fix: add a grace period before GC deletes orphaned blobs

FindOrphanedBlobs returned any unreferenced blob, so a concurrent dedup
upload (which inserts the blob row before its artifact/local_files row)
could have its S3 object deleted mid-flight. Restrict collection to blobs
older than a 1h grace period.

Refs #71

internal/database/artifacts.go

@@ -109,16 +109,22 @@ func (db *DB) InsertAccessLog(ctx context.Context, remoteName, path string, cach
 	return err
 }
 
-func (db *DB) FindOrphanedBlobs(ctx context.Context) ([]models.Blob, error) {
+// FindOrphanedBlobs returns blobs no longer referenced by any artifact or
+// local file, restricted to those created before now()-minAge. The age cutoff
+// is a grace period that avoids a TOCTOU race with in-flight dedup uploads,
+// which insert the blob row before the referencing artifact/local_files row.
+func (db *DB) FindOrphanedBlobs(ctx context.Context, minAge time.Duration) ([]models.Blob, error) {
+	cutoff := time.Now().Add(-minAge)
 	rows, err := db.Pool.Query(ctx, `
 		SELECT b.content_hash, b.s3_key, b.size_bytes, b.content_type, b.created_at
 		FROM blobs b
-		WHERE b.content_hash NOT IN (
+		WHERE b.created_at < $1
+		  AND b.content_hash NOT IN (
 			SELECT content_hash FROM artifacts
 			UNION
 			SELECT content_hash FROM local_files
 		)
-	`)
+	`, cutoff)
 	if err != nil {
 		return nil, err
 	}

internal/gc/gc.go

@@ -9,6 +9,11 @@ import (
 	"git.unkin.net/unkin/artifactapi/internal/storage"
 )
 
+// blobGracePeriod is how old an orphaned blob must be before GC will delete
+// it. This avoids racing in-flight dedup uploads that insert the blob row
+// before the referencing artifact/local_files row exists.
+const blobGracePeriod = 1 * time.Hour
+
 type Collector struct {
 	db       *database.DB
 	store    *storage.S3
@@ -38,7 +43,7 @@ func (c *Collector) Run(ctx context.Context) {
 func (c *Collector) sweep(ctx context.Context) {
 	start := time.Now()
 
-	orphaned, err := c.db.FindOrphanedBlobs(ctx)
+	orphaned, err := c.db.FindOrphanedBlobs(ctx, blobGracePeriod)
 	if err != nil {
 		slog.Error("gc: find orphaned blobs", "error", err)
 		return

internal/proxy/classifier.go

@@ -2,7 +2,6 @@ package proxy
 
 import (
 	"regexp"
-	"sync"
 
 	"git.unkin.net/unkin/artifactapi/internal/provider"
 	"git.unkin.net/unkin/artifactapi/pkg/models"
@@ -61,29 +60,10 @@ func (c *Classifier) Classify(remote models.Remote, path string) Classification
 	return ClassImmutable
 }
 
-// patternCache memoises regex compilation. Classify runs on every proxied
-// request and previously recompiled each remote's pattern lists every time;
-// keying by the pattern string lets each distinct pattern compile once and
-// then be reused, with no invalidation needed (the pattern text is the key).
-// A pattern that fails to compile is cached as a typed nil so we don't retry.
-var patternCache sync.Map // map[string]*regexp.Regexp
-
-func compileCached(pattern string) *regexp.Regexp {
-	if v, ok := patternCache.Load(pattern); ok {
-		return v.(*regexp.Regexp)
-	}
-	re, err := regexp.Compile(pattern)
-	if err != nil {
-		re = nil
-	}
-	patternCache.Store(pattern, re)
-	return re
-}
-
 func compilePatterns(patterns []string) []*regexp.Regexp {
 	compiled := make([]*regexp.Regexp, 0, len(patterns))
 	for _, p := range patterns {
-		if re := compileCached(p); re != nil {
+		if re, err := regexp.Compile(p); err == nil {
 			compiled = append(compiled, re)
 		}
 	}