feat(pipeline): skip extraction when the source has not changed (#105) (#126)

Co-authored-by: Mathias <mthbqv@gmail.com>

ingestion/internal/pipeline/build.go

@@ -76,6 +76,9 @@ func buildFrontmatter(rp RawPage, date string) string {
 		}
 		fmt.Fprintf(&sb, "date_ingested: %s\n", date)
 		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+		if rp.SourceHash != "" {
+			fmt.Fprintf(&sb, "source_hash: %s\n", rp.SourceHash)
+		}
 		if rp.Source != "" {
 			fmt.Fprintf(&sb, "source: %s\n", yamlScalar(rp.Source))
 		}

ingestion/internal/pipeline/parse.go

@@ -20,9 +20,13 @@ type RawPage struct {
 	// ingested content's own frontmatter (see parseContentFrontmatter) — never
 	// set by the LLM. json:"-" keeps them immune to same-named keys the LLM
 	// might emit. Only meaningful for Type == "source".
-	Source    string `json:"-"`
-	Author    string `json:"-"`
-	Published string `json:"-"`
+	// SourceHash is sha256 of the ingested BODY (frontmatter excluded), stamped
+	// so the next ingest of the same source can tell "unchanged" from "edited"
+	// without re-running extraction (#105).
+	SourceHash string `json:"-"`
+	Source     string `json:"-"`
+	Author     string `json:"-"`
+	Published  string `json:"-"`
 }
 
 // ParseRawPages parses LLM output as a JSON array of RawPage objects.
@@ -112,6 +116,11 @@ type sourceMeta struct {
 	Source    string
 	Author    string
 	Published string
+	// BodyHash is sha256 of the content with any leading frontmatter removed.
+	// Body-only on purpose: a re-crawl that stamps a new fetch date has not
+	// changed the source, and treating that as drift would re-extract the
+	// whole corpus every time a crawler ran (#105).
+	BodyHash string
 }
 
 // parseContentFrontmatter extracts source/author/published from a leading
@@ -154,6 +163,7 @@ func applySourceMeta(pages []RawPage, meta sourceMeta) {
 		if pages[i].Type != "source" {
 			continue
 		}
+		pages[i].SourceHash = meta.BodyHash
 		pages[i].Source = meta.Source
 		pages[i].Author = meta.Author
 		pages[i].Published = meta.Published

ingestion/internal/pipeline/pipeline.go

@@ -3,6 +3,8 @@ package pipeline
 
 import (
 	"context"
+	"crypto/sha256"
+	"encoding/hex"
 	"fmt"
 	"os"
 	"path/filepath"
@@ -26,6 +28,11 @@ type Config struct {
 type Result struct {
 	Pages    []string // relative paths written (or would-be written in dry-run)
 	Warnings []string
+	// Skipped reports that the source was byte-identical to the last ingest,
+	// so no extraction ran and nothing was written. Reported rather than
+	// silent: a run that does nothing must say so, or "the pipeline is fine"
+	// and "the pipeline stopped working" look the same (#105, #107).
+	Skipped bool
 }
 
 // Run ingests content and writes structured wiki pages to brainDir/wiki/.
@@ -43,6 +50,18 @@ func Run(ctx context.Context, cfg Config, brainDir, content, source string, dryR
 
 	sourceSlug := wiki.Slug(source)
 	date := time.Now().UTC().Format("2006-01-02")
+
+	// Drift check BEFORE any extraction: an unchanged source costs a full LLM
+	// pass over every chunk to produce a result that merges to nothing (#105).
+	// The merge is already idempotent (#103), so this is cost and signal, not
+	// correctness — which is why it is safe for it to be an early return.
+	bodyHash := hashBody(content)
+	if !dryRun && bodyHash != "" && bodyHash == storedSourceHash(brainDir, sourceSlug) {
+		return Result{Skipped: true, Warnings: []string{
+			fmt.Sprintf("source %q unchanged since last ingest (hash %s) — extraction skipped", source, bodyHash[:12]),
+		}}, nil
+	}
+
 	chunks := Chunk(content, cfg.ChunkSize)
 
 	var allRaw []RawPage
@@ -59,7 +78,9 @@ func Run(ctx context.Context, cfg Config, brainDir, content, source string, dryR
 		allWarnings = append(allWarnings, warnings...)
 	}
 
-	applySourceMeta(allRaw, parseContentFrontmatter(content))
+	meta := parseContentFrontmatter(content)
+	meta.BodyHash = bodyHash
+	applySourceMeta(allRaw, meta)
 
 	return buildAndWrite(allRaw, sourceSlug, date, brainDir, source, inventory, allWarnings, dryRun)
 }
@@ -119,6 +140,45 @@ func buildAndWrite(rawPages []RawPage, sourceSlug, date, brainDir, source string
 	return Result{Pages: written, Warnings: warnings}, nil
 }
 
+// hashBody returns sha256 of content with any leading frontmatter block
+// removed, or "" for empty content.
+//
+// Body-only on purpose: a re-crawl that stamps a new fetch date has not changed
+// the source, and treating that as drift would re-extract the corpus every time
+// a crawler ran (#105).
+func hashBody(content string) string {
+	body := content
+	if strings.HasPrefix(body, "---\n") {
+		if _, rest, found := strings.Cut(body[4:], "\n---"); found {
+			body = strings.TrimPrefix(rest, "\n")
+		}
+	}
+	if strings.TrimSpace(body) == "" {
+		return ""
+	}
+	sum := sha256.Sum256([]byte(body))
+	return hex.EncodeToString(sum[:])
+}
+
+// storedSourceHash reads source_hash from the source page a previous ingest
+// wrote, or "" when there is no such page or no such field.
+//
+// Absence always means "extract". That is the fail-safe direction: a missed
+// skip costs one extraction, while a wrong skip loses an update silently — and
+// silence is the failure mode this repo keeps paying for.
+func storedSourceHash(brainDir, sourceSlug string) string {
+	raw, err := os.ReadFile(filepath.Join(brainDir, "wiki", "sources", sourceSlug+".md"))
+	if err != nil {
+		return ""
+	}
+	for _, line := range strings.Split(string(raw), "\n") {
+		if key, value, found := strings.Cut(line, ":"); found && strings.TrimSpace(key) == "source_hash" {
+			return strings.TrimSpace(value)
+		}
+	}
+	return ""
+}
+
 // reviseOrCreate returns the bytes to write for one extracted page: merged into
 // whatever is already on disk, or the page as-is when the path is new.
 //

ingestion/internal/pipeline/pipeline_test.go

@@ -233,3 +233,63 @@ func TestRunRaw_ReIngestingUnchangedContentIsByteIdentical(t *testing.T) {
 	assert.Equal(t, string(first), string(second),
 		"re-ingesting unchanged content must leave the page byte-identical")
 }
+
+// --- #105: source drift — an unchanged re-ingest must not re-extract --------
+
+func TestRun_SkipsExtractionWhenTheSourceIsUnchanged(t *testing.T) {
+	// #103 made a re-ingest harmless (byte-identical merge). It is still not
+	// free: the full LLM extraction runs over every chunk to produce a result
+	// that merges to nothing. This is the cost half.
+	dir := t.TempDir()
+	var calls int
+	cfg := Config{Complete: func(_ context.Context, _, _ string) (string, error) {
+		calls++
+		return `[{"title":"Shape Up","type":"source","subtype":"book","domain":"product","content":"## Summary\n\nA book.\n"}]`, nil
+	}}
+
+	content := "---\nsource: https://example.com/shape-up\n---\n\nThe body of the article.\n"
+
+	first, err := Run(context.Background(), cfg, dir, content, "shape-up", false)
+	require.NoError(t, err)
+	require.Equal(t, 1, calls, "first ingest must extract")
+	assert.False(t, first.Skipped)
+
+	second, err := Run(context.Background(), cfg, dir, content, "shape-up", false)
+	require.NoError(t, err)
+	assert.Equal(t, 1, calls, "unchanged content must not be extracted again")
+	assert.True(t, second.Skipped, "the skip must be reported, not silent")
+}
+
+func TestRun_ReExtractsWhenTheSourceBodyChanged(t *testing.T) {
+	dir := t.TempDir()
+	var calls int
+	cfg := Config{Complete: func(_ context.Context, _, _ string) (string, error) {
+		calls++
+		return `[{"title":"Shape Up","type":"source","subtype":"book","domain":"product","content":"## Summary\n\nA book.\n"}]`, nil
+	}}
+
+	_, err := Run(context.Background(), cfg, dir, "---\nsource: x\n---\n\nversion one\n", "shape-up", false)
+	require.NoError(t, err)
+	_, err = Run(context.Background(), cfg, dir, "---\nsource: x\n---\n\nversion two — the source was edited\n", "shape-up", false)
+	require.NoError(t, err)
+
+	assert.Equal(t, 2, calls, "changed content must be re-extracted")
+}
+
+func TestRun_FrontmatterOnlyChangeIsNotDrift(t *testing.T) {
+	// The hash covers the body, so re-fetching a page whose metadata moved
+	// (a re-crawl stamping a new date) is not treated as the source changing.
+	dir := t.TempDir()
+	var calls int
+	cfg := Config{Complete: func(_ context.Context, _, _ string) (string, error) {
+		calls++
+		return `[{"title":"Shape Up","type":"source","subtype":"book","domain":"product","content":"## Summary\n\nA book.\n"}]`, nil
+	}}
+
+	_, err := Run(context.Background(), cfg, dir, "---\nsource: x\nfetched: monday\n---\n\nsame body\n", "shape-up", false)
+	require.NoError(t, err)
+	_, err = Run(context.Background(), cfg, dir, "---\nsource: x\nfetched: tuesday\n---\n\nsame body\n", "shape-up", false)
+	require.NoError(t, err)
+
+	assert.Equal(t, 1, calls, "only the body counts as the source")
+}

ingestion/internal/wiki/merge.go

@@ -3,6 +3,7 @@ package wiki
 
 import (
 	"fmt"
+	"sort"
 	"strings"
 )
 
@@ -38,7 +39,7 @@ type section struct {
 // not present in a are appended.
 func Merge(a, b Page) Page {
 	fmA, preambleA, secsA := parseSections(a.Content)
-	_, _, secsB := parseSections(b.Content)
+	fmB, _, secsB := parseSections(b.Content)
 
 	idx := make(map[string]int, len(secsA))
 	for i, s := range secsA {
@@ -61,7 +62,151 @@ func Merge(a, b Page) Page {
 		}
 	}
 
-	return Page{Path: a.Path, Content: rebuildContent(fmA, preambleA, secsA)}
+	return Page{Path: a.Path, Content: rebuildContent(refreshOwned(fmA, fmB), preambleA, secsA)}
+}
+
+// generatorOwned names the frontmatter fields the ingest pipeline may refresh
+// on a page it is revising. Everything else on disk wins.
+//
+// #103 made the on-disk frontmatter win wholesale, which is what stops a
+// regenerating writer from overwriting human-set metadata — a title someone
+// fixed, or the claim-property envelope (brain#21). The cost was that fields
+// the generator legitimately owns froze at their first-ingest values: when it
+// last ran, and what it last saw.
+//
+// An explicit allowlist rather than a carve-out: the ownership boundary is
+// nameable, and a field nobody has thought about stays human-owned by default,
+// which is the safe direction.
+var generatorOwned = map[string]bool{
+	"last_updated": true,
+	"source_hash":  true,
+}
+
+// fmLine is one line of a frontmatter block: a parsed key/value pair, or a
+// raw line (blank, comment, or anything else that isn't a simple "key:
+// value") kept verbatim. Same shape as api.frontmatter's fmLine — this
+// package doesn't import that one (it's unexported there, and a's/b's
+// frontmatter here always arrives as a string, not a parsed struct), so the
+// small, already-proven set()-appends-if-absent behavior is reproduced
+// locally rather than string-index surgery reinvented per call site.
+type fmLine struct {
+	key, value, raw string
+}
+
+// parseFrontmatterBlock parses a "---\n...\n---\n" fenced block (the shape
+// parseSections produces) into an ordered line list. A block with no
+// opening/closing fence — including the empty string, a page with no
+// frontmatter at all — returns nil, ok=false: there is nothing to update in
+// place, only something to potentially create.
+func parseFrontmatterBlock(block string) (lines []fmLine, ok bool) {
+	if !strings.HasPrefix(block, "---\n") {
+		return nil, false
+	}
+	rest := block[len("---\n"):]
+	end := strings.Index(rest, "\n---\n")
+	if end < 0 {
+		return nil, false
+	}
+	for _, line := range strings.Split(rest[:end], "\n") {
+		// An indented line is a continuation (a YAML block-list item, a
+		// wrapped value) never a top-level key, regardless of whether it
+		// happens to contain a colon — "  - 'Chapter 3: The Reckoning'"
+		// is not a key named "- 'Chapter 3". Checked before Cut so a
+		// colon inside one never reaches the key/value path at all.
+		if line != "" && (line[0] == ' ' || line[0] == '\t') {
+			lines = append(lines, fmLine{raw: line})
+			continue
+		}
+		key, val, found := strings.Cut(line, ":")
+		key = strings.TrimSpace(key)
+		if !found || key == "" || strings.HasPrefix(strings.TrimSpace(line), "#") {
+			lines = append(lines, fmLine{raw: line})
+			continue
+		}
+		lines = append(lines, fmLine{key: key, value: strings.TrimSpace(val)})
+	}
+	return lines, true
+}
+
+// setLine updates key's value in place if lines already has it, or appends
+// a new entry if it doesn't — the one behavior the original refreshOwned
+// got wrong (PR #126 review, round 2: it only ever updated in place).
+func setLine(lines []fmLine, key, value string) []fmLine {
+	for i := range lines {
+		if lines[i].key == key {
+			lines[i].value = value
+			return lines
+		}
+	}
+	return append(lines, fmLine{key: key, value: value})
+}
+
+func renderFrontmatterBlock(lines []fmLine) string {
+	if len(lines) == 0 {
+		return ""
+	}
+	var sb strings.Builder
+	sb.WriteString("---\n")
+	for _, l := range lines {
+		switch {
+		case l.key == "":
+			sb.WriteString(l.raw)
+		case l.value == "":
+			// A key with nothing after the colon (the YAML block-list shape:
+			// "aliases:" followed by indented "- item" lines on their own
+			// raw lines) must stay bare — "key: " with a trailing space
+			// is a different, if invisible, byte sequence, and this file's
+			// whole purpose is byte-stability across an unrelated merge.
+			sb.WriteString(l.key)
+			sb.WriteByte(':')
+		default:
+			sb.WriteString(l.key)
+			sb.WriteString(": ")
+			sb.WriteString(l.value)
+		}
+		sb.WriteByte('\n')
+	}
+	sb.WriteString("---\n")
+	return sb.String()
+}
+
+// refreshOwned returns a's frontmatter with the generator-owned fields taken
+// from b where b supplies them. Fields absent from b keep a's value, so a
+// generator that stops emitting a field cannot blank it.
+//
+// A field b supplies that a doesn't have yet — every page ingested before
+// this mechanism existed has no source_hash line at all — is appended, not
+// dropped (round 1 of review: dropping it silently meant source_hash never
+// populated for the pre-existing corpus). If a has no frontmatter fence at
+// all, one is created to hold the new fields rather than splicing raw
+// "key: value" text into the body (round 2: that corrupted the page and the
+// fields would duplicate on every subsequent merge, since unfenced text
+// isn't recognized as frontmatter by parseSections on the next pass).
+func refreshOwned(a, b string) string {
+	bLines, _ := parseFrontmatterBlock(b)
+	bVals := make(map[string]string)
+	for _, l := range bLines {
+		if l.key != "" && generatorOwned[l.key] {
+			bVals[l.key] = l.value
+		}
+	}
+	if len(bVals) == 0 {
+		return a
+	}
+
+	aLines, _ := parseFrontmatterBlock(a) // ok==false (no fence) -> aLines nil, same as "start fresh"
+
+	// Sorted for a deterministic, byte-stable result when more than one
+	// field is appended in the same call — map iteration order isn't.
+	keys := make([]string, 0, len(bVals))
+	for k := range bVals {
+		keys = append(keys, k)
+	}
+	sort.Strings(keys)
+	for _, k := range keys {
+		aLines = setLine(aLines, k, bVals[k])
+	}
+	return renderFrontmatterBlock(aLines)
 }
 
 // parseSections splits markdown into its frontmatter, its preamble (content

ingestion/internal/wiki/merge_test.go

@@ -174,3 +174,161 @@ title: X
 	assert.Contains(t, got, "Does this converge?", "existing question must survive")
 	assert.Contains(t, got, "What happens under load?", "new question must be added")
 }
+
+func TestMerge_GeneratorOwnedFrontmatterFieldsAreRefreshed(t *testing.T) {
+	// #103 made on-disk frontmatter win wholesale, which is what protects
+	// human-set fields from a regenerating writer. The cost was that fields the
+	// generator legitimately owns — when it last ran, what it last saw — froze
+	// at their first-ingest values. An explicit owned-set is the boundary:
+	// named fields the generator may refresh, everything else human-owned.
+	existing := Page{Path: "wiki/sources/x.md", Content: `---
+title: 'X'
+last_updated: 2026-01-01
+source_hash: aaaa
+half_life: durable
+claim_provenance: asserted
+---
+
+## Summary
+
+Original.
+`}
+	fresh := Page{Path: "wiki/sources/x.md", Content: `---
+title: 'Renamed by the model'
+last_updated: 2026-08-22
+source_hash: bbbb
+---
+
+## Summary
+
+Rewritten by the model.
+`}
+
+	got := Merge(existing, fresh).Content
+
+	assert.Contains(t, got, "last_updated: 2026-08-22", "generator owns last_updated")
+	assert.Contains(t, got, "source_hash: bbbb", "generator owns source_hash")
+	assert.Contains(t, got, "title: 'X'", "a human-set title must survive regeneration")
+	assert.Contains(t, got, "half_life: durable", "the claim envelope must survive regeneration")
+	assert.Contains(t, got, "claim_provenance: asserted")
+	assert.Contains(t, got, "Original.", "an existing section still wins over the model's rewrite")
+	assert.NotContains(t, got, "Renamed by the model")
+}
+
+func TestMerge_GeneratorOwnedFieldsAreAppendedWhenAPageNeverHadThemBefore(t *testing.T) {
+	// Found in review of PR #126: refreshOwned only replaced a generator-owned
+	// line that already existed in a's frontmatter — it never appended one a
+	// didn't have. Every page ingested before this feature shipped has no
+	// source_hash line at all, so on its first re-ingest after deploy, the
+	// fresh hash was silently dropped and the skip-on-unchanged feature this
+	// PR exists to build would never engage for the entire pre-existing
+	// corpus, permanently, with nothing telling anyone.
+	existing := Page{Path: "wiki/sources/x.md", Content: `---
+title: 'X'
+---
+
+## Summary
+
+Original.
+`}
+	fresh := Page{Path: "wiki/sources/x.md", Content: `---
+title: 'Renamed by the model'
+last_updated: 2026-08-22
+source_hash: bbbb
+---
+
+## Summary
+
+Rewritten by the model.
+`}
+
+	got := Merge(existing, fresh).Content
+
+	// Exact frontmatter block, not Contains: the second review round found
+	// that a substring check doesn't prove the fields landed inside a valid
+	// fence, in the right order, or that the fence itself wasn't corrupted —
+	// two independent mutations (closeIdx targeting the wrong fence, reversed
+	// sort) both survived a Contains-only version of this test.
+	want := "---\ntitle: 'X'\nlast_updated: 2026-08-22\nsource_hash: bbbb\n---\n\n## Summary\n\nOriginal.\n"
+	assert.Equal(t, want, got)
+}
+
+func TestMerge_GeneratorOwnedFieldsCreateAFrontmatterBlockWhenThePageHadNoneAtAll(t *testing.T) {
+	// Second review round on PR #126: when a has no frontmatter fence at all,
+	// the append fallback spliced raw, unfenced "key: value" lines straight
+	// into the body -- worse than the original bug, because the next
+	// parseSections call wouldn't recognize them as frontmatter (they don't
+	// start with `---`), so they'd be absorbed as ordinary preamble text and
+	// re-duplicate on every subsequent merge instead of updating in place.
+	existing := Page{Path: "wiki/sources/x.md", Content: "## Summary\n\nOriginal.\n"}
+	fresh := Page{Path: "wiki/sources/x.md", Content: `---
+last_updated: 2026-08-22
+source_hash: bbbb
+---
+
+## Summary
+
+Rewritten by the model.
+`}
+
+	got := Merge(existing, fresh).Content
+
+	want := "---\nlast_updated: 2026-08-22\nsource_hash: bbbb\n---\n\n## Summary\n\nOriginal.\n"
+	assert.Equal(t, want, got)
+}
+
+func TestMerge_GeneratorOwnedFieldsMixedReplaceAndAppend(t *testing.T) {
+	// a already has last_updated (replace in place) but not source_hash
+	// (append) -- the two code paths in the same call, together.
+	existing := Page{Path: "wiki/sources/x.md", Content: `---
+title: 'X'
+last_updated: 2026-01-01
+---
+
+## Summary
+
+Original.
+`}
+	fresh := Page{Path: "wiki/sources/x.md", Content: `---
+last_updated: 2026-08-22
+source_hash: bbbb
+---
+
+## Summary
+
+Rewritten by the model.
+`}
+
+	got := Merge(existing, fresh).Content
+
+	want := "---\ntitle: 'X'\nlast_updated: 2026-08-22\nsource_hash: bbbb\n---\n\n## Summary\n\nOriginal.\n"
+	assert.Equal(t, want, got)
+}
+
+func TestRefreshOwned_CommentLinesSurviveUnmangled(t *testing.T) {
+	// Third review round on PR #126: parseFrontmatterBlock dropped the
+	// sibling api package's comment guard (strings.HasPrefix(trimmed, "#")).
+	// Without it, a comment line containing a colon gets cut at the colon
+	// and re-rendered with collapsed whitespace instead of surviving
+	// verbatim.
+	a := "---\n#see also:   https://x/y\ntitle: 'X'\n---\n"
+	b := "---\nsource_hash: bbbb\n---\n"
+
+	got := refreshOwned(a, b)
+	assert.Equal(t, "---\n#see also:   https://x/y\ntitle: 'X'\nsource_hash: bbbb\n---\n", got)
+}
+
+func TestRefreshOwned_IndentedListItemsWithColonsAreNotMisparsedAsKeys(t *testing.T) {
+	// Same round: an indented YAML block-list item that happens to contain a
+	// colon (e.g. a title with a subtitle) is a continuation line, never a
+	// top-level key, regardless of what strings.Cut finds in it. Misparsing
+	// it as a key/value pair and re-rendering strips its indentation,
+	// de-indenting it out of the list it belongs to -- and refreshOwned
+	// re-renders this block on essentially every non-skipped ingest, so this
+	// is the normal path, not an edge case.
+	a := "---\naliases:\n  - 'Chapter 3: The Reckoning'\ntitle: 'X'\n---\n"
+	b := "---\nsource_hash: bbbb\n---\n"
+
+	got := refreshOwned(a, b)
+	assert.Equal(t, "---\naliases:\n  - 'Chapter 3: The Reckoning'\ntitle: 'X'\nsource_hash: bbbb\n---\n", got)
+}