"""Spec-integrity seam for the ingest spec (ingest-spec §11).

The D7 analog of MAF's I1 framework-guard: this repo consumes ``shared/ingest-spec.md``
UNCHANGED from commons, and this test keeps the contract honest — it goes RED when the
spec goes missing, names a concrete agent toolkit (the framework-neutrality rule), or
stops documenting a contract field. It is the load-bearing guard the ingest layer relies
on to keep being implementable "from this spec alone".
"""

from __future__ import annotations

from pathlib import Path

import pytest

SPEC = Path(__file__).resolve().parents[1] / "shared" / "ingest-spec.md"

# Concrete agent toolkits / vendor stacks the framework-neutral spec MUST NOT name.
_FORBIDDEN_TOOLKITS = (
    "claude",
    "anthropic",
    "openai",
    "gpt",
    "gemini",
    "llama",
    "langchain",
    "autogen",
    "crewai",
    "semantic kernel",
    "microsoft agent framework",
    "agent sdk",
    "bedrock",
    "vertex",
    "foundry",
    "maf",
)

# The §12 cross-check table is the ANCHOR, and the spec appoints it itself: "Every field
# of the machine-readable contracts, mapped to its normative section (completeness is
# enforced by the spec-integrity test)" — this test is that enforcer. Asserting over the
# whole spec text instead would be green-but-dead: prose saturates the field names (§1's
# honesty rule alone carries `generated: true` twice), so no amendment dropping a row
# could ever turn it red.
_CROSS_CHECK_HEADING = "## 12. Cross-check table"

# Every field of the machine-readable contracts the D7 implementation depends on — the
# spec's §12 cross-check table must keep documenting each (spec-integrity).
_CONTRACT_FIELDS = (
    "manifest_version",
    "source",
    "bundle_summary",
    "extractions",
    "source_system",
    "source_query",
    "ingested_at",
    "ingest_manifest",
    "generated",
    "okf_type",
    "max_rows",
    "root",
    "connection_ref",  # the sql source reference the D7 sql connector (I5) depends on
)


def _cross_check_table() -> str:
    """The §12 section body — heading to end-of-spec or the next section, whichever first."""
    text = SPEC.read_text(encoding="utf-8")
    start = text.index(_CROSS_CHECK_HEADING)  # RED (ValueError) if §12 is renamed or dropped
    end = text.find("\n## ", start + len(_CROSS_CHECK_HEADING))
    return text[start:] if end == -1 else text[start:end]


def test_spec_is_present() -> None:
    # RED if the spec goes missing (the layer stops being implementable from spec alone).
    assert SPEC.is_file(), "ingest-spec.md missing — subtree pull the commons contract"


def test_spec_names_no_agent_toolkit() -> None:
    text = SPEC.read_text(encoding="utf-8").lower()
    present = [tok for tok in _FORBIDDEN_TOOLKITS if tok in text]
    assert not present, f"framework-neutral spec names a concrete toolkit: {present}"


def test_cross_check_slice_is_a_slice_and_not_the_whole_spec() -> None:
    # Guards the anchor itself: a slice that degenerated into the full text would make
    # every row assertion below green-but-dead again, silently. RED if it widens.
    table = _cross_check_table()
    assert table.startswith(_CROSS_CHECK_HEADING)
    assert "Honesty rule" not in table, "slice leaked §1 prose — the anchor is not a slice"
    assert "\n## " not in table, "slice leaked a following section"


@pytest.mark.parametrize("field", _CONTRACT_FIELDS)
def test_spec_documents_contract_field(field: str) -> None:
    # The row's FIRST column is the documented-field claim; a field named only in another
    # row's "Contract" prose does not count. RED when an amendment drops or renames a row.
    table = _cross_check_table()
    assert f"| `{field}` |" in table, (
        f"contract field {field!r} is no longer a row in the §12 cross-check table"
    )