tegwick
1b9860a8ee
All four gate criteria met. False Adaptation Rate 0/7 with 12 of 13 mechanical mutations absorbed. 178 tests pass. TD-WP-0002 finished. Fitness loop closed via F-0003: actor isolation was a property of scenarios written to expose it, not of runs. Actors now carry an automatic private marker and the runner examines all of them on every scenario, with two permanent regressions behind it. Compression - six abstractions removed, each declared and never used: Verdict.SUSPICIOUS (a verdict no oracle could emit), Step.expect_refusal, ActorIsolationError, World.seed, EvidencePack.latest, Trajectory.method. F-0008: Temperature may be redundant. Crystallization was built without it ever being consulted; measured stability of realization did the work, and is observed rather than declared. Gated for removal alongside energy.py. INTENT_CHANGED and REALIZATION_FAILED had never run. Both now have purpose-built cases and a test that fails if a seventh outcome is added without one. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Assistant: claude-code Assistant-Model: opus Assistant-Process: 1629012@bnt-lap001 Assistant-Session: 78d4fb13-8a1e-474b-87a3-9b9261c49a39
107 lines
3.3 KiB
Python
107 lines
3.3 KiB
Python
"""Oracles evaluate claims and invariants and produce verdicts.
|
|
|
|
An oracle reads only the independent observation snapshot. It has no access to
|
|
the actor, to the driver, or to what either of them believes happened.
|
|
|
|
`SUSPICIOUS` was removed at T10: no oracle could produce it, and a verdict
|
|
nothing can emit is a promise the framework does not keep. It returns, with an
|
|
identifier, if a mechanism ever needs it.
|
|
|
|
`INCONCLUSIVE` is a first-class outcome, not a failure mode of the framework. An
|
|
oracle that cannot support a judgment from the retained evidence must say so
|
|
rather than defaulting either way — silently defaulting to PASS hides defects,
|
|
and silently defaulting to FAIL trains people to ignore results.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass, field
|
|
from enum import Enum
|
|
from typing import Any, Mapping
|
|
|
|
from .intent import Claim, Invariant
|
|
|
|
|
|
class Verdict(str, Enum):
|
|
PASS = "PASS"
|
|
FAIL = "FAIL"
|
|
INCONCLUSIVE = "INCONCLUSIVE"
|
|
|
|
|
|
@dataclass(frozen=True, slots=True)
|
|
class Judgment:
|
|
assertion_id: str
|
|
text: str
|
|
verdict: Verdict
|
|
step_id: str | None
|
|
detail: dict[str, Any] = field(default_factory=dict)
|
|
|
|
def as_dict(self) -> dict[str, Any]:
|
|
return {
|
|
"assertion_id": self.assertion_id,
|
|
"text": self.text,
|
|
"verdict": self.verdict.value,
|
|
"step_id": self.step_id,
|
|
"detail": self.detail,
|
|
}
|
|
|
|
|
|
class Oracle:
|
|
"""Deterministic evaluation of one assertion against an observation snapshot."""
|
|
|
|
def judge(
|
|
self,
|
|
assertion: Claim | Invariant,
|
|
snapshot: Mapping[str, Any],
|
|
step_id: str | None,
|
|
) -> Judgment:
|
|
if not snapshot:
|
|
return Judgment(
|
|
assertion.id,
|
|
assertion.text,
|
|
Verdict.INCONCLUSIVE,
|
|
step_id,
|
|
{"reason": "no observations were collected"},
|
|
)
|
|
try:
|
|
satisfied = assertion.predicate(snapshot)
|
|
except KeyError as missing:
|
|
# The evidence needed to judge this assertion was not collected.
|
|
# That is an evidence failure, never a pass and never a fail.
|
|
return Judgment(
|
|
assertion.id,
|
|
assertion.text,
|
|
Verdict.INCONCLUSIVE,
|
|
step_id,
|
|
{"reason": f"required observation {missing} missing from snapshot"},
|
|
)
|
|
except Exception as exc:
|
|
return Judgment(
|
|
assertion.id,
|
|
assertion.text,
|
|
Verdict.INCONCLUSIVE,
|
|
step_id,
|
|
{"reason": f"predicate raised {type(exc).__name__}: {exc}"},
|
|
)
|
|
return Judgment(
|
|
assertion.id,
|
|
assertion.text,
|
|
Verdict.PASS if satisfied else Verdict.FAIL,
|
|
step_id,
|
|
)
|
|
|
|
|
|
def overall(judgments: list[Judgment]) -> Verdict:
|
|
"""Aggregate run verdict.
|
|
|
|
FAIL dominates; INCONCLUSIVE outranks PASS. A run containing an unjudgeable
|
|
assertion has not passed, whatever else it did.
|
|
"""
|
|
verdicts = {j.verdict for j in judgments}
|
|
if not judgments:
|
|
return Verdict.INCONCLUSIVE
|
|
if Verdict.FAIL in verdicts:
|
|
return Verdict.FAIL
|
|
if Verdict.INCONCLUSIVE in verdicts:
|
|
return Verdict.INCONCLUSIVE
|
|
return Verdict.PASS
|