open/llm-ingestion-okf
1
0
Fork 0
Code Issues Releases 1 Activity

fix(segmentation): hash the extracted text and let the plan key fire

Browse source
This commit is contained in:
Kjell Tore Guttormsen 2026-09-02 14:38:20 +02:00
commit 9e9bb8645d
13 changed files with 272 additions and 40 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tests/test_error_codes.py
View file

@ -601,6 +601,7 @@ def segmentation_payload(**overrides: Any) -> dict[str, Any]:
payload: dict[str, Any] = {
"version": "1",
"source_sha256": "a" * 64,
"text_sha256": "c" * 64,
"extractor_id": "text",
"extractor_version": "1.0.0",
"adjudicated_at": INGESTED_AT,
@ -664,6 +665,7 @@ def test_segmentation_extractor_mismatch() -> None:
assert_plan_applies(
plan,
source_sha256="b" * 64,
text_sha256=plan.text_sha256,
extractor_id=plan.extractor_id,
extractor_version=plan.extractor_version,
)