portfolio-optimiser/tests/test_right_requirement_loadbearing.py

"""P20 DEL A — the requirement that is RIGHT, and the commission's criteria reaching the reader.

**The measured silence, three rounds and one multi-base pass deep.** P19 DEL A made a direction
NAME the requirement that binds it and made the run refuse a declaration naming a path it never
opened. The declarations then happened — and MEASURED (P19 round 3: 9 declarations over 5 paid
runs; P17b: 4 over one two-base pass) **not one of them named a fasit concept**. The rung works;
what nothing asked for was that the requirement be the RIGHT one. Two halves were missing:

* the tool answered ``{"declared": true, ...}`` to every accepted declaration, echoing back the
  caller's own three arguments. A model that had declared a requirement about something else was
  told, in the only words it got, that it had succeeded;
* the commission's own statement of what a good answer looks like — ``Mandate.success_criteria`` —
  reached ``announce`` and NOTHING else (P19 F2). It was printed for a human and withheld from the
  only reader who could act on it.

What each arm pins:

(a) A1 — the reply carries the DOCUMENT's own ``title`` and ``req_number``, read off the base, plus
    the sentence that says what the declaration BINDS. Without the document's own words the reply
    cannot contradict a wrong declaration, which is the whole correction;
(b) A1 — a path the base carries as no navigated concept (``index.md`` is the reachable case)
    answers with empty strings rather than raising: the read trace has already accepted the
    declaration, and turning "I cannot restate your title" into a refusal would fail a declaration
    the run's own evidence proves was read;
(c) A1 — the reply is read off ``Bundle.context_files``, so a ``type: verdict`` document can never
    be named back by title. The one layer no listing names stays unnamed even in an answer;
(d) A2 — ``criteria_block`` is the ONE renderer, and it is EMPTY without criteria. That omission is
    what keeps every prompt of every un-commissioned run byte-identical, the demo's included;
(e) A2 — the criteria reach the DEBATE's task message, the prompt where ``declare_requirement`` is
    available. Asserted on the text the client actually received, never on the composer;
(f) A2 — a run with NO mandate sends the task message byte-identically to before, which is the
    half that keeps ``demo-transcript.stdout`` unchanged and is asserted here rather than left to
    the golden;
(g) A3 — the navigator instruction and the tool description both name the ``read_dir(filter=...)``
    route with a worked example. A description that lies about the body IS the model's instruction
    (the Fase-3 class), and here the body is new.
"""

from __future__ import annotations

from pathlib import Path
from typing import Any

import pytest

from portfolio_optimiser import explore, okf
from portfolio_optimiser.explore import DeclaredRequirement, ToolCall, navigator_tools
from portfolio_optimiser.mandate import Approach, Mandate, criteria_block

_EXAMPLES = Path(__file__).resolve().parents[1] / "shared" / "examples"
_TUNNEL = _EXAMPLES / "tunnel-hauglia"
_BYGG = _EXAMPLES / "bygg-energi-mikro"
_PID = "BYGG-KONTOR-NORD"


def _wired(bundle_dir: Path) -> tuple[dict[str, Any], list[ToolCall], list[DeclaredRequirement]]:
    opened: list[ToolCall] = []
    declared: list[DeclaredRequirement] = []
    tools = navigator_tools((str(bundle_dir),), opened=opened, requirements=declared)
    return {t.name: t for t in tools}, opened, declared


def _declare(tools: dict[str, Any], opened: list[ToolCall], base: str, path: str) -> dict[str, Any]:
    """Read it the way a run does, then declare it — the (b) path of P19 DEL A."""
    opened.append(ToolCall(name="read_file", bundle_id=base, path=path))
    return tools["declare_requirement"].func(bundle_id=base, path=path, ref="Krav 4.1.2-1")


def _base_with_a_requirement(root: Path) -> Path:
    """A base declaring its own ``req_number`` — the form the delivered N corpora carry.

    Crafted rather than taken from ``shared/examples``: MEASURED, no example base declares a
    ``req_number`` at all, so an arm built on one of them could not tell a reply that reads the
    document from one that returns an empty string.
    """
    base = root / "n-mini"
    base.mkdir()
    (base / "index.md").write_text(
        "---\nbundle_id: n-mini\n---\n\n- [Krav](krav.md) — one requirement.\n", encoding="utf-8"
    )
    (base / "krav.md").write_text(
        "---\ntype: Krav\ntitle: Krav 4.1.2-1 Rundkjoring\nreq_number: Krav 4.1.2-1\n"
        "seksjon: '4.1.2'\n---\n\nEn rundkjoring skal ha …\n",
        encoding="utf-8",
    )
    return base


# ---------------------------------------------------------------------------------------------
# (a)-(c) the reply the model can be contradicted by
# ---------------------------------------------------------------------------------------------


def test_the_reply_carries_the_documents_own_title_and_number(tmp_path: Path) -> None:
    """(a) The base's words, not the caller's — the only thing that can say "wrong one"."""
    base = _base_with_a_requirement(tmp_path)
    tools, opened, declared = _wired(base)
    answer = _declare(tools, opened, "n-mini", "krav.md")
    assert answer["title"] == "Krav 4.1.2-1 Rundkjoring"
    assert answer["req_number"] == "Krav 4.1.2-1"
    assert "is the requirement the proposal rests on" in answer["binds"]
    assert declared == [DeclaredRequirement(bundle_id="n-mini", path="krav.md", ref="Krav 4.1.2-1")]


def test_a_path_that_is_no_concept_answers_with_empty_strings(tmp_path: Path) -> None:
    """(b) Accepted-but-unrestatable is not a refusal; the read trace already ruled."""
    base = _base_with_a_requirement(tmp_path)
    tools, opened, _declared = _wired(base)
    answer = _declare(tools, opened, "n-mini", "index.md")
    assert answer["declared"] is True
    assert (answer["title"], answer["req_number"]) == ("", "")


def test_a_verdict_document_is_never_named_back_by_title(tmp_path: Path) -> None:
    """(c) Read off ``context_files``, the property that drops the ``type: verdict`` layer."""
    base = _base_with_a_requirement(tmp_path)
    (base / "dom.md").write_text(
        "---\ntype: verdict\ntitle: A PRIOR EXPERT JUDGEMENT\nid: v1\n---\n\napproved.\n",
        encoding="utf-8",
    )
    tools, opened, _declared = _wired(base)
    answer = _declare(tools, opened, "n-mini", "dom.md")
    assert answer["declared"] is True
    assert answer["title"] == "", "the verdict layer must not be readable through this answer"
    # The control: the SAME base answers the concept's title, so the empty string above is the
    # layer being excluded rather than the reader being broken.
    assert _declare(tools, opened, "n-mini", "krav.md")["title"] == "Krav 4.1.2-1 Rundkjoring"


def test_the_tunnel_example_answers_its_own_title_and_no_number() -> None:
    """(a) control on a REAL example base: title present, reference number honestly absent."""
    tools, opened, _declared = _wired(_TUNNEL)
    path = okf.navigate_bundle(str(_TUNNEL)).context_files[0].name
    answer = _declare(tools, opened, "tunnel-hauglia", path)
    assert answer["title"].startswith("Kilder: tunnelbelysning")
    assert answer["req_number"] == "", "this base declares none, and the reply must not invent one"


# ---------------------------------------------------------------------------------------------
# (d)-(f) the criteria reaching the prompt
# ---------------------------------------------------------------------------------------------


def test_the_criteria_renderer_is_empty_without_criteria() -> None:
    """(d) Omission, never an empty heading — the ``announce`` rule, and the golden's guarantee."""
    assert criteria_block("") == ""
    rendered = criteria_block("a saving the price schedule can carry")
    assert "a saving the price schedule can carry" in rendered
    assert rendered.startswith("\n")


def test_the_commissions_criteria_reach_the_debate_task(monkeypatch: pytest.MonkeyPatch) -> None:
    """(e) Asserted on what the CLIENT received, never on the composer."""
    sent = _run_and_capture_task(
        monkeypatch,
        mandate=Mandate(
            objective="cut cost",
            approaches=(Approach(id="a1", label="L", description="D"),),
            success_criteria="SENTINEL-CRITERION-ONLY-THE-COMMISSION-CARRIES",
        ),
    )
    assert "SENTINEL-CRITERION-ONLY-THE-COMMISSION-CARRIES" in sent[0]
    assert "What the commissioner counts as success" in sent[0]


def test_a_run_without_a_mandate_sends_the_task_unchanged(monkeypatch: pytest.MonkeyPatch) -> None:
    """(f) The byte-identity half. Without it (e) could be satisfied by always appending."""
    sent = _run_and_capture_task(monkeypatch, mandate=None)
    assert sent[0].startswith(f"Find a cost-saving measure for {_PID}.\nContext:\n")


def _run_and_capture_task(monkeypatch: pytest.MonkeyPatch, *, mandate: Mandate | None) -> list[str]:
    """Drive a real ``run_project`` and capture every prompt the debate's clients received.

    The same recording-factory seam ``test_debate_navigation_cost_loadbearing`` measures S2c with:
    the assertion is on what the CLIENT was handed, never on ``criteria_block``'s return value, so
    a renderer wired nowhere cannot satisfy it.
    """
    import asyncio

    from agent_framework import BaseChatClient

    from portfolio_optimiser.run import run_project
    from portfolio_optimiser.simulation import ScriptedChatClient

    sink: list[str] = []
    valid = (
        '{"measure":"LED-retrofit","affected_items":'
        '[{"code":"ENERGI-TOTAL-EL","quantity":300000,"unit_cost":1.0}],'
        '"claimed_saving_nok":30000}'
    )

    def factory(role: str) -> BaseChatClient:
        client = ScriptedChatClient(
            "Reasoning holds.\nVERDICT: APPROVE" if role == "checker" else valid, role=role
        )
        original = client._inner_get_response  # type: ignore[attr-defined]

        def recording(*, messages, options, stream=False, **kwargs):  # type: ignore[no-untyped-def]
            sink.append("\n".join(getattr(m, "text", "") or "" for m in messages))
            return original(messages=messages, options=options, stream=stream, **kwargs)

        client._inner_get_response = recording  # type: ignore[attr-defined,method-assign]
        return client

    asyncio.run(
        run_project(
            _PID,
            "local",
            docs_dir=str(_BYGG),
            bundle_dir=str(_BYGG),
            verdict_input={"decision": "approved", "rationale": "expert reviewed (test)"},
            client_factory=factory,
            mandate=mandate,
        )
    )
    assert sink, "the debate never reached the client"
    return sink


# ---------------------------------------------------------------------------------------------
# (g) the instruction that describes the new body
# ---------------------------------------------------------------------------------------------


def test_both_descriptions_name_the_filter_route() -> None:
    """(g) A description that lies about the body IS the instruction (the Fase-3 class)."""
    instruction = explore._INSTRUCTIONS[explore.HYPOTHESISER_ROLE]
    assert "read_dir a 'filter' word" in instruction
    assert "Krav 4.1.2-1" in instruction, "the worked example is what makes the route concrete"
    tools = {t.name: t for t in navigator_tools((str(_TUNNEL),), opened=[], requirements=[])}
    description = tools["declare_requirement"].description or ""
    assert "filter='rundkjoring'" in description
    assert "own title and number" in description