Adds the per-asset incremental-ingest skip block to all three flows
(markdown / image / pdf). When `IngestOpts::force_reingest = false`
AND the asset's blake3 checksum + parser/chunker/embedding versions
all match the existing DB record, ingest emits
`AssetFinished { result: Unchanged }`, bumps `aggregate.unchanged`,
and skips parse / chunk / embed / vector upsert entirely.
Shared `try_skip_unchanged` helper performs the four checks; per-flow
callers supply the active parser_version + chunker_version + optional
embedding_version. `force_reingest = true` bypasses the skip path so
`incremental_ingest::force_reingest_bypasses_skip` still sees `Updated`.
Tests:
- new `incremental_ingest.rs` covers both paths.
- existing `ingest_idempotent_on_second_run` /
`re_ingest_image_produces_*` / `re_ingest_identical_pdf_produces_*`
updated to assert `Unchanged` on identical-bytes re-ingest (the
pre-task behaviour was `Updated`).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
All three ingest flows (markdown, image, pdf) now set
last_chunker_version and last_embedding_version on the CanonicalDocument
before calling put_document, giving Task 7's skip detection the data it
needs on the second run. No skip path is added yet.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
