Compare commits

..
Author SHA1 Message Date
mathiasandClaude Opus 5.5 77c44f298c fix: pipeline, backfill, watcher and archive writes go through the brain root (#158 part B)
CI / Lint / Test / Vet (pull_request) Successful in 1m13s
CI / Mirror to GitHub (pull_request) Skipped
The remaining writers created or rewrote brain files by path:
- pipeline buildAndWrite: os.MkdirAll + os.WriteFile of every page.
- BackfillRefs: os.WriteFile of each concept page; a page swapped for a
  symlink after the read was written through (the race test overwrote an
  in-brain target before this change).
- watcher: the raw/processed and raw/failed archive copies (os.Create),
  the .processed/.failed markers and the log.md entry (os.OpenFile).
- cmd/server: the claude-session archive.

All now go through brainfs PutRegular/AppendRegular (new package-level
PutFile/AppendFile for one-off writers: the watcher's call-site lint bans
.Open calls in that file so raw/ reads stay on OpenRegular).

Stacked on #189 (needs PutRegular/AppendRegular).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-05 23:26:02 +02:00
mathiasandClaude Opus 5.5 f4636c7ef0 fix: creating and generated writes go through the brain root (#188, #158 part A) (#189)
CI / Lint / Test / Vet (push) Failing after 1m2s
CI / Mirror to GitHub (push) Skipped
New brainfs PutRegular (create or replace), CreateRegular (create only), AppendRegular, Remove and RealParent: missing parents created one component at a time through the root, every existing component a real directory, new files created with O_EXCL and confirmed before writing. brain_write, promote/reject (O_EXCL create, source kept on refusal), StampProvenanceFile, BuildWingIndex, RebuildIndex, AppendLog and the tunnel candidate log use them; provenance.ApplyFile removed.

Fixes #188. Refs #158. Adversarial review: BLOCKED, BLOCKED, PASS.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Mathias <mthbqv@gmail.com>
2026-10-05 21:25:54 +00:00
mathiasandClaude Opus 5.5 bd989f887f fix(linkcheck): keep the write when the link index cannot be built (#178) (#191)
CI / Lint / Test / Vet (push) Successful in 1m4s
CI / Mirror to GitHub (push) Successful in 4s
StripUnresolvedLinks logs a warning and returns the content unchanged when the link index cannot be built (e.g. an unreadable subdirectory), instead of failing every brain_write/brain_update and losing the learning. Nothing is unwrapped on a partial index.

Fixes #178.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Mathias <mthbqv@gmail.com>
2026-10-05 21:16:04 +00:00
mathiasandClaude Opus 5.5 4770f97ffd fix(symlinkguard): report and remove FIFOs, sockets and devices too (#179) (#190)
CI / Lint / Test / Vet (push) Successful in 1m5s
CI / Mirror to GitHub (push) Successful in 4s
Scan reports special files (not regular, directory or symlink) in Result.Special, so the startup check refuses with a message naming them; Watch removes them through an os.Root after re-checking the type, and reports any it cannot remove (never as removed).

Fixes #179. Adversarial review: BLOCKED, BLOCKED, PASS. Flake on main tracked in #193.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Mathias <mthbqv@gmail.com>
2026-10-05 21:15:57 +00:00
13 changed files with 412 additions and 54 deletions
+9 -4
View File
@@ -17,6 +17,7 @@ import (
"github.com/mathiasbq/hyperguild/ingestion/internal/api"
"github.com/mathiasbq/hyperguild/ingestion/internal/audit"
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
"github.com/mathiasbq/hyperguild/ingestion/internal/capture"
"github.com/mathiasbq/hyperguild/ingestion/internal/capturehttp"
"github.com/mathiasbq/hyperguild/ingestion/internal/classification"
@@ -89,11 +90,15 @@ func (s *claudeSink) Ingest(ctx context.Context, b claudewatcher.Batch) error {
sb.WriteString("\n\n")
}
slug := "session-" + b.Host + "-" + b.SessionID
dest := filepath.Join(s.brainDir, "archive", "claude-sessions", b.Host, slug+".md")
if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
return fmt.Errorf("create claude-sessions archive dir: %w", err)
dest := "archive/claude-sessions/" + b.Host + "/" + slug + ".md"
// Written through the brain root, never through a symlinked directory
// or file (hyperguild#158).
bfs, err := brainfs.Open(s.brainDir)
if err != nil {
return fmt.Errorf("open brain: %w", err)
}
if err := os.WriteFile(dest, []byte(sb.String()), 0o644); err != nil {
defer func() { _ = bfs.Close() }()
if err := bfs.PutRegular(dest, []byte(sb.String())); err != nil {
return fmt.Errorf("write claude session archive: %w", err)
}
s.logger.Debug("claude session archived (non-indexed)", "path", dest)
@@ -4,6 +4,7 @@ import (
"os"
"path/filepath"
"strings"
"syscall"
"testing"
"github.com/stretchr/testify/assert"
@@ -63,3 +64,13 @@ func TestStartupSymlinkCheckRefusesAnUnlistableBrainRoot(t *testing.T) {
t.Cleanup(func() { _ = os.Chmod(brain, 0o755) })
assert.Error(t, startupSymlinkCheck(brain))
}
// hyperguild#179: a FIFO in the brain is refused at startup with a clear
// message, instead of hanging or exiting later in a reader.
func TestStartupSymlinkCheckRefusesABrainWithAFIFO(t *testing.T) {
brain := t.TempDir()
require.NoError(t, syscall.Mkfifo(filepath.Join(brain, "classification.yaml"), 0o644))
err := startupSymlinkCheck(brain)
require.Error(t, err)
assert.Contains(t, err.Error(), "classification.yaml")
}
@@ -0,0 +1,34 @@
package api_test
import (
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/mathiasbq/hyperguild/ingestion/internal/api"
)
// hyperguild#178: an unreadable directory under wiki/ made the link check
// fail and brain_write refuse the note, losing the learning. The note is now
// written with its links as given.
func TestWriteNoteKeepsTheLearningWhenTheLinkCheckCannotIndex(t *testing.T) {
if os.Geteuid() == 0 {
t.Skip("root ignores directory permissions")
}
brain := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki", "w", "facts"), 0o755))
require.NoError(t, os.WriteFile(filepath.Join(brain, "wiki", "w", "facts", "real.md"), []byte("x"), 0o644))
locked := filepath.Join(brain, "wiki", "other", "locked")
require.NoError(t, os.MkdirAll(locked, 0o755))
require.NoError(t, os.Chmod(locked, 0o000))
t.Cleanup(func() { _ = os.Chmod(locked, 0o755) })
rel, err := api.WriteNote(brain, api.WriteNoteOptions{Wing: "w", Hall: "facts", Filename: "n", Content: "learning [[real]] and [[gone]]"})
require.NoError(t, err)
got, err := os.ReadFile(filepath.Join(brain, filepath.FromSlash(rel)))
require.NoError(t, err)
assert.Contains(t, string(got), "[[gone]]", "links kept as given when the index is partial")
}
+6 -1
View File
@@ -47,7 +47,12 @@ var (
func StripUnresolvedLinks(brainDir, content string) (string, []string, error) {
index, err := entryIndex(brainDir)
if err != nil {
return "", nil, err
// A partial index cannot tell an invented link from one into the
// part it could not read, so unwrap nothing, and do not refuse the
// write either: this runs before every brain_write, and a refused
// write is a lost learning (hyperguild#178).
slog.Warn("link check skipped: cannot index the brain", "err", err)
return content, nil, nil
}
if len(index) == 0 {
return content, nil, nil
@@ -0,0 +1,41 @@
package brain_test
import (
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/mathiasbq/hyperguild/ingestion/internal/brain"
)
// hyperguild#178: StripUnresolvedLinks runs before every brain_write and
// brain_update. An unreadable directory under knowledge/ or wiki/ made it
// error, the write was refused and the learning lost. When the link index
// cannot be built, the content is now returned unchanged (no link is
// unwrapped, none is invented) and no error stops the write.
func TestStripUnresolvedLinksKeepsContentWhenTheIndexCannotBeBuilt(t *testing.T) {
if os.Geteuid() == 0 {
t.Skip("root ignores directory permissions")
}
b := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(b, "wiki", "w", "facts"), 0o755))
require.NoError(t, os.WriteFile(filepath.Join(b, "wiki", "w", "facts", "real.md"), []byte("x"), 0o644))
locked := filepath.Join(b, "wiki", "other", "locked")
require.NoError(t, os.MkdirAll(locked, 0o755))
require.NoError(t, os.Chmod(locked, 0o000))
t.Cleanup(func() { _ = os.Chmod(locked, 0o755) })
in := "learning [[real]] and [[gone]]"
out, unlinked, err := brain.StripUnresolvedLinks(b, in)
require.NoError(t, err)
assert.Equal(t, in, out, "content unchanged: no link unwrapped on a partial index")
assert.Empty(t, unlinked)
require.NoError(t, os.Chmod(locked, 0o755))
out, _, err = brain.StripUnresolvedLinks(b, in)
require.NoError(t, err)
assert.NotContains(t, out, "[[gone]]", "positive control: with a readable tree the strip runs")
}
+21
View File
@@ -243,6 +243,27 @@ func (b *Brain) RealParent(rel string) error {
return b.realDir(path.Dir(rel))
}
// PutFile opens the brain dir as a root and calls PutRegular, for one-off
// writers that hold no Brain.
func PutFile(brainDir, rel string, data []byte) error {
b, err := Open(brainDir)
if err != nil {
return err
}
defer func() { _ = b.Close() }()
return b.PutRegular(rel, data)
}
// AppendFile opens the brain dir as a root and calls AppendRegular.
func AppendFile(brainDir, rel string, data []byte) error {
b, err := Open(brainDir)
if err != nil {
return err
}
defer func() { _ = b.Close() }()
return b.AppendRegular(rel, data)
}
// mkdirReal makes sure every component of rel exists as a real directory,
// creating missing ones through the root; an existing component that is
// not a real directory is ErrNotRegular.
+1 -4
View File
@@ -7,8 +7,6 @@ import (
"fmt"
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
"io/fs"
"os"
"path/filepath"
"strings"
"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
@@ -90,8 +88,7 @@ func BackfillRefs(ctx context.Context, brainDir string) (int, error) {
}
for relPath, page := range pending {
dest := filepath.Join(brainDir, filepath.FromSlash(relPath))
if err := os.WriteFile(dest, []byte(page.Content), 0o644); err != nil {
if err := bfs.PutRegular(relPath, []byte(page.Content)); err != nil {
return 0, fmt.Errorf("write %s: %w", relPath, err)
}
}
+14 -7
View File
@@ -9,8 +9,6 @@ import (
"fmt"
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
"io/fs"
"os"
"path/filepath"
"strings"
"time"
@@ -128,10 +126,6 @@ func buildAndWrite(ctx context.Context, rawPages []RawPage, sourceSlug, date, br
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)
}
content, conflicts, err := reviseOrCreate(brainDir, page)
if err != nil {
return Result{}, err
@@ -150,7 +144,9 @@ func buildAndWrite(ctx context.Context, rawPages []RawPage, sourceSlug, date, br
if err != nil {
return Result{}, fmt.Errorf("stamp %s: %w", page.Path, err)
}
if err := os.WriteFile(dest, []byte(stamped), 0o644); err != nil {
// Written through the brain root, never through a symlinked
// directory or page (hyperguild#158).
if err := writeBrainFile(brainDir, page.Path, []byte(stamped)); err != nil {
return Result{}, fmt.Errorf("write %s: %w", page.Path, err)
}
}
@@ -201,6 +197,17 @@ func readSourcePage(brainDir, sourceSlug string) string {
return string(raw)
}
// writeBrainFile creates or replaces one brain-relative file through the
// brain root (hyperguild#158).
func writeBrainFile(brainDir, rel string, data []byte) error {
bfs, err := brainfs.Open(brainDir)
if err != nil {
return err
}
defer func() { _ = bfs.Close() }()
return bfs.PutRegular(rel, data)
}
// readBrainFile reads one brain-relative file through the brain root,
// regular files only (hyperguild#157).
func readBrainFile(brainDir, rel string) ([]byte, error) {
+25
View File
@@ -165,3 +165,28 @@ func TestBackfillRefsDoesNotCopyAPageSwappedInBehindASymlink(t *testing.T) {
require.Contains(t, read(), "[[s|S]]", "positive control: the regular page gets the source ref")
brainfstest.AssertNoLeakFrom(t, page, inside, target, 3*time.Second, read)
}
// hyperguild#158: BackfillRefs read a regular concept page, a symlink could
// be swapped in, and os.WriteFile then followed it and overwrote the link's
// target. The target is not restored between rounds here, so any
// write-through shows.
func TestBackfillRefsNeverWritesThroughAPageSwappedForASymlink(t *testing.T) {
brain := t.TempDir()
mkdirs(t, brain, "wiki/sources", "wiki/concepts", "raw")
require.NoError(t, os.WriteFile(filepath.Join(brain, "wiki", "sources", "s.md"), []byte("---\ntitle: S\n---\n[[c|C]]\n"), 0o644))
page := filepath.Join(brain, "wiki", "concepts", "c.md")
target := filepath.Join(brain, "raw", "secret.md")
require.NoError(t, os.WriteFile(target, []byte("untouched"), 0o644))
inside := "---\ntitle: C\n---\nbody\n"
require.NoError(t, os.WriteFile(page, []byte(inside), 0o644))
brainfstest.StartSwap(t, page, inside, target, false)
ok := 0
for deadline := time.Now().Add(2 * time.Second); time.Now().Before(deadline); {
if _, err := BackfillRefs(context.Background(), brain); err == nil {
ok++
}
}
got, _ := os.ReadFile(target)
assert.Equal(t, "untouched", string(got), "BackfillRefs wrote through a swapped-in symlink")
assert.Positive(t, ok, "positive control: some backfills ran")
}
@@ -0,0 +1,104 @@
package symlinkguard
import (
"context"
"net"
"os"
"path/filepath"
"syscall"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// hyperguild#179: the tripwire looked only for symlinks, so a FIFO (or
// socket) in the brain passed it. A FIFO at classification.yaml then made
// startup exit; at a note path it could hang readers that skip the handle
// check.
func TestScanReportsFIFOsAndSocketsAsSpecialFiles(t *testing.T) {
brain := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki", "w"), 0o755))
require.NoError(t, syscall.Mkfifo(filepath.Join(brain, "classification.yaml"), 0o644))
require.NoError(t, syscall.Mkfifo(filepath.Join(brain, "wiki", "w", "f.md"), 0o644))
l, err := net.Listen("unix", filepath.Join(brain, "s.sock"))
require.NoError(t, err)
defer func() { _ = l.Close() }()
require.NoError(t, os.WriteFile(filepath.Join(brain, "wiki", "w", "n.md"), []byte("n"), 0o644))
r, err := Scan(brain)
require.NoError(t, err)
assert.Equal(t, []string{"classification.yaml", "s.sock", "wiki/w/f.md"}, r.Special)
assert.False(t, r.Clean())
assert.Contains(t, r.String(), "special file")
}
// Watch removes a FIFO as it removes symlinks, and leaves a regular file
// (which Scan never reports) alone.
func TestWatchRemovesAFIFOAndLeavesAnUnreportedRegularFile(t *testing.T) {
brain := t.TempDir()
fifo := filepath.Join(brain, "f.md")
require.NoError(t, syscall.Mkfifo(fifo, 0o644))
regular := filepath.Join(brain, "n.md")
require.NoError(t, os.WriteFile(regular, []byte("n"), 0o644))
n := &recNotifier{}
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go Watch(ctx, brain, 10*time.Millisecond, n)
require.Eventually(t, func() bool {
_, err := os.Lstat(fifo)
return os.IsNotExist(err)
}, 2*time.Second, 10*time.Millisecond, "the FIFO is removed")
require.Eventually(t, func() bool { return n.count() >= 1 }, 2*time.Second, 10*time.Millisecond)
b, err := os.ReadFile(regular)
require.NoError(t, err)
assert.Equal(t, "n", string(b))
n.mu.Lock()
defer n.mu.Unlock()
assert.Contains(t, n.msgs[0], "f.md")
}
// removeSpecial re-checks the type: a path that is a regular file or a
// directory at the re-check is not removed. (A swap between the re-check and
// the unlink can still remove one; Linux has no conditional unlink. The same
// window exists in removeSymlinks.)
func TestRemoveSpecialRefusesRegularFilesAndDirectories(t *testing.T) {
brain := t.TempDir()
require.NoError(t, os.WriteFile(filepath.Join(brain, "n.md"), []byte("n"), 0o644))
require.NoError(t, os.MkdirAll(filepath.Join(brain, "d"), 0o755))
require.NoError(t, syscall.Mkfifo(filepath.Join(brain, "f.md"), 0o644))
removed, failed := removeSpecial(brain, []string{"n.md", "d", "f.md"})
assert.Equal(t, []string{"f.md"}, removed)
assert.Equal(t, []string{"n.md", "d"}, failed)
_, err := os.Stat(filepath.Join(brain, "n.md"))
assert.NoError(t, err)
}
// A special file Watch cannot remove (its directory is read-only) stays
// reported: the persistent-finding alert names it.
func TestWatchReportsASpecialFileItCannotRemove(t *testing.T) {
if os.Geteuid() == 0 {
t.Skip("root ignores directory permissions")
}
brain := t.TempDir()
ro := filepath.Join(brain, "ro")
require.NoError(t, os.MkdirAll(ro, 0o755))
require.NoError(t, syscall.Mkfifo(filepath.Join(ro, "f.md"), 0o644))
require.NoError(t, os.Chmod(ro, 0o555))
t.Cleanup(func() { _ = os.Chmod(ro, 0o755) })
n := &recNotifier{}
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go Watch(ctx, brain, 10*time.Millisecond, n)
require.Eventually(t, func() bool { return n.count() >= 1 }, 2*time.Second, 10*time.Millisecond)
_, err := os.Lstat(filepath.Join(ro, "f.md"))
require.NoError(t, err, "the FIFO could not be removed")
n.mu.Lock()
defer n.mu.Unlock()
assert.Contains(t, n.msgs[0], "ro/f.md")
assert.Contains(t, n.msgs[0], "special file")
for _, m := range n.msgs {
assert.NotContains(t, m, "removed", "a file it could not remove was reported as removed")
}
}
@@ -46,10 +46,16 @@ type Notifier interface {
type Result struct {
Symlinks []string
Unreadable []string
// Special holds FIFOs, sockets and devices (hyperguild#179): a reader
// that opens one by path can hang, and a FIFO at classification.yaml
// stops startup.
Special []string
}
// Clean reports whether the scan found nothing to act on.
func (r Result) Clean() bool { return len(r.Symlinks) == 0 && len(r.Unreadable) == 0 }
func (r Result) Clean() bool {
return len(r.Symlinks) == 0 && len(r.Unreadable) == 0 && len(r.Special) == 0
}
// String describes the findings for a log line or alert. Paths are quoted, so
// a name containing a newline cannot blur two findings together.
@@ -59,6 +65,9 @@ func (r Result) String() string {
if len(r.Symlinks) > 0 {
parts = append(parts, fmt.Sprintf("%d symlink(s): %s", len(r.Symlinks), q(r.Symlinks)))
}
if len(r.Special) > 0 {
parts = append(parts, fmt.Sprintf("%d special file(s) (FIFO, socket or device; delete them): %s", len(r.Special), q(r.Special)))
}
if len(r.Unreadable) > 0 {
parts = append(parts, fmt.Sprintf("%d unreadable dir(s): %s", len(r.Unreadable), q(r.Unreadable)))
}
@@ -113,12 +122,16 @@ func Scan(brainDir string) (Result, error) {
if d.IsDir() && p == rootGit {
return filepath.SkipDir
}
if d.Type()&os.ModeSymlink != 0 {
switch {
case d.Type()&os.ModeSymlink != 0:
r.Symlinks = append(r.Symlinks, rel)
case !d.IsDir() && !d.Type().IsRegular():
r.Special = append(r.Special, rel)
}
return nil
})
sort.Strings(r.Symlinks)
sort.Strings(r.Special)
sort.Strings(r.Unreadable)
if walkErr != nil {
// Only the root's own error reaches here (deeper errors are recorded
@@ -182,14 +195,20 @@ func Watch(ctx context.Context, brainDir string, interval time.Duration, n Notif
q.push(fmt.Sprintf("brain symlink tripwire (hyperguild#157): removed %d symlink(s) from the brain dir: %s",
len(removed), Result{}.quoted(removed)))
}
key = Result{Symlinks: failed, Unreadable: r.Unreadable}.String()
sRemoved, sFailed := removeSpecial(brainDir, r.Special)
if len(sRemoved) > 0 {
slog.Error("brain symlink tripwire removed special files", "count", len(sRemoved))
q.push(fmt.Sprintf("brain symlink tripwire (hyperguild#179): removed %d special file(s) (FIFO, socket or device) from the brain dir: %s",
len(sRemoved), Result{}.quoted(sRemoved)))
}
key = Result{Symlinks: failed, Unreadable: r.Unreadable, Special: sFailed}.String()
}
if key != reported {
reported = key
if key != "" {
slog.Error("brain symlink tripwire", "finding", key)
q.push("brain symlink tripwire (hyperguild#157): " + key +
". Readers may follow symlinks out of the brain; fix them.")
q.push("brain symlink tripwire (hyperguild#157, #179): " + key +
". Symlinks can lead readers out of the brain and special files can hang them; remove them.")
}
}
}
@@ -322,6 +341,40 @@ func permanent(err error) bool {
return errors.As(err, &p) && p.Permanent()
}
// removeSpecial unlinks each brain-relative FIFO, socket or device through
// an os.Root on the brain dir, after re-checking that it is still one: a
// path that is a regular file, a directory or a symlink at the re-check is
// left alone and reported as failed. The re-check narrows, but cannot close,
// the window before the unlink (Linux has no conditional unlink); the same
// window exists in removeSymlinks, and only a local writer can use it.
func removeSpecial(brainDir string, rels []string) (removed, failed []string) {
if len(rels) == 0 {
return nil, nil
}
resolved, err := filepath.EvalSymlinks(brainDir)
if err != nil {
return nil, rels
}
root, err := os.OpenRoot(resolved)
if err != nil {
return nil, rels
}
defer func() { _ = root.Close() }()
for _, rel := range rels {
fi, err := root.Lstat(rel)
if err != nil || fi.IsDir() || fi.Mode().IsRegular() || fi.Mode()&os.ModeSymlink != 0 {
failed = append(failed, rel)
continue
}
if err := root.Remove(rel); err != nil {
failed = append(failed, rel)
continue
}
removed = append(removed, rel)
}
return removed, failed
}
// removeSymlinks unlinks each brain-relative symlink through an os.Root on
// the brain dir, after re-checking it is still a symlink. Removing a symlink
// never touches its target. It returns what was removed and what was not.
+22 -33
View File
@@ -12,6 +12,7 @@ import (
"time"
"unicode"
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
"github.com/mathiasbq/hyperguild/ingestion/internal/extract"
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
)
@@ -145,16 +146,12 @@ func processFile(ctx context.Context, cfg Config, root *os.Root, rawDir, path, d
_, runErr := pipeline.Run(ctx, cfg.Pipeline, cfg.BrainDir, content, source, false)
if runErr != nil {
// Copy to failed/ and leave a .failed marker so we don't retry.
failedDir := filepath.Join(cfg.BrainDir, "raw", "failed")
if mkErr := os.MkdirAll(failedDir, 0o755); mkErr != nil {
return fmt.Errorf("mkdir failed dir: %w", mkErr)
}
dest := filepath.Join(failedDir, filename)
if cpErr := copyFromRoot(root, rel, dest); cpErr != nil {
// Copy to failed/ and leave a .failed marker so we don't retry. Both
// written through the brain root (hyperguild#158).
if cpErr := copyFromRoot(root, rel, cfg.BrainDir, "raw/failed/"+filename); cpErr != nil {
return fmt.Errorf("copy to failed: %w", cpErr)
}
if mkErr := os.WriteFile(path+".failed", []byte(runErr.Error()), 0o644); mkErr != nil {
if mkErr := putBrainFile(cfg.BrainDir, "raw/"+filepath.ToSlash(rel)+".failed", []byte(runErr.Error())); mkErr != nil {
slog.Error("watcher: failed to write .failed marker", "error", mkErr)
}
@@ -168,21 +165,18 @@ func processFile(ctx context.Context, cfg Config, root *os.Root, rawDir, path, d
}
// Copy to processed/YYYY-MM-DD/ and leave a .processed marker so we don't re-ingest.
processedDir := filepath.Join(cfg.BrainDir, "raw", "processed", date)
if err := os.MkdirAll(processedDir, 0o755); err != nil {
return fmt.Errorf("mkdir processed dir: %w", err)
}
dest := filepath.Join(processedDir, filename)
if _, err := os.Stat(dest); err == nil {
// Written through the brain root (hyperguild#158).
dest := "raw/processed/" + date + "/" + filename
if _, err := os.Lstat(filepath.Join(cfg.BrainDir, filepath.FromSlash(dest))); err == nil {
// Archive copy already exists; append timestamp to avoid overwriting.
ext := filepath.Ext(filename)
base := strings.TrimSuffix(filename, ext)
dest = filepath.Join(processedDir, base+"-"+time.Now().UTC().Format("150405")+ext)
dest = "raw/processed/" + date + "/" + base + "-" + time.Now().UTC().Format("150405") + ext
}
if err := copyFromRoot(root, rel, dest); err != nil {
if err := copyFromRoot(root, rel, cfg.BrainDir, dest); err != nil {
return fmt.Errorf("copy to processed: %w", err)
}
if err := os.WriteFile(path+".processed", []byte(date), 0o644); err != nil {
if err := putBrainFile(cfg.BrainDir, "raw/"+filepath.ToSlash(rel)+".processed", []byte(date)); err != nil {
slog.Error("watcher: failed to write .processed marker", "error", err)
}
@@ -214,23 +208,22 @@ func appendWatcherLog(brainDir, filename string, runErr error, date string) erro
entry := fmt.Sprintf("## %s — watcher error\n\n- **File:** %s\n- **Error:** %s\n\n",
date, filename, runErr.Error())
logPath := filepath.Join(brainDir, "log.md")
f, err := os.OpenFile(logPath, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0o644)
if err != nil {
return fmt.Errorf("open log: %w", err)
}
if _, err = f.WriteString(entry); err != nil {
f.Close() //nolint:errcheck
if err := brainfs.AppendFile(brainDir, "log.md", []byte(entry)); err != nil {
return fmt.Errorf("write log: %w", err)
}
return f.Close()
return nil
}
// putBrainFile creates or replaces a brain-relative file through the brain
// root, never through a symlinked directory or file (hyperguild#158).
func putBrainFile(brainDir, rel string, data []byte) error {
return brainfs.PutFile(brainDir, rel, data)
}
// copyFromRoot archives a raw/ file read through the root, refusing anything
// that is not a regular file, so a swapped-in symlink cannot copy an outside
// file into raw/processed/ or raw/failed/ (hyperguild#153).
func copyFromRoot(root *os.Root, rel, dst string) error {
func copyFromRoot(root *os.Root, rel, brainDir, dstRel string) error {
fi, err := root.Lstat(rel)
if err != nil {
return err
@@ -243,13 +236,9 @@ func copyFromRoot(root *os.Root, rel, dst string) error {
return err
}
defer func() { _ = in.Close() }()
out, err := os.Create(dst)
data, err := io.ReadAll(in)
if err != nil {
return err
}
if _, err := io.Copy(out, in); err != nil {
_ = out.Close()
return err
}
return out.Close()
return putBrainFile(brainDir, dstRel, data)
}
@@ -0,0 +1,66 @@
package watcher
import (
"context"
"encoding/json"
"errors"
"os"
"path/filepath"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
)
func okPipeline() pipeline.Config {
return pipeline.Config{Complete: func(context.Context, string, string) (string, error) {
b, _ := json.Marshal([]pipeline.RawPage{{Title: "X", Type: "source", Subtype: "article", Content: "## S\n\nx\n"}})
return string(b), nil
}, Schema: "# Schema"}
}
func failingPipeline() pipeline.Config {
return pipeline.Config{Complete: func(context.Context, string, string) (string, error) {
return "", errors.New("model down")
}, Schema: "# Schema"}
}
// hyperguild#158: the watcher wrote the archive copy under raw/processed or
// raw/failed, and its log.md entry, by path, so a symlinked archive
// directory or log redirected the write elsewhere in the brain or outside
// it. (A pre-planted marker symlink makes the watcher skip the note, so the
// marker write itself is reachable only by a race.)
func TestProcessDirDoesNotWriteThroughASymlinkedArchiveDirOrLog(t *testing.T) {
for name, pcfg := range map[string]pipeline.Config{"processed": okPipeline(), "failed": failingPipeline()} {
t.Run(name, func(t *testing.T) {
brainDir := setupBrainDir(t)
outside := t.TempDir()
victim := filepath.Join(brainDir, "wiki", "concepts", "v.md")
require.NoError(t, os.WriteFile(victim, []byte("untouched"), 0o644))
require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "n.md"), []byte("note"), 0o644))
require.NoError(t, os.Symlink(outside, filepath.Join(brainDir, "raw", name)))
if name == "failed" {
require.NoError(t, os.Symlink(filepath.Join("wiki", "concepts", "v.md"), filepath.Join(brainDir, "log.md")))
}
_ = processDir(context.Background(), Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: pcfg}, "2026-10-05")
got, _ := os.ReadFile(victim)
assert.Equal(t, "untouched", string(got), "the log was written through a symlink")
ents, _ := os.ReadDir(outside)
assert.Empty(t, ents, "the archive copy was written outside the brain")
})
}
}
func TestProcessDirWritesMarkersAndArchiveInRealDirectories(t *testing.T) {
brainDir := setupBrainDir(t)
require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "n.md"), []byte("note"), 0o644))
errs := processDir(context.Background(), Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: okPipeline()}, "2026-10-05")
assert.Empty(t, errs)
_, err := os.Stat(filepath.Join(brainDir, "raw", "n.md.processed"))
assert.NoError(t, err, "positive control: marker written")
_, err = os.Stat(filepath.Join(brainDir, "raw", "processed", "2026-10-05", "n.md"))
assert.NoError(t, err, "positive control: archive copy written")
}