Delete the oldest report files to stay under the size cap (closes #54)

When a report would take the report files past DATA_DIR_MAX_BYTES,
reportbuf now deletes the oldest report files until it fits, and does
the same at start when files left by an earlier run are already past
it. The buffer keeps the files it may delete in a list, oldest first; a
file joins it only once it is completely written, so a file still being
written is never deleted. A report is refused with 507 only when the
reports not yet written leave no room for it on their own, and then no
file is deleted. A file whose deletion fails keeps counting; one
already deleted by hand counts as freed.

Model: opus-5-5

backend/internal/reportbuf/reportbuf.go

@@ -1,5 +1,6 @@
 // Package reportbuf accumulates telemetry reports in memory
-// and periodically flushes them to zstd-compressed JSONL files.
+// and periodically flushes them to zstd-compressed JSONL files,
+// deleting the oldest files to keep them under a size cap.
 package reportbuf
 
 import (
@@ -37,8 +38,9 @@ const (
 	fileSuffix = ".jsonl.zst"
 )
 
-// ErrFull is returned by Append when storing the report would
-// take the report files past the configured maximum size.
+// ErrFull is returned by Append when the reports not yet written
+// leave no room for the report under the configured maximum size,
+// however many report files are deleted.
 var ErrFull = errors.New("report files at their size cap")
 
 // Params defines the dependencies for Buffer.
@@ -49,15 +51,28 @@ type Params struct {
 	Logger *logger.Logger
 }
 
+// reportFile is a report file that may be deleted to make room, with
+// the size it counts for in usedBytes.
+type reportFile struct {
+	name string
+	size int64
+}
+
 // Buffer accumulates JSON lines in memory and flushes them
 // to zstd-compressed files on disk.
 type Buffer struct {
-	buf      bytes.Buffer
-	dataDir  string
-	done     chan struct{}
-	log      *slog.Logger
-	maxBytes int64
-	mu       sync.Mutex
+	buf     bytes.Buffer
+	dataDir string
+	done    chan struct{}
+	// files are the report files that may be deleted to make room,
+	// oldest first: those in dataDir at start, then each one this
+	// buffer writes, once it is complete. A file still being written
+	// is not among them. filesBytes is their total size.
+	files      []reportFile
+	filesBytes int64
+	log        *slog.Logger
+	maxBytes   int64
+	mu         sync.Mutex
 	// now is the clock report files are named by: time.Now, except
 	// in tests that need two flushes to share a timestamp.
 	now func() time.Time
@@ -97,12 +112,28 @@ func New(
 				return fmt.Errorf("create data dir: %w", err)
 			}
 
-			// Report files left by earlier runs count too.
-			b.usedBytes, err = reportFilesSize(b.dataDir)
+			// Report files left by earlier runs count too, and are
+			// the first to be deleted to make room.
+			files, err := reportFiles(b.dataDir)
 			if err != nil {
 				return err
 			}
 
+			b.mu.Lock()
+
+			b.files = files
+			for _, f := range files {
+				b.filesBytes += f.size
+			}
+
+			b.usedBytes = b.filesBytes
+
+			// The files may be past the cap, if it was lowered since
+			// the last run.
+			b.deleteOldestFiles(0)
+
+			b.mu.Unlock()
+
 			go b.flushLoop()
 
 			return nil
@@ -128,9 +159,10 @@ func New(
 }
 
 // Append marshals v as a single JSON line and appends it to
-// the buffer. It stores nothing and returns ErrFull if the line
-// would take usedBytes past maxBytes. If the buffer reaches the
-// size threshold, it is drained and written to disk
+// the buffer. If the line would take usedBytes past maxBytes, the
+// oldest report files are deleted to make room; it stores nothing
+// and returns ErrFull if that cannot make room. If the buffer
+// reaches the size threshold, it is drained and written to disk
 // asynchronously.
 func (b *Buffer) Append(v any) error {
 	line, err := json.Marshal(v)
@@ -142,6 +174,8 @@ func (b *Buffer) Append(v any) error {
 
 	b.mu.Lock()
 
+	b.deleteOldestFiles(lineBytes)
+
 	if b.usedBytes+lineBytes > b.maxBytes {
 		b.mu.Unlock()
 
@@ -171,6 +205,37 @@ func (b *Buffer) Append(v any) error {
 	return nil
 }
 
+// deleteOldestFiles deletes report files, oldest first, until n more
+// bytes fit under maxBytes. It deletes none when the reports not yet
+// written leave no room for n even with every file gone, since that
+// would lose the files for nothing. The caller must hold b.mu.
+func (b *Buffer) deleteOldestFiles(n int64) {
+	for b.usedBytes+n > b.maxBytes && len(b.files) > 0 {
+		if b.usedBytes-b.filesBytes+n > b.maxBytes {
+			return
+		}
+
+		f := b.files[0]
+		b.files = b.files[1:]
+		b.filesBytes -= f.size
+
+		// A file already gone, deleted by hand, has freed its room too.
+		err := os.Remove(filepath.Join(b.dataDir, f.name))
+		if err != nil && !errors.Is(err, fs.ErrNotExist) {
+			// The file is still there, so it still counts. It is
+			// not tried again until the next start.
+			b.log.Error("delete report file failed",
+				"file", f.name, "error", err)
+
+			continue
+		}
+
+		b.usedBytes -= f.size
+		b.log.Info("deleted report file to make room",
+			"file", f.name, "bytes", f.size)
+	}
+}
+
 // flushLoop runs a ticker that periodically flushes buffered
 // data to disk until the done channel is closed.
 func (b *Buffer) flushLoop() {
@@ -270,25 +335,28 @@ func (b *Buffer) writeFile(data []byte) error {
 	}
 
 	// The reports counted at their uncompressed size while they
-	// waited; now they count as the file. After a failed write they
-	// stay counted as they were, which errs toward refusing reports
-	// early rather than letting the files pass the cap.
+	// waited; now they count as the file, which from here on may be
+	// deleted to make room. After a failed write they stay counted as
+	// they were, which errs toward refusing reports early rather than
+	// letting the files pass the cap.
 	b.mu.Lock()
 	b.usedBytes += info.Size() - int64(len(data))
+	b.files = append(b.files, reportFile{name: name, size: info.Size()})
+	b.filesBytes += info.Size()
 	b.mu.Unlock()
 
 	return nil
 }
 
-// reportFilesSize returns the total size of the report files in
-// dir.
-func reportFilesSize(dir string) (int64, error) {
+// reportFiles returns the report files in dir, oldest first:
+// os.ReadDir sorts them by name, and the names sort by time.
+func reportFiles(dir string) ([]reportFile, error) {
 	entries, err := os.ReadDir(dir)
 	if err != nil {
-		return 0, fmt.Errorf("read data dir: %w", err)
+		return nil, fmt.Errorf("read data dir: %w", err)
 	}
 
-	var total int64
+	files := make([]reportFile, 0, len(entries))
 
 	for _, entry := range entries {
 		name := entry.Name()
@@ -299,11 +367,11 @@ func reportFilesSize(dir string) (int64, error) {
 
 		info, err := entry.Info()
 		if err != nil {
-			return 0, fmt.Errorf("stat report file: %w", err)
+			return nil, fmt.Errorf("stat report file: %w", err)
 		}
 
-		total += info.Size()
+		files = append(files, reportFile{name: name, size: info.Size()})
 	}
 
-	return total, nil
+	return files, nil
 }