Generated from folio-assistant-core/processes/library/ingest-derive-content.bpmn by gen-processes-viz.ts — do not edit here. All processes

Ingestion subprocess — derive content from the assets

Process_DeriveContent · advisory · 6 step(s)

Derive content from an ingested source’s assets: the archive, technical metadata, images, audio, tabular data and provenance. folio-assistant — Ingestion subprocess — derive content from the assets.

Source of truth: this file. Open it in bpmn.io, Camunda Modeler, or any other BPMN 2.0 tool. The SVG under docs/assets/img/workflows/ is generated from it by bun run cat render:bpmn — never hand-edit the SVG.

The extension on an activity names the folio-assistant skill that implements it; marks a step that reads or writes the shared work plan in beans/.

BPMN diagram: Ingestion subprocess — derive content from the assets

How it connects

Called by: L1 document ingestion — a document to the L1 source knowledge graph
Calls: none
Presented on: Document ingestion — Derive content

Lanes — who acts

lane	role	what it does here
Ingestion Engine (agent, runs unattended)	`ingestion-agent`	The only lane in this subprocess, so nothing produced here is checked by a different party before it reaches the L1 graph. Five of these six tasks carry their own NOT IMPLEMENTED note; Task_Provenance does not, and its citation of who or what wrote each narrative is what is meant to stand between a generated description and its being treated as source material.

Steps

Every one of the 6 step(s) is documented.

step	lane	skill / sub-process	what it does
Archive → greppable contents manifest `Task_Archive`	Ingestion Engine (agent, runs unattended)	`document-intake`	NOT IMPLEMENTED. Tracked as a bean; see docs/document-ingestion.md. Tar/zip is opaque to every grep in the corpus until its contents are listed as data.
File info, sizes, hashes, timestamps, mimetype `Task_TechMeta`	Ingestion Engine (agent, runs unattended)	`document-intake`	NOT IMPLEMENTED. Tracked as a bean; see docs/document-ingestion.md. Mechanical and cheap; the checksum is what makes a remote asset verifiable.
Narrative description per image, localized `Task_Image`	Ingestion Engine (agent, runs unattended)	`document-intake`	NOT IMPLEMENTED. Tracked as a bean; see docs/document-ingestion.md. Applies equally to an image EXTRACTED FROM A PDF, not only to an uploaded one.
Transcribe and translate audio `Task_Audio`	Ingestion Engine (agent, runs unattended)	`document-intake`	NOT IMPLEMENTED. Tracked as a bean; see docs/document-ingestion.md.
Sheet names, headers, shape, narrative `Task_Tabular`	Ingestion Engine (agent, runs unattended)	`document-intake`	NOT IMPLEMENTED. Tracked as a bean; see docs/document-ingestion.md. CSV and spreadsheet: tabs, column and row headers, sizes, and what the dataset is about.
Cite the author of every narrative `Task_Provenance`	Ingestion Engine (agent, runs unattended)	`document-intake`	A generated description is a claim by someone. Record whether a human or an agent wrote it, and for an agent the model version. An uncited narrative is indistinguishable from a transcription of the source.