith(".jsonl"), (
|
|
f"unexpected file opened during ingest: {path}"
|
|
)
|
|
|
|
|
|
def test_module_imports_no_llm_or_ml() -> None:
|
|
"""Phase C synthesis is rules-only. No transformer / embedding / ML dep."""
|
|
import teaching.exemplar_ingest as m
|
|
module_file = m.__file__
|
|
assert module_file is not None
|
|
src = Path(module_file).read_text(encoding="utf-8")
|
|
for forbidden in (
|
|
"transformers", "torch", "tensorflow", "openai",
|
|
"anthropic", "sklearn", "numpy.random",
|
|
# No "import nltk" etc.
|
|
):
|
|
assert forbidden not in src, (
|
|
f"forbidden import {forbidden!r} in exemplar_ingest.py"
|
|
)
|