feat(ingestion): symlink tripwire for the Syncthing-shared brain dir
CI / Lint / Test / Vet (pull_request) Successful in 34s
CI / Mirror to GitHub (pull_request) Skipped

The brain dir is a Syncthing sendreceive folder and Syncthing syncs
symlinks; search, vectorstore, context and graph readers follow one out
of the brain and would index or return what it points to (reproduced
with search.Query). Decision (#157): a tripwire now, brain-wide os.Root
readers next.

- symlinkguard.Scan lists every symlink inside the brain dir (skipping
  .git; the brain dir itself may be a mount symlink).
- At startup the server refuses to start while any exists, naming them.
- symlinkguard.Watch rescans every BRAIN_SYMLINK_SCAN_INTERVAL seconds
  (default 300) and sends one ntfy alert per new set of symlinks.

The live brain dir had 0 symlinks on 2026-10-03, checked before this
change, so deploying it does not trip.

Refs #157

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-03 17:04:41 +02:00
co-authored by Claude Opus 5.5
parent cfe3f24e25
commit 796d226497
5 changed files with 235 additions and 0 deletions
@@ -0,0 +1,87 @@
package symlinkguard
import (
"context"
"os"
"path/filepath"
"sync"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// hyperguild#157: the brain dir is a Syncthing sendreceive folder and
// Syncthing syncs symlinks; search, vectorstore, context and graph readers
// follow them out of the brain. Until every reader goes through an os.Root,
// a symlink anywhere in the brain is a tripwire: the server refuses to start
// on one, and reports one that appears while it runs.
func TestScanFindsSymlinksAtAnyDepthAndSkipsGit(t *testing.T) {
brain := t.TempDir()
outside := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki", "w", "facts"), 0o755))
require.NoError(t, os.MkdirAll(filepath.Join(brain, ".git", "objects"), 0o755))
require.NoError(t, os.WriteFile(filepath.Join(brain, "wiki", "w", "facts", "ok.md"), []byte("x"), 0o644))
require.NoError(t, os.Symlink(filepath.Join(outside, "f"), filepath.Join(brain, "wiki", "w", "facts", "leak.md")))
require.NoError(t, os.Symlink(outside, filepath.Join(brain, "wiki", "dirlink")))
require.NoError(t, os.Symlink(outside, filepath.Join(brain, ".git", "objects", "alt")))
found, err := Scan(brain)
require.NoError(t, err)
assert.ElementsMatch(t, []string{"wiki/w/facts/leak.md", "wiki/dirlink"}, found)
}
func TestScanOfACleanBrainFindsNothing(t *testing.T) {
brain := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(brain, "raw"), 0o755))
require.NoError(t, os.WriteFile(filepath.Join(brain, "raw", "n.md"), []byte("x"), 0o644))
found, err := Scan(brain)
require.NoError(t, err)
assert.Empty(t, found)
}
// The brain dir itself being a symlink is fine (the volume mount may be one);
// only entries inside it are checked.
func TestScanFollowsTheRootButNotEntries(t *testing.T) {
real := t.TempDir()
link := filepath.Join(t.TempDir(), "brain")
require.NoError(t, os.Symlink(real, link))
require.NoError(t, os.WriteFile(filepath.Join(real, "n.md"), []byte("x"), 0o644))
found, err := Scan(link)
require.NoError(t, err)
assert.Empty(t, found)
}
type recNotifier struct {
mu sync.Mutex
msgs []string
}
func (r *recNotifier) Notify(_ context.Context, m string) error {
r.mu.Lock()
defer r.mu.Unlock()
r.msgs = append(r.msgs, m)
return nil
}
func (r *recNotifier) count() int { r.mu.Lock(); defer r.mu.Unlock(); return len(r.msgs) }
// Watch reports a symlink that appears while running, once per distinct set.
func TestWatchNotifiesOncePerNewSymlinkSet(t *testing.T) {
brain := t.TempDir()
n := &recNotifier{}
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go Watch(ctx, brain, 10*time.Millisecond, n)
time.Sleep(50 * time.Millisecond)
assert.Zero(t, n.count(), "a clean brain raises nothing")
require.NoError(t, os.Symlink(t.TempDir(), filepath.Join(brain, "planted")))
require.Eventually(t, func() bool { return n.count() == 1 }, 2*time.Second, 10*time.Millisecond)
time.Sleep(60 * time.Millisecond)
assert.Equal(t, 1, n.count(), "the same symlink set is reported once, not every tick")
assert.Contains(t, n.msgs[0], "planted")
}