Oekt 17 found the class on four named files. This sweep ENUMERATES it: 42 negative substring assertions across 21 test files (STATE's "~34 across 23" was a premise -- measured, it is 42/21). Sixteen of them measured an absence without ever having shown presence; all sixteen now carry a positive control asserting the searched-for string PRESENT in the source artifact, in EXACTLY the form the negative looks for. Files touched: test_costsim, test_loop, test_okf (3 sites), test_preflight, test_run_entrance, test_s10_run_layer, test_sdk_version_guard, test_simulation (2 sites), test_step1_expel, test_step5_refine, test_step7_async_loop, test_step8_promotion, test_valuereport. VALUE-PROOF (green-without / red-with, per the oekt-17 rule that a detach proof is not a value proof). Seven source/fixture mutations, each making the negative vacuous: M1 verdict fixture loses the realization signal VALUE-PROVEN M2 decoy fixture loses its text VALUE-PROVEN M3 renderer stops emitting typed section headings VALUE-PROVEN M4 promotion stops writing the marker VALUE-PROVEN (pass 2) M5 fold stops rendering the realization surface VALUE-PROVEN M6 report stops labelling the cost section VALUE-PROVEN M7 preflight stops importing the SDK VALUE-PROVEN M4 needed pass 2: a PRECEDING assertion caught the same mutation, hiding the new control behind it -- the oekt-17 lesson reproduced. The remaining nine controls are vacuity guards (non-emptiness / form-presence) whose mutation would have to break the source artificially; they are stated as guards, not claimed as value-proven. MEASURED FINDING (test_loop): the FIRST-RUN-MARKER negative cannot be given a positive control at all. Within a run only the CHECKER's critique is fed back -- the proposer's own prior reasoning crosses no prompt boundary, not even within a run. So that negative holds trivially. Left in place with the limitation stated in the test rather than dressed up as a controlled seam; the CRITIQUE negative beside it IS controlled and is the real seam. Mutations were in-place on src/ and shared/ with original bytes restored and sha-verified; git status clean before and after. Suite 688 -> 688 (assertions added inside existing tests, no new test cases). ruff + mypy --strict green. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017Vc5PmZGjwuJypdhzKnJa5
196 lines
8.4 KiB
Python
196 lines
8.4 KiB
Python
"""Closed-loop two-run simulation — LOAD-BEARING (K4/R-1; method-spec §11 «Closed loop»).
|
|
|
|
The seam this file keeps alive: the persona's marker crosses from run A to
|
|
run B's hypothesis prompt VIA the §6 promotion gate — and NEVER crosses
|
|
without it. Both directions are bound: detach the promotion step from the
|
|
driver → the marker is absent from run B → red; render the verdict layer
|
|
into the read-context → the marker leaks around the gated fold → red (the
|
|
verdict-exclusion invariant, re-proven at simulation level).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from _scripted import ScriptedClient, reply
|
|
|
|
from portfolio_optimiser_claude.ir import load_validator_input
|
|
from portfolio_optimiser_claude.okf import bundle_context
|
|
from portfolio_optimiser_claude.persona import load_persona_example
|
|
from portfolio_optimiser_claude.simulation import ClosedLoopResult, simulate_closed_loop
|
|
|
|
SHARED_BUNDLE = Path(__file__).resolve().parents[1] / "shared" / "examples" / "bygg-energi-mikro"
|
|
SHARED_ARTIFACT = (
|
|
Path(__file__).resolve().parents[1]
|
|
/ "shared"
|
|
/ "skills"
|
|
/ "expert-reviewer"
|
|
/ "references"
|
|
/ "example-verdict.json"
|
|
)
|
|
# The shared artifact's own marker (realiseringsgrad=0.79) — distinct from the
|
|
# bundle seed's 0.82, so its presence in run B proves the PROMOTION crossing,
|
|
# not the pre-existing seeding path.
|
|
MARKER = load_persona_example(SHARED_ARTIFACT).marker
|
|
|
|
TIMESTAMP = "2026-07-17T04:00:00Z"
|
|
EXPERIMENT = "K4-closed-loop-sim"
|
|
|
|
|
|
@pytest.fixture()
|
|
def bundle(tmp_path: Path) -> Path:
|
|
import shutil
|
|
|
|
target = tmp_path / "bundle"
|
|
shutil.copytree(SHARED_BUNDLE, target)
|
|
return target
|
|
|
|
|
|
def _proposal_json(bundle: Path, *, measure_suffix: str = "") -> str:
|
|
proposal = load_validator_input(bundle).model_dump()
|
|
if measure_suffix:
|
|
proposal["measure"] = f"{proposal['measure']}{measure_suffix}"
|
|
return json.dumps(proposal)
|
|
|
|
|
|
def _scripted_client(proposal_json: str) -> ScriptedClient:
|
|
# One full run: debate round (proposer + approving checker) + generation.
|
|
return ScriptedClient(
|
|
replies=[reply("debate reasoning"), reply("VERDICT: APPROVE"), reply(proposal_json)]
|
|
)
|
|
|
|
|
|
def _simulate(
|
|
bundle: Path, artifact: Path, inbox: Path
|
|
) -> tuple[ClosedLoopResult, ScriptedClient, ScriptedClient]:
|
|
# Run A proposes a DISTINCT candidate (measure variant): the persona's
|
|
# verdict then gets its own §4.2 id. Judging the bundle seed's own
|
|
# candidate would mint the seed's id, and the store's first-write-wins
|
|
# would silently shadow the promoted rationale behind the seed (the known
|
|
# C-F5 feature-keying limitation — deferred to C3.2, not worked around
|
|
# in src).
|
|
client_a = _scripted_client(_proposal_json(bundle, measure_suffix="-simulert-variant"))
|
|
client_b = _scripted_client(_proposal_json(bundle))
|
|
result = simulate_closed_loop(
|
|
bundle,
|
|
artifact,
|
|
inbox,
|
|
client_a=client_a,
|
|
client_b=client_b,
|
|
timestamp=TIMESTAMP,
|
|
experiment=EXPERIMENT,
|
|
)
|
|
return result, client_a, client_b
|
|
|
|
|
|
def _rejecting_artifact(tmp_path: Path, marker: str) -> Path:
|
|
path = tmp_path / "rejecting-example-verdict.json"
|
|
path.write_text(
|
|
json.dumps(
|
|
{
|
|
"decision": "rejected",
|
|
"marker": marker,
|
|
"rationale": f"Avvist: driftstimene er overestimert ({marker}).",
|
|
}
|
|
),
|
|
encoding="utf-8",
|
|
)
|
|
return path
|
|
|
|
|
|
class TestMarkerCrossesViaPromotion:
|
|
"""§11 «Closed loop», direction 1: WITH promotion the marker MUST cross."""
|
|
|
|
def test_the_persona_marker_reaches_run_b_via_promotion(
|
|
self, bundle: Path, tmp_path: Path
|
|
) -> None:
|
|
result, _, client_b = _simulate(bundle, SHARED_ARTIFACT, tmp_path / "inbox")
|
|
# The marker did not exist anywhere before the persona judged run A.
|
|
assert MARKER not in result.run_a.composed.context
|
|
# The gate promoted the approved verdict into the bundle...
|
|
assert result.promoted_path is not None and result.promoted_path.is_file()
|
|
assert result.promotion_refusal is None
|
|
# ...and run B's FRESH store picked it up through seeding into the fold.
|
|
assert result.run_b.composed.seeded == result.run_a.composed.seeded + 1
|
|
assert MARKER in result.run_b.composed.context
|
|
# Detach proof 1 anchor: the marker reaches run B's actual prompts.
|
|
assert any(MARKER in prompt for prompt in client_b.prompts("proposer"))
|
|
|
|
def test_both_runs_complete_against_the_scripted_clients(
|
|
self, bundle: Path, tmp_path: Path
|
|
) -> None:
|
|
result, _, _ = _simulate(bundle, SHARED_ARTIFACT, tmp_path / "inbox")
|
|
assert result.run_a.result.validator_decision == "validated"
|
|
assert result.run_b.result.validator_decision == "validated"
|
|
# The persona judged run A's candidate — the verdict carries its rationale.
|
|
assert MARKER in result.verdict.rationale
|
|
|
|
|
|
class TestMarkerNeverCrossesWithoutPromotion:
|
|
"""§11 «Closed loop», direction 2: WITHOUT promotion the marker NEVER crosses.
|
|
|
|
The rejected persona verdict IS authored into the inbox — if run B read the
|
|
inbox (or any channel other than the promoted wiki layer), the marker would
|
|
cross anyway and this control goes red.
|
|
"""
|
|
|
|
def test_a_rejected_verdict_is_refused_and_the_marker_stays_out(
|
|
self, bundle: Path, tmp_path: Path
|
|
) -> None:
|
|
marker = "realiseringsgrad=0.11"
|
|
artifact = _rejecting_artifact(tmp_path, marker)
|
|
result, _, client_b = _simulate(bundle, artifact, tmp_path / "inbox")
|
|
assert result.promoted_path is None
|
|
assert result.promotion_refusal is not None
|
|
assert "rejected" in result.promotion_refusal
|
|
# Positive controls: the docstring's claim that the marker IS authored into the
|
|
# artifact the run reads, asserted rather than stated — and prompts really were
|
|
# issued, since `all()` over an empty list is vacuously True. Without both, this
|
|
# control would pass for a marker that was never written anywhere.
|
|
assert marker in artifact.read_text(encoding="utf-8")
|
|
assert client_b.prompts("proposer")
|
|
assert marker not in result.run_b.composed.context
|
|
assert all(marker not in prompt for prompt in client_b.prompts("proposer"))
|
|
|
|
def test_a_refused_promotion_leaves_the_bundle_untouched(
|
|
self, bundle: Path, tmp_path: Path
|
|
) -> None:
|
|
before = {p.name: p.read_bytes() for p in bundle.iterdir()}
|
|
_simulate(
|
|
bundle, _rejecting_artifact(tmp_path, "realiseringsgrad=0.11"), tmp_path / "inbox"
|
|
)
|
|
after = {p.name: p.read_bytes() for p in bundle.iterdir()}
|
|
assert after == before
|
|
|
|
|
|
class TestGatedFoldIsTheOnlyChannel:
|
|
"""LOAD-BEARING (§11): the marker crosses ONLY via the gated experience fold.
|
|
|
|
Detach proof 2 anchor: render the verdict layer into the read-context and
|
|
the marker leaks into the base context around the fold — red.
|
|
"""
|
|
|
|
def test_the_verdict_layer_is_never_rendered_into_either_context(
|
|
self, bundle: Path, tmp_path: Path
|
|
) -> None:
|
|
result, _, _ = _simulate(bundle, SHARED_ARTIFACT, tmp_path / "inbox")
|
|
assert MARKER in result.run_b.composed.context # crossing happened...
|
|
# ...but NO verdict-typed concept is rendered into the read-context —
|
|
# a `## verdict` section in either run's context means the seed's (or
|
|
# a promoted file's) body leaked around the gated fold (§3 Step 1).
|
|
# Positive control: `## `-typed sections ARE rendered into both contexts, so the
|
|
# two negatives measure a GATED type and not a context without sections at all.
|
|
assert "## project:" in result.run_a.composed.context
|
|
assert "## project:" in result.run_b.composed.context
|
|
assert "## verdict" not in result.run_a.composed.context
|
|
assert "## verdict" not in result.run_b.composed.context
|
|
# Belt and braces: the promoted marker itself never surfaces via
|
|
# rendering (promoted files are frontmatter-only by design, §6).
|
|
# Positive control: the marker IS live on disk in the promoted file, so the
|
|
# absence below measures the RENDERING boundary, not a marker never written.
|
|
assert result.promoted_path is not None
|
|
assert MARKER in result.promoted_path.read_text(encoding="utf-8")
|
|
assert MARKER not in bundle_context(bundle)
|