"""HITL verdict routing + pending tracking (method-spec §5; S5.1; paritetsrad 22; K9).

The operator's view of the long feedback loop: which proposals still AWAIT an
expert verdict, and who should judge each. A pure file-based id-join across the
three layers this module READS — it never writes any of them (role split §3
Step 7: the expert writes the inbox, the system reads it; notification is K10's
job, never this).

* **outbox** (K5) — each completed run persists a ``{run_id}`` PAIR; the
  ``{run_id}-outcome.json`` carries the join key ``verdict_id`` (minted the SAME
  way the inbox mints a verdict id, ``mint_verdict_id`` over the candidate
  features — pinned in K5's test, reused here). Read verbatim, never re-minted.
* **inbox** (§4.2/§5) — expert verdict files; a proposal is SETTLED once a
  §4.2-valid verdict for its id is loaded (``load_inbox`` polices the decision
  vocabulary — a skipped/unknown decision never settles anything).
* **promoted** (§6) — a promoted verdict in a bundle's context layer carries its
  ``verdict_id`` in frontmatter and settles the proposal too. Optional
  (``bundle_dirs``) so the core join is exactly the two layers outbox↔inbox.

A proposal is *pending* when its ``verdict_id`` is in NONE of the settled sets.
Routing maps the proposal's ``measure`` (a config-string key NOW — K13 formalizes
the dimension catalog) to an expert; an unmatched measure falls to the optional
``default_expert``, else the proposal is UNROUTED (nobody configured to judge it).
The routing config is schema-validated fail-fast (§10) — a malformed table never
reaches a routed report.

Run:  uv run python -m portfolio_optimiser_claude.hitl pending --outbox <dir> --inbox <dir>
      uv run python -m portfolio_optimiser_claude.hitl route  --outbox <dir> --inbox <dir> \
          --routing <file.json> [--bundle <dir> ...]
"""

from __future__ import annotations

import argparse
import json
from dataclasses import dataclass
from pathlib import Path
from typing import Annotated, Any, Sequence

from pydantic import BaseModel, Field, ValidationError, model_validator

from portfolio_optimiser_claude.inbox import load_inbox
from portfolio_optimiser_claude.ir import SavingsProposal
from portfolio_optimiser_claude.notify import (
    EgressNotPermitted,
    Notification,
    Notifier,
    Transport,
    add_notify_args,
    build_notifiers,
    emit,
    notify_config_from_args,
)
from portfolio_optimiser_claude.okf import navigate_bundle

_OUTCOME_SUFFIX = "-outcome.json"
_PROPOSAL_SUFFIX = "-proposal.json"
_VERDICT_TYPE = "verdict"

# An expert id is a non-empty config string (K13 gives it a formal catalog).
_ExpertId = Annotated[str, Field(min_length=1)]


@dataclass(frozen=True)
class PendingProposal:
    """One outbox proposal awaiting a verdict — the join key plus routing fields.

    ``measure`` is the routing dimension read as a config string today (K13
    formalizes the dimension catalog); ``verdict_id`` is the persisted K5 join
    key, read verbatim from the outcome file (never re-minted here).
    """

    run_id: str
    verdict_id: str
    project_id: str
    measure: str
    claimed_saving_nok: float


@dataclass(frozen=True)
class RoutedProposal:
    """A pending proposal plus its assigned expert (``None`` = UNROUTED)."""

    proposal: PendingProposal
    expert: str | None


class RoutingContract(BaseModel):
    """nøkkel→ekspert routing table (§10, fail-fast before any routed report).

    Keys are opaque config strings NOW (K13 formalizes the dimension catalog);
    values are non-empty expert ids. The table must be non-empty (an empty table
    could never route anyone). ``default_expert`` is the optional fall-through for
    an unmatched key; absent means an unmatched proposal is UNROUTED.
    """

    routes: dict[str, _ExpertId] = Field(min_length=1)
    default_expert: _ExpertId | None = None

    @model_validator(mode="after")
    def _keys_non_empty(self) -> RoutingContract:
        for key in self.routes:
            if not key.strip():
                raise ValueError("routing key must be a non-empty string")
        return self


def load_routing(raw: dict[str, Any]) -> RoutingContract:
    """Validate the routing config at startup (§10) — ``ValidationError`` fail-fast."""
    return RoutingContract(**raw)


def load_outbox_proposals(outbox_dir: Path) -> list[PendingProposal]:
    """Read every persisted outbox pair into a ``PendingProposal`` (sorted by run_id).

    Each ``{run_id}-outcome.json`` supplies the join key ``verdict_id`` and the
    ``run_id``; its sibling ``{run_id}-proposal.json`` supplies the routing/display
    fields. A pair that cannot be read as a well-formed unit (bad JSON, missing
    field, absent sibling) is SKIPPED — a defensive read boundary over the
    system's own deterministic output, never a crash. Nothing is written.
    """
    if not outbox_dir.is_dir():
        return []
    proposals: list[PendingProposal] = []
    for outcome_path in sorted(outbox_dir.glob(f"*{_OUTCOME_SUFFIX}")):
        stem = outcome_path.name[: -len(_OUTCOME_SUFFIX)]
        proposal_path = outcome_path.with_name(f"{stem}{_PROPOSAL_SUFFIX}")
        try:
            record = json.loads(outcome_path.read_text("utf-8"))
            run_id = str(record["run_id"])
            verdict_id = str(record["verdict_id"])
            proposal = SavingsProposal.model_validate(json.loads(proposal_path.read_text("utf-8")))
        except (OSError, KeyError, ValueError, ValidationError):
            continue  # a broken pair is skipped — read boundary, never a raise
        proposals.append(
            PendingProposal(
                run_id=run_id,
                verdict_id=verdict_id,
                project_id=proposal.project_id,
                measure=proposal.measure,
                claimed_saving_nok=proposal.claimed_saving_nok,
            )
        )
    return sorted(proposals, key=lambda p: p.run_id)


def _promoted_verdict_ids(bundle_dir: Path) -> set[str]:
    """The verdict ids of PROMOTED verdicts in a bundle (§6) — read-only.

    A promoted file carries ``type: verdict`` plus a ``verdict_id`` in its
    frontmatter; a hand-authored seed verdict has no ``verdict_id`` and is not a
    judgment of an outbox proposal, so it is ignored.
    """
    return {
        vid
        for concept in navigate_bundle(bundle_dir)
        if concept.type == _VERDICT_TYPE and (vid := concept.frontmatter.get("verdict_id"))
    }


def settled_verdict_ids(inbox_dir: Path, *, bundle_dirs: Sequence[Path] = ()) -> set[str]:
    """Every verdict id already settled: §4.2-valid inbox verdicts ∪ promoted verdicts.

    Inbox ids come THROUGH ``load_inbox`` (decision-vocabulary policed — a skipped
    unknown decision never settles a proposal; a capacity breach still fails fast).
    Promoted ids come from each bundle's context layer. Read-only.
    """
    ids = {document.id for document in load_inbox(inbox_dir)}
    for bundle_dir in bundle_dirs:
        ids |= _promoted_verdict_ids(bundle_dir)
    return ids


def pending_proposals(
    outbox_dir: Path, inbox_dir: Path, *, bundle_dirs: Sequence[Path] = ()
) -> list[PendingProposal]:
    """Outbox proposals whose ``verdict_id`` is in NONE of the settled sets (the id-join).

    The load-bearing seam: an outbox proposal survives ONLY if it is not settled.
    Drop the ``not in settled`` filter and a judged proposal is still listed —
    the loop's whole point (surface only the outstanding) collapses.
    """
    settled = settled_verdict_ids(inbox_dir, bundle_dirs=bundle_dirs)
    return [
        proposal
        for proposal in load_outbox_proposals(outbox_dir)
        if proposal.verdict_id not in settled
    ]


def route_pending(
    pending: Sequence[PendingProposal], routing: RoutingContract
) -> list[RoutedProposal]:
    """Assign an expert to each pending proposal by its ``measure`` (config-string key).

    An unmatched measure falls to ``default_expert`` (``None`` when absent →
    UNROUTED). No I/O — a pure mapping over the already-loaded pending set.
    """
    return [
        RoutedProposal(
            proposal=proposal,
            expert=routing.routes.get(proposal.measure, routing.default_expert),
        )
        for proposal in pending
    ]


def _bundle_dirs(values: list[str] | None) -> list[Path]:
    return [Path(value) for value in (values or [])]


def _cmd_pending(args: argparse.Namespace, notifiers: Sequence[Notifier]) -> int:
    pending = pending_proposals(
        Path(args.outbox), Path(args.inbox), bundle_dirs=_bundle_dirs(args.bundle)
    )
    print(f"PENDING — {len(pending)} proposal(s) awaiting a verdict:")
    for proposal in pending:
        print(
            f"  {proposal.run_id}  verdict_id={proposal.verdict_id}  "
            f"measure={proposal.measure!r}  project={proposal.project_id}"
        )
    # K10: notification is egress, NOT writing any of the three read layers —
    # the read-only invariant (§3 Step 7) holds (proven by the seam test's
    # before/after byte snapshot of outbox+inbox).
    emit(
        notifiers,
        Notification(
            event="hitl.pending",
            summary=f"{len(pending)} proposal(s) awaiting a verdict",
            fields={"pending": len(pending)},
        ),
    )
    return 0


def _cmd_route(args: argparse.Namespace, notifiers: Sequence[Notifier]) -> int:
    try:
        routing = load_routing(json.loads(Path(args.routing).read_text("utf-8")))
    except (OSError, ValueError, ValidationError) as exc:
        print(f"ROUTE FAILED — invalid routing config (fail-fast, §10): {exc}")
        return 1
    pending = pending_proposals(
        Path(args.outbox), Path(args.inbox), bundle_dirs=_bundle_dirs(args.bundle)
    )
    routed = route_pending(pending, routing)
    print(f"ROUTE — {len(routed)} pending proposal(s), assigned expert per measure:")
    for item in routed:
        expert = item.expert if item.expert is not None else "UNROUTED (no route, no default)"
        print(
            f"  {item.proposal.run_id}  measure={item.proposal.measure!r}  "
            f"verdict_id={item.proposal.verdict_id}  -> {expert}"
        )
    unrouted = sum(1 for item in routed if item.expert is None)
    emit(
        notifiers,
        Notification(
            event="hitl.route",
            summary=f"{len(routed)} pending proposal(s) routed, {unrouted} UNROUTED",
            fields={"pending": len(routed), "unrouted": unrouted},
        ),
    )
    return 0


def main(argv: list[str] | None = None, *, notifier_transport: Transport | None = None) -> int:
    """The thin CLI: ``pending`` lists outstanding proposals; ``route`` adds experts.

    ``pending`` is a pure report (exit 0). ``route`` loads the routing config
    fail-fast — a malformed/missing config exits non-zero WITHOUT touching any
    layer (§10). Neither subcommand writes any of the three read layers.

    An optional notify seam (K10) delivers a summary event; a ``--notify-webhook``
    without ``--allow-webhook-egress`` is refused fail-fast (§8) BEFORE any read.
    ``notifier_transport`` is the injected webhook transport (canned in the suite,
    ``default_webhook_transport`` on the CLI path — no socket in tests).
    """
    parser = argparse.ArgumentParser(
        description=(
            "Show which proposals still await an expert verdict (pending) and who "
            "should judge each (route) — a read-only file-based id-join across the "
            "outbox, the inbox, and promoted verdicts. This never writes any layer."
        )
    )
    subparsers = parser.add_subparsers(dest="command", required=True)

    def _add_common(sub: argparse.ArgumentParser) -> None:
        sub.add_argument("--outbox", required=True, help="outbox dir (run_id-named pairs, K5)")
        sub.add_argument("--inbox", required=True, help="inbox dir (expert verdict files, §5)")
        sub.add_argument(
            "--bundle",
            action="append",
            help="bundle dir whose promoted verdicts also settle a proposal (repeatable)",
        )
        add_notify_args(sub)

    pending_parser = subparsers.add_parser("pending", help="list proposals awaiting a verdict")
    _add_common(pending_parser)
    pending_parser.set_defaults(func=_cmd_pending)

    route_parser = subparsers.add_parser("route", help="assign an expert to each pending proposal")
    _add_common(route_parser)
    route_parser.add_argument(
        "--routing", required=True, help="routing config JSON (nøkkel→ekspert, schema-validated)"
    )
    route_parser.set_defaults(func=_cmd_route)

    args = parser.parse_args(argv)
    # K10 (§8): build the notify sinks BEFORE any read — a --notify-webhook
    # without --allow-webhook-egress is refused fail-fast here (the opt-in is a
    # run argument, never a config field).
    try:
        notifiers = build_notifiers(
            notify_config_from_args(args), webhook_transport=notifier_transport
        )
    except EgressNotPermitted as exc:
        parser.error(str(exc))
    result: int = args.func(args, notifiers)
    return result


if __name__ == "__main__":
    raise SystemExit(main())