Keep checkpoints aligned with PromptKit profiles

internal/framework/llm/promptkit_profile_fingerprint.go

@@ -0,0 +1,82 @@
+package llm
+
+import (
+	"crypto/sha256"
+	"encoding/hex"
+	"fmt"
+	"io/fs"
+	"os"
+	"path/filepath"
+	"sort"
+	"strings"
+)
+
+const (
+	promptKitProfileFingerprintName = "promptkit_profile_source"
+	// The built-in profile catalog is compiled into this pinned PromptKit
+	// release. Update this identity when the dependency is upgraded.
+	promptKitBuiltinProfileCatalogID = "promptkit:v0.1.0:builtin-profiles"
+)
+
+func promptKitProfileFingerprint(profileDir, profileFile string) (CheckpointFingerprint, error) {
+	hasher := sha256.New()
+	writeFingerprintPart(hasher, []byte(promptKitBuiltinProfileCatalogID))
+
+	switch {
+	case strings.TrimSpace(profileFile) != "":
+		data, err := os.ReadFile(strings.TrimSpace(profileFile))
+		if err != nil {
+			return CheckpointFingerprint{}, fmt.Errorf("read PromptKit profile file for checkpoint identity: %w", err)
+		}
+		writeFingerprintPart(hasher, data)
+	case strings.TrimSpace(profileDir) != "":
+		digests, err := promptKitProfileFileDigests(strings.TrimSpace(profileDir))
+		if err != nil {
+			return CheckpointFingerprint{}, err
+		}
+		for _, digest := range digests {
+			writeFingerprintPart(hasher, digest)
+		}
+	}
+
+	return CheckpointFingerprint{
+		Name:  promptKitProfileFingerprintName,
+		Value: "sha256:" + hex.EncodeToString(hasher.Sum(nil)),
+	}, nil
+}
+
+func promptKitProfileFileDigests(root string) ([][]byte, error) {
+	var digests [][]byte
+	err := filepath.WalkDir(root, func(name string, entry fs.DirEntry, walkErr error) error {
+		if walkErr != nil {
+			return walkErr
+		}
+		if entry.IsDir() {
+			return nil
+		}
+		extension := filepath.Ext(entry.Name())
+		if extension != ".yaml" && extension != ".yml" {
+			return nil
+		}
+		data, err := os.ReadFile(name)
+		if err != nil {
+			return err
+		}
+		sum := sha256.Sum256(data)
+		digests = append(digests, append([]byte(nil), sum[:]...))
+		return nil
+	})
+	if err != nil {
+		return nil, fmt.Errorf("read PromptKit profile directory for checkpoint identity: %w", err)
+	}
+	sort.Slice(digests, func(i, j int) bool {
+		return string(digests[i]) < string(digests[j])
+	})
+	return digests, nil
+}
+
+func writeFingerprintPart(hasher interface{ Write([]byte) (int, error) }, value []byte) {
+	length := []byte(fmt.Sprintf("%d:", len(value)))
+	_, _ = hasher.Write(length)
+	_, _ = hasher.Write(value)
+}