4.3 KiB
4.3 KiB
Ingestion pipeline
Version 0.3.0. Host-executed procedure for kb-ingest; not a background scheduler. Follow the contribution protocol for budgets, checkpoints and retry identity.
| Stage | Input | Output / checkpoint | Gate |
|---|---|---|---|
| Context | User-selected material, explicit project and get_project_context lens |
Objective, authorized project lens including four default research lenses and saved guidance, scope, run identity and pinned pack versions | Required tools/schema are available; otherwise report blocked. |
| Capture | Explicitly selected local files, user-pasted text or an allowlisted public URL | Verified artifact digest, stable source ID, content-bound revision ID, metadata candidate and extraction availability | Use the connector for local files, source_capture_text for explicitly supplied UTF-8 text/Markdown (maximum 1 MB), or source_capture_url for a configured public host. Pasted text requires a stable capture ID and source key, and returns an archived artifact, extraction and candidate marked pasted-text; retry with the same ID and identical inputs after uncertainty, since changed inputs conflict. The service retains at most 1,024 private capture receipts. The capture does not register the source. The connector returns a typed source_candidate; .vtt and .srt files are parsed into cue-timed blocks and tagged transcript. Cite the precise cue times together with the quote span. The connector can record a declared NotebookLM export provenance for supported text, Markdown or PDF files, but does not verify that provenance; omit source_revision_id to derive a revision from file identity, content digest and its durable retry checkpoint, or supply a stable revision ID when resuming an existing workflow. Submit candidates through proposal_submit; staging alone does not register a source. Failed fetches return a capture-failed candidate without artifact bytes; register it only when a bookmark is useful. PDF extraction currently requires the supported Linux sandbox. HTML citations refer to visible extracted text, not markup-byte offsets. |
| Triage | Source plus project lens and four default lenses (technical, conceptual, cultural-historical, financial-market) | Included sections, explicit clear-exclusion reasons and review flags | Treat lenses as coverage prompts, not quotas. Historical, philosophical, cultural or commercial evidence is not automatically out of scope. Exclude only clearly unrelated or unavailable material, or user-excluded topics. Continue normal evidence-backed proposal processing for plausible material; add ingest_review_create as a follow-up notification/filter flag when human relevance review would help. |
| Extract | Included sections and immutable maps | Atomic proposal draft with field-level evidence | Exact quotes/locators; no invented revisions. |
| Assess | Assertion/evidence bindings | Support judgments, assessor/run and rationale | Unsupported/unavailable claims remain drafts. |
| Evaluate | Complete bounded bundle and base revision | proposal_evaluate findings and eligible status |
Evaluation is read-only; it does not reserve an ID or store the proposal. |
| Submit | Evaluated bounded bundle and stable proposal identity | proposal_submit outcome and eventual receipt |
Every affected domain's policy applies; protected decisions remain external. |
| Human review | Stored review flag and authorized editor/admin decision | Include, exclude or defer feedback; optionally saved project/lens guidance | The flag never blocks proposal evaluation/submission or marks knowledge accepted. Decisions are feedback only. Save reusable guidance only on explicit reviewer opt-in. |
| Report | proposal_status, receipts, review flags and coverage records |
Accepted/held work, review notifications, index state, limitations and resume point | Never equate upload, evaluation, review-flag creation or partial acceptance with complete processing. |
Resume calls source_upload_status or proposal_status using the exact checkpointed ID and revision before returning to a stage. Changed assertion/evidence invalidates assessment and later stages. Correct only actionable findings; repeated identical failure stops for diagnosis. Pipeline instructions may be replaced independently of the skill's extraction criteria if these input/output and recovery obligations remain valid.