feat(brain): audit-log every tools/call; server-owned write provenance (#147)

Closes #144 (audit line per tools/call) and #145 (origin/written_by stamped on every model-reachable write, surfaced in brain_query/brain_get).

Passed pr-gatekeeper after four rounds of adversarial review, verified by execution: #147

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Mathias <mthbqv@gmail.com>

ingestion/internal/pipeline/build.go

@@ -3,6 +3,7 @@ package pipeline
 
 import (
 	"fmt"
+	"regexp"
 	"strings"
 
 	"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
@@ -16,6 +17,12 @@ func BuildPages(rawPages []RawPage, sourceSlug, date string) ([]wiki.Page, []str
 	out := make([]wiki.Page, 0, len(rawPages))
 	var warnings []string
 	for _, rp := range rawPages {
+		// The type becomes a directory under wiki/; "../raw" wrote outside it
+		// (PR #147 review). Only a plain lower-case name is a page type.
+		if !validPageType.MatchString(rp.Type) {
+			warnings = append(warnings, fmt.Sprintf("skipped page with invalid type %q", rp.Type))
+			continue
+		}
 		slug := computeSlug(rp, sourceSlug)
 		if slug == "" {
 			warnings = append(warnings, fmt.Sprintf("skipped page with empty title (type: %s)", rp.Type))
@@ -26,6 +33,8 @@ func BuildPages(rawPages []RawPage, sourceSlug, date string) ([]wiki.Page, []str
 	return out, warnings
 }
 
+var validPageType = regexp.MustCompile(`^[a-z][a-z0-9-]*$`)
+
 func computeSlug(rp RawPage, sourceSlug string) string {
 	if rp.Type == "source" {
 		return sourceSlug
@@ -114,5 +123,9 @@ func buildFrontmatter(rp RawPage, date string) string {
 }
 
 func yamlScalar(s string) string {
+	// A raw newline or CR would end the scalar for every line-oriented
+	// frontmatter reader and start a new key (PR #147 review: a title of
+	// "x\norigin: static" forged provenance). Fold all line breaks to spaces.
+	s = strings.NewReplacer("\r\n", " ", "\r", " ", "\n", " ").Replace(s)
 	return "'" + strings.ReplaceAll(s, "'", "''") + "'"
 }

ingestion/internal/pipeline/pipeline.go

@@ -11,6 +11,7 @@ import (
 	"strings"
 	"time"
 
+	"github.com/mathiasbq/hyperguild/ingestion/internal/provenance"
 	"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
 )
 
@@ -89,13 +90,17 @@ func Run(ctx context.Context, cfg Config, brainDir, content, source string, dryR
 	meta.BodyHash = bodyHash
 	applySourceMeta(allRaw, meta)
 
-	return buildAndWrite(allRaw, sourceSlug, date, brainDir, source, inventory, allWarnings, dryRun)
+	return buildAndWrite(ctx, 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) {
+//
+// Every page written is stamped with provenance.FromContext(ctx)
+// (hyperguild#145); a caller that knows the principal attaches it with
+// provenance.WithStamp, everyone else stamps origin: unknown.
+func RunRaw(ctx context.Context, 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)
@@ -104,11 +109,11 @@ func RunRaw(brainDir, source string, rawPages []RawPage, dryRun bool) (Result, e
 	sourceSlug := wiki.Slug(source)
 	date := time.Now().UTC().Format("2006-01-02")
 
-	return buildAndWrite(rawPages, sourceSlug, date, brainDir, source, inventory, nil, dryRun)
+	return buildAndWrite(ctx, 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) {
+func buildAndWrite(ctx context.Context, 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)
@@ -136,7 +141,13 @@ func buildAndWrite(rawPages []RawPage, sourceSlug, date, brainDir, source string
 					"%s: source now disagrees on section %q — on-disk version kept",
 					page.Path, heading))
 			}
-			if err := os.WriteFile(dest, []byte(content), 0o644); err != nil {
+			// Stamped as the last step, after merge/revise, so a page that
+			// was merged into is re-attributed to this ingest too.
+			stamped, err := provenance.Apply(content, provenance.FromContext(ctx))
+			if err != nil {
+				return Result{}, fmt.Errorf("stamp %s: %w", page.Path, err)
+			}
+			if err := os.WriteFile(dest, []byte(stamped), 0o644); err != nil {
 				return Result{}, fmt.Errorf("write %s: %w", page.Path, err)
 			}
 		}

ingestion/internal/pipeline/pipeline_test.go

@@ -196,7 +196,7 @@ A book about shaping product work.
 Read this before the next planning cycle.
 `), 0o644))
 
-	_, err := RunRaw(dir, "shape-up", []RawPage{{
+	_, err := RunRaw(context.Background(), dir, "shape-up", []RawPage{{
 		Title: "Shape Up", Type: "source", Subtype: "book", Domain: "product-strategy",
 		Content: "## Summary\n\nA book about shaping product work.\n\n## Key Claims\n\n- Appetite beats estimation.\n",
 	}}, false)
@@ -221,12 +221,12 @@ func TestRunRaw_ReIngestingUnchangedContentIsByteIdentical(t *testing.T) {
 		Content: "## Summary\n\nA book about shaping product work.\n\n## Open Questions\n\n- Does appetite scale?\n",
 	}}
 
-	_, err := RunRaw(dir, "shape-up", raw, false)
+	_, err := RunRaw(context.Background(), dir, "shape-up", raw, false)
 	require.NoError(t, err)
 	first, err := os.ReadFile(filepath.Join(dir, "wiki", "sources", "shape-up.md"))
 	require.NoError(t, err)
 
-	_, err = RunRaw(dir, "shape-up", raw, false)
+	_, err = RunRaw(context.Background(), dir, "shape-up", raw, false)
 	require.NoError(t, err)
 	second, err := os.ReadFile(filepath.Join(dir, "wiki", "sources", "shape-up.md"))
 	require.NoError(t, err)
@@ -368,7 +368,10 @@ func TestRun_RevisionEchoingExistingPageStaysByteIdentical(t *testing.T) {
 	require.NoError(t, err)
 
 	want := "---\ntitle: 'Shape Up'\nlast_updated: " + time.Now().UTC().Format("2006-01-02") +
-		"\nsource_hash: " + hashBody(content) + "\n---\n\n" +
+		"\nsource_hash: " + hashBody(content) +
+		// Every page an ingest writes carries provenance (hyperguild#145);
+		// no stamp in ctx here, so origin: unknown.
+		"\norigin: unknown\n---\n\n" +
 		"## Summary\n\nA book about shaping product work.\n\n" +
 		"## Key Claims\n\n- Appetite beats estimation.\n"
 	assert.Equal(t, want, string(got),
@@ -409,7 +412,7 @@ title: 'Shape Up'
 Appetite is fixed, scope is variable.
 `), 0o644))
 
-	res, err := RunRaw(dir, "shape-up", []RawPage{{
+	res, err := RunRaw(context.Background(), dir, "shape-up", []RawPage{{
 		Title: "Shape Up", Type: "source", Subtype: "book", Domain: "product",
 		Content: "## Summary\n\nAppetite is negotiable and scope is fixed.\n",
 	}}, false)