"""The verdict file and the inbox folder contract (method-spec §4.2, §5).

The long feedback loop's folder interface: an expert (or, in simulation, the
persona) drops one verdict per ``{id}.json`` file into an inbox folder; a
separate, later run picks it up — fully resumable, no live-session assumption.
Role split (§3 Step 7, unwaivable): the system READS the inbox (tolerant load,
merge into the store); writing is the authoring primitive's job, used only by
the expert/persona side — a run never persists its own captured verdict back.

Decision vocabulary at this layer (C2.5, C-F7): loading polices the §4.2 set
{approved, rejected, approved_with_adjustment} with SKIP semantics — an
unknown decision never reaches the store, but never raises either (the raw
layer is written out of band). The run-path feedback contract (§4.1) and the
promotion gate's accepted set (§6) police their own vocabularies on top.
Capacity is the exception to tolerance: an inbox over the file cap, or a
rationale over the length cap, FAILS FAST with a precise error — a silent
skip there would silently drop expert knowledge (never a silent cut).
"""

from __future__ import annotations

import json
import re
from pathlib import Path

from pydantic import BaseModel, Field, ValidationError

from portfolio_optimiser_claude.experience import (
    CandidateFeatures,
    VerdictRecord,
    VerdictStore,
    mint_verdict_id,
)

# R-6 id grammar — mirrors the ingest-spec §4 id grammar (enforced by the
# llm-ingestion-okf library on the ingest side): lowercase alphanumerics and
# hyphens only, so a verdict id can NEVER traverse paths (no dots, no
# separators). Minted ids (16 hex chars, §4.2) always match.
_ID_RE = re.compile(r"^[a-z0-9][a-z0-9-]*$")

# §4.2: the file layer's full decision vocabulary.
_FILE_DECISIONS = frozenset({"approved", "rejected", "approved_with_adjustment"})

# Fail-fast capacity defaults — generous for any real expert inbox, small
# enough that a runaway writer cannot flood the fold.
_DEFAULT_MAX_FILES = 1_000
_DEFAULT_MAX_RATIONALE_CHARS = 20_000


class InboxLimitError(ValueError):
    """An inbox cap was exceeded — refusing to load (fail-fast, never a silent cut)."""


class ProposalFeatures(BaseModel):
    """§4.2 ``proposal_features``: the structural features of the judged candidate.

    ``description`` is surface text — deliberately excluded from both
    similarity ranking and id minting.
    """

    affected_codes: list[str]
    measure_type: str
    claimed_saving_nok: float
    description: str


class VerdictDocument(BaseModel):
    """One verdict file (§4.2). A LOADED ``id`` is kept verbatim — never re-minted."""

    id: str = Field(min_length=1, pattern=_ID_RE.pattern)
    decision: str = Field(min_length=1)
    rationale: str = Field(min_length=1)
    proposal_features: ProposalFeatures

    @classmethod
    def from_candidate(
        cls,
        features: CandidateFeatures,
        *,
        decision: str,
        rationale: str,
        description: str,
    ) -> VerdictDocument:
        """Author a verdict for a candidate — the id is minted per §4.2."""
        return cls(
            id=mint_verdict_id(features),
            decision=decision,
            rationale=rationale,
            proposal_features=ProposalFeatures(
                affected_codes=sorted(features.affected_codes),
                measure_type=features.measure_type,
                claimed_saving_nok=features.claimed_saving_nok,
                description=description,
            ),
        )

    def features(self) -> CandidateFeatures:
        return CandidateFeatures(
            affected_codes=frozenset(self.proposal_features.affected_codes),
            measure_type=self.proposal_features.measure_type,
            claimed_saving_nok=self.proposal_features.claimed_saving_nok,
        )

    def to_record(self) -> VerdictRecord:
        return VerdictRecord(
            verdict_id=self.id,  # verbatim (§4.2) — raw number formatting could diverge
            decision=self.decision,
            rationale=self.rationale,
            features=self.features(),
        )


def write_verdict(inbox_dir: Path, verdict: VerdictDocument) -> Path:
    """The authoring primitive (§5): ``{id}.json``, written deterministically.

    Creates the directory if needed; sorted keys, 2-space indent. The disk
    layer is LAST-write-wins per file (§4.2). The id grammar is re-checked
    HERE (R-6): ``model_copy(update=...)`` bypasses model validation, so the
    write seam fails closed on its own — nothing is ever written outside
    ``inbox_dir``.
    """
    if _ID_RE.fullmatch(verdict.id) is None:
        raise ValueError(
            f"refusing to write verdict: id {verdict.id!r} violates the id grammar "
            f"{_ID_RE.pattern!r} (R-6 path safety)"
        )
    inbox_dir.mkdir(parents=True, exist_ok=True)
    path = inbox_dir / f"{verdict.id}.json"
    payload = json.dumps(verdict.model_dump(), sort_keys=True, indent=2)
    path.write_text(payload, encoding="utf-8")
    return path


def load_inbox(
    inbox_dir: Path,
    *,
    max_files: int = _DEFAULT_MAX_FILES,
    max_rationale_chars: int = _DEFAULT_MAX_RATIONALE_CHARS,
) -> list[VerdictDocument]:
    """Tolerant load (§5): the raw layer is written out of band — skip, never raise.

    A missing folder yields zero verdicts; files that are not ``.json``, fail
    to parse, lack a required top-level key, violate the id grammar, or carry
    a decision outside the §4.2 vocabulary are SKIPPED. Deterministic order:
    sorted by filename. The caps are the one place tolerance ends: more
    candidate files than ``max_files``, or a rationale longer than
    ``max_rationale_chars``, raises :class:`InboxLimitError` (C2.5).
    """
    if not inbox_dir.is_dir():
        return []
    paths = [
        path
        for path in sorted(inbox_dir.iterdir(), key=lambda p: p.name)
        if path.suffix == ".json" and path.is_file()
    ]
    if len(paths) > max_files:
        raise InboxLimitError(
            f"inbox {inbox_dir} holds {len(paths)} verdict files, over the cap of "
            f"{max_files} — refusing to load"
        )
    verdicts: list[VerdictDocument] = []
    for path in paths:
        try:
            document = VerdictDocument.model_validate(json.loads(path.read_text("utf-8")))
        except (OSError, ValueError, ValidationError):
            continue
        if document.decision not in _FILE_DECISIONS:
            continue  # §4.2 vocabulary (C-F7): unknown decision → SKIP, never the store
        # Outside the tolerant try on purpose — a cap breach must NEVER be
        # swallowed as one more skipped file.
        if len(document.rationale) > max_rationale_chars:
            raise InboxLimitError(
                f"verdict file {path.name} carries a rationale of "
                f"{len(document.rationale)} chars, over the cap of "
                f"{max_rationale_chars} — refusing to load"
            )
        verdicts.append(document)
    return verdicts


def merge_inbox_into_store(
    store: VerdictStore,
    inbox_dir: Path,
    *,
    max_files: int = _DEFAULT_MAX_FILES,
    max_rationale_chars: int = _DEFAULT_MAX_RATIONALE_CHARS,
) -> int:
    """Merge, never replace (§5): per-verdict add, first-write-wins per id.

    Runs BEFORE the Step-1 fold, so a passed-in store's existing verdicts
    survive (cross-project threading) and repeated merges are idempotent.
    Returns the number of inbox verdicts ingested; never writes anything.
    """
    verdicts = load_inbox(inbox_dir, max_files=max_files, max_rationale_chars=max_rationale_chars)
    for verdict in verdicts:
        store.add(verdict.to_record())
    return len(verdicts)