feat(pipeline): replace ParsePages with ParseRawPages + RawPage type

Strips slug authority from the LLM. The new RawPage type carries only
{title, type, subtype, domain, content} — no paths or frontmatter.
Pipeline will derive slugs deterministically (Task 4).

pipeline.go gets a temporary bridge stub (TODO task4) to keep the
package compiling between tasks.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

ingestion/internal/pipeline/parse.go

@@ -5,13 +5,21 @@ import (
 	"encoding/json"
 	"fmt"
 	"strings"
-
-	"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
 )
 
-// ParsePages parses LLM output as a JSON array of {path, content} objects.
+// RawPage is the LLM's output format — minimal structured data with no path or frontmatter.
+// The pipeline derives slugs, paths, and frontmatter from these fields.
+type RawPage struct {
+	Title   string `json:"title"`
+	Type    string `json:"type"`    // "source" | "concept" | "entity"
+	Subtype string `json:"subtype"` // entity: person|company|tool|model|framework|technology; source: article|pdf|book|video|note|project
+	Domain  string `json:"domain"`
+	Content string `json:"content"` // Markdown body only — no frontmatter
+}
+
+// ParseRawPages parses LLM output as a JSON array of RawPage objects.
 // If the array is truncated mid-object (token limit), it salvages all complete objects.
-func ParsePages(output string) ([]wiki.Page, []string) {
+func ParseRawPages(output string) ([]RawPage, []string) {
 	output = strings.TrimSpace(output)
 	if output == "" {
 		return nil, []string{"LLM returned empty output"}
@@ -19,7 +27,7 @@ func ParsePages(output string) ([]wiki.Page, []string) {
 
 	output = stripFences(output)
 
-	var pages []wiki.Page
+	var pages []RawPage
 	if err := json.Unmarshal([]byte(output), &pages); err == nil {
 		return pages, nil
 	}

ingestion/internal/pipeline/parse_test.go

@@ -8,39 +8,54 @@ import (
 	"github.com/stretchr/testify/require"
 )
 
-func TestParsePages_ValidJSON(t *testing.T) {
-	input := `[{"path":"wiki/sources/foo.md","content":"# Foo"},{"path":"wiki/concepts/bar.md","content":"# Bar"}]`
-	pages, warnings := ParsePages(input)
+func TestParseRawPages_ValidJSON(t *testing.T) {
+	input := `[{"title":"Shape Up","type":"source","subtype":"book","domain":"product-strategy","content":"## Summary\n\nFoo."},{"title":"Betting","type":"concept","content":"## Definition\n\nA technique."}]`
+	pages, warnings := ParseRawPages(input)
 	require.Len(t, pages, 2)
 	assert.Empty(t, warnings)
-	assert.Equal(t, "wiki/sources/foo.md", pages[0].Path)
-	assert.Equal(t, "wiki/concepts/bar.md", pages[1].Path)
+	assert.Equal(t, "Shape Up", pages[0].Title)
+	assert.Equal(t, "source", pages[0].Type)
+	assert.Equal(t, "book", pages[0].Subtype)
+	assert.Equal(t, "product-strategy", pages[0].Domain)
+	assert.Equal(t, "Betting", pages[1].Title)
+	assert.Equal(t, "concept", pages[1].Type)
+	assert.Empty(t, pages[1].Subtype)
 }
 
-func TestParsePages_StripsFences(t *testing.T) {
-	input := "```json\n[{\"path\":\"wiki/sources/foo.md\",\"content\":\"# Foo\"}]\n```"
-	pages, warnings := ParsePages(input)
-	assert.Len(t, pages, 1)
-	assert.Empty(t, warnings)
-}
-
-func TestParsePages_TruncationRecovery(t *testing.T) {
-	input := `[{"path":"wiki/sources/foo.md","content":"# Foo"},{"path":"wiki/concepts/bar.md","content":"trunc`
-	pages, warnings := ParsePages(input)
+func TestParseRawPages_StripsFences(t *testing.T) {
+	input := "```json\n[{\"title\":\"Foo\",\"type\":\"concept\",\"content\":\"## Definition\\n\\nFoo.\"}]\n```"
+	pages, warnings := ParseRawPages(input)
 	require.Len(t, pages, 1)
-	assert.Equal(t, "wiki/sources/foo.md", pages[0].Path)
+	assert.Empty(t, warnings)
+	assert.Equal(t, "Foo", pages[0].Title)
+}
+
+func TestParseRawPages_TruncationRecovery(t *testing.T) {
+	input := `[{"title":"Foo","type":"concept","content":"## Definition\n\nFoo."},{"title":"Bar","type":"concept","content":"trunc`
+	pages, warnings := ParseRawPages(input)
+	require.Len(t, pages, 1)
+	assert.Equal(t, "Foo", pages[0].Title)
 	assert.NotEmpty(t, warnings)
 }
 
-func TestParsePages_EmptyInput(t *testing.T) {
-	pages, warnings := ParsePages("")
+func TestParseRawPages_EmptyInput(t *testing.T) {
+	pages, warnings := ParseRawPages("")
 	assert.Empty(t, pages)
 	assert.NotEmpty(t, warnings)
 }
 
-func TestParsePages_PlainFence(t *testing.T) {
-	input := "```\n[{\"path\":\"wiki/sources/foo.md\",\"content\":\"ok\"}]\n```"
-	pages, warnings := ParsePages(input)
-	assert.Len(t, pages, 1)
+func TestParseRawPages_PlainFence(t *testing.T) {
+	input := "```\n[{\"title\":\"Foo\",\"type\":\"concept\",\"content\":\"ok\"}]\n```"
+	pages, warnings := ParseRawPages(input)
+	require.Len(t, pages, 1)
 	assert.Empty(t, warnings)
 }
+
+func TestParseRawPages_MissingTitle(t *testing.T) {
+	// Missing title — still parsed, Title is empty string
+	input := `[{"type":"concept","content":"## Definition\n\nFoo."}]`
+	pages, warnings := ParseRawPages(input)
+	require.Len(t, pages, 1)
+	assert.Empty(t, warnings)
+	assert.Empty(t, pages[0].Title)
+}

ingestion/internal/pipeline/pipeline.go

@@ -52,8 +52,11 @@ func Run(ctx context.Context, cfg Config, brainDir, content, source string, dryR
 		if err != nil {
 			return Result{}, fmt.Errorf("LLM call: %w", err)
 		}
-		pages, warnings := ParsePages(output)
-		allPages = append(allPages, pages...)
+		// TODO(task4): replace with RawPage-based pipeline
+		rawPages, warnings := ParseRawPages(output)
+		for _, rp := range rawPages {
+			allPages = append(allPages, wiki.Page{Path: rp.Type + "/" + rp.Title, Content: rp.Content})
+		}
 		allWarnings = append(allWarnings, warnings...)
 	}