diff --git a/docs/superpowers/plans/2026-04-23-level3-slug-authority.md b/docs/superpowers/plans/2026-04-23-level3-slug-authority.md
new file mode 100644
index 0000000..088feac
--- /dev/null
+++ b/docs/superpowers/plans/2026-04-23-level3-slug-authority.md
@@ -0,0 +1,1323 @@
+# Level 3: Strip Slug Authority from LLM — Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Remove slug/path/frontmatter generation from the LLM; pipeline derives all slugs deterministically from titles via `wiki.Slug()`.
+
+**Architecture:** Add `RawPage` type + `ParseRawPages` (LLM returns minimal JSON), `BuildPages` (computes slugs/paths/frontmatter), and `CanonicalizeLinks` (converts `[[Display Name]]` → `[[slug|Display Name]]`). Wire into `pipeline.Run`. Update system prompt and schema doc.
+
+**Tech Stack:** Go 1.23, `encoding/json`, `regexp`, `strings`, `testify`
+
+**Working directory for all commands:** `ingestion/` (the Go module root — always `cd ingestion` before running `go` commands)
+
+---
+
+## File Map
+
+| File | Action | Responsibility |
+|------|--------|---------------|
+| `ingestion/internal/pipeline/parse.go` | Modify | Replace `ParsePages`+`wiki.Page` deserialization with `ParseRawPages`+`RawPage` type |
+| `ingestion/internal/pipeline/parse_test.go` | Modify | Replace old `ParsePages` tests with `ParseRawPages` tests |
+| `ingestion/internal/pipeline/build.go` | Create | `BuildPages` — computes slug, path, frontmatter from `RawPage` |
+| `ingestion/internal/pipeline/build_test.go` | Create | Tests for `BuildPages` |
+| `ingestion/internal/pipeline/links.go` | Create | `CanonicalizeLinks` — converts `[[Display Name]]` → `[[slug|Display Name]]` |
+| `ingestion/internal/pipeline/links_test.go` | Create | Tests for `CanonicalizeLinks` |
+| `ingestion/internal/pipeline/pipeline.go` | Modify | Wire `ParseRawPages → BuildPages → CanonicalizeLinks` into `Run`; update tests |
+| `ingestion/internal/pipeline/pipeline_test.go` | Modify | Update mock LLM responses to new JSON format |
+| `ingestion/internal/pipeline/prompt.go` | Modify | New system prompt + updated `BuildPrompt` for new JSON contract |
+| `brain/schema.md` | Modify | Update wikilink format and JSON output format |
+
+**Unchanged:** `resolve.go`, `refs.go`, `backfill.go`, `merge.go`, `chunk.go`, `resolve_test.go`, `refs_test.go`, `backfill_test.go`
+
+---
+
+## Task 1: `RawPage` type + `ParseRawPages`
+
+**Files:**
+- Modify: `ingestion/internal/pipeline/parse.go`
+- Modify: `ingestion/internal/pipeline/parse_test.go`
+
+- [ ] **Step 1: Write failing tests**
+
+Replace the entire content of `ingestion/internal/pipeline/parse_test.go` with:
+
+```go
+// ingestion/internal/pipeline/parse_test.go
+package pipeline
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+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, "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 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.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 TestParseRawPages_EmptyInput(t *testing.T) {
+	pages, warnings := ParseRawPages("")
+	assert.Empty(t, pages)
+	assert.NotEmpty(t, warnings)
+}
+
+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)
+}
+```
+
+- [ ] **Step 2: Run tests to verify they fail**
+
+```bash
+cd ingestion && go test ./internal/pipeline/ -run TestParseRawPages -v
+```
+
+Expected: FAIL — `ParseRawPages` undefined, `RawPage` undefined.
+
+- [ ] **Step 3: Replace `parse.go` with new implementation**
+
+Replace the entire content of `ingestion/internal/pipeline/parse.go` with:
+
+```go
+// ingestion/internal/pipeline/parse.go
+package pipeline
+
+import (
+	"encoding/json"
+	"fmt"
+	"strings"
+)
+
+// 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 ParseRawPages(output string) ([]RawPage, []string) {
+	output = strings.TrimSpace(output)
+	if output == "" {
+		return nil, []string{"LLM returned empty output"}
+	}
+
+	output = stripFences(output)
+
+	var pages []RawPage
+	if err := json.Unmarshal([]byte(output), &pages); err == nil {
+		return pages, nil
+	}
+
+	// Truncation recovery: find last `}` that closes a complete object.
+	idx := strings.LastIndex(output, "}")
+	if idx < 0 {
+		return nil, []string{"LLM output contained no complete JSON objects"}
+	}
+
+	start := strings.Index(output, "[")
+	if start < 0 {
+		return nil, []string{"LLM output contained no JSON array opening bracket"}
+	}
+
+	candidate := output[start:idx+1] + "]"
+	if err := json.Unmarshal([]byte(candidate), &pages); err != nil {
+		return nil, []string{fmt.Sprintf("truncation recovery failed: %v", err)}
+	}
+
+	return pages, []string{fmt.Sprintf("LLM output was truncated; recovered %d page(s)", len(pages))}
+}
+
+func stripFences(s string) string {
+	for _, prefix := range []string{"```json\n", "```json\r\n", "```\n", "```\r\n"} {
+		if strings.HasPrefix(s, prefix) {
+			s = strings.TrimPrefix(s, prefix)
+			s = strings.TrimSuffix(strings.TrimSpace(s), "```")
+			return strings.TrimSpace(s)
+		}
+	}
+	return s
+}
+```
+
+- [ ] **Step 4: Run tests to verify they pass**
+
+```bash
+cd ingestion && go test ./internal/pipeline/ -run TestParseRawPages -v
+```
+
+Expected: all 6 tests PASS.
+
+- [ ] **Step 5: Verify package still compiles (pipeline.go still references old ParsePages — that's expected for now)**
+
+```bash
+cd ingestion && go build ./...
+```
+
+Expected: compile error mentioning `ParsePages` undefined — that's fine, we'll fix it in Task 4. If the error is something else, investigate.
+
+Actually the old `ParsePages` no longer exists so `pipeline.go` will fail. That's OK — this task is intentionally breaking the pipeline step to set up for Task 4. If CI blocks on this, group Tasks 1–4 into a single commit.
+
+- [ ] **Step 6: Commit**
+
+```bash
+cd ingestion && git add internal/pipeline/parse.go internal/pipeline/parse_test.go
+git commit -m "feat(pipeline): replace ParsePages with ParseRawPages + RawPage type"
+```
+
+---
+
+## Task 2: `BuildPages`
+
+**Files:**
+- Create: `ingestion/internal/pipeline/build.go`
+- Create: `ingestion/internal/pipeline/build_test.go`
+
+- [ ] **Step 1: Write failing tests**
+
+Create `ingestion/internal/pipeline/build_test.go`:
+
+```go
+// ingestion/internal/pipeline/build_test.go
+package pipeline
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestBuildPages_SourcePage(t *testing.T) {
+	raw := []RawPage{
+		{
+			Title:   "Shape Up",
+			Type:    "source",
+			Subtype: "book",
+			Domain:  "product-strategy",
+			Content: "## Summary\n\nA book about shaping product work.\n",
+		},
+	}
+	pages := BuildPages(raw, "shape-up", "2026-04-23")
+	require.Len(t, pages, 1)
+
+	p := pages[0]
+	assert.Equal(t, "wiki/sources/shape-up.md", p.Path)
+	assert.Contains(t, p.Content, "title: Shape Up")
+	assert.Contains(t, p.Content, "type: book")
+	assert.Contains(t, p.Content, "domain: product-strategy")
+	assert.Contains(t, p.Content, "date_ingested: 2026-04-23")
+	assert.Contains(t, p.Content, "last_updated: 2026-04-23")
+	assert.Contains(t, p.Content, "aliases:\n  - Shape Up")
+	assert.Contains(t, p.Content, "## Summary")
+	assert.True(t, strings.HasPrefix(p.Content, "---\n"), "content must start with frontmatter")
+}
+
+func TestBuildPages_ConceptPage(t *testing.T) {
+	raw := []RawPage{
+		{
+			Title:   "Betting",
+			Type:    "concept",
+			Domain:  "product-strategy",
+			Content: "## Definition\n\nA resource allocation technique.\n",
+		},
+	}
+	pages := BuildPages(raw, "shape-up", "2026-04-23")
+	require.Len(t, pages, 1)
+
+	p := pages[0]
+	assert.Equal(t, "wiki/concepts/betting.md", p.Path)
+	assert.Contains(t, p.Content, "title: Betting")
+	assert.Contains(t, p.Content, "domain: product-strategy")
+	assert.Contains(t, p.Content, "last_updated: 2026-04-23")
+	assert.Contains(t, p.Content, "aliases:\n  - Betting")
+	assert.NotContains(t, p.Content, "date_ingested")
+	assert.Contains(t, p.Content, "## Definition")
+}
+
+func TestBuildPages_EntityPage(t *testing.T) {
+	raw := []RawPage{
+		{
+			Title:   "Ryan Singer",
+			Type:    "entity",
+			Subtype: "person",
+			Domain:  "product-strategy",
+			Content: "## Description\n\nA product designer.\n",
+		},
+	}
+	pages := BuildPages(raw, "shape-up", "2026-04-23")
+	require.Len(t, pages, 1)
+
+	p := pages[0]
+	assert.Equal(t, "wiki/entities/ryan-singer.md", p.Path)
+	assert.Contains(t, p.Content, "title: Ryan Singer")
+	assert.Contains(t, p.Content, "type: person")
+	assert.Contains(t, p.Content, "domain: product-strategy")
+	assert.Contains(t, p.Content, "last_updated: 2026-04-23")
+	assert.Contains(t, p.Content, "aliases:\n  - Ryan Singer")
+	assert.NotContains(t, p.Content, "date_ingested")
+}
+
+func TestBuildPages_SourceSlugUsedForSourcePage(t *testing.T) {
+	// LLM title differs from filename — pipeline uses sourceSlug for the source page path.
+	raw := []RawPage{
+		{Title: "FinBERT: A Pretrained Model", Type: "source", Subtype: "article", Content: "## Summary\n\nA model.\n"},
+	}
+	pages := BuildPages(raw, "finbert-huggingface", "2026-04-23")
+	require.Len(t, pages, 1)
+	assert.Equal(t, "wiki/sources/finbert-huggingface.md", pages[0].Path)
+	// Concept/entity slugs derived from title, not sourceSlug
+}
+
+func TestBuildPages_ConceptSlugDerivedFromTitle(t *testing.T) {
+	raw := []RawPage{
+		{Title: "Domain-Driven Design", Type: "concept", Content: "## Definition\n\nFoo.\n"},
+	}
+	pages := BuildPages(raw, "some-source", "2026-04-23")
+	require.Len(t, pages, 1)
+	assert.Equal(t, "wiki/concepts/domain-driven-design.md", pages[0].Path)
+}
+
+func TestBuildPages_SourceDefaultSubtype(t *testing.T) {
+	// If subtype is omitted for a source, default to "article"
+	raw := []RawPage{
+		{Title: "Some Post", Type: "source", Content: "## Summary\n\nA post.\n"},
+	}
+	pages := BuildPages(raw, "some-post", "2026-04-23")
+	require.Len(t, pages, 1)
+	assert.Contains(t, pages[0].Content, "type: article")
+}
+
+func TestBuildPages_OmitsDomainWhenEmpty(t *testing.T) {
+	raw := []RawPage{
+		{Title: "Betting", Type: "concept", Content: "## Definition\n\nFoo.\n"},
+	}
+	pages := BuildPages(raw, "src", "2026-04-23")
+	require.Len(t, pages, 1)
+	assert.NotContains(t, pages[0].Content, "domain:")
+}
+
+func TestBuildPages_MultiplePages(t *testing.T) {
+	raw := []RawPage{
+		{Title: "Shape Up", Type: "source", Subtype: "book", Content: "## Summary\n\nA book.\n"},
+		{Title: "Betting", Type: "concept", Content: "## Definition\n\nA technique.\n"},
+		{Title: "Ryan Singer", Type: "entity", Subtype: "person", Content: "## Description\n\nA designer.\n"},
+	}
+	pages := BuildPages(raw, "shape-up", "2026-04-23")
+	require.Len(t, pages, 3)
+	assert.Equal(t, "wiki/sources/shape-up.md", pages[0].Path)
+	assert.Equal(t, "wiki/concepts/betting.md", pages[1].Path)
+	assert.Equal(t, "wiki/entities/ryan-singer.md", pages[2].Path)
+}
+```
+
+- [ ] **Step 2: Run tests to verify they fail**
+
+```bash
+cd ingestion && go test ./internal/pipeline/ -run TestBuildPages -v
+```
+
+Expected: FAIL — `BuildPages` undefined.
+
+- [ ] **Step 3: Create `build.go`**
+
+Create `ingestion/internal/pipeline/build.go`:
+
+```go
+// ingestion/internal/pipeline/build.go
+package pipeline
+
+import (
+	"fmt"
+	"strings"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
+)
+
+// BuildPages converts RawPages from the LLM into wiki.Pages with computed slugs,
+// paths, and YAML frontmatter. sourceSlug is the slug of the source being ingested
+// (derived from the filename, not the LLM title).
+func BuildPages(rawPages []RawPage, sourceSlug, date string) []wiki.Page {
+	out := make([]wiki.Page, 0, len(rawPages))
+	for _, rp := range rawPages {
+		out = append(out, buildPage(rp, sourceSlug, date))
+	}
+	return out
+}
+
+func buildPage(rp RawPage, sourceSlug, date string) wiki.Page {
+	var slug, dir string
+	switch rp.Type {
+	case "source":
+		slug = sourceSlug
+		dir = "wiki/sources"
+	case "concept":
+		slug = wiki.Slug(rp.Title)
+		dir = "wiki/concepts"
+	case "entity":
+		slug = wiki.Slug(rp.Title)
+		dir = "wiki/entities"
+	default:
+		slug = wiki.Slug(rp.Title)
+		dir = "wiki/" + rp.Type
+	}
+
+	path := dir + "/" + slug + ".md"
+	fm := buildFrontmatter(rp, date)
+
+	return wiki.Page{
+		Path:    path,
+		Content: fm + "\n" + rp.Content,
+	}
+}
+
+func buildFrontmatter(rp RawPage, date string) string {
+	var sb strings.Builder
+	sb.WriteString("---\n")
+	fmt.Fprintf(&sb, "title: %s\n", rp.Title)
+
+	switch rp.Type {
+	case "source":
+		subtype := rp.Subtype
+		if subtype == "" {
+			subtype = "article"
+		}
+		fmt.Fprintf(&sb, "type: %s\n", subtype)
+		if rp.Domain != "" {
+			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+		}
+		fmt.Fprintf(&sb, "date_ingested: %s\n", date)
+		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+	case "concept":
+		if rp.Domain != "" {
+			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+		}
+		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+	case "entity":
+		if rp.Subtype != "" {
+			fmt.Fprintf(&sb, "type: %s\n", rp.Subtype)
+		}
+		if rp.Domain != "" {
+			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+		}
+		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+	default:
+		if rp.Domain != "" {
+			fmt.Fprintf(&sb, "domain: %s\n", rp.Domain)
+		}
+		fmt.Fprintf(&sb, "last_updated: %s\n", date)
+	}
+
+	fmt.Fprintf(&sb, "aliases:\n  - %s\n", rp.Title)
+	sb.WriteString("---\n")
+	return sb.String()
+}
+```
+
+- [ ] **Step 4: Run tests to verify they pass**
+
+```bash
+cd ingestion && go test ./internal/pipeline/ -run TestBuildPages -v
+```
+
+Expected: all 8 tests PASS.
+
+- [ ] **Step 5: Commit**
+
+```bash
+git add ingestion/internal/pipeline/build.go ingestion/internal/pipeline/build_test.go
+git commit -m "feat(pipeline): add BuildPages — compute slugs/paths/frontmatter from RawPage"
+```
+
+---
+
+## Task 3: `CanonicalizeLinks`
+
+**Files:**
+- Create: `ingestion/internal/pipeline/links.go`
+- Create: `ingestion/internal/pipeline/links_test.go`
+
+- [ ] **Step 1: Write failing tests**
+
+Create `ingestion/internal/pipeline/links_test.go`:
+
+```go
+// ingestion/internal/pipeline/links_test.go
+package pipeline
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
+)
+
+func TestCanonicalizeLinks_KnownTitle(t *testing.T) {
+	pages := []wiki.Page{
+		{
+			Path:    "wiki/sources/shape-up.md",
+			Content: "---\ntitle: Shape Up\n---\n\n## Summary\n\nSee [[Betting]].\n",
+		},
+	}
+	inventory := map[wiki.PageType][]wiki.Entry{
+		wiki.PageTypeConcept: {
+			{Slug: "betting", Title: "Betting"},
+		},
+	}
+	got, warnings := CanonicalizeLinks(pages, inventory)
+	require.Len(t, got, 1)
+	assert.Empty(t, warnings)
+	assert.Contains(t, got[0].Content, "[[betting|Betting]]")
+	assert.NotContains(t, got[0].Content, "[[Betting]]")
+}
+
+func TestCanonicalizeLinks_UnknownTitleLeftAsIs(t *testing.T) {
+	pages := []wiki.Page{
+		{
+			Path:    "wiki/sources/shape-up.md",
+			Content: "---\ntitle: Shape Up\n---\n\n## Summary\n\nSee [[Ghost Concept]].\n",
+		},
+	}
+	inventory := map[wiki.PageType][]wiki.Entry{}
+	got, warnings := CanonicalizeLinks(pages, inventory)
+	require.Len(t, got, 1)
+	assert.NotEmpty(t, warnings)
+	assert.Contains(t, got[0].Content, "[[Ghost Concept]]")
+}
+
+func TestCanonicalizeLinks_AlreadyCanonicalLinkUntouched(t *testing.T) {
+	// Links already in [[slug|Display]] format must not be double-converted
+	pages := []wiki.Page{
+		{
+			Path:    "wiki/sources/shape-up.md",
+			Content: "---\ntitle: Shape Up\n---\n\n## Summary\n\nSee [[betting|Betting]].\n",
+		},
+	}
+	inventory := map[wiki.PageType][]wiki.Entry{
+		wiki.PageTypeConcept: {
+			{Slug: "betting", Title: "Betting"},
+		},
+	}
+	got, warnings := CanonicalizeLinks(pages, inventory)
+	require.Len(t, got, 1)
+	assert.Empty(t, warnings)
+	// Should remain exactly as-is — not double-wrapped
+	assert.Contains(t, got[0].Content, "[[betting|Betting]]")
+	assert.NotContains(t, got[0].Content, "[[betting|[[betting|Betting]]]]")
+}
+
+func TestCanonicalizeLinks_CaseInsensitiveMatch(t *testing.T) {
+	pages := []wiki.Page{
+		{
+			Path:    "wiki/sources/foo.md",
+			Content: "---\ntitle: Foo\n---\n\n## Summary\n\nSee [[domain driven design]].\n",
+		},
+	}
+	inventory := map[wiki.PageType][]wiki.Entry{
+		wiki.PageTypeConcept: {
+			{Slug: "domain-driven-design", Title: "Domain Driven Design"},
+		},
+	}
+	got, warnings := CanonicalizeLinks(pages, inventory)
+	require.Len(t, got, 1)
+	assert.Empty(t, warnings)
+	assert.Contains(t, got[0].Content, "[[domain-driven-design|domain driven design]]")
+}
+
+func TestCanonicalizeLinks_CurrentBatchPagesResolved(t *testing.T) {
+	// A concept created in the same batch should be canonicalizable
+	pages := []wiki.Page{
+		{
+			Path:    "wiki/sources/shape-up.md",
+			Content: "---\ntitle: Shape Up\n---\n\n## Summary\n\nSee [[Betting]].\n",
+		},
+		{
+			Path:    "wiki/concepts/betting.md",
+			Content: "---\ntitle: Betting\n---\n\n## Definition\n\nA technique.\n",
+		},
+	}
+	inventory := map[wiki.PageType][]wiki.Entry{} // empty — Betting is in the batch, not inventory
+
+	got, warnings := CanonicalizeLinks(pages, inventory)
+	require.Len(t, got, 2)
+	assert.Empty(t, warnings)
+	assert.Contains(t, got[0].Content, "[[betting|Betting]]")
+}
+
+func TestCanonicalizeLinks_MultipleLinksInOnePage(t *testing.T) {
+	pages := []wiki.Page{
+		{
+			Path:    "wiki/sources/foo.md",
+			Content: "---\ntitle: Foo\n---\n\n## Summary\n\nSee [[Betting]] and [[Shape Up]].\n",
+		},
+	}
+	inventory := map[wiki.PageType][]wiki.Entry{
+		wiki.PageTypeConcept: {
+			{Slug: "betting", Title: "Betting"},
+		},
+		wiki.PageTypeSource: {
+			{Slug: "shape-up", Title: "Shape Up"},
+		},
+	}
+	got, warnings := CanonicalizeLinks(pages, inventory)
+	require.Len(t, got, 1)
+	assert.Empty(t, warnings)
+	assert.Contains(t, got[0].Content, "[[betting|Betting]]")
+	assert.Contains(t, got[0].Content, "[[shape-up|Shape Up]]")
+}
+```
+
+- [ ] **Step 2: Run tests to verify they fail**
+
+```bash
+cd ingestion && go test ./internal/pipeline/ -run TestCanonicalizeLinks -v
+```
+
+Expected: FAIL — `CanonicalizeLinks` undefined.
+
+- [ ] **Step 3: Create `links.go`**
+
+Create `ingestion/internal/pipeline/links.go`:
+
+```go
+// ingestion/internal/pipeline/links.go
+package pipeline
+
+import (
+	"fmt"
+	"path/filepath"
+	"regexp"
+	"strings"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
+)
+
+// plainLinkRE matches [[Display Name]] — wikilinks without a slug pipe.
+// It does NOT match [[slug|Display]] (those already have a pipe).
+var plainLinkRE = regexp.MustCompile(`\[\[([^\]|]+)\]\]`)
+
+// CanonicalizeLinks converts [[Display Name]] wikilinks to [[slug|Display Name]]
+// using a title→slug map built from the inventory and current batch.
+// Unknown titles are left as-is and returned as warnings.
+func CanonicalizeLinks(pages []wiki.Page, inventory map[wiki.PageType][]wiki.Entry) ([]wiki.Page, []string) {
+	titleToSlug := buildTitleMap(pages, inventory)
+
+	var allWarnings []string
+	out := make([]wiki.Page, len(pages))
+	for i, p := range pages {
+		newContent, warnings := canonicalizeContent(p.Content, titleToSlug)
+		p.Content = newContent
+		out[i] = p
+		allWarnings = append(allWarnings, warnings...)
+	}
+	return out, allWarnings
+}
+
+// buildTitleMap builds a lowercase-title → slug map from inventory and current batch.
+// Current batch entries take precedence over inventory (they may be updates).
+func buildTitleMap(pages []wiki.Page, inventory map[wiki.PageType][]wiki.Entry) map[string]string {
+	m := make(map[string]string)
+	for _, entries := range inventory {
+		for _, e := range entries {
+			m[strings.ToLower(e.Title)] = e.Slug
+		}
+	}
+	// Current batch overrides inventory
+	for _, p := range pages {
+		title := extractTitle(p.Content)
+		slug := strings.TrimSuffix(filepath.Base(p.Path), ".md")
+		if title != "" && slug != "" {
+			m[strings.ToLower(title)] = slug
+		}
+	}
+	return m
+}
+
+func canonicalizeContent(content string, titleToSlug map[string]string) (string, []string) {
+	var warnings []string
+	result := plainLinkRE.ReplaceAllStringFunc(content, func(match string) string {
+		sub := plainLinkRE.FindStringSubmatch(match)
+		if len(sub) < 2 {
+			return match
+		}
+		displayName := sub[1]
+		slug, ok := titleToSlug[strings.ToLower(displayName)]
+		if !ok {
+			warnings = append(warnings, fmt.Sprintf("unknown wikilink: [[%s]]", displayName))
+			return match
+		}
+		return "[[" + slug + "|" + displayName + "]]"
+	})
+	return result, warnings
+}
+```
+
+- [ ] **Step 4: Run tests to verify they pass**
+
+```bash
+cd ingestion && go test ./internal/pipeline/ -run TestCanonicalizeLinks -v
+```
+
+Expected: all 6 tests PASS.
+
+- [ ] **Step 5: Commit**
+
+```bash
+git add ingestion/internal/pipeline/links.go ingestion/internal/pipeline/links_test.go
+git commit -m "feat(pipeline): add CanonicalizeLinks — convert [[Display Name]] to [[slug|Display Name]]"
+```
+
+---
+
+## Task 4: Wire `pipeline.go` + update `pipeline_test.go`
+
+**Files:**
+- Modify: `ingestion/internal/pipeline/pipeline.go`
+- Modify: `ingestion/internal/pipeline/pipeline_test.go`
+
+- [ ] **Step 1: Update `pipeline_test.go` to use new LLM response format**
+
+Replace the entire content of `ingestion/internal/pipeline/pipeline_test.go` with:
+
+```go
+// ingestion/internal/pipeline/pipeline_test.go
+package pipeline
+
+import (
+	"context"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/llm"
+)
+
+func TestRun_WritesPages(t *testing.T) {
+	brainDir := t.TempDir()
+	for _, sub := range []string{"wiki/concepts", "wiki/entities", "wiki/sources"} {
+		require.NoError(t, os.MkdirAll(filepath.Join(brainDir, sub), 0o755))
+	}
+
+	llmResponse := mustJSON([]RawPage{
+		{
+			Title:   "Test Article",
+			Type:    "source",
+			Subtype: "article",
+			Domain:  "software-engineering",
+			Content: "## Summary\n\nA test article.\n\n## Key Claims\n\n- It tests things.\n\n## Concepts Introduced or Reinforced\n\n[[Testing]]\n\n## Entities Mentioned\n\n## Open Questions Raised\n",
+		},
+		{
+			Title:   "Testing",
+			Type:    "concept",
+			Domain:  "software-engineering",
+			Content: "## Definition\n\nThe practice of verifying software.\n\n## Why It Matters\n\nCatches bugs.\n\n## Related Concepts\n\n## Related Entities\n\n## Sources\n\n## Evolving Notes\n",
+		},
+	})
+
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		_ = json.NewEncoder(w).Encode(map[string]any{
+			"choices": []map[string]any{
+				{"message": map[string]any{"role": "assistant", "content": llmResponse}},
+			},
+		})
+	}))
+	defer srv.Close()
+
+	cfg := Config{
+		Complete:  llm.New(srv.URL, "", "test-model", 30*time.Second).Complete,
+		ChunkSize: 0,
+	}
+
+	result, err := Run(context.Background(), cfg, brainDir, "An article about testing.", "test-article", false)
+	require.NoError(t, err)
+	assert.Len(t, result.Pages, 2)
+
+	_, err = os.Stat(filepath.Join(brainDir, "wiki", "sources", "test-article.md"))
+	require.NoError(t, err)
+	_, err = os.Stat(filepath.Join(brainDir, "wiki", "concepts", "testing.md"))
+	require.NoError(t, err)
+	_, err = os.Stat(filepath.Join(brainDir, "wiki", "index.md"))
+	require.NoError(t, err)
+	_, err = os.Stat(filepath.Join(brainDir, "log.md"))
+	require.NoError(t, err)
+}
+
+func TestRun_DryRunDoesNotWrite(t *testing.T) {
+	brainDir := t.TempDir()
+	for _, sub := range []string{"wiki/concepts", "wiki/entities", "wiki/sources"} {
+		require.NoError(t, os.MkdirAll(filepath.Join(brainDir, sub), 0o755))
+	}
+
+	llmResponse := mustJSON([]RawPage{{
+		Title:   "Foo",
+		Type:    "source",
+		Subtype: "article",
+		Content: "## Summary\n\nFoo.\n",
+	}})
+
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		_ = json.NewEncoder(w).Encode(map[string]any{
+			"choices": []map[string]any{{"message": map[string]any{"content": llmResponse}}},
+		})
+	}))
+	defer srv.Close()
+
+	cfg := Config{Complete: llm.New(srv.URL, "", "m", 30*time.Second).Complete}
+	result, err := Run(context.Background(), cfg, brainDir, "foo content", "foo", true)
+	require.NoError(t, err)
+	assert.Len(t, result.Pages, 1)
+
+	_, err = os.Stat(filepath.Join(brainDir, "wiki", "sources", "foo.md"))
+	assert.True(t, os.IsNotExist(err))
+}
+
+func TestRun_MergesDuplicatePaths(t *testing.T) {
+	brainDir := t.TempDir()
+	for _, sub := range []string{"wiki/concepts", "wiki/entities", "wiki/sources"} {
+		require.NoError(t, os.MkdirAll(filepath.Join(brainDir, sub), 0o755))
+	}
+
+	// LLM returns same title twice (simulates multi-chunk duplicate)
+	llmResponse := mustJSON([]RawPage{
+		{Title: "Foo", Type: "concept", Content: "## Definition\n\nFirst.\n\n## Related Concepts\n\n[[Bar]]\n"},
+		{Title: "Foo", Type: "concept", Content: "## Definition\n\nSecond.\n\n## Related Concepts\n\n[[Baz]]\n"},
+	})
+
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		_ = json.NewEncoder(w).Encode(map[string]any{
+			"choices": []map[string]any{{"message": map[string]any{"content": llmResponse}}},
+		})
+	}))
+	defer srv.Close()
+
+	cfg := Config{Complete: llm.New(srv.URL, "", "m", 30*time.Second).Complete}
+	result, err := Run(context.Background(), cfg, brainDir, "content", "foo", false)
+	require.NoError(t, err)
+	assert.Len(t, result.Pages, 1) // deduplicated
+
+	content, err := os.ReadFile(filepath.Join(brainDir, "wiki", "concepts", "foo.md"))
+	require.NoError(t, err)
+	// keep-first for Definition, union for Related Concepts
+	assert.Contains(t, string(content), "First.")
+	// Bar and Baz unknown → left as plain [[links]]
+	assert.Contains(t, string(content), "[[Bar]]")
+	assert.Contains(t, string(content), "[[Baz]]")
+}
+
+func mustJSON(v any) string {
+	b, err := json.Marshal(v)
+	if err != nil {
+		panic(err)
+	}
+	return string(b)
+}
+```
+
+- [ ] **Step 2: Run tests to verify they fail (expected — pipeline.go still uses old ParsePages)**
+
+```bash
+cd ingestion && go test ./internal/pipeline/ -run TestRun -v
+```
+
+Expected: compile error or test failures — that's fine.
+
+- [ ] **Step 3: Update `pipeline.go` to wire new steps**
+
+Replace the entire content of `ingestion/internal/pipeline/pipeline.go` with:
+
+```go
+// ingestion/internal/pipeline/pipeline.go
+package pipeline
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"time"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
+)
+
+// CompleteFunc is the function signature for LLM calls.
+type CompleteFunc func(ctx context.Context, system, user string) (string, error)
+
+// Config holds pipeline configuration.
+type Config struct {
+	Complete  CompleteFunc
+	ChunkSize int    // 0 = no chunking
+	Schema    string // overrides brain/schema.md when set (useful in tests)
+}
+
+// Result is the outcome of a pipeline run.
+type Result struct {
+	Pages    []string // relative paths written (or would-be written in dry-run)
+	Warnings []string
+}
+
+// Run ingests content and writes structured wiki pages to brainDir/wiki/.
+// In dry-run mode, pages are returned but not written to disk.
+func Run(ctx context.Context, cfg Config, brainDir, content, source string, dryRun bool) (Result, error) {
+	inventory, err := wiki.LoadInventory(brainDir)
+	if err != nil {
+		return Result{}, fmt.Errorf("load inventory: %w", err)
+	}
+
+	schema := cfg.Schema
+	if schema == "" {
+		schema = loadSchema(brainDir)
+	}
+
+	sourceSlug := wiki.Slug(source)
+	date := time.Now().UTC().Format("2006-01-02")
+	chunks := Chunk(content, cfg.ChunkSize)
+
+	var allRaw []RawPage
+	var allWarnings []string
+
+	for _, chunk := range chunks {
+		userPrompt := BuildPrompt(schema, source, chunk, inventory)
+		output, err := cfg.Complete(ctx, systemPrompt, userPrompt)
+		if err != nil {
+			return Result{}, fmt.Errorf("LLM call: %w", err)
+		}
+		raw, warnings := ParseRawPages(output)
+		allRaw = append(allRaw, raw...)
+		allWarnings = append(allWarnings, warnings...)
+	}
+
+	pages := BuildPages(allRaw, sourceSlug, date)
+	resolved := Resolve(pages, inventory)
+	canonicalized, linkWarnings := CanonicalizeLinks(resolved, inventory)
+	allWarnings = append(allWarnings, linkWarnings...)
+	withRefs := injectSourceRefs(canonicalized, inventory, brainDir)
+	merged := mergeAll(withRefs)
+
+	var written []string
+	for _, page := range merged {
+		if !dryRun {
+			dest := filepath.Join(brainDir, filepath.FromSlash(page.Path))
+			if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
+				return Result{}, fmt.Errorf("mkdir for %s: %w", page.Path, err)
+			}
+			if err := os.WriteFile(dest, []byte(page.Content), 0o644); err != nil {
+				return Result{}, fmt.Errorf("write %s: %w", page.Path, err)
+			}
+		}
+		written = append(written, page.Path)
+	}
+
+	if !dryRun {
+		if err := wiki.RebuildIndex(brainDir, date); err != nil {
+			allWarnings = append(allWarnings, 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))
+		}
+	}
+
+	return Result{Pages: written, Warnings: allWarnings}, nil
+}
+
+// mergeAll deduplicates pages by path, merging content from later occurrences.
+func mergeAll(pages []wiki.Page) []wiki.Page {
+	order := make([]string, 0, len(pages))
+	byPath := make(map[string]wiki.Page, len(pages))
+	for _, p := range pages {
+		if _, seen := byPath[p.Path]; !seen {
+			order = append(order, p.Path)
+			byPath[p.Path] = p
+		} else {
+			byPath[p.Path] = wiki.Merge(byPath[p.Path], p)
+		}
+	}
+	result := make([]wiki.Page, 0, len(order))
+	for _, path := range order {
+		result = append(result, byPath[path])
+	}
+	return result
+}
+
+const defaultSchema = `# Brain Wiki Schema
+Three page types: wiki/sources/, wiki/concepts/, wiki/entities/.
+See brain/schema.md for the full schema.
+`
+
+func loadSchema(brainDir string) string {
+	b, err := os.ReadFile(filepath.Join(brainDir, "schema.md"))
+	if err != nil {
+		return defaultSchema
+	}
+	return strings.TrimSpace(string(b))
+}
+```
+
+- [ ] **Step 4: Run all pipeline tests**
+
+```bash
+cd ingestion && go test ./internal/pipeline/ -v
+```
+
+Expected: all tests PASS. If `TestRun_WritesPages` has a warning about unknown wikilink `[[Testing]]` in warnings (since the Testing concept is in the same batch and should be resolved via `CanonicalizeLinks`), check that `CanonicalizeLinks` builds the batch map correctly before checking `result.Warnings`.
+
+Note: `TestRun_WritesPages` now calls `assert.Len(t, result.Pages, 2)` without `assert.Empty(t, result.Warnings)` — unknown-link warnings from `CanonicalizeLinks` are acceptable since "Testing" is in the batch and should canonicalize cleanly. If the test fails with unexpected warnings, investigate `buildTitleMap` — it should find "Testing" from the current batch.
+
+- [ ] **Step 5: Run full test suite**
+
+```bash
+cd ingestion && go test ./... 2>&1
+```
+
+Expected: all packages pass.
+
+- [ ] **Step 6: Commit**
+
+```bash
+git add ingestion/internal/pipeline/pipeline.go ingestion/internal/pipeline/pipeline_test.go
+git commit -m "feat(pipeline): wire ParseRawPages+BuildPages+CanonicalizeLinks into Run"
+```
+
+---
+
+## Task 5: Update `prompt.go`
+
+**Files:**
+- Modify: `ingestion/internal/pipeline/prompt.go`
+
+- [ ] **Step 1: Replace `prompt.go`**
+
+Replace the entire content of `ingestion/internal/pipeline/prompt.go` with:
+
+```go
+// ingestion/internal/pipeline/prompt.go
+package pipeline
+
+import (
+	"fmt"
+	"strings"
+	"time"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
+)
+
+const systemPrompt = `You are a wiki agent. Read the source material and produce structured wiki pages following the schema provided.
+
+Output ONLY a valid JSON array — no markdown fences, no other text before or after.
+Each element must have exactly these fields:
+  "title"   — exact page title (e.g. "FinBERT", "Ryan Singer", "Shape Up")
+  "type"    — exactly one of: "source", "concept", "entity"
+  "subtype" — for source: article|pdf|book|video|note|project; for entity: person|company|tool|model|framework|technology; omit for concept
+  "domain"  — one of the domains in the schema (omit if none fits)
+  "content" — Markdown body only — NO frontmatter, NO path, NO slug
+
+Wikilinks in content: [[Display Name]] — just the display name, no slug, no pipe separator.
+Only link to pages listed in the inventory or pages you are creating in this response.`
+
+// BuildPrompt constructs the user prompt for a single chunk.
+func BuildPrompt(schema, source, content string, inventory map[wiki.PageType][]wiki.Entry) string {
+	var sb strings.Builder
+
+	fmt.Fprintf(&sb, "Today's date is %s.\n\n", time.Now().UTC().Format("2006-01-02"))
+
+	sb.WriteString("## Schema\n\n")
+	sb.WriteString(schema)
+	sb.WriteString("\n\n")
+
+	sb.WriteString("## Existing wiki pages\n\n")
+	sb.WriteString("Reference these pages by display name only — [[Display Name]] — in your content.\n\n")
+
+	for _, pt := range []wiki.PageType{wiki.PageTypeConcept, wiki.PageTypeEntity, wiki.PageTypeSource} {
+		entries := inventory[pt]
+		label := strings.ToUpper(string(pt)[:1]) + string(pt)[1:]
+		if len(entries) == 0 {
+			fmt.Fprintf(&sb, "%s — (none yet)\n\n", label)
+			continue
+		}
+		fmt.Fprintf(&sb, "%s:\n", label)
+		for _, e := range entries {
+			fmt.Fprintf(&sb, "  - %s\n", e.Title)
+		}
+		sb.WriteString("\n")
+	}
+
+	sb.WriteString("## Non-negotiable rules\n\n")
+	sb.WriteString("1. Output ONLY a valid JSON array — no prose, no fences.\n")
+	sb.WriteString("2. Fields: title, type, subtype (if applicable), domain (if applicable), content.\n")
+	sb.WriteString("3. Wikilinks: [[Display Name]] — no slug, no pipe. The pipeline handles slugs.\n")
+	sb.WriteString("4. Section links must match their section type (Related Concepts → concepts only, etc.).\n")
+	sb.WriteString("5. One source page per book — if inventory shows it exists, return it as an UPDATE.\n\n")
+
+	fmt.Fprintf(&sb, "## Source: %s\n\n", source)
+	sb.WriteString(content)
+
+	return sb.String()
+}
+```
+
+- [ ] **Step 2: Verify compile and tests still pass**
+
+```bash
+cd ingestion && go test ./... 2>&1
+```
+
+Expected: all tests PASS (prompt.go has no direct unit tests — covered via integration tests in pipeline_test.go).
+
+- [ ] **Step 3: Commit**
+
+```bash
+git add ingestion/internal/pipeline/prompt.go
+git commit -m "feat(pipeline): update system prompt for new LLM JSON contract (no slugs)"
+```
+
+---
+
+## Task 6: Update `brain/schema.md`
+
+**Files:**
+- Modify: `brain/schema.md`
+
+- [ ] **Step 1: Update the schema doc**
+
+Replace the entire content of `brain/schema.md` with:
+
+```markdown
+# Brain Wiki Schema
+
+This document defines the three page types in the brain wiki.
+The LLM must follow this schema exactly when generating wiki pages.
+
+## Output Format
+
+Return a JSON array. Each element:
+
+```json
+{
+  "title":   "exact page title",
+  "type":    "source | concept | entity",
+  "subtype": "see below — omit for concept",
+  "domain":  "see domains — omit if none fits",
+  "content": "Markdown body only — no frontmatter, no path"
+}
+```
+
+- `subtype` for **source**: `article | pdf | book | video | note | project`
+- `subtype` for **entity**: `person | company | tool | model | framework | technology`
+- The pipeline computes slugs and frontmatter — never include them in output.
+
+## Wikilink Format
+
+All cross-references use `[[Display Name]]` — just the display name, no slug, no pipe.
+
+Rules:
+- Only link to pages in the inventory or pages you are creating in this response
+- The pipeline converts `[[Display Name]]` to `[[slug|Display Name]]` automatically
+- Section links must match their section type (Related Concepts → concept pages only, etc.)
+
+Examples: `[[Domain Driven Design]]`, `[[Ryan Singer]]`, `[[Shape Up]]`
+
+## Domains
+
+Use one of: `ai-llm`, `software-engineering`, `product-strategy`, `finance-markets`,
+`personal`, `consulting`, `climate`, `infrastructure`, `security`
+
+---
+
+## Source Pages — wiki/sources/<slug>.md
+
+One page per ingested source. Books are NEVER split across multiple source pages — update the existing one.
+
+Body sections (in this order):
+
+### Summary
+2–3 sentences. Core argument or finding.
+
+### Key Claims
+Bulleted list. Paraphrase — no verbatim quotes or code.
+
+### Concepts Introduced or Reinforced
+Wikilinks to concept pages ONLY. One per line.
+
+### Entities Mentioned
+Wikilinks to entity pages ONLY. One per line.
+
+### Open Questions Raised
+Gaps or follow-up questions from this source.
+
+For books only, also add:
+
+### Chapters
+One bullet per chapter with 1–2 sentence summary.
+
+### Argument Arc
+Overall narrative as it becomes clear across chapters.
+
+### Updates
+Dated entries appended on re-ingestion. NEVER rewrite — only append.
+
+---
+
+## Concept Pages — wiki/concepts/<slug>.md
+
+One page per idea, framework, methodology, or pattern.
+
+Body sections (in this order):
+
+### Definition
+One-paragraph plain-language explanation.
+
+### Why It Matters
+Practical significance. Why should anyone care?
+
+### Related Concepts
+Wikilinks to concept pages ONLY.
+
+### Related Entities
+Wikilinks to entity pages ONLY.
+
+### Sources
+Wikilinks to source pages ONLY.
+
+### Evolving Notes
+Updated as new sources arrive. Append, do not rewrite.
+
+---
+
+## Entity Pages — wiki/entities/<slug>.md
+
+One page per person, tool, organisation, technology, or product.
+
+Body sections (in this order):
+
+### Description
+One-line description.
+
+### Relevance
+Why this entity matters to this knowledge base.
+
+### Key Positions, Products, or Claims
+With dates where known.
+
+### Related Concepts
+Wikilinks to concept pages ONLY.
+
+### Related Entities
+Wikilinks to entity pages ONLY.
+
+### Sources
+Wikilinks to source pages ONLY.
+
+---
+
+## Non-Negotiable Rules
+
+1. Output ONLY a valid JSON array — no markdown fences, no prose before or after
+2. Each element: `{"title": "...", "type": "...", "subtype": "...", "domain": "...", "content": "..."}`
+3. Never include slugs, paths, or frontmatter in output — the pipeline handles these
+4. Wikilinks: `[[Display Name]]` only — no pipe, no slug
+5. Dates always YYYY-MM-DD (used only in content body where contextually relevant)
+6. Never reproduce verbatim code — describe the pattern or technique
+7. Section links must match their section type
+8. One source page per book — if inventory shows it exists, include it as an UPDATE
+```
+
+- [ ] **Step 2: Verify Go tests still pass (schema.md is loaded at runtime, not compile time)**
+
+```bash
+cd ingestion && go test ./... 2>&1
+```
+
+Expected: all tests PASS.
+
+- [ ] **Step 3: Commit**
+
+```bash
+git add brain/schema.md
+git commit -m "docs(schema): update LLM output format and wikilink convention for Level 3"
+```
+
+---
+
+## Self-Review
+
+**Spec coverage check:**
+
+| Spec requirement | Task |
+|-----------------|------|
+| LLM returns `{title, type, subtype, domain, content}` | Task 1 (RawPage), Task 5 (prompt) |
+| Pipeline computes all slugs via `wiki.Slug(title)` | Task 2 (BuildPages) |
+| Source page uses `sourceSlug` from filename | Task 2 (buildPage: `case "source": slug = sourceSlug`) |
+| Frontmatter assembled by pipeline | Task 2 (buildFrontmatter) |
+| `[[Display Name]]` → `[[slug|Display Name]]` canonicalization | Task 3 (CanonicalizeLinks) |
+| CanonicalizeLinks runs after BuildPages, before injectSourceRefs | Task 4 (pipeline.go step order) |
+| Unknown titles left as-is + warnings | Task 3 (links_test: UnknownTitleLeftAsIs) |
+| Current-batch pages resolvable | Task 3 (buildTitleMap includes batch) |
+| `injectSourceRefs` unchanged | — (no task needed) |
+| `Resolve` unchanged | — (no task needed) |
+| `brain/schema.md` updated | Task 6 |
+| Integration test for no slug duplication across chunks | Task 4 (TestRun_MergesDuplicatePaths uses same title twice) |
+
+All spec requirements covered.
+
+**Placeholder scan:** None found.
+
+**Type consistency:**
+- `RawPage` defined in Task 1, used in Tasks 2, 4 ✓
+- `BuildPages([]RawPage, string, string) []wiki.Page` defined in Task 2, called in Task 4 ✓
+- `CanonicalizeLinks([]wiki.Page, map[wiki.PageType][]wiki.Entry) ([]wiki.Page, []string)` defined in Task 3, called in Task 4 ✓
+- `ParseRawPages(string) ([]RawPage, []string)` defined in Task 1, called in Task 4 ✓
+- `extractTitle` used in Task 3 (`links.go`) — defined in `resolve.go` (same package) ✓