feat(pipeline): add POST /ingest-raw for direct batch ingestion without LLM

Allows callers to provide pre-structured RawPage data directly, bypassing the
LLM extraction step. The pipeline still handles slug computation, frontmatter,
link canonicalization, source back-references, and dedup — only the extraction
is skipped. Useful when a more capable model or manual curation produces the
structured data.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

ingestion/internal/pipeline/pipeline.go

@@ -59,11 +59,31 @@ func Run(ctx context.Context, cfg Config, brainDir, content, source string, dryR
 		allWarnings = append(allWarnings, warnings...)
 	}
 
-	pages, buildWarnings := BuildPages(allRaw, sourceSlug, date)
-	allWarnings = append(allWarnings, buildWarnings...)
+	return buildAndWrite(allRaw, sourceSlug, date, brainDir, source, inventory, allWarnings, dryRun)
+}
+
+// RunRaw runs the pipeline on pre-parsed RawPages, skipping the LLM extraction
+// step. Use this when the caller has already produced the structured RawPage data
+// (e.g. from a more capable model or manual curation).
+func RunRaw(brainDir, source string, rawPages []RawPage, dryRun bool) (Result, error) {
+	inventory, err := wiki.LoadInventory(brainDir)
+	if err != nil {
+		return Result{}, fmt.Errorf("load inventory: %w", err)
+	}
+
+	sourceSlug := wiki.Slug(source)
+	date := time.Now().UTC().Format("2006-01-02")
+
+	return buildAndWrite(rawPages, sourceSlug, date, brainDir, source, inventory, nil, dryRun)
+}
+
+// buildAndWrite runs BuildPages through write for both Run and RunRaw.
+func buildAndWrite(rawPages []RawPage, sourceSlug, date, brainDir, source string, inventory map[wiki.PageType][]wiki.Entry, warnings []string, dryRun bool) (Result, error) {
+	pages, buildWarnings := BuildPages(rawPages, sourceSlug, date)
+	warnings = append(warnings, buildWarnings...)
 	resolved := Resolve(pages, inventory)
 	canonicalized, linkWarnings := CanonicalizeLinks(resolved, inventory)
-	allWarnings = append(allWarnings, linkWarnings...)
+	warnings = append(warnings, linkWarnings...)
 	withRefs := injectSourceRefs(canonicalized, inventory, brainDir)
 	merged := mergeAll(withRefs)
 
@@ -83,14 +103,14 @@ func Run(ctx context.Context, cfg Config, brainDir, content, source string, dryR
 
 	if !dryRun {
 		if err := wiki.RebuildIndex(brainDir, date); err != nil {
-			allWarnings = append(allWarnings, fmt.Sprintf("rebuild index: %v", err))
+			warnings = append(warnings, fmt.Sprintf("rebuild index: %v", err))
 		}
-		if err := wiki.AppendLog(brainDir, source, written, allWarnings, date); err != nil {
-			allWarnings = append(allWarnings, fmt.Sprintf("append log: %v", err))
+		if err := wiki.AppendLog(brainDir, source, written, warnings, date); err != nil {
+			warnings = append(warnings, fmt.Sprintf("append log: %v", err))
 		}
 	}
 
-	return Result{Pages: written, Warnings: allWarnings}, nil
+	return Result{Pages: written, Warnings: warnings}, nil
 }
 
 // mergeAll deduplicates pages by path, merging content from later occurrences.