feat(mcp): add brain_read + brain_edit, contained to the sync source (brain#4)

brain_read returns a note verbatim; brain_edit is str_replace with an
exactly-once match. Both operate on INGEST_BRAIN_DIR, which is the pod's
mount of /var/lib/supervisor/brain — the tree brain-sync commits from, so
an edit reaches gitea on the next cycle rather than landing somewhere the
sync cannot see it (brain#2).

An adversarial design review before implementation changed three things,
each of which would otherwise have shipped:

1. Governance files are NOT in the model-facing tool. The original plan
   allowed root *.md so CLAUDE.md had an MCP path at all — the absence of
   one is what pushed a session to edit via the gitea REST API on
   2026-06-16 and wedge the sync. But brain content is ingested from the
   outside world, reaches a model's context via brain_query, and that
   model would hold the editor: one poisoned page could rewrite the
   CLAUDE.md a .dispatch-allow agent later loads as instructions. Worse,
   brain-sync merges with --strategy-option=ours, so the live tree wins
   against a human's corrective push on exactly the conflicting lines.
   CLAUDE.md now goes through brain_edit_root: de-surfaced from
   tools/list (the brain_index precedent, ADR-0012 rule 4) and gated on
   the local static principal, so a claude.ai-origin session is refused.
   The two scopes are disjoint — the privileged door has the smaller reach.

2. Reads needed the same allowlist, and brain_get already lacked it.
   api.ReadNote resolves any brain-relative path and parseFrontmatter
   returns the whole file when there is no fence, so brain_get reads
   verbatim session transcripts under archive/ (up to 500 KB, never
   BM25-indexed, so nobody thinks of them as reachable). A test proves
   the exposure was live; the same Resolve now gates brain_get.

3. Canonicalise before allowlisting. A prefix check on the raw argument
   accepts knowledge/../.git/hooks/post-commit, which Clean collapses to
   a git hook that brain-sync executes inside a pod holding the Gitea
   push credentials. Traversal, symlink escape, dotfiles, .git/, archive/,
   sessions/ and raw/ are refused by a static backstop that does not
   depend on the allowlist being right. There were no traversal tests in
   this repo before.

Also from the review: overlapping match counting (bytes.Count says "aa"
occurs once in "aaa", so a Count-based uniqueness check accepts an
ambiguous edit); UTF-8 validation on both sides, because encoding/json
substitutes U+FFFD and would hand back bytes the file does not contain,
making every derived old_str unmatchable; refusal while .git/MERGE_HEAD
or index.lock exists, since an edit racing brain-sync's merge is either
hard-reset away or committed as a wrongly resolved conflict; flock plus a
per-path mutex with the read taken inside the lock, because two pods
share the hostPath during a RollingUpdate and uniqueness evaluated
against a stale read loses an update while reporting success; same-dir
*.tmp + rename + chmod 0644 + fsync of file and parent; and reindex only
when the edit touches frontmatter, since BM25 walks live and embeddings
are mtime-driven.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BeAp5LTscnz2W7Ubt4eJ6m

ingestion/internal/notes/edit.go

@@ -0,0 +1,276 @@
+package notes
+
+import (
+	"crypto/sha256"
+	"encoding/hex"
+	"errors"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"sync"
+	"syscall"
+	"unicode/utf8"
+)
+
+// maxNoteBytes caps what Read will hand back. Generous for knowledge/ and
+// wiki/ (the largest note today is far under it) and small enough that a
+// pathological file cannot flood a caller's context.
+const maxNoteBytes = 256 << 10
+
+// Errors callers distinguish.
+var (
+	ErrNoMatch    = errors.New("notes: old_str not found")
+	ErrAmbiguous  = errors.New("notes: old_str matches more than once")
+	ErrNotUTF8    = errors.New("notes: content is not valid UTF-8")
+	ErrGitBusy    = errors.New("notes: a git operation is in progress")
+	ErrTooLarge   = errors.New("notes: file exceeds the readable size limit")
+	ErrDegenerate = errors.New("notes: edit is degenerate")
+	ErrInConflict = errors.New("notes: file contains unresolved conflict markers")
+)
+
+// pathLocks serialises edits per file within this process. The flock below
+// covers the cross-process case (two pods share the hostPath during a rolling
+// update, and brain-fix/brain-enrich write the same tree).
+var pathLocks sync.Map // string -> *sync.Mutex
+
+// Result is what a successful edit reports.
+type Result struct {
+	Path         string `json:"path"`
+	ContentHash  string `json:"content_hash"`
+	BytesBefore  int    `json:"bytes_before"`
+	BytesAfter   int    `json:"bytes_after"`
+	ReindexError string `json:"reindex_error,omitempty"`
+}
+
+// Read returns a note's bytes verbatim.
+//
+// No frontmatter parsing, no excerpting, no normalisation: the entire purpose
+// is to give a caller an exact basis for an edit. An excerpt from brain_query
+// would be truncated and normalised, and every old_str built from one would
+// miss.
+func Read(brainDir, path string) ([]byte, error) {
+	t, err := Resolve(brainDir, path, ScopeNotes)
+	if err != nil {
+		return nil, err
+	}
+	return readContained(t)
+}
+
+// ReadScoped is Read for a caller already holding the privileged scope.
+func ReadScoped(brainDir, path string, scope Scope) ([]byte, error) {
+	t, err := Resolve(brainDir, path, scope)
+	if err != nil {
+		return nil, err
+	}
+	return readContained(t)
+}
+
+func readContained(t Target) ([]byte, error) {
+	fi, err := os.Stat(t.Abs)
+	if err != nil {
+		return nil, fmt.Errorf("notes: stat %s: %w", t.Rel, err)
+	}
+	if fi.Size() > maxNoteBytes {
+		return nil, fmt.Errorf("%w: %s is %d bytes (limit %d)", ErrTooLarge, t.Rel, fi.Size(), maxNoteBytes)
+	}
+	b, err := os.ReadFile(t.Abs)
+	if err != nil {
+		return nil, fmt.Errorf("notes: read %s: %w", t.Rel, err)
+	}
+	// The MCP response marshals this into a JSON string, and encoding/json
+	// substitutes U+FFFD for invalid UTF-8 — silently returning different
+	// bytes than the file holds, which defeats "verbatim" entirely.
+	if !utf8.Valid(b) {
+		return nil, fmt.Errorf("%w: %s", ErrNotUTF8, t.Rel)
+	}
+	return b, nil
+}
+
+// Edit replaces exactly one occurrence of oldStr with newStr, in place.
+//
+// Fails loudly and writes nothing on: zero matches, more than one match
+// (counted with overlap), degenerate arguments, invalid UTF-8, a git operation
+// in flight, or unresolved conflict markers in the target.
+func Edit(brainDir, path, oldStr, newStr string, scope Scope) (Result, error) {
+	t, err := Resolve(brainDir, path, scope)
+	if err != nil {
+		return Result{}, err
+	}
+	if oldStr == "" {
+		return Result{}, fmt.Errorf("%w: old_str is empty", ErrDegenerate)
+	}
+	if oldStr == newStr {
+		return Result{}, fmt.Errorf("%w: old_str equals new_str", ErrDegenerate)
+	}
+	if !utf8.ValidString(newStr) {
+		return Result{}, fmt.Errorf("%w: new_str", ErrNotUTF8)
+	}
+	// brain#2 guard: refuse to write to a tree the sync does not commit from.
+	if err := assertSyncSource(brainDir); err != nil {
+		return Result{}, err
+	}
+	if err := assertGitIdle(brainDir); err != nil {
+		return Result{}, err
+	}
+
+	mu := lockFor(t.Abs)
+	mu.Lock()
+	defer mu.Unlock()
+
+	unlock, err := flockFile(t.Abs)
+	if err != nil {
+		return Result{}, err
+	}
+	defer unlock()
+
+	// Read INSIDE the lock: the match count must be evaluated against the
+	// bytes we are about to overwrite, or a concurrent edit is silently lost
+	// while both callers are told they succeeded.
+	before, err := readContained(t)
+	if err != nil {
+		return Result{}, err
+	}
+	if hasConflictMarkers(before) {
+		return Result{}, fmt.Errorf("%w: %s", ErrInConflict, t.Rel)
+	}
+
+	switch n := countOverlapping(string(before), oldStr); {
+	case n == 0:
+		return Result{}, fmt.Errorf("%w in %s (0 matches)%s", ErrNoMatch, t.Rel, crlfHint(string(before), oldStr))
+	case n > 1:
+		return Result{}, fmt.Errorf("%w in %s (%d matches) — extend old_str until it is unique",
+			ErrAmbiguous, t.Rel, n)
+	}
+
+	after := strings.Replace(string(before), oldStr, newStr, 1)
+	if err := writeAtomic(t.Abs, []byte(after)); err != nil {
+		return Result{}, err
+	}
+
+	sum := sha256.Sum256([]byte(after))
+	return Result{
+		Path:        t.Rel,
+		ContentHash: hex.EncodeToString(sum[:]),
+		BytesBefore: len(before),
+		BytesAfter:  len(after),
+	}, nil
+}
+
+// countOverlapping counts occurrences allowing overlap. bytes.Count does not:
+// "aa" occurs once in "aaa" by its reckoning, so a Count-based uniqueness
+// check accepts an ambiguous edit as unique.
+func countOverlapping(s, sub string) int {
+	var n, from int
+	for {
+		i := strings.Index(s[from:], sub)
+		if i < 0 {
+			return n
+		}
+		n++
+		from += i + 1
+	}
+}
+
+// crlfHint reports whether the caller's old_str would have matched if line
+// endings agreed. It never normalises — that would break byte-identity — but
+// an opaque "no match" is unfixable from the caller's side, and a stripped \r
+// is the likeliest cause.
+func crlfHint(content, oldStr string) string {
+	if strings.Contains(content, "\r\n") && !strings.Contains(oldStr, "\r\n") {
+		if strings.Contains(strings.ReplaceAll(content, "\r\n", "\n"), oldStr) {
+			return " — the file uses CRLF line endings and old_str does not; include the \\r"
+		}
+	}
+	return ""
+}
+
+func hasConflictMarkers(b []byte) bool {
+	s := string(b)
+	return strings.Contains(s, "\n<<<<<<< ") || strings.HasPrefix(s, "<<<<<<< ")
+}
+
+// assertGitIdle refuses while brain-sync (or brain-fix, or a human) has a git
+// operation in flight. An edit landing between `git merge` and its abort is
+// either hard-reset away or committed as a wrongly resolved conflict — and the
+// caller was told it succeeded.
+func assertGitIdle(brainDir string) error {
+	for _, marker := range []string{"MERGE_HEAD", "REBASE_HEAD", "CHERRY_PICK_HEAD", "index.lock"} {
+		if _, err := os.Stat(filepath.Join(brainDir, ".git", marker)); err == nil {
+			return fmt.Errorf("%w (.git/%s present) — retry after the sync settles", ErrGitBusy, marker)
+		}
+	}
+	return nil
+}
+
+func lockFor(abs string) *sync.Mutex {
+	v, _ := pathLocks.LoadOrStore(abs, &sync.Mutex{})
+	return v.(*sync.Mutex)
+}
+
+// flockFile takes an advisory lock covering other processes sharing the
+// hostPath — during a RollingUpdate two ingestion pods do.
+func flockFile(abs string) (func(), error) {
+	f, err := os.OpenFile(abs+".lock", os.O_CREATE|os.O_RDWR, 0o644)
+	if err != nil {
+		return nil, fmt.Errorf("notes: lock %s: %w", filepath.Base(abs), err)
+	}
+	if err := syscall.Flock(int(f.Fd()), syscall.LOCK_EX); err != nil {
+		_ = f.Close()
+		return nil, fmt.Errorf("notes: flock %s: %w", filepath.Base(abs), err)
+	}
+	return func() {
+		_ = syscall.Flock(int(f.Fd()), syscall.LOCK_UN)
+		_ = f.Close()
+		_ = os.Remove(abs + ".lock")
+	}, nil
+}
+
+// writeAtomic replaces the file via a same-directory temp + rename, then
+// fsyncs the directory so the rename survives a node crash.
+//
+// Same directory because a rename across the hostPath boundary fails with
+// EXDEV; the ".tmp" suffix because the tree's .gitignore already covers it, so
+// a leaked temp is not committed by `git add -A`.
+func writeAtomic(abs string, content []byte) error {
+	dir := filepath.Dir(abs)
+	tmp, err := os.CreateTemp(dir, filepath.Base(abs)+".*.tmp")
+	if err != nil {
+		return fmt.Errorf("notes: temp file: %w", err)
+	}
+	tmpName := tmp.Name()
+	defer func() { _ = os.Remove(tmpName) }() // no-op once renamed
+
+	if _, err := tmp.Write(content); err != nil {
+		_ = tmp.Close()
+		return fmt.Errorf("notes: write temp: %w", err)
+	}
+	if err := tmp.Sync(); err != nil {
+		_ = tmp.Close()
+		return fmt.Errorf("notes: sync temp: %w", err)
+	}
+	if err := tmp.Close(); err != nil {
+		return fmt.Errorf("notes: close temp: %w", err)
+	}
+	// CreateTemp makes 0600; every other writer of this tree uses 0644 and
+	// other uids read it.
+	if err := os.Chmod(tmpName, 0o644); err != nil {
+		return fmt.Errorf("notes: chmod temp: %w", err)
+	}
+	if err := os.Rename(tmpName, abs); err != nil {
+		return fmt.Errorf("notes: rename: %w", err)
+	}
+	return fsyncDir(dir)
+}
+
+func fsyncDir(dir string) error {
+	d, err := os.Open(dir)
+	if err != nil {
+		return fmt.Errorf("notes: open dir: %w", err)
+	}
+	defer func() { _ = d.Close() }()
+	if err := d.Sync(); err != nil {
+		return fmt.Errorf("notes: fsync dir: %w", err)
+	}
+	return nil
+}

ingestion/internal/notes/edit_test.go

@@ -0,0 +1,256 @@
+package notes
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"sync"
+	"testing"
+)
+
+func seed(t *testing.T, dir, rel, content string) string {
+	t.Helper()
+	abs := filepath.Join(dir, rel)
+	if err := os.MkdirAll(filepath.Dir(abs), 0o755); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(abs, []byte(content), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	return abs
+}
+
+func read(t *testing.T, abs string) string {
+	t.Helper()
+	b, err := os.ReadFile(abs)
+	if err != nil {
+		t.Fatal(err)
+	}
+	return string(b)
+}
+
+func TestRead_ReturnsVerbatimBytes(t *testing.T) {
+	dir := newBrain(t)
+	const body = "---\ntitle: 'x'\n---\n\nbody with  double  spaces\r\nand a CRLF line\nno trailing newline"
+	seed(t, dir, "knowledge/verbatim.md", body)
+
+	got, err := Read(dir, "knowledge/verbatim.md")
+	if err != nil {
+		t.Fatalf("Read: %v", err)
+	}
+	if string(got) != body {
+		t.Errorf("Read returned %q, want the file byte-for-byte", got)
+	}
+}
+
+func TestRead_RefusesNonUTF8RatherThanCorruptingIt(t *testing.T) {
+	// The response is marshalled into a JSON string, and encoding/json
+	// replaces invalid UTF-8 with U+FFFD. Returning it would mean every
+	// old_str the caller derives from that region can never match, and
+	// pasting it back would write the corruption to disk permanently.
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/bad.md", "ok \xff\xfe broken\n")
+
+	if _, err := Read(dir, "knowledge/bad.md"); err == nil {
+		t.Fatal("Read accepted invalid UTF-8; it must refuse rather than silently substitute")
+	}
+}
+
+func TestEdit_ReplacesExactlyOnceAndLeavesEveryOtherByteAlone(t *testing.T) {
+	dir := newBrain(t)
+	const body = "---\ntitle: 'x'\n---\n\nalpha\nbeta\ngamma\n"
+	abs := seed(t, dir, "knowledge/n.md", body)
+
+	res, err := Edit(dir, "knowledge/n.md", "beta", "BETA", ScopeNotes)
+	if err != nil {
+		t.Fatalf("Edit: %v", err)
+	}
+	want := strings.Replace(body, "beta", "BETA", 1)
+	if got := read(t, abs); got != want {
+		t.Errorf("file = %q, want %q", got, want)
+	}
+	if res.ContentHash == "" {
+		t.Error("result should carry a content hash for read-after-write confirmation")
+	}
+}
+
+func TestEdit_RefusesAmbiguousAndAbsentMatchesWithoutWriting(t *testing.T) {
+	dir := newBrain(t)
+	const body = "alpha\nalpha\n"
+	abs := seed(t, dir, "knowledge/n.md", body)
+
+	cases := []struct{ name, old, want string }{
+		{"two matches", "alpha", "2"},
+		{"no match", "delta", "0"},
+	}
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			_, err := Edit(dir, "knowledge/n.md", tc.old, "x", ScopeNotes)
+			if err == nil {
+				t.Fatal("want a loud refusal")
+			}
+			if !strings.Contains(err.Error(), tc.want) {
+				t.Errorf("error must state the match count, got %v", err)
+			}
+			if got := read(t, abs); got != body {
+				t.Errorf("file changed on a refused edit: %q", got)
+			}
+		})
+	}
+}
+
+func TestEdit_CountsOverlappingMatches(t *testing.T) {
+	// bytes.Count counts NON-overlapping occurrences: "aa" in "aaa" is 1, so
+	// a Count-based uniqueness check calls an ambiguous edit unique.
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "aaa\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "aa", "b", ScopeNotes); err == nil {
+		t.Fatal("overlapping matches must be reported as ambiguous")
+	}
+}
+
+func TestEdit_RejectsDegenerateArguments(t *testing.T) {
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "alpha\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "", "x", ScopeNotes); err == nil {
+		t.Error("empty old_str must be rejected")
+	}
+	if _, err := Edit(dir, "knowledge/n.md", "alpha", "alpha", ScopeNotes); err == nil {
+		t.Error("a no-op edit must be rejected rather than burning a sync cycle")
+	}
+}
+
+func TestEdit_DeletionIsLegal(t *testing.T) {
+	dir := newBrain(t)
+	abs := seed(t, dir, "knowledge/n.md", "keep\ndrop\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "drop\n", "", ScopeNotes); err != nil {
+		t.Fatalf("Edit: %v", err)
+	}
+	if got := read(t, abs); got != "keep\n" {
+		t.Errorf("file = %q, want %q", got, "keep\n")
+	}
+}
+
+func TestEdit_ReportsWhenOnlyLineEndingsDiffer(t *testing.T) {
+	// The likeliest real failure: the caller's old_str lost its \r. Never
+	// normalise silently — that breaks byte-identity — but say so, because an
+	// opaque "no match" is unfixable from the caller's side.
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "alpha\r\nbeta\r\n")
+
+	_, err := Edit(dir, "knowledge/n.md", "alpha\nbeta", "x", ScopeNotes)
+	if err == nil {
+		t.Fatal("want a refusal")
+	}
+	if !strings.Contains(err.Error(), "line ending") {
+		t.Errorf("error should point at CRLF, got %v", err)
+	}
+}
+
+func TestEdit_RefusesWhileGitIsMidOperation(t *testing.T) {
+	// brain-sync runs `git merge -X ours origin/main`, and aborts on conflict
+	// with a hard reset. An edit landing inside that window is either erased
+	// or committed as a wrongly-resolved conflict, and the caller was told it
+	// succeeded.
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "alpha\n")
+
+	for _, marker := range []string{"MERGE_HEAD", "index.lock", "REBASE_HEAD"} {
+		t.Run(marker, func(t *testing.T) {
+			p := filepath.Join(dir, ".git", marker)
+			if err := os.WriteFile(p, []byte("x"), 0o644); err != nil {
+				t.Fatal(err)
+			}
+			defer func() { _ = os.Remove(p) }()
+
+			if _, err := Edit(dir, "knowledge/n.md", "alpha", "beta", ScopeNotes); err == nil {
+				t.Errorf("edit accepted while %s exists", marker)
+			}
+		})
+	}
+}
+
+func TestEdit_RefusesAFileHoldingConflictMarkers(t *testing.T) {
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "<<<<<<< HEAD\nours\n=======\ntheirs\n>>>>>>> origin/main\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "ours", "x", ScopeNotes); err == nil {
+		t.Fatal("editing one side of an unresolved conflict must be refused")
+	}
+}
+
+func TestEdit_ConcurrentEditsBothApply(t *testing.T) {
+	// Read-modify-write with no lock loses one update AND reports success for
+	// both. old_str uniqueness does not protect against it: uniqueness is
+	// evaluated against the stale read.
+	dir := newBrain(t)
+	abs := seed(t, dir, "knowledge/n.md", "alpha\nbeta\n")
+
+	var wg sync.WaitGroup
+	errs := make([]error, 2)
+	for i, pair := range [][2]string{{"alpha", "ALPHA"}, {"beta", "BETA"}} {
+		wg.Add(1)
+		go func(i int, old, new string) {
+			defer wg.Done()
+			_, errs[i] = Edit(dir, "knowledge/n.md", old, new, ScopeNotes)
+		}(i, pair[0], pair[1])
+	}
+	wg.Wait()
+
+	for i, err := range errs {
+		if err != nil {
+			t.Fatalf("edit %d failed: %v", i, err)
+		}
+	}
+	if got := read(t, abs); got != "ALPHA\nBETA\n" {
+		t.Errorf("file = %q, want both edits applied", got)
+	}
+}
+
+func TestEdit_LeavesNoTemporaryFileBehind(t *testing.T) {
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "alpha\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "alpha", "beta", ScopeNotes); err != nil {
+		t.Fatal(err)
+	}
+	entries, err := os.ReadDir(filepath.Join(dir, "knowledge"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	for _, e := range entries {
+		if e.Name() != "note.md" && e.Name() != "n.md" {
+			t.Errorf("stray file left in the tree: %q (git add -A would commit it)", e.Name())
+		}
+	}
+}
+
+func TestEdit_PreservesReadableMode(t *testing.T) {
+	// Other uids write this tree (brain-fix, brain-enrich). os.CreateTemp
+	// yields 0600 and rename preserves it, which would break them silently.
+	dir := newBrain(t)
+	abs := seed(t, dir, "knowledge/n.md", "alpha\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "alpha", "beta", ScopeNotes); err != nil {
+		t.Fatal(err)
+	}
+	fi, err := os.Stat(abs)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if fi.Mode().Perm() != 0o644 {
+		t.Errorf("mode = %v, want 0644", fi.Mode().Perm())
+	}
+}
+
+func TestEdit_RefusesNonUTF8Replacement(t *testing.T) {
+	dir := newBrain(t)
+	seed(t, dir, "knowledge/n.md", "alpha\n")
+
+	if _, err := Edit(dir, "knowledge/n.md", "alpha", "bad \xff", ScopeNotes); err == nil {
+		t.Fatal("new_str with invalid UTF-8 must be refused, not written")
+	}
+}

ingestion/internal/notes/path.go

@@ -0,0 +1,201 @@
+// Package notes provides containment-checked read and surgical edit of brain
+// notes on the live tree that brain-sync commits from.
+//
+// Everything here is defensive for one reason: brain content is ingested from
+// the outside world, that content reaches a model's context via brain_query /
+// brain_context, and these primitives are callable by that model. A path bug
+// is therefore not a path bug — it is an outside author choosing a file.
+package notes
+
+import (
+	"errors"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+)
+
+// Scope is which part of the tree a caller is allowed to touch.
+type Scope int
+
+const (
+	// ScopeNotes is the model-facing scope: markdown under knowledge/ and
+	// wiki/ only.
+	ScopeNotes Scope = iota
+	// ScopeRoot admits the named governance files and NOTHING else. It exists so
+	// there is an MCP path to CLAUDE.md at all — the absence of one is what
+	// pushed a session to edit via the gitea REST API on 2026-06-16, which
+	// never reached the live tree and wedged brain-sync for hours. It is NOT
+	// reachable from the model-facing toolset; see tools_notes.go.
+	ScopeRoot
+)
+
+// rootFiles is an exact-name allowlist, deliberately not a "root *.md" glob.
+//
+// Two reasons. log.md is gitignored, so an edit to it applies to the live tree
+// and never reaches gitea — the exact shape of brain#2, admitted by a glob. And
+// a glob auto-admits whatever governance file appears next (AGENTS.md, a
+// bootstrap doc) with nobody reviewing that decision.
+var rootFiles = map[string]bool{"CLAUDE.md": true}
+
+// noteDirs are the two trees that hold notes.
+var noteDirs = []string{"knowledge/", "wiki/"}
+
+// deniedPrefixes are refused in every scope, independent of the allowlist.
+//
+// A static backstop rather than a consequence of the allowlist being right:
+// .git/hooks/post-commit is executed by brain-sync inside a pod holding the
+// Gitea push credentials, and archive/ + sessions/ hold verbatim session
+// transcripts that BM25 never indexes and so nobody thinks of as reachable.
+var deniedPrefixes = []string{".git/", "archive/", "sessions/", "raw/", "training-data/", ".obsidian/"}
+
+// Errors are sentinels so callers can distinguish a refusal from an I/O fault.
+var (
+	ErrOutsideBrain  = errors.New("notes: path escapes the brain dir")
+	ErrNotAllowed    = errors.New("notes: path is not editable through this tool")
+	ErrNotSyncSource = errors.New("notes: brain dir is not the sync source")
+)
+
+// Target is a resolved, contained path.
+type Target struct {
+	Rel string // brain-relative, cleaned
+	Abs string // absolute, symlink-checked
+}
+
+// Resolve canonicalises path, then checks it against the scope's allowlist,
+// then re-checks containment after symlink evaluation.
+//
+// Order matters and is the point: a prefix test on the raw argument accepts
+// "knowledge/../.git/hooks/post-commit", because Clean only collapses it
+// afterwards.
+func Resolve(brainDir, path string, scope Scope) (Target, error) {
+	// Note: the sync-source assertion lives on the WRITE path (Edit), not
+	// here. brain#2 was an edit landing where the sync could not commit it; a
+	// read from such a tree is merely a read.
+
+	// 1. Canonicalise. Rooting at "/" makes Clean collapse every ".." that
+	//    would otherwise escape, and ToSlash normalises separators first.
+	clean := strings.TrimPrefix(filepath.Clean("/"+filepath.ToSlash(path)), "/")
+	if clean == "" || clean == "." {
+		return Target{}, fmt.Errorf("%w: empty path", ErrNotAllowed)
+	}
+
+	// 2. Static denials, before any allowlist reasoning.
+	for _, d := range deniedPrefixes {
+		if strings.HasPrefix(clean+"/", d) {
+			return Target{}, fmt.Errorf("%w: %q is not note content", ErrNotAllowed, clean)
+		}
+	}
+	if strings.HasPrefix(filepath.Base(clean), ".") {
+		return Target{}, fmt.Errorf("%w: dotfiles are not editable", ErrNotAllowed)
+	}
+
+	// 3. Scope allowlist.
+	if err := allow(clean, scope); err != nil {
+		return Target{}, err
+	}
+
+	// 4. Containment, lexically.
+	abs := filepath.Join(brainDir, filepath.FromSlash(clean))
+	if !within(brainDir, abs) {
+		return Target{}, fmt.Errorf("%w: %q", ErrOutsideBrain, path)
+	}
+
+	// 5. Containment again, after resolving symlinks. The tree is Syncthing
+	//    managed, so a link can appear without anyone adding one on purpose;
+	//    a symlinked note or directory would otherwise read and write outside
+	//    the brain entirely.
+	if err := assertNoSymlinkEscape(brainDir, abs); err != nil {
+		return Target{}, err
+	}
+
+	return Target{Rel: clean, Abs: abs}, nil
+}
+
+// allow enforces the scope's allowlist. The two scopes are DISJOINT, not
+// nested: the privileged root scope reaches governance files and nothing else,
+// so the tool that carries the higher privilege carries the smaller reach.
+func allow(clean string, scope Scope) error {
+	if scope == ScopeRoot {
+		if !rootFiles[clean] {
+			return fmt.Errorf("%w: %q is not a governance file", ErrNotAllowed, clean)
+		}
+		return nil
+	}
+	if !isNotePath(clean) {
+		return fmt.Errorf("%w: %q is outside knowledge/ and wiki/", ErrNotAllowed, clean)
+	}
+	return nil
+}
+
+func isNotePath(clean string) bool {
+	var inDir bool
+	for _, d := range noteDirs {
+		if strings.HasPrefix(clean, d) {
+			inDir = true
+			break
+		}
+	}
+	if !inDir || filepath.Ext(clean) != ".md" {
+		return false
+	}
+	// _index.md is generated per wing, and brain-sync's conflict resolver
+	// deliberately resolves it in origin's favour — an edit here is reverted
+	// by design, so accepting one would be a lie.
+	return filepath.Base(clean) != "_index.md"
+}
+
+func within(root, abs string) bool {
+	rel, err := filepath.Rel(root, abs)
+	if err != nil {
+		return false
+	}
+	return rel != ".." && !strings.HasPrefix(rel, ".."+string(filepath.Separator))
+}
+
+// assertNoSymlinkEscape resolves the deepest existing ancestor of abs and
+// requires it to still be inside brainDir. The file itself need not exist
+// (a create is legal); its directory chain must be real and contained.
+func assertNoSymlinkEscape(brainDir, abs string) error {
+	if fi, err := os.Lstat(abs); err == nil && fi.Mode()&os.ModeSymlink != 0 {
+		return fmt.Errorf("%w: %q is a symlink", ErrNotAllowed, abs)
+	}
+
+	realRoot, err := filepath.EvalSymlinks(brainDir)
+	if err != nil {
+		return fmt.Errorf("notes: resolve brain dir: %w", err)
+	}
+
+	dir := filepath.Dir(abs)
+	for {
+		resolved, err := filepath.EvalSymlinks(dir)
+		if err == nil {
+			if !within(realRoot, resolved) {
+				return fmt.Errorf("%w: %q resolves outside the brain dir", ErrOutsideBrain, dir)
+			}
+			return nil
+		}
+		if !os.IsNotExist(err) {
+			return fmt.Errorf("notes: resolve %q: %w", dir, err)
+		}
+		parent := filepath.Dir(dir)
+		if parent == dir {
+			return fmt.Errorf("%w: no existing ancestor for %q", ErrOutsideBrain, abs)
+		}
+		dir = parent
+	}
+}
+
+// assertSyncSource refuses a brain dir that is not a git working tree.
+//
+// brain#2 was an edit landing on a directory the sync does not commit from.
+// That cannot be prevented by review — a wrong INGEST_BRAIN_DIR in a future
+// manifest reintroduces it while every unit test still passes — so it is
+// asserted at runtime, the same check brain-sync itself makes before running.
+func assertSyncSource(brainDir string) error {
+	if fi, err := os.Stat(filepath.Join(brainDir, ".git")); err != nil || !fi.IsDir() {
+		return fmt.Errorf("%w: %q has no .git, so an edit there would never be committed",
+			ErrNotSyncSource, brainDir)
+	}
+	return nil
+}

ingestion/internal/notes/path_test.go

@@ -0,0 +1,146 @@
+package notes
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+// newBrain lays out a tree shaped like the live one: a git dir, note dirs,
+// and the non-note areas that must never be reachable.
+func newBrain(t *testing.T) string {
+	t.Helper()
+	dir := t.TempDir()
+	for _, d := range []string{
+		".git/hooks", "knowledge", "wiki/homelab/facts", "archive/claude-sessions/koala",
+		"sessions", "raw", ".obsidian",
+	} {
+		if err := os.MkdirAll(filepath.Join(dir, d), 0o755); err != nil {
+			t.Fatal(err)
+		}
+	}
+	write := func(p, s string) {
+		t.Helper()
+		if err := os.WriteFile(filepath.Join(dir, p), []byte(s), 0o644); err != nil {
+			t.Fatal(err)
+		}
+	}
+	write("CLAUDE.md", "# instructions\n")
+	write("log.md", "ignored scratch\n")
+	write("knowledge/note.md", "# note\n")
+	write("wiki/homelab/facts/f.md", "# fact\n")
+	write("wiki/homelab/_index.md", "# index\n")
+	write("archive/claude-sessions/koala/session-1.md", "verbatim transcript\n")
+	write("sessions/s.jsonl", "{}\n")
+	write(".git/hooks/post-commit", "#!/bin/sh\n")
+	return dir
+}
+
+func TestResolve_AcceptsNotePaths(t *testing.T) {
+	dir := newBrain(t)
+	for _, p := range []string{"knowledge/note.md", "wiki/homelab/facts/f.md"} {
+		got, err := Resolve(dir, p, ScopeNotes)
+		if err != nil {
+			t.Errorf("Resolve(%q): %v", p, err)
+			continue
+		}
+		if !strings.HasPrefix(got.Abs, dir) {
+			t.Errorf("Resolve(%q).Abs = %q, want inside %q", p, got.Abs, dir)
+		}
+	}
+}
+
+func TestResolve_RefusesEscapesAndNonNoteAreas(t *testing.T) {
+	dir := newBrain(t)
+
+	// Canonicalisation must happen BEFORE the allowlist check. A prefix test
+	// on the raw argument accepts every one of these: "knowledge/..%2f" style
+	// inputs collapse to .git, and .git/hooks/post-commit is executed by
+	// brain-sync inside a pod holding the Gitea push credentials.
+	refuse := []string{
+		"knowledge/../.git/hooks/post-commit",
+		"wiki/../.git/config",
+		"./knowledge/../.git/config",
+		"knowledge//../.git/config",
+		"../../etc/passwd",
+		"/etc/passwd",
+		".git/config",
+		"archive/claude-sessions/koala/session-1.md", // verbatim transcripts
+		"sessions/s.jsonl",
+		"raw/x.md",
+		".obsidian/workspace.json",
+		"log.md",                 // gitignored: an edit here would never sync (brain#2)
+		"wiki/homelab/_index.md", // generated; brain-sync resolves it in origin's favour
+		"knowledge/note.txt",     // not markdown
+		"CLAUDE.md",              // root file — not reachable in the notes scope
+	}
+	for _, p := range refuse {
+		if _, err := Resolve(dir, p, ScopeNotes); err == nil {
+			t.Errorf("Resolve(%q) = nil error, want refusal", p)
+		}
+	}
+}
+
+func TestResolve_RootScopeAdmitsOnlyNamedFiles(t *testing.T) {
+	dir := newBrain(t)
+
+	if _, err := Resolve(dir, "CLAUDE.md", ScopeRoot); err != nil {
+		t.Errorf("Resolve(CLAUDE.md, ScopeRoot): %v", err)
+	}
+	// log.md is the reason this is an exact-name list and not "root *.md":
+	// it is gitignored, so an edit would apply locally and never reach gitea.
+	for _, p := range []string{"log.md", "AGENTS.md", "knowledge/note.md", ".git/config"} {
+		if _, err := Resolve(dir, p, ScopeRoot); err == nil {
+			t.Errorf("Resolve(%q, ScopeRoot) = nil error, want refusal", p)
+		}
+	}
+}
+
+func TestResolve_RefusesSymlinkedTargets(t *testing.T) {
+	dir := newBrain(t)
+	outside := filepath.Join(t.TempDir(), "secret.md")
+	if err := os.WriteFile(outside, []byte("secret\n"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	// The tree is Syncthing-managed, so a symlink can appear without anyone
+	// adding one deliberately. Containment must survive it.
+	if err := os.Symlink(outside, filepath.Join(dir, "knowledge/link.md")); err != nil {
+		t.Skipf("symlinks unavailable: %v", err)
+	}
+	if _, err := Resolve(dir, "knowledge/link.md", ScopeNotes); err == nil {
+		t.Error("Resolve followed a symlink out of the brain dir")
+	}
+
+	if err := os.Symlink(filepath.Dir(outside), filepath.Join(dir, "wiki/escape")); err != nil {
+		t.Skipf("symlinks unavailable: %v", err)
+	}
+	if _, err := Resolve(dir, "wiki/escape/secret.md", ScopeNotes); err == nil {
+		t.Error("Resolve followed a symlinked directory out of the brain dir")
+	}
+}
+
+func TestResolve_RefusesWhenTheTreeIsNotTheSyncSource(t *testing.T) {
+	// brain#2 was "wrote to a directory the sync does not commit from". No
+	// code review prevents that recurring — a wrong INGEST_BRAIN_DIR in a
+	// future manifest reintroduces it and every unit test still passes. So
+	// assert the property at runtime, the way brain-sync itself does.
+	dir := t.TempDir()
+	if err := os.MkdirAll(filepath.Join(dir, "knowledge"), 0o755); err != nil {
+		t.Fatal(err)
+	}
+	if err := os.WriteFile(filepath.Join(dir, "knowledge/note.md"), []byte("x"), 0o644); err != nil {
+		t.Fatal(err)
+	}
+	// Reads are fine anywhere; the guard belongs to writes.
+	if _, err := Resolve(dir, "knowledge/note.md", ScopeNotes); err != nil {
+		t.Fatalf("Resolve should not require .git for a read: %v", err)
+	}
+	_, err := Edit(dir, "knowledge/note.md", "x", "y", ScopeNotes)
+	if err == nil {
+		t.Fatal("Edit accepted a tree with no .git — the write would never be committed")
+	}
+	if !strings.Contains(err.Error(), "sync source") {
+		t.Errorf("error should name the cause, got %v", err)
+	}
+}