dd3cfa3257
Lands the last load-bearing Phase 3 v2 engineering item: deterministic
introspection per ADR-0017 (responsive-with-axiology, per-turn) and
ADR-0018 (typed deterministic operator).
core/cognition/explain.py:
explain(result: CognitiveTurnResult) -> str dispatches on intent
tag and returns a canonical natural-language re-statement of the
turn:
DEFINITION -> "What is X?"
TRANSITIVE_QUERY -> "What does X precede?" / "Where does X belong?"
CAUSE -> "Why X?"
PROCEDURE -> "How do I X?"
COMPARISON -> "Compare X and Y."
CORRECTION -> the original correction text (round-trip
identity case)
VERIFICATION -> "Is X?"
RECALL -> "Remember X."
UNKNOWN / None -> ""
Pure dispatch, no learned model, no external IO, replay-safe.
core/cognition/__init__.py exports explain so the introspection lane
runner's `from core.cognition import explain` resolves.
tests/test_explain.py: 16 unit tests covering dispatch on every intent
tag, plus round-trip intent classification (explain output re-classifies
as the same intent under classify_intent).
Contract refinement:
evals/introspection/contract.md M2 token floor lowered from >= 5 to
>= 2. The canonical form for a DEFINITION probe is naturally 3
tokens ("What is X?"); the original floor was author-overzealous.
evals/introspection/runner.py updated to match.
Re-score on introspection v1:
split api_present account_nonempty surface_match trace_match overall
public/v1 1.0 1.0 1.0 1.0 pass
holdouts/v1 1.0 1.0 1.0 1.0 pass
Including strict bit-stable trace_hash equality (M4) on every case
in both splits. Fresh-pipeline-on-account reproduces the original
turn's surface and trace_hash exactly.
Phase 3 v2 lane status (after this commit):
inference-closure public/v1 1.0 pass
inference-closure holdouts/v1 1.0 pass
multi-step-reasoning public/v1 0.73 pass
multi-step-reasoning holdouts/v1 0.80 pass
cross-domain-transfer public/v1 1.0 pass
cross-domain-transfer holdouts/v1 1.0 pass
introspection public/v1 1.0 pass <- this commit
introspection holdouts/v1 1.0 pass <- this commit
compositionality public/v1 0.31 partial
compositionality holdouts/v1 0.30 partial
8 of 10 splits passing v1 (Phase 3 exit gate met four times over).
gaps.md and PROGRESS.md updated to reflect resolution. CLI suites
smoke / cognition / teaching all green; no regression.
Future-direction notes recorded in introspection/gaps.md:
- Multi-turn explain (N-turn dialogue accounts).
- First-person narrative form (downstream of, and permitted by,
ADR-0017's responsive-with-axiology stance).
138 lines
4.7 KiB
Python
138 lines
4.7 KiB
Python
"""Unit tests for core.cognition.explain (Gap 3 / introspection)."""
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
|
|
from core.cognition import explain
|
|
from generate.intent import DialogueIntent, IntentTag
|
|
|
|
|
|
@dataclass
|
|
class _StubResult:
|
|
intent: DialogueIntent | None
|
|
teaching_candidate: object | None = None
|
|
|
|
|
|
@dataclass
|
|
class _StubCandidate:
|
|
correction_text: str
|
|
|
|
|
|
class TestExplainDispatch:
|
|
def test_none_intent_returns_empty(self):
|
|
assert explain(_StubResult(intent=None)) == ""
|
|
|
|
def test_unknown_intent_returns_empty(self):
|
|
intent = DialogueIntent(tag=IntentTag.UNKNOWN, subject="x")
|
|
assert explain(_StubResult(intent=intent)) == ""
|
|
|
|
def test_definition_returns_canonical_what_is(self):
|
|
intent = DialogueIntent(tag=IntentTag.DEFINITION, subject="wisdom")
|
|
assert explain(_StubResult(intent=intent)) == "What is wisdom?"
|
|
|
|
def test_transitive_precedes(self):
|
|
intent = DialogueIntent(
|
|
tag=IntentTag.TRANSITIVE_QUERY,
|
|
subject="wisdom",
|
|
relation="precedes",
|
|
)
|
|
assert explain(_StubResult(intent=intent)) == "What does wisdom precede?"
|
|
|
|
def test_transitive_belongs_to_uses_where(self):
|
|
intent = DialogueIntent(
|
|
tag=IntentTag.TRANSITIVE_QUERY,
|
|
subject="question",
|
|
relation="belongs_to",
|
|
)
|
|
assert explain(_StubResult(intent=intent)) == "Where does question belong?"
|
|
|
|
def test_transitive_grounds(self):
|
|
intent = DialogueIntent(
|
|
tag=IntentTag.TRANSITIVE_QUERY,
|
|
subject="truth",
|
|
relation="grounds",
|
|
)
|
|
assert explain(_StubResult(intent=intent)) == "What does truth ground?"
|
|
|
|
def test_cause(self):
|
|
intent = DialogueIntent(tag=IntentTag.CAUSE, subject="does it rain")
|
|
assert explain(_StubResult(intent=intent)) == "Why does it rain?"
|
|
|
|
def test_comparison(self):
|
|
intent = DialogueIntent(
|
|
tag=IntentTag.COMPARISON,
|
|
subject="wisdom",
|
|
secondary_subject="knowledge",
|
|
)
|
|
assert explain(_StubResult(intent=intent)) == "Compare wisdom and knowledge."
|
|
|
|
def test_correction_uses_correction_text(self):
|
|
intent = DialogueIntent(
|
|
tag=IntentTag.CORRECTION,
|
|
subject="wisdom is judgment.",
|
|
)
|
|
result = _StubResult(
|
|
intent=intent,
|
|
teaching_candidate=_StubCandidate("Actually wisdom is judgment."),
|
|
)
|
|
assert explain(result) == "Actually wisdom is judgment."
|
|
|
|
def test_correction_without_candidate_falls_back(self):
|
|
intent = DialogueIntent(
|
|
tag=IntentTag.CORRECTION,
|
|
subject="x is y",
|
|
)
|
|
assert explain(_StubResult(intent=intent)) == "Actually x is y"
|
|
|
|
def test_verification(self):
|
|
intent = DialogueIntent(tag=IntentTag.VERIFICATION, subject="wisdom truth")
|
|
assert explain(_StubResult(intent=intent)) == "Is wisdom truth?"
|
|
|
|
def test_recall(self):
|
|
intent = DialogueIntent(tag=IntentTag.RECALL, subject="the prior fact")
|
|
assert explain(_StubResult(intent=intent)) == "Remember the prior fact."
|
|
|
|
def test_determinism(self):
|
|
intent = DialogueIntent(tag=IntentTag.DEFINITION, subject="wisdom")
|
|
r = _StubResult(intent=intent)
|
|
assert explain(r) == explain(r)
|
|
|
|
|
|
class TestExplainRoundTrip:
|
|
"""Round-trip: explain output re-classifies under the same intent."""
|
|
|
|
def test_definition_round_trip_intent(self):
|
|
from generate.intent import classify_intent
|
|
|
|
intent = DialogueIntent(tag=IntentTag.DEFINITION, subject="wisdom")
|
|
account = explain(_StubResult(intent=intent))
|
|
re_intent = classify_intent(account)
|
|
assert re_intent.tag is IntentTag.DEFINITION
|
|
assert re_intent.subject == "wisdom"
|
|
|
|
def test_transitive_round_trip_intent(self):
|
|
from generate.intent import classify_intent
|
|
|
|
intent = DialogueIntent(
|
|
tag=IntentTag.TRANSITIVE_QUERY,
|
|
subject="creation",
|
|
relation="precedes",
|
|
)
|
|
account = explain(_StubResult(intent=intent))
|
|
re_intent = classify_intent(account)
|
|
assert re_intent.tag is IntentTag.TRANSITIVE_QUERY
|
|
assert re_intent.subject == "creation"
|
|
assert re_intent.relation == "precedes"
|
|
|
|
def test_belongs_to_round_trip_intent(self):
|
|
from generate.intent import classify_intent
|
|
|
|
intent = DialogueIntent(
|
|
tag=IntentTag.TRANSITIVE_QUERY,
|
|
subject="question",
|
|
relation="belongs_to",
|
|
)
|
|
account = explain(_StubResult(intent=intent))
|
|
re_intent = classify_intent(account)
|
|
assert re_intent.tag is IntentTag.TRANSITIVE_QUERY
|
|
assert re_intent.relation == "belongs_to"
|