Complete local generalisation tasks and document remaining experiment blockers

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0e76f-be98-7ae3-965d-e0b31290a4c4

src/testdriver/__init__.py

@@ -2,7 +2,6 @@
 
 from .actions import SemanticAction, Surface, SurfaceNotPermitted
 from .drivers import DirectDriver, Realization
-from .energy import EnergyEvent, EnergyEventType
 from .evidence import EvidencePack, Observation, Stratum
 from .intent import Claim, Invariant, UseCase
 from .observers import StateObserver, Watch
@@ -14,7 +13,7 @@ from .world import Actor, Cast, World
 
 __all__ = [
     "Actor", "Cast", "Claim", "CollectorIndependenceError",
-    "DirectDriver", "EnergyEvent", "EnergyEventType", "EvidencePack",
+    "DirectDriver", "EvidencePack",
     "InadmissibleProvenance", "Invariant", "Judgment", "Observation", "Oracle",
     "Provenance", "Realization", "RunResult", "Runner", "Scenario",
     "SemanticAction", "StateObserver", "Step", "Stratum", "Surface",

src/testdriver/energy.py

@@ -1,45 +0,0 @@
-"""Energy events — capture only.
-
-H-005 is dormant by decision: verification energy is not testable at the current
-scale, and a scoring function producing a number nobody can check is worse than
-no number. Events are recorded from the first run because history cannot be
-reconstructed later; scores always can.
-
-There is deliberately no score() function in this module.
-"""
-
-from __future__ import annotations
-
-from dataclasses import asdict, dataclass, field
-from datetime import datetime, timezone
-from enum import Enum
-from typing import Any
-
-
-class EnergyEventType(str, Enum):
-    DEFECT_DETECTED = "DEFECT_DETECTED"
-    REGRESSION_CAUGHT = "REGRESSION_CAUGHT"
-    MECHANICAL_ADAPTATION = "MECHANICAL_ADAPTATION"
-    SEMANTIC_ADAPTATION = "SEMANTIC_ADAPTATION"
-    TEST_DEFECT = "TEST_DEFECT"
-    FALSE_POSITIVE = "FALSE_POSITIVE"
-    DUPLICATE = "DUPLICATE"
-    CRYSTALLIZED = "CRYSTALLIZED"
-    USECASE_DEPRECATED = "USECASE_DEPRECATED"
-    EXECUTED = "EXECUTED"
-
-
-@dataclass(frozen=True, slots=True)
-class EnergyEvent:
-    """Immutable. Energy is derived from event history, never stored as state."""
-
-    asset_id: str
-    run_id: str
-    event_type: EnergyEventType
-    detail: dict[str, Any] = field(default_factory=dict)
-    at: str = field(
-        default_factory=lambda: datetime.now(timezone.utc).isoformat()
-    )
-
-    def as_dict(self) -> dict[str, Any]:
-        return {**asdict(self), "event_type": self.event_type.value}

src/testdriver/evidence.py

@@ -63,7 +63,6 @@ class EvidencePack:
     finished_at: str | None = None
     observations: list[Observation] = field(default_factory=list)
     verdicts: list[dict[str, Any]] = field(default_factory=list)
-    energy_events: list[dict[str, Any]] = field(default_factory=list)
     provenance_index: dict[str, str] = field(default_factory=dict)
 
     def record(self, observation: Observation) -> None:

src/testdriver/intent.py

@@ -20,7 +20,12 @@ Predicate = Callable[[Mapping[str, object]], bool]
 
 @dataclass(frozen=True, slots=True)
 class Claim:
-    """A statement that must hold at a specific point in a scenario."""
+    """A statement that must hold at a specific point in a scenario.
+
+    Public contract (TD-WP-0003-T05): predicates remain Python callables over
+    independent snapshots. Generated tests import these original claims; no
+    serialized claim language is promised. See TestDriverGeneralisationReview.
+    """
 
     id: str
     text: str

src/testdriver/runner.py

@@ -15,7 +15,6 @@ from typing import Any
 
 from .actions import SurfaceNotPermitted
 from .drivers import Driver
-from .energy import EnergyEvent, EnergyEventType
 from .evidence import EvidencePack, Observation, Stratum
 from .observers import StateObserver
 from .oracles import Judgment, Oracle, Verdict, overall
@@ -125,9 +124,6 @@ class Runner:
             **{c.id: c.provenance.value for c in scenario.use_case.claims},
             **{i.id: i.provenance.value for i in scenario.use_case.invariants},
         }
-        pack.energy_events.append(
-            EnergyEvent(asset.id, run_id, EnergyEventType.EXECUTED).as_dict()
-        )
 
         isolation = self._isolation_violations()
         self._record(
@@ -229,8 +225,4 @@ class Runner:
         pack.finished_at = datetime.now(timezone.utc).isoformat()
 
         result_verdict = overall(judgments)
-        if result_verdict is Verdict.FAIL:
-            pack.energy_events.append(
-                EnergyEvent(asset.id, run_id, EnergyEventType.DEFECT_DETECTED).as_dict()
-            )
         return RunResult(run_id, result_verdict, judgments, pack)