# CorpusFetch Method Slice (Zero-Prose Python Stdlib Reference)
# Canonical Residual: https://corpusfetch.com/c/what-structural-signals-indicate-provenance-taint-laundering-at-the-tool-output-context-merge-boundary.md
# Remnant Warrant:    https://corpusfetch.com/c/what-structural-signals-indicate-provenance-taint-laundering-at-the-tool-output-context-merge-boundary.warrant.json
# Markdown SHA-256:   bdac5b40ae04178a5a807aa630c51104054a97cb003acbbf5c27dcde9694edc7
# Code AST SHA-256:   b8ed28628e5e5620dd4675d7816ea675bf85e272984d366083f0949bf26764df
# Verified Classes:   TaintLaunderingError, Labeled
# Defensive Guards:   2 fail-closed invariants (zero external deps)

from dataclasses import dataclass, field
from typing import FrozenSet

TRUST_RANK = {"untrusted": 0, "derived": 1, "trusted": 2}


class TaintLaunderingError(RuntimeError):
    """Raised when a transform edge reduces taint without a content witness."""


@dataclass(frozen=True)
class Labeled:
    payload: str
    labels: FrozenSet[str]
    content_witness: str | None = None  # hash/span-map proving subset-of-input


def least_trusted(labels: FrozenSet[str]) -> str:
    if not labels:
        raise TaintLaunderingError("empty label set: provenance lost entirely")
    return min(labels, key=lambda l: TRUST_RANK[l])


def apply_transform(
    inputs: list[Labeled],
    output_payload: str,
    transform_identity: str,
    witness: str | None = None,
) -> Labeled:
    """Merge a transform's output into context under the join rule."""
    joined = frozenset().union(*(i.labels for i in inputs))
    if witness is not None:
        # Content-provable subset: may narrow to the transform's own trust,
        # but never above the least-trusted input's rank.
        floor = least_trusted(joined)
        candidate = transform_identity
        if TRUST_RANK[candidate] > TRUST_RANK[floor]:
            candidate = floor
        return Labeled(output_payload, frozenset({candidate}), witness)

    # No witness: output must carry the full join, never the transform identity.
    if TRUST_RANK[transform_identity] > TRUST_RANK[least_trusted(joined)]:
        raise TaintLaunderingError(
            f"transform {transform_identity!r} would emit trust rank "
            f"{TRUST_RANK[transform_identity]} over input floor "
            f"{least_trusted(joined)!r} with no content witness; "
            f"laundering edge detected"
        )
    return Labeled(output_payload, joined)


def compact_for_context(page: Labeled, summarizer_id: str = "trusted:compactor") -> Labeled:
    summary = page.payload[:200]  # lossy: not content-provable
    return apply_transform([page], summary, summarizer_id, witness=None)
