Kjell Tore Guttormsen
5732d13369
Replace the local 391-line ingest implementation with a thin adapter over the shared llm-ingestion-okf library (git-pinned dae0bd1a via Forgejo, tool.uv.sources). The materialize() signature is preserved; error types are now the library's typed hierarchy rooted in IngestError, re-exported from the consumer seam. - tests/test_ingest_adoption.py: new load-bearing seam tests (delegation, offline invariant — allow_network is never passed, error contract), detach-proven red twice. - Golden suites (file + sql) pass UNCHANGED — byte-exact behaviour proven against the repo-local fixtures. - 6 test files migrated to the library error hierarchy; escaping/typed-cell unit tests dropped (byte-bound by the ingest-edge.md golden, unit-owned by the library's own 189-test suite). Provenance stamp now asserted independently from the §5 rule. - mypy override follow_untyped_imports for llm_ingestion_okf (no py.typed upstream yet — reported as a finding). Suite: 386 passed; ruff + format + mypy --strict clean; shared/, examples/, runs/s10/ and run_s10.py byte-untouched. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
101 lines
3.8 KiB
Python
101 lines
3.8 KiB
Python
"""Adoption seam: Door A ingest is the shared llm-ingestion-okf library (§11).
|
|
|
|
This repo's local ingest implementation was replaced by the shared library
|
|
(first consumer adoption). These load-bearing tests bind the adapter seam:
|
|
|
|
- Delegation — ``ingest.materialize`` IS a call into the library (RED if a
|
|
local reimplementation sneaks back in).
|
|
- Offline invariant — the adapter NEVER passes the per-run network opt-in:
|
|
an http-source manifest is refused at the library's network gate (RED if
|
|
the adapter starts granting network access).
|
|
- Error contract — the consumer-facing error types ARE the library's typed
|
|
hierarchy rooted in ``IngestError`` (RED if the seam re-wraps or forks).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
import llm_ingestion_okf
|
|
from portfolio_optimiser_claude import ingest
|
|
|
|
INGESTED_AT = "2026-07-16T12:00:00Z"
|
|
|
|
|
|
def _http_manifest() -> dict[str, Any]:
|
|
return {
|
|
"manifest_version": 1,
|
|
"source": {"type": "http", "id": "api", "base_url": "https://example.invalid"},
|
|
"bundle_summary": "s",
|
|
"extractions": [
|
|
{"id": "e", "title": "T", "query": "rows", "okf_type": "dataset", "max_rows": 1}
|
|
],
|
|
}
|
|
|
|
|
|
class TestDelegation:
|
|
"""Seam: the consumer entry points are the library's (RED if detached)."""
|
|
|
|
def test_load_manifest_is_the_library_entry_point(self) -> None:
|
|
assert ingest.load_manifest is llm_ingestion_okf.load_manifest
|
|
|
|
def test_materialize_delegates_with_the_offline_default(
|
|
self, monkeypatch: pytest.MonkeyPatch, tmp_path: Path
|
|
) -> None:
|
|
calls: dict[str, Any] = {}
|
|
|
|
def fake(
|
|
manifest_path: Path, bundle_dir: Path, ingested_at: str, **kwargs: Any
|
|
) -> llm_ingestion_okf.IngestResult:
|
|
calls["args"] = (manifest_path, bundle_dir, ingested_at)
|
|
calls["kwargs"] = kwargs
|
|
return llm_ingestion_okf.IngestResult(written=(tmp_path / "ingest-e.md",))
|
|
|
|
monkeypatch.setattr(ingest, "materialize_bundle", fake)
|
|
out = ingest.materialize(tmp_path / "manifest.json", tmp_path / "bundle", INGESTED_AT)
|
|
assert out == [tmp_path / "ingest-e.md"] # IngestResult.written → list, order kept
|
|
assert calls["args"] == (tmp_path / "manifest.json", tmp_path / "bundle", INGESTED_AT)
|
|
# The offline invariant at the seam: allow_network/http_get are NEVER
|
|
# passed — the library's local-only default stays in force.
|
|
assert calls["kwargs"] == {}
|
|
|
|
|
|
class TestOfflineInvariant:
|
|
"""Seam: the adapter cannot grant network access (RED if it opts in)."""
|
|
|
|
def test_http_source_is_refused_at_the_network_gate(self, tmp_path: Path) -> None:
|
|
manifest = tmp_path / "manifest.json"
|
|
manifest.write_text(json.dumps(_http_manifest()), encoding="utf-8")
|
|
bundle = tmp_path / "bundle"
|
|
with pytest.raises(ingest.NetworkGateError):
|
|
ingest.materialize(manifest, bundle, INGESTED_AT)
|
|
assert not bundle.exists() or not any(bundle.iterdir()) # gate fires before any write
|
|
|
|
|
|
class TestErrorContract:
|
|
"""Seam: consumer-facing errors ARE the library hierarchy (RED if forked)."""
|
|
|
|
def test_error_types_are_the_library_types(self) -> None:
|
|
for name in (
|
|
"IngestError",
|
|
"ManifestError",
|
|
"MaterializationError",
|
|
"NetworkGateError",
|
|
"RenderError",
|
|
"SourceError",
|
|
):
|
|
assert getattr(ingest, name) is getattr(llm_ingestion_okf, name)
|
|
|
|
def test_every_error_roots_in_ingest_error(self) -> None:
|
|
for exc in (
|
|
ingest.ManifestError,
|
|
ingest.MaterializationError,
|
|
ingest.NetworkGateError,
|
|
ingest.RenderError,
|
|
ingest.SourceError,
|
|
):
|
|
assert issubclass(exc, ingest.IngestError)
|