portfolio-optimiser/tests/test_dimension_loadbearing.py

"""Step 2 load-bearing seam (SC2 + brief §4.1, målbilde §2/§6): a run's ``dimension`` does TWO
things, each with a named detach point:

- **Candidate constraint (§4.1b):** a validator-VALID candidate (P90-valid, empty assumptions)
  whose ``measure_type`` falls OUTSIDE the run's dimension is rejected WHEN a dimension is set.
  The proposal validates on the numbers, so the ONLY possible rejecter is the ``admits`` scope
  gate (closes the green-but-dead trap). RED if ``admits`` is removed ⇒ the foreign candidate
  slips through. Control: an in-dimension candidate passes.
- **Context scope (§4.1a), as it stands after S2c:** the promise is unchanged — a dimension-scoped
  run lets the agents read ONLY dimension-matched bundle knowledge — but the debate no longer
  RECEIVES a rendered context, it NAVIGATES the base, so the filter had to move from
  ``bundle_context`` to the tools the debate is handed. These two arms gate the FIRST rung: the
  listing the debate can see never names a foreign-dimension document. RED if the ``dimension=``
  arg is dropped anywhere along ``run_project`` → ``navigator_tools`` → ``directory_listing``.
  Control: ``dimension=None`` ⇒ the same document IS listed. The SECOND rung (``read_file``
  refusing a foreign document by path) is gated in
  ``tests/test_debate_navigation_cost_loadbearing.py`` — a listing filter with an ungated reader
  behind it is a filter in name only, so the two halves get their own arms and their own
  mutations.

Patterns: ``test_checker_gate_loadbearing.py:59/87`` (gate + causality control),
``conftest.py:184`` (recording client), ``test_step8_promotion_loadbearing.py:51`` (bundle copy).
"""

from __future__ import annotations

import shutil
from collections.abc import Callable
from pathlib import Path

import pytest
from agent_framework import BaseChatClient
from conftest import SyntheticUsageChatClient

from portfolio_optimiser import okf
from portfolio_optimiser.dimension import Dimension
from portfolio_optimiser.run import run_project
from portfolio_optimiser.validator import Rejection, ValidatedProposal

BUNDLE_DIR = Path(__file__).resolve().parents[1] / "shared" / "examples" / "bygg-energi-mikro"

_ENERGY_DIM = Dimension(
    id="energi", label="Energi", allowed_measure_types=frozenset({"energy_efficiency"})
)
_VERDICT_INPUT = {"decision": "approved", "rationale": "expert reviewed (sim)"}

# A marker that appears ONLY in the asfalt-marked concept file's body, so it can reach the prompt
# solely through un-filtered context — its presence/absence is the §4.1a leak probe.
_ASFALT_SENTINEL = "ASFALT-LEAK-SENTINEL-x7y8z9"


def _valid_reply(measure: str, code: str) -> str:
    """A validator-VALID proposal: affected total 300000, degenerate P90 = 0.30 x 300000 = 90000
    >= claimed 30000, empty assumptions -> validates on the numbers regardless of ``measure``/``code``
    (so a rejection can only come from the dimension scope gate)."""
    return (
        '{"measure":"' + measure + '","affected_items":'
        '[{"code":"' + code + '","quantity":300000,"unit_cost":1.0}],"claimed_saving_nok":30000}'
    )


def _role_factory(proposer_reply: str, checker_reply: str) -> Callable[[str], BaseChatClient]:
    def factory(role: str) -> BaseChatClient:
        return SyntheticUsageChatClient(
            default_reply=checker_reply if role == "checker" else proposer_reply
        )

    return factory


# --- Candidate constraint (§4.1b) ----------------------------------------------------------------


async def test_foreign_dimension_candidate_rejected_when_dimension_set() -> None:
    """LOAD-BEARING: a foreign-dimension candidate that validates on the numbers is rejected by the
    scope gate. RED if ``admits`` is detached (the foreign candidate slips through as validated).

    The cost code is one the delivered base NAMES (P7). It used to be ``SENTINEL-FOREIGN``, which
    the base does not carry — so once identifier grounding existed the candidate fell for a reason
    that has nothing to do with the dimension, and this arm would have ridden on that instead of on
    ``admits``. Only the MEASURE is foreign now, which is what §4.1b is about."""
    factory = _role_factory(
        _valid_reply("paving_renegotiation", "ENERGI-TOTAL-EL"), "VERDICT: APPROVE"
    )

    result = await run_project(
        "BYGG-KONTOR-NORD",
        "local",
        docs_dir=str(BUNDLE_DIR),
        bundle_dir=str(BUNDLE_DIR),
        verdict_input=_VERDICT_INPUT,
        dimension=_ENERGY_DIM,
        client_factory=factory,
    )

    assert isinstance(result.outcome, Rejection), (
        "a foreign-dimension candidate slipped through — the admits scope gate is not gating"
    )
    assert "outside dimension" in result.outcome.reason
    # Provenance honesty: the VALIDATOR passed (the numbers are feasible); only the scope gate
    # rejected. validator_decision reflects the numbers ONLY — never the scope gate.
    assert result.provenance.validator_decision == "validated"


async def test_in_dimension_candidate_passes() -> None:
    """CAUSALITY CONTROL: the SAME shape with an in-dimension ``measure_type`` validates normally —
    proving the rejection above is caused by the dimension scope, not the fixture."""
    factory = _role_factory(
        _valid_reply("energy_efficiency", "ENERGI-TOTAL-EL"), "VERDICT: APPROVE"
    )

    result = await run_project(
        "BYGG-KONTOR-NORD",
        "local",
        docs_dir=str(BUNDLE_DIR),
        bundle_dir=str(BUNDLE_DIR),
        verdict_input=_VERDICT_INPUT,
        dimension=_ENERGY_DIM,
        client_factory=factory,
    )

    assert isinstance(result.outcome, ValidatedProposal)


# --- Context scope (§4.1a) -----------------------------------------------------------------------


def _bundle_with_asfalt_file(tmp_path: Path) -> str:
    """A throwaway copy of the shared bundle with one extra asfalt-marked concept file carrying the
    sentinel in its body, linked from the index so ``navigate_bundle`` reaches it. The shared,
    framework-neutral fixture is never mutated (mirrors ``_copy_bundle``)."""
    dst = tmp_path / "bundle"
    shutil.copytree(BUNDLE_DIR, dst)
    (dst / "asfalt-note.md").write_text(
        f"---\ntype: methodology\ndimension: asfalt\n---\n\n{_ASFALT_SENTINEL} — paving method note\n",
        encoding="utf-8",
    )
    index = dst / "index.md"
    index.write_text(
        index.read_text(encoding="utf-8") + "\n- [asfalt](asfalt-note.md)\n", encoding="utf-8"
    )
    return str(dst)


async def _listing_the_debate_can_see(bundle_dir: str, dimension: Dimension | None) -> str:
    """Run the bundle path, capture the tools the debate was built with, and return what its
    ``read_bundle`` rung answers — the S2c successor to reading the prompt text.

    The tool is invoked DIRECTLY afterwards rather than through an agent turn, because a
    ``ScriptedChatClient`` returns text and never emits a ``function_call``: a test that only drove
    the run would leave the entire tool surface outside the gate (``test_explore_loadbearing``'s
    own measured correction)."""
    import portfolio_optimiser.run as run_module

    captured: list[list[object]] = []
    original = run_module.fresh_workflow

    def spy(*args: object, **kwargs: object) -> object:
        captured.append(list(kwargs.get("tools") or []))  # type: ignore[arg-type]
        return original(*args, **kwargs)  # type: ignore[arg-type]

    def factory(role: str) -> BaseChatClient:
        return SyntheticUsageChatClient(
            default_reply=_valid_reply("energy_efficiency", "ENERGI-TOTAL-EL")
        )

    monkeypatch = pytest.MonkeyPatch()
    try:
        monkeypatch.setattr(run_module, "fresh_workflow", spy)
        await run_project(
            "BYGG-KONTOR-NORD",
            "local",
            docs_dir=bundle_dir,
            bundle_dir=bundle_dir,
            verdict_input=_VERDICT_INPUT,
            dimension=dimension,
            client_factory=factory,
        )
    finally:
        monkeypatch.undo()

    assert captured, "the debate was never built"
    read_bundle = next(t for t in captured[0] if getattr(t, "name", "") == "read_bundle")
    bundle_id = okf.reconcile_bundle_id(bundle_dir).id
    answer = await read_bundle.invoke(arguments={"bundle_id": bundle_id})
    return "".join(getattr(c, "text", "") or "" for c in answer)


async def test_dimension_scopes_the_agent_context(tmp_path) -> None:
    """LOAD-BEARING (§4.1a, first rung): under a dimension the listing the debate can see does NOT
    name the foreign-dimension document. RED if ``dimension=`` is dropped anywhere between
    ``run_project`` and ``directory_listing``.

    Asserts on the FILE NAME rather than the body sentinel, because a listing carries names and
    sizes, never bodies — an assert on the sentinel would be green against every implementation
    and would prove nothing (the vacuous form this repo keeps measuring)."""
    bundle_dir = _bundle_with_asfalt_file(tmp_path)

    scoped = await _listing_the_debate_can_see(bundle_dir, _ENERGY_DIM)
    assert "asfalt-note.md" not in scoped, (
        "another dimension's document is listed to the agents — the tools are not dimension-scoped"
    )


async def test_no_dimension_leaves_context_unscoped(tmp_path) -> None:
    """CAUSALITY CONTROL: with ``dimension=None`` the asfalt document IS listed — proving its
    absence above is caused by the dimension scope, not by the file being unreachable."""
    bundle_dir = _bundle_with_asfalt_file(tmp_path)

    unscoped = await _listing_the_debate_can_see(bundle_dir, None)
    assert "asfalt-note.md" in unscoped, (
        "the asfalt file is unreachable even without a filter — the control does not prove causality"
    )