portfolio-optimiser-claude/tests/test_persona_skill_loadbearing.py

"""Persona artifact — LOAD-BEARING (method-spec §4.3, §11).

The seam this file keeps alive: the persona judgement is sourced from the
SHARED skill artifact at call time — never from an inlined copy — and the
example stays conformant with the pipeline schema (a persona-authored verdict
must round-trip the §4.2/§5 inbox unchanged). RED when the example drifts from
the schema or when the judgement is re-inlined instead of artifact-sourced.
"""

from __future__ import annotations

import json
from pathlib import Path

import pytest
from pydantic import ValidationError

from portfolio_optimiser_claude.experience import (
    CandidateFeatures,
    VerdictStore,
    fold_experience,
    mint_verdict_id,
)
from portfolio_optimiser_claude.inbox import load_inbox, merge_inbox_into_store
from portfolio_optimiser_claude.persona import drop_persona_verdict, load_persona_example

SHARED_ARTIFACT = (
    Path(__file__).resolve().parents[1]
    / "shared"
    / "skills"
    / "expert-reviewer"
    / "references"
    / "example-verdict.json"
)

FEATURES = CandidateFeatures(
    affected_codes=frozenset({"E01"}), measure_type="led-retrofit", claimed_saving_nok=25000.0
)


def _artifact(tmp_path: Path, marker: str = "rate=0.5", rationale: str | None = None) -> Path:
    path = tmp_path / "example-verdict.json"
    path.write_text(
        json.dumps(
            {
                "decision": "approved",
                "marker": marker,
                "rationale": rationale if rationale is not None else f"Approved; {marker} holds.",
            }
        ),
        encoding="utf-8",
    )
    return path


class TestSharedArtifactConformance:
    """§4.3: the DELTE artifact itself — proving the shared core is shared."""

    def test_the_shared_artifact_loads_and_is_run_path_approved(self) -> None:
        persona = load_persona_example(SHARED_ARTIFACT)
        assert persona.decision == "approved"

    def test_the_marker_is_the_traceable_payload_inside_the_rationale(self) -> None:
        persona = load_persona_example(SHARED_ARTIFACT)
        assert persona.marker in persona.rationale
        assert persona.marker  # non-empty — there must be something to trace


class TestFailFastLoading:
    """§4.3: the artifact is REQUIRED input — fail-fast, never tolerant."""

    def test_missing_artifact_raises(self, tmp_path: Path) -> None:
        with pytest.raises(FileNotFoundError):
            load_persona_example(tmp_path / "no-such-artifact.json")

    def test_malformed_json_raises(self, tmp_path: Path) -> None:
        path = tmp_path / "broken.json"
        path.write_text("{not json", encoding="utf-8")
        with pytest.raises(ValueError):
            load_persona_example(path)

    def test_seed_only_decision_vocabulary_is_rejected(self, tmp_path: Path) -> None:
        # §4.3: decision MUST be a run-path value — approved_with_adjustment
        # exists only in seed frontmatter and the promotion gate's accepted set.
        path = tmp_path / "example-verdict.json"
        path.write_text(
            json.dumps(
                {
                    "decision": "approved_with_adjustment",
                    "marker": "m",
                    "rationale": "m in here",
                }
            ),
            encoding="utf-8",
        )
        with pytest.raises(ValidationError):
            load_persona_example(path)

    def test_marker_not_a_substring_of_rationale_is_rejected(self, tmp_path: Path) -> None:
        path = _artifact(tmp_path, marker="rate=0.5", rationale="no payload here")
        with pytest.raises(ValidationError):
            load_persona_example(path)


class TestArtifactSourcedJudgement:
    """LOAD-BEARING (§11): sourced at call time — RED if the judgement is re-inlined."""

    def test_editing_the_artifact_changes_the_next_dropped_verdict(self, tmp_path: Path) -> None:
        artifact = _artifact(tmp_path, marker="rate=0.5")
        inbox = tmp_path / "inbox"
        first = drop_persona_verdict(inbox, artifact, FEATURES, description="LED retrofit")
        assert "rate=0.5" in first.rationale
        _artifact(tmp_path, marker="rate=0.9")  # the artifact is edited in place
        second = drop_persona_verdict(
            inbox,
            artifact,
            CandidateFeatures(
                affected_codes=frozenset({"E02"}),
                measure_type="led-retrofit",
                claimed_saving_nok=25000.0,
            ),
            description="LED retrofit",
        )
        assert "rate=0.9" in second.rationale  # re-inlining would freeze the judgement


class TestPipelineSchemaConformance:
    """§4.3 + §4.2: a persona-authored verdict round-trips the inbox unchanged."""

    def test_dropped_verdict_is_a_conformant_inbox_file(self, tmp_path: Path) -> None:
        artifact = _artifact(tmp_path)
        inbox = tmp_path / "inbox"
        dropped = drop_persona_verdict(inbox, artifact, FEATURES, description="LED retrofit")
        assert dropped.id == mint_verdict_id(FEATURES)
        assert (inbox / f"{dropped.id}.json").is_file()
        (loaded,) = load_inbox(inbox)
        assert loaded == dropped

    def test_the_persona_marker_reaches_a_later_prompt_via_the_inbox(self, tmp_path: Path) -> None:
        # Persona → authoring primitive → tolerant load → merge → fold: the
        # traceable payload follows the persona's judgement into the prompt.
        artifact = _artifact(tmp_path, marker="rate=0.77")
        inbox = tmp_path / "inbox"
        drop_persona_verdict(inbox, artifact, FEATURES, description="LED retrofit")
        store = VerdictStore()
        merge_inbox_into_store(store, inbox)
        prompt = fold_experience(store, FEATURES, "Base task.", k=3)
        assert "rate=0.77" in prompt

    def test_the_shared_artifact_feeds_the_pipeline_directly(self, tmp_path: Path) -> None:
        # The canonical example itself flows end-to-end — schema drift in the
        # shared artifact turns this RED.
        inbox = tmp_path / "inbox"
        drop_persona_verdict(inbox, SHARED_ARTIFACT, FEATURES, description="LED retrofit")
        persona = load_persona_example(SHARED_ARTIFACT)
        store = VerdictStore()
        merge_inbox_into_store(store, inbox)
        prompt = fold_experience(store, FEATURES, "Base task.", k=3)
        assert persona.marker in prompt