Compare commits

..
Author SHA1 Message Date
mathiasandClaude Opus 5.5 2f8b03fe15 fix(linkcheck): keep the write when the link index cannot be built (#178)
CI / Mirror to GitHub (pull_request) Skipped
CI / Lint / Test / Vet (pull_request) Successful in 1m13s
StripUnresolvedLinks runs before every brain_write and brain_update. Any
walk error below a linked tree's root (e.g. one unreadable subdirectory)
made it return an error, and the write was refused: the learning was
lost. Already true on main.

It now logs a warning and returns the content unchanged: a partial index
cannot tell an invented link from one into the unreadable part, so it
unwraps nothing (never inventing a resolution) and the note is written
with its links as given.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-05 22:44:45 +02:00
26 changed files with 139 additions and 1213 deletions
+4 -9
View File
@@ -17,7 +17,6 @@ import (
"github.com/mathiasbq/hyperguild/ingestion/internal/api" "github.com/mathiasbq/hyperguild/ingestion/internal/api"
"github.com/mathiasbq/hyperguild/ingestion/internal/audit" "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/capture"
"github.com/mathiasbq/hyperguild/ingestion/internal/capturehttp" "github.com/mathiasbq/hyperguild/ingestion/internal/capturehttp"
"github.com/mathiasbq/hyperguild/ingestion/internal/classification" "github.com/mathiasbq/hyperguild/ingestion/internal/classification"
@@ -90,15 +89,11 @@ func (s *claudeSink) Ingest(ctx context.Context, b claudewatcher.Batch) error {
sb.WriteString("\n\n") sb.WriteString("\n\n")
} }
slug := "session-" + b.Host + "-" + b.SessionID slug := "session-" + b.Host + "-" + b.SessionID
dest := "archive/claude-sessions/" + b.Host + "/" + slug + ".md" dest := filepath.Join(s.brainDir, "archive", "claude-sessions", b.Host, slug+".md")
// Written through the brain root, never through a symlinked directory if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
// or file (hyperguild#158). return fmt.Errorf("create claude-sessions archive dir: %w", err)
bfs, err := brainfs.Open(s.brainDir)
if err != nil {
return fmt.Errorf("open brain: %w", err)
} }
defer func() { _ = bfs.Close() }() if err := os.WriteFile(dest, []byte(sb.String()), 0o644); err != nil {
if err := bfs.PutRegular(dest, []byte(sb.String())); err != nil {
return fmt.Errorf("write claude session archive: %w", err) return fmt.Errorf("write claude session archive: %w", err)
} }
s.logger.Debug("claude session archived (non-indexed)", "path", dest) s.logger.Debug("claude session archived (non-indexed)", "path", dest)
-24
View File
@@ -76,27 +76,3 @@ 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")
})
}
}
@@ -4,7 +4,6 @@ import (
"os" "os"
"path/filepath" "path/filepath"
"strings" "strings"
"syscall"
"testing" "testing"
"github.com/stretchr/testify/assert" "github.com/stretchr/testify/assert"
@@ -64,13 +63,3 @@ func TestStartupSymlinkCheckRefusesAnUnlistableBrainRoot(t *testing.T) {
t.Cleanup(func() { _ = os.Chmod(brain, 0o755) }) t.Cleanup(func() { _ = os.Chmod(brain, 0o755) })
assert.Error(t, startupSymlinkCheck(brain)) 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")
}
+5 -14
View File
@@ -12,7 +12,6 @@ import (
"time" "time"
"github.com/mathiasbq/hyperguild/ingestion/internal/brain" "github.com/mathiasbq/hyperguild/ingestion/internal/brain"
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
"github.com/mathiasbq/hyperguild/ingestion/internal/claim" "github.com/mathiasbq/hyperguild/ingestion/internal/claim"
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline" "github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
"github.com/mathiasbq/hyperguild/ingestion/internal/search" "github.com/mathiasbq/hyperguild/ingestion/internal/search"
@@ -228,22 +227,14 @@ func writeHallNote(brainDir string, opts WriteNoteOptions) (string, error) {
// The directory is created only once the note is known to be writable: // The directory is created only once the note is known to be writable:
// a refused write leaves nothing behind, not even an empty hall dir // a refused write leaves nothing behind, not even an empty hall dir
// (brain#21; provenance refusal joins the envelope refusal here). // (brain#21; provenance refusal joins the envelope refusal here).
// Created through the brain root, never through a symlinked wing or if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
// hall directory (hyperguild#188). return "", fmt.Errorf("create hall dir: %w", err)
rel, err := filepath.Rel(brainDir, dest)
if err != nil {
return "", fmt.Errorf("note path: %w", err)
} }
rel = filepath.ToSlash(rel) if err := os.WriteFile(dest, []byte(final), 0o644); err != nil {
bfs, err := brainfs.Open(brainDir)
if err != nil {
return "", fmt.Errorf("open brain: %w", err)
}
defer func() { _ = bfs.Close() }()
if err := bfs.PutRegular(rel, []byte(final)); err != nil {
return "", fmt.Errorf("write: %w", err) return "", fmt.Errorf("write: %w", err)
} }
return rel, nil rel, _ := filepath.Rel(brainDir, dest)
return filepath.ToSlash(rel), nil
} }
// scalarValues flattens frontmatter fields to key -> scalar value for // scalarValues flattens frontmatter fields to key -> scalar value for
+12 -10
View File
@@ -127,18 +127,18 @@ func PromoteNote(brainDir string, opts PromoteOptions) (string, error) {
} }
fm.set("promoted_at", now) fm.set("promoted_at", now)
// Write-then-delete: the source survives any write failure. Both go if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
// through the brain root (hyperguild#188). return "", fmt.Errorf("create wing dir: %w", err)
}
// Write-then-delete: the source survives any write failure.
promoted, err := StampProvenance(fm.render()+body, opts.Origin, opts.WrittenBy) promoted, err := StampProvenance(fm.render()+body, opts.Origin, opts.WrittenBy)
if err != nil { if err != nil {
return "", err return "", err
} }
// Created with O_EXCL: a note that appeared after the collision check if err := os.WriteFile(dest, []byte(promoted), 0o644); err != nil {
// above is never overwritten.
if err := createBrainFile(brainDir, dest, []byte(promoted)); err != nil {
return "", fmt.Errorf("write promoted note: %w", err) return "", fmt.Errorf("write promoted note: %w", err)
} }
if err := removeBrainFile(brainDir, src); err != nil { if err := os.Remove(src); err != nil {
return "", fmt.Errorf("promoted note written but source removal failed: %w", err) return "", fmt.Errorf("promoted note written but source removal failed: %w", err)
} }
@@ -196,12 +196,14 @@ func RejectNote(brainDir string, opts RejectOptions) (string, error) {
fm.set("reject_reason", opts.Reason) fm.set("reject_reason", opts.Reason)
} }
// Write-then-delete: the source survives any write failure. Both go if err := os.MkdirAll(filepath.Dir(dest), 0o755); err != nil {
// through the brain root (hyperguild#188). return "", fmt.Errorf("create rejected dir: %w", err)
if err := createBrainFile(brainDir, dest, []byte(fm.render()+body)); err != nil { }
// Write-then-delete: the source survives any write failure.
if err := os.WriteFile(dest, []byte(fm.render()+body), 0o644); err != nil {
return "", fmt.Errorf("write rejected note: %w", err) return "", fmt.Errorf("write rejected note: %w", err)
} }
if err := removeBrainFile(brainDir, src); err != nil { if err := os.Remove(src); err != nil {
return "", fmt.Errorf("rejected note written but source removal failed: %w", err) return "", fmt.Errorf("rejected note written but source removal failed: %w", err)
} }
@@ -1,87 +0,0 @@
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#188: promote and reject wrote the destination with
// os.MkdirAll + os.WriteFile by path, so a symlinked wing (promote) or a
// symlinked raw/rejected (reject) redirected the note; the raw source was
// then removed.
func TestPromoteAndRejectRefuseASymlinkedDestinationDirectory(t *testing.T) {
brain := t.TempDir()
outside := t.TempDir()
raw := filepath.Join(brain, "raw")
require.NoError(t, os.MkdirAll(raw, 0o755))
require.NoError(t, os.WriteFile(filepath.Join(raw, "2026-10-05-n.md"), []byte("---\ntitle: n\n---\nbody\n"), 0o644))
require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki"), 0o755))
require.NoError(t, os.Symlink(outside, filepath.Join(brain, "wiki", "lw")))
require.NoError(t, os.Symlink(outside, filepath.Join(raw, "rejected")))
_, err := api.PromoteNote(brain, api.PromoteOptions{Filename: "2026-10-05-n.md", Wing: "lw", Hall: "facts"})
assert.Error(t, err)
_, err = api.RejectNote(brain, api.RejectOptions{Filename: "2026-10-05-n.md"})
assert.Error(t, err)
ents, _ := os.ReadDir(outside)
assert.Empty(t, ents, "a note was written outside the brain")
_, err = os.Stat(filepath.Join(raw, "2026-10-05-n.md"))
assert.NoError(t, err, "the raw source is kept when the write is refused")
require.NoError(t, os.Remove(filepath.Join(raw, "rejected")))
_, err = api.PromoteNote(brain, api.PromoteOptions{Filename: "2026-10-05-n.md", Wing: "w", Hall: "facts"})
require.NoError(t, err, "positive control: promote into a real wing")
}
// StampProvenanceFile read and rewrote the note by path (provenance.ApplyFile).
func TestStampProvenanceFileRefusesANoteBehindASymlinkedDirectory(t *testing.T) {
brain := t.TempDir()
victim := filepath.Join(brain, "raw", "facts", "v.md")
require.NoError(t, os.MkdirAll(filepath.Dir(victim), 0o755))
require.NoError(t, os.WriteFile(victim, []byte("---\ntitle: v\n---\nuntouched\n"), 0o644))
require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki", "w"), 0o755))
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "facts"), filepath.Join(brain, "wiki", "w", "alias")))
assert.Error(t, api.StampProvenanceFile(brain, "wiki/w/alias/v.md", "static", "x"))
got, _ := os.ReadFile(victim)
assert.Equal(t, "---\ntitle: v\n---\nuntouched\n", string(got))
real := filepath.Join(brain, "wiki", "w", "facts", "r.md")
require.NoError(t, os.MkdirAll(filepath.Dir(real), 0o755))
require.NoError(t, os.WriteFile(real, []byte("---\ntitle: r\n---\nbody\n"), 0o644))
require.NoError(t, api.StampProvenanceFile(brain, "wiki/w/facts/r.md", "static", "x"), "positive control")
got, _ = os.ReadFile(real)
assert.Contains(t, string(got), "written_by: x")
}
// The same through an in-brain symlinked wing and raw/rejected, which
// os.Root alone would follow.
func TestPromoteAndRejectRefuseAnInBrainSymlinkedDestinationDirectory(t *testing.T) {
brain := t.TempDir()
raw := filepath.Join(brain, "raw")
require.NoError(t, os.MkdirAll(raw, 0o755))
require.NoError(t, os.WriteFile(filepath.Join(raw, "2026-10-05-n.md"), []byte("---\ntitle: n\n---\nbody\n"), 0o644))
target := filepath.Join(brain, "archive")
require.NoError(t, os.MkdirAll(target, 0o755))
require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki"), 0o755))
require.NoError(t, os.Symlink(filepath.Join("..", "archive"), filepath.Join(brain, "wiki", "lw")))
require.NoError(t, os.Symlink(filepath.Join("..", "archive"), filepath.Join(raw, "rejected")))
_, err := api.PromoteNote(brain, api.PromoteOptions{Filename: "2026-10-05-n.md", Wing: "lw", Hall: "facts"})
assert.Error(t, err)
_, err = api.RejectNote(brain, api.RejectOptions{Filename: "2026-10-05-n.md"})
assert.Error(t, err)
ents, _ := os.ReadDir(target)
assert.Empty(t, ents, "a note was written at the in-brain link's target")
_, err = os.Stat(filepath.Join(raw, "2026-10-05-n.md"))
assert.NoError(t, err, "the raw source is kept")
require.NoError(t, os.Remove(filepath.Join(raw, "rejected")))
_, err = api.RejectNote(brain, api.RejectOptions{Filename: "2026-10-05-n.md"})
require.NoError(t, err, "positive control: reject into a real raw/rejected")
}
+3 -57
View File
@@ -1,10 +1,6 @@
package api package api
import ( import (
"fmt"
"path/filepath"
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
"github.com/mathiasbq/hyperguild/ingestion/internal/provenance" "github.com/mathiasbq/hyperguild/ingestion/internal/provenance"
) )
@@ -15,61 +11,11 @@ func StampProvenance(content, origin, writtenBy string) (string, error) {
return provenance.Apply(content, provenance.Stamp{Origin: origin, WrittenBy: writtenBy}) return provenance.Apply(content, provenance.Stamp{Origin: origin, WrittenBy: writtenBy})
} }
// StampProvenanceFile applies StampProvenance to a brain-relative note path, // StampProvenanceFile applies StampProvenance to a brain-relative note path.
// read and rewritten through the brain root (hyperguild#158).
func StampProvenanceFile(brainDir, relPath, origin, writtenBy string) error { func StampProvenanceFile(brainDir, relPath, origin, writtenBy string) error {
rel, _, err := resolveWithin(brainDir, relPath) _, abs, err := resolveWithin(brainDir, relPath)
if err != nil { if err != nil {
return err return err
} }
bfs, err := brainfs.Open(brainDir) return provenance.ApplyFile(abs, provenance.Stamp{Origin: origin, WrittenBy: writtenBy})
if err != nil {
return fmt.Errorf("open brain: %w", err)
}
defer func() { _ = bfs.Close() }()
b, err := bfs.ReadRegular(rel)
if err != nil {
return fmt.Errorf("read for provenance: %w", err)
}
out, err := provenance.Apply(string(b), provenance.Stamp{Origin: origin, WrittenBy: writtenBy})
if err != nil {
return err
}
if out == string(b) {
return nil
}
if err := bfs.WriteRegular(rel, []byte(out)); err != nil {
return fmt.Errorf("write provenance: %w", err)
}
return nil
}
// createBrainFile creates the file at abs (inside brainDir) through the
// brain root and fails if anything is already there.
func createBrainFile(brainDir, abs string, data []byte) error {
rel, err := filepath.Rel(brainDir, abs)
if err != nil {
return err
}
bfs, err := brainfs.Open(brainDir)
if err != nil {
return fmt.Errorf("open brain: %w", err)
}
defer func() { _ = bfs.Close() }()
return bfs.CreateRegular(filepath.ToSlash(rel), data)
}
// removeBrainFile removes the file at abs (inside brainDir) through the
// brain root.
func removeBrainFile(brainDir, abs string) error {
rel, err := filepath.Rel(brainDir, abs)
if err != nil {
return err
}
bfs, err := brainfs.Open(brainDir)
if err != nil {
return fmt.Errorf("open brain: %w", err)
}
defer func() { _ = bfs.Close() }()
return bfs.Remove(filepath.ToSlash(rel))
} }
@@ -1,43 +0,0 @@
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#188: brain_write created a new note with os.MkdirAll +
// os.WriteFile by path, so a symlinked wing directory redirected the note
// elsewhere in the brain or outside it.
func TestWriteNoteRefusesASymlinkedWing(t *testing.T) {
for name, target := range map[string]func(t *testing.T, brain string) string{
"in-brain": func(t *testing.T, brain string) string {
require.NoError(t, os.MkdirAll(filepath.Join(brain, "raw"), 0o755))
return filepath.Join("..", "raw")
},
"outside": func(t *testing.T, _ string) string { return t.TempDir() },
} {
t.Run(name, func(t *testing.T) {
brain := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(brain, "wiki"), 0o755))
link := target(t, brain)
require.NoError(t, os.Symlink(link, filepath.Join(brain, "wiki", "lw")))
_, err := api.WriteNote(brain, api.WriteNoteOptions{Wing: "lw", Hall: "facts", Filename: "n", Content: "learning"})
assert.Error(t, err)
resolved := link
if !filepath.IsAbs(resolved) {
resolved = filepath.Join(brain, "wiki", link)
}
_, serr := os.Stat(filepath.Join(resolved, "facts"))
assert.True(t, os.IsNotExist(serr), "a hall was created at the link's target")
_, err = api.WriteNote(brain, api.WriteNoteOptions{Wing: "w", Hall: "facts", Filename: "n", Content: "learning"})
require.NoError(t, err, "positive control: a real wing is written")
})
}
}
+5 -3
View File
@@ -7,6 +7,8 @@ import (
"fmt" "fmt"
"io" "io"
"io/fs" "io/fs"
"os"
"path/filepath"
"sort" "sort"
"strings" "strings"
"time" "time"
@@ -30,6 +32,7 @@ func BuildWingIndex(brainDir, wing string) error {
if w == "" { if w == "" {
return fmt.Errorf("invalid wing %q", wing) return fmt.Errorf("invalid wing %q", wing)
} }
wingDir := filepath.Join(brainDir, "wiki", w)
// Listed and read through the brain root (hyperguild#157): a wing or // Listed and read through the brain root (hyperguild#157): a wing or
// hall that is a symlink is not followed, and notes are regular files. // hall that is a symlink is not followed, and notes are regular files.
bfs, err := brainfs.Open(brainDir) bfs, err := brainfs.Open(brainDir)
@@ -60,9 +63,8 @@ func BuildWingIndex(brainDir, wing string) error {
fmt.Fprintf(&b, "| %s | [%s](%s/%s.md) | %s |\n", e.Hall, e.Title, e.Hall, e.Slug, e.Created) fmt.Fprintf(&b, "| %s | [%s](%s/%s.md) | %s |\n", e.Hall, e.Title, e.Hall, e.Slug, e.Created)
} }
// Written through the brain root, never through a symlinked _index.md dest := filepath.Join(wingDir, "_index.md")
// (hyperguild#158). return os.WriteFile(dest, []byte(b.String()), 0o644)
return bfs.PutRegular("wiki/"+w+"/_index.md", []byte(b.String()))
} }
// BuildAllWingIndexes regenerates _index.md for every wing under brain/wiki/. // BuildAllWingIndexes regenerates _index.md for every wing under brain/wiki/.
+25 -12
View File
@@ -5,6 +5,7 @@ import (
"errors" "errors"
"fmt" "fmt"
"io/fs" "io/fs"
"os"
"path" "path"
"path/filepath" "path/filepath"
"strings" "strings"
@@ -175,23 +176,35 @@ func logFuzzyCandidates(brainDir, sourcePath string, cs []TunnelCandidate) error
if len(cs) == 0 { if len(cs) == 0 {
return nil return nil
} }
// Appended through the brain root, never through a symlinked raw/ or rawDir := filepath.Join(brainDir, "raw")
// log file (hyperguild#158). if err := os.MkdirAll(rawDir, 0o755); err != nil {
bfs, err := brainfs.Open(brainDir) return err
if err != nil {
return fmt.Errorf("open brain: %w", err)
} }
defer func() { _ = bfs.Close() }()
stamp := time.Now().UTC().Format("2006-01-02") stamp := time.Now().UTC().Format("2006-01-02")
rel := "raw/tunnel-candidates-" + stamp + ".md" path := filepath.Join(rawDir, "tunnel-candidates-"+stamp+".md")
var buf strings.Builder existed := fileExists(path)
if _, err := bfs.Lstat(rel); errors.Is(err, fs.ErrNotExist) { f, err := os.OpenFile(path, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0o644)
buf.WriteString("# Tunnel candidates " + stamp + "\n\nFuzzy cross-wing matches surfaced by AutoTunnel. Review and promote to a tunnel via `brain_tunnel` if relevant.\n\n") if err != nil {
return err
}
defer func() { _ = f.Close() }()
if !existed {
if _, err := f.WriteString("# Tunnel candidates " + stamp + "\n\nFuzzy cross-wing matches surfaced by AutoTunnel. Review and promote to a tunnel via `brain_tunnel` if relevant.\n\n"); err != nil {
return err
}
} }
for _, c := range cs { for _, c := range cs {
fmt.Fprintf(&buf, "- `%s` ↔ `%s` (term: %q)\n", sourcePath, c.TargetPath, c.MatchedTerm) line := fmt.Sprintf("- `%s` ↔ `%s` (term: %q)\n", sourcePath, c.TargetPath, c.MatchedTerm)
if _, err := f.WriteString(line); err != nil {
return err
} }
return bfs.AppendRegular(rel, []byte(buf.String())) }
return nil
}
func fileExists(p string) bool {
_, err := os.Stat(p)
return err == nil
} }
// WriteTunnel appends a bidirectional wikilink between sourcePath and // WriteTunnel appends a bidirectional wikilink between sourcePath and
@@ -1,52 +0,0 @@
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#158: BuildWingIndex wrote wiki/<wing>/_index.md with
// os.WriteFile, so a symlinked _index.md was written through.
func TestBuildWingIndexDoesNotWriteThroughASymlinkedIndex(t *testing.T) {
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", "n.md"), []byte("---\ntitle: zqn\n---\n"), 0o644))
victim := filepath.Join(b, "raw", "v.md")
require.NoError(t, os.MkdirAll(filepath.Dir(victim), 0o755))
require.NoError(t, os.WriteFile(victim, []byte("untouched"), 0o644))
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "v.md"), filepath.Join(b, "wiki", "w", "_index.md")))
assert.Error(t, brain.BuildWingIndex(b, "w"))
got, _ := os.ReadFile(victim)
assert.Equal(t, "untouched", string(got))
require.NoError(t, os.Remove(filepath.Join(b, "wiki", "w", "_index.md")))
require.NoError(t, brain.BuildWingIndex(b, "w"), "positive control")
idx, _ := os.ReadFile(filepath.Join(b, "wiki", "w", "_index.md"))
assert.Contains(t, string(idx), "zqn")
}
// AutoTunnel's fuzzy-candidate log appended to raw/tunnel-candidates-*.md
// with os.OpenFile, so a symlinked raw/ (or log file) was written through.
func TestAutoTunnelDoesNotAppendTheCandidateLogThroughASymlinkedRaw(t *testing.T) {
b := t.TempDir()
outside := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(b, "wiki", "a", "facts"), 0o755))
require.NoError(t, os.MkdirAll(filepath.Join(b, "wiki", "b", "facts"), 0o755))
// "zq widget" matches as a substring of "zq widgets", a fuzzy candidate.
require.NoError(t, os.WriteFile(filepath.Join(b, "wiki", "b", "facts", "t.md"), []byte("---\ntitle: Zq Widget\n---\n"), 0o644))
require.NoError(t, os.Symlink(outside, filepath.Join(b, "raw")))
_ = brain.AutoTunnel(b, "wiki/a/facts/s.md", "about zq widgets")
ents, _ := os.ReadDir(outside)
assert.Empty(t, ents, "the candidate log was written outside the brain")
require.NoError(t, os.Remove(filepath.Join(b, "raw")))
require.NoError(t, brain.AutoTunnel(b, "wiki/a/facts/s.md", "about zq widgets"))
logs, _ := filepath.Glob(filepath.Join(b, "raw", "tunnel-candidates-*.md"))
assert.Len(t, logs, 1, "positive control: the fuzzy candidate is logged in the real raw/")
}
+1 -156
View File
@@ -109,7 +109,7 @@ func (b *Brain) ReadDirRegular(relDir string) ([]string, error) {
// after following a symlink, and a ".." after a symlinked directory would // after following a symlink, and a ".." after a symlinked directory would
// otherwise pass the check and redirect the read or write. // otherwise pass the check and redirect the read or write.
func cleanRel(rel string) error { func cleanRel(rel string) error {
if rel == "" || path.Clean(rel) != rel || !filepath.IsLocal(rel) { if rel == "" || path.Clean(rel) != rel || !filepath.IsLocal(rel) || strings.Contains(rel, "\\") {
return fmt.Errorf("%q: not a clean brain-relative path: %w", rel, ErrNotRegular) return fmt.Errorf("%q: not a clean brain-relative path: %w", rel, ErrNotRegular)
} }
return nil return nil
@@ -136,161 +136,6 @@ func (b *Brain) ReadDirDirs(relDir string) ([]string, error) {
return names, nil return names, nil
} }
// PutRegular creates or replaces a regular file at a brain-relative path,
// for creating writes (hyperguild#188, #158). Missing parent directories are
// created one component at a time through the root, and every existing
// component must be a real directory, so a symlinked directory cannot
// redirect the write elsewhere in the brain or outside it. An existing file
// is replaced only if it is regular (WriteRegular's checks); a new file is
// created with O_EXCL and confirmed to be the file that was opened. A
// directory swapped in after the checks is the #167 residual.
func (b *Brain) PutRegular(rel string, data []byte) error {
if err := cleanRel(rel); err != nil {
return err
}
if err := b.mkdirReal(path.Dir(rel)); err != nil {
return err
}
if _, err := b.root.Lstat(rel); err == nil {
return b.WriteRegular(rel, data)
} else if !errors.Is(err, fs.ErrNotExist) {
return err
}
return b.createNew(rel, data)
}
// CreateRegular creates a new regular file at a brain-relative path, with
// PutRegular's parent rules, and fails with fs.ErrExist if anything is
// already there: for writers that must never overwrite (promote, reject).
func (b *Brain) CreateRegular(rel string, data []byte) error {
if err := cleanRel(rel); err != nil {
return err
}
if err := b.mkdirReal(path.Dir(rel)); err != nil {
return err
}
return b.createNew(rel, data)
}
// createNew creates rel with O_EXCL and writes data only after confirming
// the path is the regular file it created.
func (b *Brain) createNew(rel string, data []byte) error {
f, err := b.root.OpenFile(rel, os.O_WRONLY|os.O_CREATE|os.O_EXCL|syscall.O_NOFOLLOW|syscall.O_NONBLOCK, 0o644)
if err != nil {
return err
}
defer func() { _ = f.Close() }()
hfi, herr := f.Stat()
lfi, lerr := b.root.Lstat(rel)
if herr != nil || lerr != nil || !lfi.Mode().IsRegular() || !os.SameFile(lfi, hfi) {
return fmt.Errorf("%s: changed while creating: %w", rel, ErrNotRegular)
}
if _, err := f.Write(data); err != nil {
return err
}
return f.Close()
}
// AppendRegular appends data to a regular file at a brain-relative path,
// creating it (and missing parent directories, as PutRegular does) if it is
// absent. It writes only after confirming the path is the regular file it
// opened, so a final symlink or special file, or one swapped in, is refused.
func (b *Brain) AppendRegular(rel string, data []byte) error {
if err := cleanRel(rel); err != nil {
return err
}
if err := b.mkdirReal(path.Dir(rel)); err != nil {
return err
}
if fi, err := b.root.Lstat(rel); err == nil && !fi.Mode().IsRegular() {
return fmt.Errorf("%s: %w", rel, ErrNotRegular)
} else if err != nil && !errors.Is(err, fs.ErrNotExist) {
return err
}
f, err := b.root.OpenFile(rel, os.O_WRONLY|os.O_APPEND|os.O_CREATE|syscall.O_NOFOLLOW|syscall.O_NONBLOCK, 0o644)
if err != nil {
return err
}
defer func() { _ = f.Close() }()
hfi, herr := f.Stat()
lfi, lerr := b.root.Lstat(rel)
if herr != nil || lerr != nil || !lfi.Mode().IsRegular() || !os.SameFile(lfi, hfi) {
return fmt.Errorf("%s: changed while opening: %w", rel, ErrNotRegular)
}
if _, err := f.Write(data); err != nil {
return err
}
return f.Close()
}
// Remove removes the file at a clean brain-relative path through the root,
// refusing a path behind a symlinked directory. A final symlink is removed
// itself, never its target.
func (b *Brain) Remove(rel string) error {
if err := b.RealParent(rel); err != nil {
return err
}
return b.root.Remove(rel)
}
// RealParent returns ErrNotRegular unless rel is clean and every directory
// above it is a real directory, for writers that do their own I/O (an atomic
// rename) but must not be redirected by a symlinked directory.
func (b *Brain) RealParent(rel string) error {
if err := cleanRel(rel); err != nil {
return err
}
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.
func (b *Brain) mkdirReal(rel string) error {
if rel == "." {
return nil
}
prefix := ""
for _, part := range strings.Split(rel, "/") {
prefix = path.Join(prefix, part)
fi, err := b.root.Lstat(prefix)
if errors.Is(err, fs.ErrNotExist) {
if err := b.root.Mkdir(prefix, 0o755); err != nil && !errors.Is(err, fs.ErrExist) {
return err
}
fi, err = b.root.Lstat(prefix)
}
if err != nil {
return err
}
if !fi.IsDir() {
return fmt.Errorf("%s: component %s is not a directory: %w", rel, prefix, ErrNotRegular)
}
}
return nil
}
// ReadRegular reads a brain-relative path, refusing anything that is not a // ReadRegular reads a brain-relative path, refusing anything that is not a
// regular file, both before the open and on the opened handle. // regular file, both before the open and on the opened handle.
func (b *Brain) ReadRegular(rel string) ([]byte, error) { func (b *Brain) ReadRegular(rel string) ([]byte, error) {
-170
View File
@@ -376,173 +376,3 @@ func TestReadAndWriteRegularRefuseAPathThatIsNotClean(t *testing.T) {
got, _ := os.ReadFile(filepath.Join(dir, "raw", "v.md")) got, _ := os.ReadFile(filepath.Join(dir, "raw", "v.md"))
assert.Equal(t, "untouched", string(got)) assert.Equal(t, "untouched", string(got))
} }
// hyperguild#188: PutRegular creates or replaces a regular file through the
// root. Missing parent directories are created; an existing component that
// is not a real directory, a final symlink or special file, and an unclean
// path are refused, and nothing is created at a link's target.
func TestPutRegularCreatesOrReplacesOnlyThroughRealDirectories(t *testing.T) {
dir := t.TempDir()
outside := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw"), 0o755))
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki"), 0o755))
require.NoError(t, os.Symlink(filepath.Join("..", "raw"), filepath.Join(dir, "wiki", "inwing")))
require.NoError(t, os.Symlink(outside, filepath.Join(dir, "wiki", "outwing")))
require.NoError(t, os.WriteFile(filepath.Join(dir, "raw", "v.md"), []byte("untouched"), 0o644))
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki", "w"), 0o755))
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "v.md"), filepath.Join(dir, "wiki", "w", "link.md")))
require.NoError(t, syscall.Mkfifo(filepath.Join(dir, "wiki", "w", "f.md"), 0o644))
b, err := Open(dir)
require.NoError(t, err)
defer func() { _ = b.Close() }()
for _, rel := range []string{"wiki/inwing/facts/n.md", "wiki/outwing/facts/n.md", "wiki/w/link.md", "wiki/w/f.md", "wiki/w/../../raw/v.md", "/abs.md"} {
assert.ErrorIs(t, b.PutRegular(rel, []byte("x")), ErrNotRegular, rel)
}
ents, _ := os.ReadDir(outside)
assert.Empty(t, ents, "nothing created outside the brain")
_, err = os.Stat(filepath.Join(dir, "raw", "facts"))
assert.True(t, os.IsNotExist(err), "nothing created through the in-brain link")
got, _ := os.ReadFile(filepath.Join(dir, "raw", "v.md"))
assert.Equal(t, "untouched", string(got))
require.NoError(t, b.PutRegular("wiki/new/facts/n.md", []byte("one")), "positive control: create with missing parents")
got, _ = os.ReadFile(filepath.Join(dir, "wiki", "new", "facts", "n.md"))
assert.Equal(t, "one", string(got))
require.NoError(t, b.PutRegular("wiki/new/facts/n.md", []byte("two")), "positive control: replace")
got, _ = os.ReadFile(filepath.Join(dir, "wiki", "new", "facts", "n.md"))
assert.Equal(t, "two", string(got))
}
func TestAppendRegularCreatesOrAppendsOnlyThroughRealDirectories(t *testing.T) {
dir := t.TempDir()
outside := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw"), 0o755))
require.NoError(t, os.WriteFile(filepath.Join(dir, "raw", "v.md"), []byte("untouched"), 0o644))
require.NoError(t, os.Symlink(outside, filepath.Join(dir, "outdir")))
require.NoError(t, os.Symlink("raw", filepath.Join(dir, "indir")))
require.NoError(t, os.Symlink(filepath.Join("raw", "v.md"), filepath.Join(dir, "log.md")))
require.NoError(t, syscall.Mkfifo(filepath.Join(dir, "f.md"), 0o644))
b, err := Open(dir)
require.NoError(t, err)
defer func() { _ = b.Close() }()
for _, rel := range []string{"outdir/l.md", "indir/v.md", "log.md", "f.md", "raw/../log.md"} {
assert.ErrorIs(t, b.AppendRegular(rel, []byte("x")), ErrNotRegular, rel)
}
ents, _ := os.ReadDir(outside)
assert.Empty(t, ents)
got, _ := os.ReadFile(filepath.Join(dir, "raw", "v.md"))
assert.Equal(t, "untouched", string(got))
require.NoError(t, b.AppendRegular("logs/a.md", []byte("one\n")), "positive control: create")
require.NoError(t, b.AppendRegular("logs/a.md", []byte("two\n")), "positive control: append")
got, _ = os.ReadFile(filepath.Join(dir, "logs", "a.md"))
assert.Equal(t, "one\ntwo\n", string(got))
}
func TestRealParentRefusesASymlinkedDirectoryOrUncleanPath(t *testing.T) {
dir := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw"), 0o755))
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki"), 0o755))
require.NoError(t, os.Symlink(filepath.Join("..", "raw"), filepath.Join(dir, "wiki", "alias")))
b, err := Open(dir)
require.NoError(t, err)
defer func() { _ = b.Close() }()
assert.ErrorIs(t, b.RealParent("wiki/alias/x.md"), ErrNotRegular)
assert.ErrorIs(t, b.RealParent("wiki/../raw/x.md"), ErrNotRegular)
assert.NoError(t, b.RealParent("wiki/x.md"), "positive control")
}
// cleanRel must refuse an unclean path on its own: here the ".." resolves,
// after a symlinked directory, to a real regular file, so only the clean
// check stands between the call and that file.
func TestAppendRegularRefusesAnUncleanPathThatResolvesToARealFile(t *testing.T) {
dir := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw", "keep"), 0o755))
require.NoError(t, os.WriteFile(filepath.Join(dir, "raw", "v.md"), []byte("untouched"), 0o644))
require.NoError(t, os.Symlink(filepath.Join("raw", "keep"), filepath.Join(dir, "indir")))
b, err := Open(dir)
require.NoError(t, err)
defer func() { _ = b.Close() }()
assert.ErrorIs(t, b.AppendRegular("indir/../v.md", []byte("x")), ErrNotRegular)
assert.ErrorIs(t, b.PutRegular("indir/../v.md", []byte("x")), ErrNotRegular)
got, _ := os.ReadFile(filepath.Join(dir, "raw", "v.md"))
assert.Equal(t, "untouched", string(got))
}
func TestRemoveRefusesAPathBehindASymlinkedDirectoryAndRemovesOnlyTheLink(t *testing.T) {
dir := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw"), 0o755))
require.NoError(t, os.WriteFile(filepath.Join(dir, "raw", "v.md"), []byte("keep"), 0o644))
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki"), 0o755))
require.NoError(t, os.Symlink(filepath.Join("..", "raw"), filepath.Join(dir, "wiki", "alias")))
require.NoError(t, os.Symlink(filepath.Join("..", "raw", "v.md"), filepath.Join(dir, "wiki", "link.md")))
require.NoError(t, os.WriteFile(filepath.Join(dir, "wiki", "n.md"), []byte("n"), 0o644))
b, err := Open(dir)
require.NoError(t, err)
defer func() { _ = b.Close() }()
assert.ErrorIs(t, b.Remove("wiki/alias/v.md"), ErrNotRegular)
_, err = os.Stat(filepath.Join(dir, "raw", "v.md"))
assert.NoError(t, err, "the file behind the symlinked directory is kept")
require.NoError(t, b.Remove("wiki/link.md"))
_, err = os.Stat(filepath.Join(dir, "raw", "v.md"))
assert.NoError(t, err, "removing a final symlink never removes its target")
require.NoError(t, b.Remove("wiki/n.md"), "positive control")
_, err = os.Stat(filepath.Join(dir, "wiki", "n.md"))
assert.True(t, os.IsNotExist(err))
}
// CreateRegular is the only write path for promote and reject: it creates
// missing parents through the root, refuses an in-brain symlinked parent and
// an unclean path, and never replaces anything already there (fs.ErrExist,
// content unchanged), including a dangling link.
func TestCreateRegularCreatesOnlyNewFilesThroughRealDirectories(t *testing.T) {
dir := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(dir, "raw", "keep"), 0o755))
require.NoError(t, os.MkdirAll(filepath.Join(dir, "wiki"), 0o755))
require.NoError(t, os.Symlink(filepath.Join("..", "raw"), filepath.Join(dir, "wiki", "inwing")))
require.NoError(t, os.WriteFile(filepath.Join(dir, "raw", "v.md"), []byte("untouched"), 0o644))
require.NoError(t, os.Symlink(filepath.Join("raw", "keep"), filepath.Join(dir, "indir")))
require.NoError(t, os.WriteFile(filepath.Join(dir, "wiki", "exists.md"), []byte("original"), 0o644))
require.NoError(t, os.Symlink("nowhere.md", filepath.Join(dir, "wiki", "dangling.md")))
b, err := Open(dir)
require.NoError(t, err)
defer func() { _ = b.Close() }()
assert.ErrorIs(t, b.CreateRegular("wiki/inwing/facts/n.md", []byte("x")), ErrNotRegular)
_, err = os.Stat(filepath.Join(dir, "raw", "facts"))
assert.True(t, os.IsNotExist(err), "nothing created through the in-brain link")
assert.ErrorIs(t, b.CreateRegular("indir/../v.md", []byte("x")), ErrNotRegular)
got, _ := os.ReadFile(filepath.Join(dir, "raw", "v.md"))
assert.Equal(t, "untouched", string(got))
assert.ErrorIs(t, b.CreateRegular("wiki/exists.md", []byte("x")), fs.ErrExist)
got, _ = os.ReadFile(filepath.Join(dir, "wiki", "exists.md"))
assert.Equal(t, "original", string(got))
assert.ErrorIs(t, b.CreateRegular("wiki/dangling.md", []byte("x")), fs.ErrExist)
_, err = os.Stat(filepath.Join(dir, "wiki", "nowhere.md"))
assert.True(t, os.IsNotExist(err), "nothing created at the dangling link's target")
require.NoError(t, b.CreateRegular("wiki/new/facts/n.md", []byte("one")), "positive control: create with missing parents")
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))
}
@@ -88,6 +88,7 @@ func TestNoPackageReferencesExtractTextOutsideExtract(t *testing.T) {
// osOpenAllowed names the functions in guarded files that may call os.Open* // osOpenAllowed names the functions in guarded files that may call os.Open*
// on a path that is not a raw/ read. // on a path that is not a raw/ read.
var osOpenAllowed = map[string]bool{ 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 // Text reads by path; outside this package only TextIn's temp copy reaches
// it (TestNoPackageReferencesExtractTextOutsideExtract enforces that). // it (TestNoPackageReferencesExtractTextOutsideExtract enforces that).
"internal/extract/extract.go:Text": true, "internal/extract/extract.go:Text": true,
@@ -1,36 +0,0 @@
package notes
import (
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// hyperguild#188/#173: brain_edit's atomic rename must not be redirected by
// a symlinked directory inside the brain.
func TestEditRefusesANoteBehindASymlinkedDirectory(t *testing.T) {
b := t.TempDir()
// Edit refuses a tree that is not the sync source before any path
// check, so the test needs a .git to reach the symlink refusal.
require.NoError(t, os.MkdirAll(filepath.Join(b, ".git"), 0o755))
victim := filepath.Join(b, "raw", "facts", "v.md")
require.NoError(t, os.MkdirAll(filepath.Dir(victim), 0o755))
require.NoError(t, os.WriteFile(victim, []byte("old text\n"), 0o644))
require.NoError(t, os.MkdirAll(filepath.Join(b, "wiki", "w"), 0o755))
require.NoError(t, os.Symlink(filepath.Join("..", "..", "raw", "facts"), filepath.Join(b, "wiki", "w", "alias")))
_, err := Edit(b, "wiki/w/alias/v.md", "old text", "new text", ScopeNotes)
assert.Error(t, err)
got, _ := os.ReadFile(victim)
assert.Equal(t, "old text\n", string(got))
real := filepath.Join(b, "wiki", "w", "facts", "r.md")
require.NoError(t, os.MkdirAll(filepath.Dir(real), 0o755))
require.NoError(t, os.WriteFile(real, []byte("old text\n"), 0o644))
_, err = Edit(b, "wiki/w/facts/r.md", "old text", "new text", ScopeNotes)
require.NoError(t, err, "positive control: a note in a real directory is edited")
got, _ = os.ReadFile(real)
assert.Equal(t, "new text\n", string(got))
}
+4 -1
View File
@@ -7,6 +7,8 @@ import (
"fmt" "fmt"
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs" "github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
"io/fs" "io/fs"
"os"
"path/filepath"
"strings" "strings"
"github.com/mathiasbq/hyperguild/ingestion/internal/wiki" "github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
@@ -88,7 +90,8 @@ func BackfillRefs(ctx context.Context, brainDir string) (int, error) {
} }
for relPath, page := range pending { for relPath, page := range pending {
if err := bfs.PutRegular(relPath, []byte(page.Content)); err != nil { dest := filepath.Join(brainDir, filepath.FromSlash(relPath))
if err := os.WriteFile(dest, []byte(page.Content), 0o644); err != nil {
return 0, fmt.Errorf("write %s: %w", relPath, err) return 0, fmt.Errorf("write %s: %w", relPath, err)
} }
} }
+7 -14
View File
@@ -9,6 +9,8 @@ import (
"fmt" "fmt"
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs" "github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
"io/fs" "io/fs"
"os"
"path/filepath"
"strings" "strings"
"time" "time"
@@ -126,6 +128,10 @@ func buildAndWrite(ctx context.Context, rawPages []RawPage, sourceSlug, date, br
var written []string var written []string
for _, page := range merged { for _, page := range merged {
if !dryRun { 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) content, conflicts, err := reviseOrCreate(brainDir, page)
if err != nil { if err != nil {
return Result{}, err return Result{}, err
@@ -144,9 +150,7 @@ func buildAndWrite(ctx context.Context, rawPages []RawPage, sourceSlug, date, br
if err != nil { if err != nil {
return Result{}, fmt.Errorf("stamp %s: %w", page.Path, err) return Result{}, fmt.Errorf("stamp %s: %w", page.Path, err)
} }
// Written through the brain root, never through a symlinked if err := os.WriteFile(dest, []byte(stamped), 0o644); err != nil {
// 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) return Result{}, fmt.Errorf("write %s: %w", page.Path, err)
} }
} }
@@ -197,17 +201,6 @@ func readSourcePage(brainDir, sourceSlug string) string {
return string(raw) 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, // readBrainFile reads one brain-relative file through the brain root,
// regular files only (hyperguild#157). // regular files only (hyperguild#157).
func readBrainFile(brainDir, rel string) ([]byte, error) { func readBrainFile(brainDir, rel string) ([]byte, error) {
-50
View File
@@ -165,53 +165,3 @@ func TestBackfillRefsDoesNotCopyAPageSwappedInBehindASymlink(t *testing.T) {
require.Contains(t, read(), "[[s|S]]", "positive control: the regular page gets the source ref") 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) 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")
}
// 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 returned without error")
}
@@ -28,6 +28,7 @@ import (
"context" "context"
"errors" "errors"
"fmt" "fmt"
"os"
"regexp" "regexp"
"strings" "strings"
@@ -101,6 +102,25 @@ func Apply(content string, s Stamp) (string, error) {
return out, nil return out, nil
} }
// ApplyFile applies the stamp to the note at absPath in place.
func ApplyFile(absPath string, s Stamp) error {
b, err := os.ReadFile(absPath)
if err != nil {
return fmt.Errorf("read for provenance: %w", err)
}
out, err := Apply(string(b), s)
if err != nil {
return err
}
if out == string(b) {
return nil
}
if err := os.WriteFile(absPath, []byte(out), 0o644); err != nil {
return fmt.Errorf("write provenance: %w", err)
}
return nil
}
// plainGroups keeps the provably plain key groups of a frontmatter block. // plainGroups keeps the provably plain key groups of a frontmatter block.
func plainGroups(block string) string { func plainGroups(block string) string {
lines := strings.Split(strings.TrimSuffix(block, "\n"), "\n") lines := strings.Split(strings.TrimSuffix(block, "\n"), "\n")
@@ -1,104 +0,0 @@
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")
}
}
@@ -46,16 +46,10 @@ type Notifier interface {
type Result struct { type Result struct {
Symlinks []string Symlinks []string
Unreadable []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. // Clean reports whether the scan found nothing to act on.
func (r Result) Clean() bool { func (r Result) Clean() bool { return len(r.Symlinks) == 0 && len(r.Unreadable) == 0 }
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 // String describes the findings for a log line or alert. Paths are quoted, so
// a name containing a newline cannot blur two findings together. // a name containing a newline cannot blur two findings together.
@@ -65,9 +59,6 @@ func (r Result) String() string {
if len(r.Symlinks) > 0 { if len(r.Symlinks) > 0 {
parts = append(parts, fmt.Sprintf("%d symlink(s): %s", len(r.Symlinks), q(r.Symlinks))) 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 { if len(r.Unreadable) > 0 {
parts = append(parts, fmt.Sprintf("%d unreadable dir(s): %s", len(r.Unreadable), q(r.Unreadable))) parts = append(parts, fmt.Sprintf("%d unreadable dir(s): %s", len(r.Unreadable), q(r.Unreadable)))
} }
@@ -122,16 +113,12 @@ func Scan(brainDir string) (Result, error) {
if d.IsDir() && p == rootGit { if d.IsDir() && p == rootGit {
return filepath.SkipDir return filepath.SkipDir
} }
switch { if d.Type()&os.ModeSymlink != 0 {
case d.Type()&os.ModeSymlink != 0:
r.Symlinks = append(r.Symlinks, rel) r.Symlinks = append(r.Symlinks, rel)
case !d.IsDir() && !d.Type().IsRegular():
r.Special = append(r.Special, rel)
} }
return nil return nil
}) })
sort.Strings(r.Symlinks) sort.Strings(r.Symlinks)
sort.Strings(r.Special)
sort.Strings(r.Unreadable) sort.Strings(r.Unreadable)
if walkErr != nil { if walkErr != nil {
// Only the root's own error reaches here (deeper errors are recorded // Only the root's own error reaches here (deeper errors are recorded
@@ -195,20 +182,14 @@ 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", q.push(fmt.Sprintf("brain symlink tripwire (hyperguild#157): removed %d symlink(s) from the brain dir: %s",
len(removed), Result{}.quoted(removed))) len(removed), Result{}.quoted(removed)))
} }
sRemoved, sFailed := removeSpecial(brainDir, r.Special) key = Result{Symlinks: failed, Unreadable: r.Unreadable}.String()
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 { if key != reported {
reported = key reported = key
if key != "" { if key != "" {
slog.Error("brain symlink tripwire", "finding", key) slog.Error("brain symlink tripwire", "finding", key)
q.push("brain symlink tripwire (hyperguild#157, #179): " + key + q.push("brain symlink tripwire (hyperguild#157): " + key +
". Symlinks can lead readers out of the brain and special files can hang them; remove them.") ". Readers may follow symlinks out of the brain; fix them.")
} }
} }
} }
@@ -341,40 +322,6 @@ func permanent(err error) bool {
return errors.As(err, &p) && p.Permanent() 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 // 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 // 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. // never touches its target. It returns what was removed and what was not.
+35 -72
View File
@@ -3,18 +3,15 @@ package watcher
import ( import (
"context" "context"
"errors"
"fmt" "fmt"
"io" "io"
"log/slog" "log/slog"
"os" "os"
"path/filepath" "path/filepath"
"strings" "strings"
"sync"
"time" "time"
"unicode" "unicode"
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
"github.com/mathiasbq/hyperguild/ingestion/internal/extract" "github.com/mathiasbq/hyperguild/ingestion/internal/extract"
"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline" "github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
) )
@@ -112,28 +109,14 @@ func processDir(ctx context.Context, cfg Config, date string) []error {
} }
// Skip files that have already been processed or permanently failed. // Skip files that have already been processed or permanently failed.
// Any entry at the marker path counts (Lstat, not Stat): a dangling if _, err := os.Stat(path + ".processed"); err == nil {
// 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 return nil
} }
if _, err := os.Lstat(path + ".failed"); err == nil { if _, err := os.Stat(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 return nil
} }
if err := processFile(ctx, cfg, root, rawDir, path, date); err != 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)) errs = append(errs, fmt.Errorf("process %s: %w", filepath.Base(path), err))
} }
return nil return nil
@@ -162,15 +145,16 @@ func processFile(ctx context.Context, cfg Config, root *os.Root, rawDir, path, d
_, runErr := pipeline.Run(ctx, cfg.Pipeline, cfg.BrainDir, content, source, false) _, runErr := pipeline.Run(ctx, cfg.Pipeline, cfg.BrainDir, content, source, false)
if runErr != nil { if runErr != nil {
// Copy to failed/ and leave a .failed marker so we don't retry. Both // Copy to failed/ and leave a .failed marker so we don't retry.
// written through the brain root (hyperguild#158). failedDir := filepath.Join(cfg.BrainDir, "raw", "failed")
if cpErr := copyFromRoot(root, rel, cfg.BrainDir, "raw/failed/"+filename); cpErr != nil { 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 {
return fmt.Errorf("copy to failed: %w", cpErr) return fmt.Errorf("copy to failed: %w", cpErr)
} }
if mkErr := putBrainFile(cfg.BrainDir, "raw/"+filepath.ToSlash(rel)+".failed", []byte(runErr.Error())); mkErr != nil { if mkErr := os.WriteFile(path+".failed", []byte(runErr.Error()), 0o644); 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) slog.Error("watcher: failed to write .failed marker", "error", mkErr)
} }
@@ -184,21 +168,21 @@ 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. // Copy to processed/YYYY-MM-DD/ and leave a .processed marker so we don't re-ingest.
// Written through the brain root (hyperguild#158). processedDir := filepath.Join(cfg.BrainDir, "raw", "processed", date)
dest := "raw/processed/" + date + "/" + filename if err := os.MkdirAll(processedDir, 0o755); err != nil {
if _, err := os.Lstat(filepath.Join(cfg.BrainDir, filepath.FromSlash(dest))); err == nil { return fmt.Errorf("mkdir processed dir: %w", err)
}
dest := filepath.Join(processedDir, filename)
if _, err := os.Stat(dest); err == nil {
// Archive copy already exists; append timestamp to avoid overwriting. // Archive copy already exists; append timestamp to avoid overwriting.
ext := filepath.Ext(filename) ext := filepath.Ext(filename)
base := strings.TrimSuffix(filename, ext) base := strings.TrimSuffix(filename, ext)
dest = "raw/processed/" + date + "/" + base + "-" + time.Now().UTC().Format("150405") + ext dest = filepath.Join(processedDir, base+"-"+time.Now().UTC().Format("150405")+ext)
} }
if err := copyFromRoot(root, rel, cfg.BrainDir, dest); err != nil { if err := copyFromRoot(root, rel, dest); err != nil {
return fmt.Errorf("copy to processed: %w", err) return fmt.Errorf("copy to processed: %w", err)
} }
if err := putBrainFile(cfg.BrainDir, "raw/"+filepath.ToSlash(rel)+".processed", []byte(date)); err != nil { if err := os.WriteFile(path+".processed", []byte(date), 0o644); 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) slog.Error("watcher: failed to write .processed marker", "error", err)
} }
@@ -206,32 +190,6 @@ func processFile(ctx context.Context, cfg Config, root *os.Root, rawDir, path, d
return nil 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. // deriveSource turns a filename into a human-readable source name.
// "shape-up-book.md" → "Shape Up Book" // "shape-up-book.md" → "Shape Up Book"
func deriveSource(filename string) string { func deriveSource(filename string) string {
@@ -256,22 +214,23 @@ 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", entry := fmt.Sprintf("## %s — watcher error\n\n- **File:** %s\n- **Error:** %s\n\n",
date, filename, runErr.Error()) date, filename, runErr.Error())
if err := brainfs.AppendFile(brainDir, "log.md", []byte(entry)); err != nil { logPath := filepath.Join(brainDir, "log.md")
return fmt.Errorf("write log: %w", err) f, err := os.OpenFile(logPath, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0o644)
} if err != nil {
return nil return fmt.Errorf("open log: %w", err)
} }
// putBrainFile creates or replaces a brain-relative file through the brain if _, err = f.WriteString(entry); err != nil {
// root, never through a symlinked directory or file (hyperguild#158). f.Close() //nolint:errcheck
func putBrainFile(brainDir, rel string, data []byte) error { return fmt.Errorf("write log: %w", err)
return brainfs.PutFile(brainDir, rel, data) }
return f.Close()
} }
// copyFromRoot archives a raw/ file read through the root, refusing anything // 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 // that is not a regular file, so a swapped-in symlink cannot copy an outside
// file into raw/processed/ or raw/failed/ (hyperguild#153). // file into raw/processed/ or raw/failed/ (hyperguild#153).
func copyFromRoot(root *os.Root, rel, brainDir, dstRel string) error { func copyFromRoot(root *os.Root, rel, dst string) error {
fi, err := root.Lstat(rel) fi, err := root.Lstat(rel)
if err != nil { if err != nil {
return err return err
@@ -284,9 +243,13 @@ func copyFromRoot(root *os.Root, rel, brainDir, dstRel string) error {
return err return err
} }
defer func() { _ = in.Close() }() defer func() { _ = in.Close() }()
data, err := io.ReadAll(in) out, err := os.Create(dst)
if err != nil { if err != nil {
return err return err
} }
return putBrainFile(brainDir, dstRel, data) if _, err := io.Copy(out, in); err != nil {
_ = out.Close()
return err
}
return out.Close()
} }
@@ -1,186 +0,0 @@
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 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)
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)))
_ = processDir(context.Background(), Config{BrainDir: brainDir, Interval: time.Hour, Pipeline: pcfg}, "2026-10-05")
got, _ := os.ReadFile(victim)
assert.Equal(t, "untouched", string(got))
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")
}
// 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) {
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
// 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)
}
+4 -2
View File
@@ -3,6 +3,8 @@ package wiki
import ( import (
"fmt" "fmt"
"os"
"path/filepath"
"strings" "strings"
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs" "github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
@@ -48,8 +50,8 @@ func RebuildIndex(brainDir, date string) error {
sb.WriteString("\n") sb.WriteString("\n")
} }
// Written through the brain root, never through a symlink (#158). dest := filepath.Join(brainDir, "wiki", "index.md")
return bfs.PutRegular("wiki/index.md", []byte(sb.String())) return os.WriteFile(dest, []byte(sb.String()), 0o644)
} }
// pageFirstSentence reads the page through the brain root, regular files // pageFirstSentence reads the page through the brain root, regular files
+8 -7
View File
@@ -3,7 +3,8 @@ package wiki
import ( import (
"fmt" "fmt"
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs" "os"
"path/filepath"
"strings" "strings"
) )
@@ -26,14 +27,14 @@ func AppendLog(brainDir, source string, pages, warnings []string, date string) e
} }
sb.WriteString("\n") sb.WriteString("\n")
// Appended through the brain root, never through a symlink (#158). logPath := filepath.Join(brainDir, "log.md")
bfs, err := brainfs.Open(brainDir) f, err := os.OpenFile(logPath, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0o644)
if err != nil { if err != nil {
return fmt.Errorf("open brain: %w", err) return fmt.Errorf("open log: %w", err)
} }
defer func() { _ = bfs.Close() }() if _, err = f.WriteString(sb.String()); err != nil {
if err := bfs.AppendRegular("log.md", []byte(sb.String())); err != nil { f.Close() //nolint:errcheck
return fmt.Errorf("write log: %w", err) return fmt.Errorf("write log: %w", err)
} }
return nil return f.Close()
} }
@@ -1,35 +0,0 @@
package wiki
import (
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// hyperguild#158: RebuildIndex wrote wiki/index.md and AppendLog appended
// log.md with os.WriteFile / os.OpenFile, so a symlinked file was written
// through.
func TestRebuildIndexAndAppendLogDoNotWriteThroughSymlinks(t *testing.T) {
b := t.TempDir()
require.NoError(t, os.MkdirAll(filepath.Join(b, "wiki", "concepts"), 0o755))
victim := filepath.Join(b, "raw", "v.md")
require.NoError(t, os.MkdirAll(filepath.Dir(victim), 0o755))
require.NoError(t, os.WriteFile(victim, []byte("untouched"), 0o644))
require.NoError(t, os.Symlink(filepath.Join("..", "raw", "v.md"), filepath.Join(b, "wiki", "index.md")))
require.NoError(t, os.Symlink(filepath.Join("raw", "v.md"), filepath.Join(b, "log.md")))
assert.Error(t, RebuildIndex(b, "2026-10-05"))
assert.Error(t, AppendLog(b, "src", []string{"p"}, nil, "2026-10-05"))
got, _ := os.ReadFile(victim)
assert.Equal(t, "untouched", string(got))
require.NoError(t, os.Remove(filepath.Join(b, "wiki", "index.md")))
require.NoError(t, os.Remove(filepath.Join(b, "log.md")))
require.NoError(t, RebuildIndex(b, "2026-10-05"), "positive control")
require.NoError(t, AppendLog(b, "src", []string{"p"}, nil, "2026-10-05"), "positive control")
l, _ := os.ReadFile(filepath.Join(b, "log.md"))
assert.Contains(t, string(l), "src")
}