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 <noreply@anthropic.com>
This commit is contained in:
@@ -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)
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user