portfolio-optimiser/tests/spikes/test_d_verdictstore.py

112 lines
4.1 KiB
Python

"""Spike D tests — non-tautological top-K retrieval (B2).
The true match shares the *structured* similarity fields with the query but uses different
description text; the decoys share surface description text but differ structurally. A
text-matching retriever would be fooled by the decoys — a structural one is not.
Pattern: tests/test_reference_domain.py.
"""
import pytest
from spikes.d_verdictstore import (
ExpeLContextProvider,
ProposalFeatures,
Verdict,
VerdictStore,
seed_store,
)
_QUERY = ProposalFeatures(
affected_codes=frozenset({"05.2", "03.1"}),
measure_type="scope_reduction",
claimed_saving_nok=220_000, # bucket [100k, 500k)
description="asphalt base course reduction near school",
)
def _store_with_true_match_and_decoys() -> tuple[VerdictStore, str]:
true_match = Verdict(
id="TRUE",
proposal_features=ProposalFeatures(
affected_codes=frozenset({"05.2", "03.1"}), # same codes
measure_type="scope_reduction", # same measure type
claimed_saving_nok=200_000, # same magnitude bucket
description="zzz totally unrelated wording alpha beta", # DIFFERENT text
),
decision="approved",
rationale="prior scope reduction on the same codes was approved",
)
# Decoys share the query's SURFACE text but differ structurally (disjoint codes,
# different measure type, different magnitude bucket).
decoy_low = Verdict(
id="DECOY-LOW",
proposal_features=ProposalFeatures(
affected_codes=frozenset({"09.1"}),
measure_type="rate_renegotiation",
claimed_saving_nok=50_000, # bucket [0, 100k)
description="asphalt base course reduction near school", # same words as query
),
decision="rejected",
rationale="surface-text decoy",
)
decoy_high = Verdict(
id="DECOY-HIGH",
proposal_features=ProposalFeatures(
affected_codes=frozenset({"21.2"}),
measure_type="material_substitution",
claimed_saving_nok=700_000, # bucket [500k, 1M)
description="asphalt base course reduction extra words",
),
decision="rejected",
rationale="surface-text decoy",
)
# Order deliberately not putting the true match first.
return VerdictStore(verdicts=[decoy_low, true_match, decoy_high]), "TRUE"
def test_retrieve_finds_structural_match_over_text_decoys() -> None:
store, true_id = _store_with_true_match_and_decoys()
hits = store.retrieve(_QUERY, k=3)
assert hits[0].id == true_id # structural match ranks #1 despite different wording
assert true_id in {h.id for h in hits[:1]} # within top-K (top-1 here)
def test_retrieve_is_deterministic() -> None:
store, _ = _store_with_true_match_and_decoys()
assert [h.id for h in store.retrieve(_QUERY, k=3)] == [
h.id for h in store.retrieve(_QUERY, k=3)
]
def test_retrieve_rejects_non_positive_k() -> None:
store, _ = _store_with_true_match_and_decoys()
with pytest.raises(ValueError):
store.retrieve(_QUERY, k=0)
def test_seed_store_has_10_to_20_verdicts() -> None:
store = seed_store()
assert 10 <= len(store.verdicts) <= 20
class _RecordingContext:
"""Duck-typed stand-in for SessionContext — records injected instructions without
depending on the (private) SessionContext internals."""
def __init__(self) -> None:
self.instructions: list[str] = []
def extend_instructions(self, items: list[str]) -> None:
self.instructions.extend(items)
async def test_expel_provider_injects_retrieved_fewshot() -> None:
store, true_id = _store_with_true_match_and_decoys()
provider = ExpeLContextProvider(store, _QUERY, k=2)
# The deterministic deliverable: the few-shot text carries the retrieved true match.
assert true_id in provider.format_fewshot()
# The injection hook (real ContextProvider.before_run signature) extends instructions.
ctx = _RecordingContext()
await provider.before_run(agent=None, session=None, context=ctx, state={})
assert len(ctx.instructions) == 1
assert true_id in ctx.instructions[0]