fix(pipeline,classification): read the brain through brainfs (#157, slice 6) (#176)

Ingest pipeline readers (readSourcePage and loadSchema feed the LLM prompt; reviseOrCreate; injectSourceRefs; BackfillRefs list and reads) and classification.Load read through brainfs: symlinked or special files no longer reach the prompt, written pages or the I1 sovereignty config, and a FIFO no longer hangs ingest or startup. A symlinked/special classification.yaml is a hard error; an absent one still yields defaults.

Refs #157. Adversarial review: BLOCKED, BLOCKED, PASS. Follow-ups: #158 (write paths), #179 (FIFO tripwire).

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

ingestion/internal/pipeline/pipeline.go

@@ -5,7 +5,10 @@ import (
 	"context"
 	"crypto/sha256"
 	"encoding/hex"
+	"errors"
 	"fmt"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
+	"io/fs"
 	"os"
 	"path/filepath"
 	"strings"
@@ -129,7 +132,7 @@ func buildAndWrite(ctx context.Context, rawPages []RawPage, sourceSlug, date, br
 			if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
 				return Result{}, fmt.Errorf("mkdir for %s: %w", page.Path, err)
 			}
-			content, conflicts, err := reviseOrCreate(dest, page)
+			content, conflicts, err := reviseOrCreate(brainDir, page)
 			if err != nil {
 				return Result{}, err
 			}
@@ -188,14 +191,27 @@ func hashBody(content string) string {
 
 // readSourcePage returns the full on-disk content of the source page at
 // wiki/sources/<sourceSlug>.md, or "" when it doesn't exist yet.
+// It reads through the brain root, regular files only (hyperguild#157): the
+// content goes into the LLM prompt.
 func readSourcePage(brainDir, sourceSlug string) string {
-	raw, err := os.ReadFile(filepath.Join(brainDir, "wiki", "sources", sourceSlug+".md"))
+	raw, err := readBrainFile(brainDir, "wiki/sources/"+sourceSlug+".md")
 	if err != nil {
 		return ""
 	}
 	return string(raw)
 }
 
+// readBrainFile reads one brain-relative file through the brain root,
+// regular files only (hyperguild#157).
+func readBrainFile(brainDir, rel string) ([]byte, error) {
+	bfs, err := brainfs.Open(brainDir)
+	if err != nil {
+		return nil, err
+	}
+	defer func() { _ = bfs.Close() }()
+	return bfs.ReadRegular(rel)
+}
+
 // storedSourceHash reads source_hash from the source page a previous ingest
 // wrote, or "" when there is no such page or no such field.
 //
@@ -230,10 +246,10 @@ func storedSourceHash(brainDir, sourceSlug string) string {
 // its first-ingest date on a revised page. Left deliberately — the alternative
 // is this function editing frontmatter it does not own, and no lint reads that
 // field today.
-func reviseOrCreate(dest string, page wiki.Page) (string, []string, error) {
-	existing, err := os.ReadFile(dest)
+func reviseOrCreate(brainDir string, page wiki.Page) (string, []string, error) {
+	existing, err := readBrainFile(brainDir, page.Path)
 	switch {
-	case os.IsNotExist(err):
+	case errors.Is(err, fs.ErrNotExist):
 		return page.Content, nil, nil
 	case err != nil:
 		return "", nil, fmt.Errorf("read existing %s: %w", page.Path, err)
@@ -267,7 +283,7 @@ See brain/schema.md for the full schema.
 `
 
 func loadSchema(brainDir string) string {
-	b, err := os.ReadFile(filepath.Join(brainDir, "schema.md"))
+	b, err := readBrainFile(brainDir, "schema.md")
 	if err != nil {
 		return defaultSchema
 	}