"""Step-7 load-bearing seam (målbilde §3 / §5 row 7 / §7): the LONG/async feedback loop — a
verdict file that lands in a folder AFTER one run MUST be consumed by a separate, later run.

The gap (fot-i-bakken, verified in code): the short loop captured the expert verdict inline
(``verdict_input``) into an IN-MEMORY ``VerdictStore`` — so a verdict that arrives days/weeks
later, in a separate run, could not influence any future hypothesis. Fase 5 adds a file inbox:
``run_project(verdict_dir=...)`` ingests expert/persona-authored verdict files (plain JSON, R2 raw
layer) and MERGES them into the store BEFORE the Step-1 ExpeL fold, so the dropped verdict reaches
the next run's hypothesis prompt through the existing fold.

These two tests are a load-bearing PAIR (per the Fase-2 green-but-dead trap):
- the positive test keys on a realization marker that occurs NOWHERE in the bundle (0.57, not the
  bundle seed's 0.82), carried in the dropped verdict's rationale — proving the learning PAYLOAD
  round-tripped end to end (write -> file -> ingest -> retrieve -> fold -> prompt), not merely that
  an object was retrieved. It goes RED the moment the ingest is detached.
- the control proves causality: the SAME run with an EMPTY inbox carries no marker — so the signal
  is caused by the file loop, not incidental to the bundle. ``bundle_context`` excludes
  ``type: verdict`` files (okf.py), so the marker can ONLY arrive via ingest -> store -> fold.

Critical invariant: run B uses a FRESH store (never run A's object) — otherwise the transfer would
be in-memory carryover, not the file loop.
"""

from __future__ import annotations

from pathlib import Path

from portfolio_optimiser.run import run_project
from portfolio_optimiser.validator import ValidatedProposal
from portfolio_optimiser.verdicts import (
    Verdict,
    VerdictStore,
    bundle_candidate_features,
    write_verdict,
)

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

# A VALID BYGG-KONTOR-NORD proposal (same as the Step-1 test): P90 = 0.30 x 300000 = 90000 >=
# claimed 30000 -> validates on the first attempt.
_ENERGY_REPLY = (
    '{"measure":"LED-retrofit av kontorbelysning","affected_items":'
    '[{"code":"ENERGI-TOTAL-EL","quantity":300000,"unit_cost":1.0}],"claimed_saving_nok":30000}'
)
_VERDICT_INPUT = {"decision": "approved", "rationale": "expert reviewed (sim)"}

# Two load-bearing markers carried by the DROPPED verdict, by design:
#  - a realization value absent from EVERY bundle file (the bundle seed is 0.82). It can reach a
#    prompt only via the ingest->fold path -> isolates the file loop AND would catch a regression
#    where bundle navigation starts leaking verdict files (a 0.82 marker would pass for the wrong
#    reason and mask that).
#  - a sentinel verdict id (cannot appear in the bundle's raw text) for object identity.
_MARKER = "realiseringsgrad=0.57"
_DROP_ID = "STEG7-DROP"


def _generation_prompts(sink: list[str]) -> list[str]:
    """The generation-call prompts (``generate._build_messages`` embeds 'SavingsProposal'),
    isolated from the debate-round prompts also captured in the sink."""
    return [p for p in sink if "SavingsProposal" in p]


def _drop_expert_verdict(inbox: Path) -> None:
    """Simulate the long loop: an expert/persona drops a verdict file into the inbox AFTER a run.
    Keyed on the bundle candidate's features (the same key the Step-1 fold queries on), carrying the
    realization marker in its rationale. ``write_verdict`` is the public authoring primitive a
    persona (sim) or human (prod) uses against the SAME folder interface."""
    verdict = Verdict(
        id=_DROP_ID,
        proposal_features=bundle_candidate_features(str(BUNDLE_DIR)),
        decision="approved",
        rationale=f"LED-retrofit godkjent med realiseringskorreksjon ({_MARKER})",
    )
    write_verdict(str(inbox), verdict)


async def test_dropped_verdict_reaches_later_run(make_recording_client_factory, tmp_path) -> None:
    """LOAD-BEARING: a verdict dropped into the inbox AFTER run A reaches run B's hypothesis prompt.
    Goes RED if ``run_project`` stops ingesting ``verdict_dir`` before the Step-1 fold (the marker
    never arrives -> no fold -> the assertion fails)."""
    inbox = tmp_path / "verdict-inbox"
    inbox.mkdir()

    # Run A: an earlier run with an EMPTY store and an EMPTY inbox -> nothing folds in, and (no
    # auto-persist) run A does NOT write its own captured verdict back to the inbox.
    factory_a, recorded_a = make_recording_client_factory(_ENERGY_REPLY)
    await run_project(
        "BYGG-KONTOR-NORD",
        "local",
        docs_dir=str(BUNDLE_DIR),
        bundle_dir=str(BUNDLE_DIR),
        verdict_input=_VERDICT_INPUT,
        store=VerdictStore(verdicts=[]),
        verdict_dir=str(inbox),
        client_factory=factory_a,
    )
    assert all(_MARKER not in p for p in recorded_a), "precondition: run A carries no marker"

    # Days/weeks later, out of band: the expert drops a verdict into the inbox folder.
    _drop_expert_verdict(inbox)

    # Run B: a SEPARATE, later run with a FRESH store (never run A's object) -> the dropped verdict
    # must reach the hypothesis prompt purely via the file loop.
    factory_b, recorded_b = make_recording_client_factory(_ENERGY_REPLY)
    result = await run_project(
        "BYGG-KONTOR-NORD",
        "local",
        docs_dir=str(BUNDLE_DIR),
        bundle_dir=str(BUNDLE_DIR),
        verdict_input=_VERDICT_INPUT,
        store=VerdictStore(verdicts=[]),
        verdict_dir=str(inbox),
        client_factory=factory_b,
    )

    assert isinstance(result.outcome, ValidatedProposal)
    gen_prompts = _generation_prompts(recorded_b)
    assert gen_prompts, "the generation call must have happened"
    assert any(_MARKER in p for p in gen_prompts), (
        "the dropped verdict's realization signal did not reach run B's hypothesis prompt — the "
        "async file inbox is not ingested before the Step-1 fold"
    )
    assert any(_DROP_ID in p for p in gen_prompts), (
        "the dropped verdict's id did not reach the prompt"
    )


async def test_empty_inbox_leaves_no_signal(make_recording_client_factory, tmp_path) -> None:
    """CAUSALITY CONTROL: the same run with an EMPTY inbox carries no marker into any prompt —
    proving the positive test's signal is caused by the file loop, not incidental to the bundle
    (``bundle_context`` excludes ``type: verdict`` files, so the marker has no other path)."""
    inbox = tmp_path / "verdict-inbox"
    inbox.mkdir()

    factory, recorded = make_recording_client_factory(_ENERGY_REPLY)
    await run_project(
        "BYGG-KONTOR-NORD",
        "local",
        docs_dir=str(BUNDLE_DIR),
        bundle_dir=str(BUNDLE_DIR),
        verdict_input=_VERDICT_INPUT,
        store=VerdictStore(verdicts=[]),
        verdict_dir=str(inbox),
        client_factory=factory,
    )

    assert all(_MARKER not in p for p in recorded), (
        "the realization marker reached a prompt with an EMPTY inbox — the positive test is not "
        "load-bearing (the signal is incidental, not caused by the ingest seam)"
    )
    assert all(_DROP_ID not in p for p in recorded), "the sentinel id leaked without a dropped file"