Files
openclaw/qa/scenarios/media/pdf-document-extraction-dispatch.yaml

29 lines
1.2 KiB
YAML

title: PDF document extraction dispatch
scenario:
id: pdf-document-extraction-dispatch
surface: media
category: media.media-intake-and-access
coverage:
primary:
- media.pdf-document-extraction-dispatch
objective: Verify PDF intake dispatches through the bundled document extractor to real clawpdf and reports disabled extraction explicitly.
successCriteria:
- The bundled document-extract plugin supplies the PDF extractor.
- A parseable inline PDF yields its sentinel text through real clawpdf.
- The document extractor runtime tags the result with extractor pdf.
- Disabling document extraction produces the explicit unavailable error.
docsRefs:
- docs/plugins/reference/document-extract.md
- docs/tools/pdf.md
codeRefs:
- src/media/pdf-extract.ts
- src/media/document-extractors.runtime.ts
- src/plugins/document-extractors.runtime.ts
- extensions/document-extract/document-extractor.ts
- test/e2e/qa-lab/media/pdf-document-extraction-dispatch.e2e.test.ts
execution:
kind: vitest
path: test/e2e/qa-lab/media/pdf-document-extraction-dispatch.e2e.test.ts
summary: Run a parseable inline PDF through bundled extractor discovery, real clawpdf extraction, and the disabled-plugin failure path.