fix(vectorstore): walk and read the brain through brainfs (#157, slice 3)
Sync walked wiki/ and knowledge/ with filepath.WalkDir and read each .md with os.ReadFile. A symlinked note (Syncthing syncs symlinks) had its target embedded into pgvector and served by semantic search; a FIFO stalled the sync. The walk and read now go through brainfs: regular files only, type checked on the opened handle. - Chunks already embedded from a symlinked note are deleted on the next sync, because the note is no longer seen. - A walk error still aborts Sync before the delete pass, so an unreadable subdir does not delete chunks of files that exist. A missing scan dir is skipped as before. - brainfs gains Lstat, used for the mtime staleness check. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -2,12 +2,15 @@ package vectorstore
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io/fs"
|
||||
"log/slog"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"path"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/mathiasbq/hyperguild/ingestion/internal/brainfs"
|
||||
)
|
||||
|
||||
// Embedder produces dense vectors. The embed package's Client satisfies
|
||||
@@ -90,31 +93,36 @@ func Sync(ctx context.Context, brainDir string, store Store, embedder Embedder)
|
||||
}
|
||||
seenParents := make(map[string]struct{})
|
||||
|
||||
for _, sub := range scanDirs {
|
||||
root := filepath.Join(brainDir, sub)
|
||||
if _, err := os.Stat(root); os.IsNotExist(err) {
|
||||
continue
|
||||
}
|
||||
// Through the brain root, regular files only (hyperguild#157): the brain
|
||||
// is a Syncthing folder, and os.ReadFile followed a synced symlink into
|
||||
// the embeddings and blocked on a FIFO.
|
||||
bfs, err := brainfs.Open(brainDir)
|
||||
if err != nil {
|
||||
return res, fmt.Errorf("open brain: %w", err)
|
||||
}
|
||||
defer func() { _ = bfs.Close() }()
|
||||
|
||||
err = filepath.WalkDir(root, func(path string, d os.DirEntry, err error) error {
|
||||
if err != nil {
|
||||
return err
|
||||
for _, sub := range scanDirs {
|
||||
var walkErr error
|
||||
onErr := func(rel string, err error) {
|
||||
if rel == sub && errors.Is(err, fs.ErrNotExist) {
|
||||
return
|
||||
}
|
||||
if d.IsDir() || !strings.HasSuffix(path, ".md") || d.Name() == "_index.md" {
|
||||
if walkErr == nil {
|
||||
walkErr = fmt.Errorf("%s: %w", rel, err)
|
||||
}
|
||||
}
|
||||
err = bfs.WalkRegular(sub, func(relSlash string) error {
|
||||
if !strings.HasSuffix(relSlash, ".md") || path.Base(relSlash) == "_index.md" {
|
||||
return nil
|
||||
}
|
||||
rel, err := filepath.Rel(brainDir, path)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
relSlash := filepath.ToSlash(rel)
|
||||
seenParents[relSlash] = struct{}{}
|
||||
|
||||
if ps, ok := parents[relSlash]; ok {
|
||||
// File already has chunks in the store. Re-embed only when
|
||||
// the file has been edited since the oldest chunk was
|
||||
// written. Tolerate clock skew with a sub-second grace.
|
||||
info, statErr := d.Info()
|
||||
info, statErr := bfs.Lstat(relSlash)
|
||||
if statErr != nil {
|
||||
res.Errors = append(res.Errors, fmt.Errorf("stat %s: %w", relSlash, statErr))
|
||||
return nil
|
||||
@@ -132,7 +140,7 @@ func Sync(ctx context.Context, brainDir string, store Store, embedder Embedder)
|
||||
}
|
||||
}
|
||||
|
||||
content, readErr := os.ReadFile(path)
|
||||
content, readErr := bfs.ReadRegular(relSlash)
|
||||
if readErr != nil {
|
||||
res.Errors = append(res.Errors, fmt.Errorf("read %s: %w", relSlash, readErr))
|
||||
return nil
|
||||
@@ -151,7 +159,12 @@ func Sync(ctx context.Context, brainDir string, store Store, embedder Embedder)
|
||||
res.Added++
|
||||
}
|
||||
return nil
|
||||
})
|
||||
}, onErr)
|
||||
if err == nil {
|
||||
err = walkErr
|
||||
}
|
||||
// Abort before the delete pass: an incomplete walk would leave
|
||||
// seenParents short and delete chunks of files that still exist.
|
||||
if err != nil {
|
||||
return res, fmt.Errorf("walk %s: %w", sub, err)
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user