fix(sync): use aggregate hermes archive fingerprints

Hermes archive freshness needs the state.db sync path to compare the same aggregate fingerprint it persists. Discovering through the public Hermes session lister reselected state.db and missed sibling transcripts, so state.db events could avoid real skip-cache parity.\n\nEnumerate direct transcript files for the archive snapshot and stamp archive parse results with the aggregate state.db fingerprint before writing. This keeps unchanged archive syncs comparable while still refreshing when sibling transcripts change.\n\nValidation: go test -tags "fts5" ./internal/parser ./internal/sync; go vet ./...; make nilaway

Author: mariusvniekerk

internal/sync/engine.go

@@ -6399,6 +6399,11 @@ func (e *Engine) processHermes(
 		if err != nil {
 			return processResult{err: err}
 		}
+		for i := range results {
+			results[i].Session.File.Path = file.Path
+			results[i].Session.File.Size = info.Size()
+			results[i].Session.File.Mtime = info.ModTime().UnixNano()
+		}
 		return processResult{results: results, forceReplace: true}
 	}
 
@@ -6431,8 +6436,8 @@ func hermesArchiveEffectiveInfo(path string, info os.FileInfo) os.FileInfo {
 	}
 	size := info.Size()
 	mtime := info.ModTime().UnixNano()
-	for _, file := range parser.DiscoverHermesSessions(sessionsDir) {
-		fileInfo, err := os.Stat(file.Path)
+	for _, path := range hermesArchiveTranscriptFiles(sessionsDir) {
+		fileInfo, err := os.Stat(path)
 		if err != nil || fileInfo == nil || fileInfo.IsDir() {
 			continue
 		}
@@ -6444,6 +6449,29 @@ func hermesArchiveEffectiveInfo(path string, info os.FileInfo) os.FileInfo {
 	return fakeSnapshotInfo{fSize: size, fMtime: mtime}
 }
 
+func hermesArchiveTranscriptFiles(sessionsDir string) []string {
+	if sessionsDir == "" {
+		return nil
+	}
+	entries, err := os.ReadDir(sessionsDir)
+	if err != nil {
+		return nil
+	}
+	paths := make([]string, 0, len(entries))
+	for _, entry := range entries {
+		if entry.IsDir() {
+			continue
+		}
+		name := entry.Name()
+		if strings.HasSuffix(name, ".jsonl") ||
+			strings.HasPrefix(name, "session_") && strings.HasSuffix(name, ".json") {
+			paths = append(paths, filepath.Join(sessionsDir, name))
+		}
+	}
+	slices.Sort(paths)
+	return paths
+}
+
 func hermesArchiveSourcePaths(path string) (stateDB, sessionsDir string, ok bool) {
 	path = filepath.Clean(path)
 	switch filepath.Base(path) {

internal/sync/hermes_archive_test.go

@@ -0,0 +1,143 @@
+package sync
+
+import (
+	"database/sql"
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+
+	_ "github.com/mattn/go-sqlite3"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"go.kenn.io/agentsview/internal/dbtest"
+	"go.kenn.io/agentsview/internal/parser"
+)
+
+func TestHermesArchiveEffectiveInfoIncludesDirectTranscripts(t *testing.T) {
+	root := t.TempDir()
+	stateDB := writeHermesArchiveStateDB(t, root)
+	transcriptPath := filepath.Join(root, "sessions", "extra.jsonl")
+	require.NoError(t, os.MkdirAll(filepath.Dir(transcriptPath), 0o755))
+	require.NoError(t, os.WriteFile(transcriptPath, []byte("{}\n{}\n"), 0o644))
+
+	stateInfo, err := os.Stat(stateDB)
+	require.NoError(t, err)
+	transcriptInfo, err := os.Stat(transcriptPath)
+	require.NoError(t, err)
+	transcriptTime := time.Now().Add(2 * time.Second).Truncate(time.Second)
+	require.NoError(t, os.Chtimes(transcriptPath, transcriptTime, transcriptTime))
+
+	got := hermesArchiveEffectiveInfo(stateDB, stateInfo)
+
+	assert.Equal(t, stateInfo.Size()+transcriptInfo.Size(), got.Size())
+	assert.Equal(t, transcriptTime.UnixNano(), got.ModTime().UnixNano())
+}
+
+func TestProcessHermesArchivePersistsAggregateFingerprint(t *testing.T) {
+	root := t.TempDir()
+	stateDB := writeHermesArchiveStateDB(t, root)
+	transcriptPath := filepath.Join(root, "sessions", "extra.jsonl")
+	require.NoError(t, os.MkdirAll(filepath.Dir(transcriptPath), 0o755))
+	require.NoError(t, os.WriteFile(
+		transcriptPath,
+		[]byte(
+			`{"role":"session_meta","platform":"cli","timestamp":"2026-05-14T10:00:00.000000"}`+"\n"+
+				`{"role":"user","content":"new transcript","timestamp":"2026-05-14T10:01:00.000000"}`+"\n",
+		),
+		0o644,
+	))
+
+	stateInfo, err := os.Stat(stateDB)
+	require.NoError(t, err)
+	effectiveInfo := hermesArchiveEffectiveInfo(stateDB, stateInfo)
+	engine := NewEngine(dbtest.OpenTestDB(t), EngineConfig{
+		AgentDirs: map[parser.AgentType][]string{
+			parser.AgentHermes: {filepath.Join(root, "sessions")},
+		},
+		Machine: "local",
+	})
+
+	res := engine.processHermes(parser.DiscoveredFile{
+		Path:  stateDB,
+		Agent: parser.AgentHermes,
+	}, stateInfo)
+
+	require.NoError(t, res.err)
+	require.NotEmpty(t, res.results)
+	for _, result := range res.results {
+		assert.Equal(t, stateDB, result.Session.File.Path)
+		assert.Equal(t, effectiveInfo.Size(), result.Session.File.Size)
+		assert.Equal(t, effectiveInfo.ModTime().UnixNano(), result.Session.File.Mtime)
+	}
+}
+
+func writeHermesArchiveStateDB(t *testing.T, root string) string {
+	t.Helper()
+	stateDB := filepath.Join(root, "state.db")
+	conn, err := sql.Open("sqlite3", stateDB)
+	require.NoError(t, err)
+	t.Cleanup(func() { _ = conn.Close() })
+
+	_, err = conn.Exec(`
+		CREATE TABLE sessions (
+			id TEXT PRIMARY KEY,
+			source TEXT NOT NULL,
+			user_id TEXT,
+			model TEXT,
+			model_config TEXT,
+			system_prompt TEXT,
+			parent_session_id TEXT,
+			started_at REAL NOT NULL,
+			ended_at REAL,
+			end_reason TEXT,
+			message_count INTEGER DEFAULT 0,
+			tool_call_count INTEGER DEFAULT 0,
+			input_tokens INTEGER DEFAULT 0,
+			output_tokens INTEGER DEFAULT 0,
+			cache_read_tokens INTEGER DEFAULT 0,
+			cache_write_tokens INTEGER DEFAULT 0,
+			reasoning_tokens INTEGER DEFAULT 0,
+			billing_provider TEXT,
+			billing_base_url TEXT,
+			billing_mode TEXT,
+			estimated_cost_usd REAL,
+			actual_cost_usd REAL,
+			cost_status TEXT,
+			cost_source TEXT,
+			pricing_version TEXT,
+			title TEXT,
+			api_call_count INTEGER DEFAULT 0
+		);
+		CREATE TABLE messages (
+			id INTEGER PRIMARY KEY AUTOINCREMENT,
+			session_id TEXT NOT NULL,
+			role TEXT NOT NULL,
+			content TEXT,
+			tool_call_id TEXT,
+			tool_calls TEXT,
+			tool_name TEXT,
+			timestamp REAL NOT NULL,
+			token_count INTEGER,
+			finish_reason TEXT,
+			reasoning TEXT,
+			reasoning_content TEXT,
+			reasoning_details TEXT,
+			codex_reasoning_items TEXT,
+			codex_message_items TEXT
+		);
+		INSERT INTO sessions (
+			id, source, model, started_at, ended_at, message_count
+		) VALUES (
+			'child', 'discord', 'gpt-5.4', 1778767200.0, 1778767800.0, 1
+		);
+		INSERT INTO messages (
+			session_id, role, content, timestamp
+		) VALUES (
+			'child', 'user', 'state db message', 1778767210.0
+		);
+	`)
+	require.NoError(t, err)
+	return stateDB
+}