From 77c44f298c60d69f17d436ad77f74408b3089130 Mon Sep 17 00:00:00 2001 From: Mathias Date: Mon, 5 Oct 2026 22:54:53 +0200 Subject: [PATCH 1/3] fix: pipeline, backfill, watcher and archive writes go through the brain root (#158 part B) 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 --- ingestion/cmd/server/main.go | 13 ++-- ingestion/internal/brainfs/brainfs.go | 21 ++++++ ingestion/internal/pipeline/backfill.go | 5 +- ingestion/internal/pipeline/pipeline.go | 21 ++++-- ingestion/internal/pipeline/root_test.go | 25 +++++++ ingestion/internal/watcher/watcher.go | 55 +++++++--------- .../internal/watcher/writes_redirect_test.go | 66 +++++++++++++++++++ 7 files changed, 158 insertions(+), 48 deletions(-) create mode 100644 ingestion/internal/watcher/writes_redirect_test.go diff --git a/ingestion/cmd/server/main.go b/ingestion/cmd/server/main.go index db721e4..62dd95a 100644 --- a/ingestion/cmd/server/main.go +++ b/ingestion/cmd/server/main.go @@ -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) diff --git a/ingestion/internal/brainfs/brainfs.go b/ingestion/internal/brainfs/brainfs.go index f7f423d..d8ebeac 100644 --- a/ingestion/internal/brainfs/brainfs.go +++ b/ingestion/internal/brainfs/brainfs.go @@ -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. diff --git a/ingestion/internal/pipeline/backfill.go b/ingestion/internal/pipeline/backfill.go index 1217f57..8774f9a 100644 --- a/ingestion/internal/pipeline/backfill.go +++ b/ingestion/internal/pipeline/backfill.go @@ -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) } } diff --git a/ingestion/internal/pipeline/pipeline.go b/ingestion/internal/pipeline/pipeline.go index c368d7f..76f97fb 100644 --- a/ingestion/internal/pipeline/pipeline.go +++ b/ingestion/internal/pipeline/pipeline.go @@ -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) { diff --git a/ingestion/internal/pipeline/root_test.go b/ingestion/internal/pipeline/root_test.go index b9f7b6c..d6f4fba 100644 --- a/ingestion/internal/pipeline/root_test.go +++ b/ingestion/internal/pipeline/root_test.go @@ -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") +} diff --git a/ingestion/internal/watcher/watcher.go b/ingestion/internal/watcher/watcher.go index b5c41b3..069590f 100644 --- a/ingestion/internal/watcher/watcher.go +++ b/ingestion/internal/watcher/watcher.go @@ -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) } diff --git a/ingestion/internal/watcher/writes_redirect_test.go b/ingestion/internal/watcher/writes_redirect_test.go new file mode 100644 index 0000000..ed46375 --- /dev/null +++ b/ingestion/internal/watcher/writes_redirect_test.go @@ -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") +} -- 2.54.0 From 1a2a93d2f486e941ad0f00fc61e0d384d3293f1f Mon Sep 17 00:00:00 2001 From: Mathias Date: Mon, 5 Oct 2026 23:40:19 +0200 Subject: [PATCH 2/3] fix(watcher): refusals end in a terminal state; pin every converted writer (#158) Review round 1 on PR #195: - A refused marker or archive write left no marker, so the note was reprocessed every interval (archive copies piling up; an LLM call per round on the failure path). The marker check now uses Lstat (any entry at the marker path counts, so a dangling marker link skips the note instead of looping), and a note whose archive copy or marker write is refused is remembered (path, size, mtime) and not retried until it changes. - cleanRel no longer refuses a backslash: it is a legal filename byte on Linux, not a traversal, and a raw note named with one was never archived or marked. - Tests now reach every converted writer: the log.md append (real raw/failed so the log is reached, symlinked log.md), a dangling marker link, the refused-retry loop with a positive control, a backslash name, a buildAndWrite swap race, and the claude-session archive with in-brain and outside symlinked archive dirs. The stale lint allowlist entry for appendWatcherLog is removed. Co-Authored-By: Claude Opus 5.5 --- ingestion/cmd/server/main_test.go | 24 ++++++ ingestion/internal/brainfs/brainfs.go | 2 +- ingestion/internal/extract/callsites_test.go | 1 - ingestion/internal/pipeline/root_test.go | 25 +++++++ ingestion/internal/watcher/watcher.go | 52 ++++++++++++- .../internal/watcher/writes_redirect_test.go | 74 +++++++++++++++++-- 6 files changed, 169 insertions(+), 9 deletions(-) diff --git a/ingestion/cmd/server/main_test.go b/ingestion/cmd/server/main_test.go index 4d1236d..b52f0c7 100644 --- a/ingestion/cmd/server/main_test.go +++ b/ingestion/cmd/server/main_test.go @@ -76,3 +76,27 @@ func TestAlertingWarnings(t *testing.T) { }) } } + +// hyperguild#158: the claude-session archive was written with os.MkdirAll + +// os.WriteFile by path, so a symlinked archive directory redirected it. +func TestClaudeSinkDoesNotWriteThroughASymlinkedArchiveDir(t *testing.T) { + for name, mk := range map[string]func(t *testing.T, dir string) (link, target string){ + "outside": func(t *testing.T, _ string) (string, string) { o := t.TempDir(); return o, o }, + "in-brain": func(t *testing.T, dir string) (string, string) { + require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw"), 0o755)) + return filepath.Join("..", "raw"), filepath.Join(dir, "raw") + }, + } { + t.Run(name, func(t *testing.T) { + dir := t.TempDir() + link, target := mk(t, dir) + require.NoError(t, os.Symlink(link, filepath.Join(dir, "archive"))) + sink := &claudeSink{brainDir: dir, logger: slog.New(slog.NewTextHandler(os.Stderr, nil))} + err := sink.Ingest(context.Background(), claudewatcher.Batch{Host: "koala", SessionID: "abc", + Turns: []claudewatcher.Turn{{Type: "assistant", Content: "x"}}}) + assert.Error(t, err) + ents, _ := os.ReadDir(target) + assert.Empty(t, ents, "the archive was written at the link's target") + }) + } +} diff --git a/ingestion/internal/brainfs/brainfs.go b/ingestion/internal/brainfs/brainfs.go index d8ebeac..f083f50 100644 --- a/ingestion/internal/brainfs/brainfs.go +++ b/ingestion/internal/brainfs/brainfs.go @@ -109,7 +109,7 @@ func (b *Brain) ReadDirRegular(relDir string) ([]string, error) { // after following a symlink, and a ".." after a symlinked directory would // otherwise pass the check and redirect the read or write. func cleanRel(rel string) error { - if rel == "" || path.Clean(rel) != rel || !filepath.IsLocal(rel) || strings.Contains(rel, "\\") { + if rel == "" || path.Clean(rel) != rel || !filepath.IsLocal(rel) { return fmt.Errorf("%q: not a clean brain-relative path: %w", rel, ErrNotRegular) } return nil diff --git a/ingestion/internal/extract/callsites_test.go b/ingestion/internal/extract/callsites_test.go index c544e2e..293ec54 100644 --- a/ingestion/internal/extract/callsites_test.go +++ b/ingestion/internal/extract/callsites_test.go @@ -88,7 +88,6 @@ func TestNoPackageReferencesExtractTextOutsideExtract(t *testing.T) { // osOpenAllowed names the functions in guarded files that may call os.Open* // on a path that is not a raw/ read. var osOpenAllowed = map[string]bool{ - "internal/watcher/watcher.go:appendWatcherLog": true, // ingest log append, not a raw/ read // Text reads by path; outside this package only TextIn's temp copy reaches // it (TestNoPackageReferencesExtractTextOutsideExtract enforces that). "internal/extract/extract.go:Text": true, diff --git a/ingestion/internal/pipeline/root_test.go b/ingestion/internal/pipeline/root_test.go index d6f4fba..a727e2d 100644 --- a/ingestion/internal/pipeline/root_test.go +++ b/ingestion/internal/pipeline/root_test.go @@ -190,3 +190,28 @@ func TestBackfillRefsNeverWritesThroughAPageSwappedForASymlink(t *testing.T) { assert.Equal(t, "untouched", string(got), "BackfillRefs wrote through a swapped-in symlink") assert.Positive(t, ok, "positive control: some backfills ran") } + +// hyperguild#158: buildAndWrite wrote each page with os.WriteFile by path, so +// a page read as regular and swapped for a symlink before the write was +// written through. The target is not restored between rounds, so any +// write-through shows. +func TestBuildAndWriteNeverWritesThroughAPageSwappedForASymlink(t *testing.T) { + brain := t.TempDir() + mkdirs(t, brain, "wiki/sources", "wiki/concepts", "wiki/entities", "raw") + page := filepath.Join(brain, "wiki", "concepts", "zq-concept.md") + target := filepath.Join(brain, "raw", "secret.md") + require.NoError(t, os.WriteFile(target, []byte("untouched"), 0o644)) + inside := "---\ntitle: Zq Concept\n---\nbody\n" + require.NoError(t, os.WriteFile(page, []byte(inside), 0o644)) + pages := []RawPage{{Title: "Zq Concept", Type: "concept", Content: "## About\n\nmore\n"}} + brainfstest.StartSwap(t, page, inside, target, false) + ok := 0 + for deadline := time.Now().Add(2 * time.Second); time.Now().Before(deadline); { + if _, err := RunRaw(context.Background(), brain, "zq source", pages, false); err == nil { + ok++ + } + } + got, _ := os.ReadFile(target) + assert.Equal(t, "untouched", string(got), "buildAndWrite wrote through a swapped-in symlink") + assert.Positive(t, ok, "positive control: some runs wrote the page") +} diff --git a/ingestion/internal/watcher/watcher.go b/ingestion/internal/watcher/watcher.go index 069590f..348eb47 100644 --- a/ingestion/internal/watcher/watcher.go +++ b/ingestion/internal/watcher/watcher.go @@ -3,12 +3,14 @@ package watcher import ( "context" + "errors" "fmt" "io" "log/slog" "os" "path/filepath" "strings" + "sync" "time" "unicode" @@ -110,14 +112,28 @@ func processDir(ctx context.Context, cfg Config, date string) []error { } // Skip files that have already been processed or permanently failed. - if _, err := os.Stat(path + ".processed"); err == nil { + // Any entry at the marker path counts (Lstat, not Stat): a dangling + // marker symlink made os.Stat report nothing and the note was + // reprocessed every interval (hyperguild#158). + if _, err := os.Lstat(path + ".processed"); err == nil { return nil } - if _, err := os.Stat(path + ".failed"); err == nil { + if _, err := os.Lstat(path + ".failed"); err == nil { + return nil + } + // A note whose archive copy or marker was refused is not retried + // until it changes: a refusal has no marker to stop the next round, + // and each round can cost an LLM call (hyperguild#158). + info, ierr := d.Info() + if ierr == nil && refusedUnchanged(path, info) { return nil } if err := processFile(ctx, cfg, root, rawDir, path, date); err != nil { + if ierr == nil && errors.Is(err, brainfs.ErrNotRegular) { + rememberRefused(path, info) + slog.Error("watcher: note refused; not retried until it changes", "file", filepath.Base(path), "error", err) + } errs = append(errs, fmt.Errorf("process %s: %w", filepath.Base(path), err)) } return nil @@ -152,6 +168,9 @@ func processFile(ctx context.Context, cfg Config, root *os.Root, rawDir, path, d return fmt.Errorf("copy to failed: %w", cpErr) } if mkErr := putBrainFile(cfg.BrainDir, "raw/"+filepath.ToSlash(rel)+".failed", []byte(runErr.Error())); mkErr != nil { + if errors.Is(mkErr, brainfs.ErrNotRegular) { + return fmt.Errorf("write .failed marker: %w", mkErr) + } slog.Error("watcher: failed to write .failed marker", "error", mkErr) } @@ -177,6 +196,9 @@ func processFile(ctx context.Context, cfg Config, root *os.Root, rawDir, path, d return fmt.Errorf("copy to processed: %w", err) } if err := putBrainFile(cfg.BrainDir, "raw/"+filepath.ToSlash(rel)+".processed", []byte(date)); err != nil { + if errors.Is(err, brainfs.ErrNotRegular) { + return fmt.Errorf("write .processed marker: %w", err) + } slog.Error("watcher: failed to write .processed marker", "error", err) } @@ -184,6 +206,32 @@ func processFile(ctx context.Context, cfg Config, root *os.Root, rawDir, path, d return nil } +// refused remembers notes whose archive copy or marker write was refused, +// by path, with the size and mtime they had, for the life of the process. +var refused sync.Map + +type refusedStamp struct { + size int64 + mtime time.Time +} + +func rememberRefused(path string, info os.FileInfo) { + refused.Store(path, refusedStamp{size: info.Size(), mtime: info.ModTime()}) +} + +func refusedUnchanged(path string, info os.FileInfo) bool { + v, ok := refused.Load(path) + if !ok { + return false + } + st := v.(refusedStamp) + if st.size == info.Size() && st.mtime.Equal(info.ModTime()) { + return true + } + refused.Delete(path) + return false +} + // deriveSource turns a filename into a human-readable source name. // "shape-up-book.md" → "Shape Up Book" func deriveSource(filename string) string { diff --git a/ingestion/internal/watcher/writes_redirect_test.go b/ingestion/internal/watcher/writes_redirect_test.go index ed46375..fe4efed 100644 --- a/ingestion/internal/watcher/writes_redirect_test.go +++ b/ingestion/internal/watcher/writes_redirect_test.go @@ -33,7 +33,7 @@ func failingPipeline() pipeline.Config { // 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) { +func TestProcessDirDoesNotWriteThroughASymlinkedArchiveDir(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) @@ -42,12 +42,9 @@ func TestProcessDirDoesNotWriteThroughASymlinkedArchiveDirOrLog(t *testing.T) { 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") + assert.Equal(t, "untouched", string(got)) ents, _ := os.ReadDir(outside) assert.Empty(t, ents, "the archive copy was written outside the brain") }) @@ -64,3 +61,70 @@ func TestProcessDirWritesMarkersAndArchiveInRealDirectories(t *testing.T) { _, err = os.Stat(filepath.Join(brainDir, "raw", "processed", "2026-10-05", "n.md")) assert.NoError(t, err, "positive control: archive copy written") } + +// The log.md entry for a failed note is appended through the brain root: with +// a real raw/failed (so the archive copy succeeds and the log is reached), a +// symlinked log.md is not written through. +func TestProcessDirDoesNotAppendTheLogThroughASymlink(t *testing.T) { + brainDir := setupBrainDir(t) + 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(filepath.Join("wiki", "concepts", "v.md"), filepath.Join(brainDir, "log.md"))) + _ = processDir(context.Background(), Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: failingPipeline()}, "2026-10-05") + _, err := os.Stat(filepath.Join(brainDir, "raw", "failed", "n.md")) + require.NoError(t, err, "positive control: the archive copy was written, so the log append was reached") + got, _ := os.ReadFile(victim) + assert.Equal(t, "untouched", string(got), "the log was appended through a symlink") +} + +// A marker path holding anything (here a dangling symlink) counts as a +// marker: the note is skipped and nothing is created at the link's target. +// (os.Stat followed the link, saw nothing, and processed the note again.) +func TestProcessDirTreatsAnyEntryAtTheMarkerPathAsAMarker(t *testing.T) { + brainDir := setupBrainDir(t) + outside := filepath.Join(t.TempDir(), "created") + require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "n.md"), []byte("note"), 0o644)) + require.NoError(t, os.Symlink(outside, filepath.Join(brainDir, "raw", "n.md.processed"))) + calls := 0 + cfg := Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: pipeline.Config{ + Complete: func(context.Context, string, string) (string, error) { calls++; return "[]", nil }, Schema: "# Schema"}} + _ = processDir(context.Background(), cfg, "2026-10-05") + assert.Zero(t, calls, "the note was processed despite an entry at its marker path") + _, err := os.Lstat(outside) + assert.True(t, os.IsNotExist(err), "a file was created at the marker link's target") +} + +// A refused archive copy must not retry every interval: the note is +// remembered and skipped until it changes (a symlinked raw/failed cost one +// LLM call per round before). +func TestProcessDirDoesNotRetryANoteWhoseArchiveCopyIsRefused(t *testing.T) { + brainDir := setupBrainDir(t) + require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "n.md"), []byte("note"), 0o644)) + require.NoError(t, os.Symlink(t.TempDir(), filepath.Join(brainDir, "raw", "failed"))) + calls := 0 + cfg := Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: pipeline.Config{ + Complete: func(context.Context, string, string) (string, error) { calls++; return "", errors.New("model down") }, Schema: "# Schema"}} + for i := 0; i < 3; i++ { + _ = processDir(context.Background(), cfg, "2026-10-05") + } + assert.Equal(t, 1, calls, "the refused note was retried every round") + + // Once the note changes it is tried again. + require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "n.md"), []byte("note, edited"), 0o644)) + future := time.Now().Add(2 * time.Second) + require.NoError(t, os.Chtimes(filepath.Join(brainDir, "raw", "n.md"), future, future)) + _ = processDir(context.Background(), cfg, "2026-10-05") + assert.Equal(t, 2, calls, "positive control: a changed note is tried again") +} + +// A note whose name has a backslash is legal on Linux and must be processed +// (cleanRel refused it, so it was never archived or marked). +func TestProcessDirProcessesANoteWithABackslashInItsName(t *testing.T) { + brainDir := setupBrainDir(t) + require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "a\\b.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", "a\\b.md.processed")) + assert.NoError(t, err) +} -- 2.54.0 From 22d0653b6196146f3f8c1c9e57afeadf83f4b52e Mon Sep 17 00:00:00 2001 From: Mathias Date: Mon, 5 Oct 2026 23:47:24 +0200 Subject: [PATCH 3/3] test(watcher): a marker link planted during the run is refused and not retried (#158) Review round 2 on PR #195: the marker writes had no test, so reverting them to by-path writes, or the refusal to log-only, stayed green. The link is planted from inside the fake model call, between the walk's Lstat and the marker write, for both markers and both an outside and an in-brain relative target; red on all four flips. The marker-entry skip is now checked for .failed too. Also pins cleanRel's acceptance of a backslash as a filename byte in brainfs itself, and stops the buildAndWrite control claiming writes it does not count. Co-Authored-By: Claude Opus 5.5 --- ingestion/internal/brainfs/brainfs_test.go | 17 ++++ ingestion/internal/pipeline/root_test.go | 2 +- .../internal/watcher/writes_redirect_test.go | 78 ++++++++++++++++--- 3 files changed, 85 insertions(+), 12 deletions(-) diff --git a/ingestion/internal/brainfs/brainfs_test.go b/ingestion/internal/brainfs/brainfs_test.go index 0f5570b..5ac4f4d 100644 --- a/ingestion/internal/brainfs/brainfs_test.go +++ b/ingestion/internal/brainfs/brainfs_test.go @@ -529,3 +529,20 @@ func TestCreateRegularCreatesOnlyNewFilesThroughRealDirectories(t *testing.T) { got, _ = os.ReadFile(filepath.Join(dir, "wiki", "new", "facts", "n.md")) assert.Equal(t, "one", string(got)) } + +// On Linux a backslash is an ordinary filename byte, not a separator, so a +// name containing one stays a single in-root component (hyperguild#158: the +// watcher retried such a note forever while cleanRel refused it). +func TestReadAndPutRegularTreatABackslashAsAFilenameByte(t *testing.T) { + dir := t.TempDir() + b, err := Open(dir) + require.NoError(t, err) + defer func() { _ = b.Close() }() + require.NoError(t, b.PutRegular(`a\..\b.md`, []byte("x"))) + got, err := os.ReadFile(filepath.Join(dir, `a\..\b.md`)) + require.NoError(t, err, "the name was not kept as one component") + assert.Equal(t, "x", string(got)) + got, err = b.ReadRegular(`a\..\b.md`) + require.NoError(t, err) + assert.Equal(t, "x", string(got)) +} diff --git a/ingestion/internal/pipeline/root_test.go b/ingestion/internal/pipeline/root_test.go index a727e2d..9b92cde 100644 --- a/ingestion/internal/pipeline/root_test.go +++ b/ingestion/internal/pipeline/root_test.go @@ -213,5 +213,5 @@ func TestBuildAndWriteNeverWritesThroughAPageSwappedForASymlink(t *testing.T) { } got, _ := os.ReadFile(target) assert.Equal(t, "untouched", string(got), "buildAndWrite wrote through a swapped-in symlink") - assert.Positive(t, ok, "positive control: some runs wrote the page") + assert.Positive(t, ok, "positive control: some runs returned without error") } diff --git a/ingestion/internal/watcher/writes_redirect_test.go b/ingestion/internal/watcher/writes_redirect_test.go index fe4efed..dc06188 100644 --- a/ingestion/internal/watcher/writes_redirect_test.go +++ b/ingestion/internal/watcher/writes_redirect_test.go @@ -82,17 +82,73 @@ func TestProcessDirDoesNotAppendTheLogThroughASymlink(t *testing.T) { // marker: the note is skipped and nothing is created at the link's target. // (os.Stat followed the link, saw nothing, and processed the note again.) func TestProcessDirTreatsAnyEntryAtTheMarkerPathAsAMarker(t *testing.T) { - brainDir := setupBrainDir(t) - outside := filepath.Join(t.TempDir(), "created") - require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "n.md"), []byte("note"), 0o644)) - require.NoError(t, os.Symlink(outside, filepath.Join(brainDir, "raw", "n.md.processed"))) - calls := 0 - cfg := Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: pipeline.Config{ - Complete: func(context.Context, string, string) (string, error) { calls++; return "[]", nil }, Schema: "# Schema"}} - _ = processDir(context.Background(), cfg, "2026-10-05") - assert.Zero(t, calls, "the note was processed despite an entry at its marker path") - _, err := os.Lstat(outside) - assert.True(t, os.IsNotExist(err), "a file was created at the marker link's target") + for _, kind := range []string{"processed", "failed"} { + t.Run(kind, func(t *testing.T) { + brainDir := setupBrainDir(t) + outside := filepath.Join(t.TempDir(), "created") + require.NoError(t, os.WriteFile(filepath.Join(brainDir, "raw", "n.md"), []byte("note"), 0o644)) + require.NoError(t, os.Symlink(outside, filepath.Join(brainDir, "raw", "n.md."+kind))) + calls := 0 + cfg := Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: pipeline.Config{ + Complete: func(context.Context, string, string) (string, error) { calls++; return "[]", nil }, Schema: "# Schema"}} + _ = processDir(context.Background(), cfg, "2026-10-05") + assert.Zero(t, calls, "the note was processed despite an entry at its marker path") + _, err := os.Lstat(outside) + assert.True(t, os.IsNotExist(err), "a file was created at the marker link's target") + }) + } +} + +// The marker write itself is reachable while pipeline.Run is in flight +// (in production, an LLM call): a link planted at the marker path then is +// refused, and the note is remembered, so removing the link (as +// symlinkguard does) does not make the watcher call the model again. +func TestProcessDirRefusesAMarkerLinkPlantedDuringTheRunAndDoesNotRetry(t *testing.T) { + for _, kind := range []string{"processed", "failed"} { + for _, target := range []string{"outside", "in-brain"} { + t.Run(kind+"/"+target, func(t *testing.T) { + brainDir := setupBrainDir(t) + raw := filepath.Join(brainDir, "raw") + marker := filepath.Join(raw, "n.md."+kind) + require.NoError(t, os.WriteFile(filepath.Join(raw, "n.md"), []byte("note"), 0o644)) + // The in-brain target is relative, so os.Root itself would + // follow it; only the regular-file check refuses it. + victim := filepath.Join(raw, "victim") + link := filepath.Join(t.TempDir(), "created") + if target == "in-brain" { + require.NoError(t, os.WriteFile(victim, []byte("untouched"), 0o644)) + link = "victim" + } + ok := okPipeline().Complete + calls := 0 + cfg := Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: pipeline.Config{Schema: "# Schema", + Complete: func(ctx context.Context, sys, user string) (string, error) { + calls++ + require.NoError(t, os.Symlink(link, marker)) + if kind == "failed" { + return "", errors.New("model down") + } + return ok(ctx, sys, user) + }}} + for i := 0; i < 3; i++ { + errs := processDir(context.Background(), cfg, "2026-10-05") + if i == 0 { + require.NotEmpty(t, errs, "the planted link was not refused") + } + _ = os.Remove(marker) + } + assert.Equal(t, 1, calls, "the note was retried after its marker write was refused") + if target == "in-brain" { + got, err := os.ReadFile(victim) + require.NoError(t, err) + assert.Equal(t, "untouched", string(got), "the marker was written through the link") + } else { + _, err := os.Lstat(link) + assert.True(t, os.IsNotExist(err), "the marker was written through the link") + } + }) + } + } } // A refused archive copy must not retry every interval: the note is -- 2.54.0