feat: add local-vs-cloud token and throughput metrics (#85)

bin/timmy-dashboard

@@ -9,6 +9,7 @@ Usage:
 
 import json
 import os
+import sqlite3
 import subprocess
 import sys
 import time
@@ -16,6 +17,12 @@ import urllib.request
 from datetime import datetime, timezone, timedelta
 from pathlib import Path
 
+REPO_ROOT = Path(__file__).resolve().parent.parent
+if str(REPO_ROOT) not in sys.path:
+    sys.path.insert(0, str(REPO_ROOT))
+
+from metrics_helpers import summarize_local_metrics, summarize_session_rows
+
 HERMES_HOME = Path.home() / ".hermes"
 TIMMY_HOME = Path.home() / ".timmy"
 METRICS_DIR = TIMMY_HOME / "metrics"
@@ -60,6 +67,30 @@ def get_hermes_sessions():
         return []
 
 
+def get_session_rows(hours=24):
+    state_db = HERMES_HOME / "state.db"
+    if not state_db.exists():
+        return []
+    cutoff = time.time() - (hours * 3600)
+    try:
+        conn = sqlite3.connect(str(state_db))
+        rows = conn.execute(
+            """
+            SELECT model, source, COUNT(*) as sessions,
+                   SUM(message_count) as msgs,
+                   SUM(tool_call_count) as tools
+            FROM sessions
+            WHERE started_at > ? AND model IS NOT NULL AND model != ''
+            GROUP BY model, source
+            """,
+            (cutoff,),
+        ).fetchall()
+        conn.close()
+        return rows
+    except Exception:
+        return []
+
+
 def get_heartbeat_ticks(date_str=None):
     if not date_str:
         date_str = datetime.now().strftime("%Y%m%d")
@@ -130,6 +161,9 @@ def render(hours=24):
     ticks = get_heartbeat_ticks()
     metrics = get_local_metrics(hours)
     sessions = get_hermes_sessions()
+    session_rows = get_session_rows(hours)
+    local_summary = summarize_local_metrics(metrics)
+    session_summary = summarize_session_rows(session_rows)
 
     loaded_names = {m.get("name", "") for m in loaded}
     now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
@@ -159,28 +193,18 @@ def render(hours=24):
     print(f"\n  {BOLD}LOCAL INFERENCE ({len(metrics)} calls, last {hours}h){RST}")
     print(f"  {DIM}{'-' * 55}{RST}")
     if metrics:
-        by_caller = {}
-        for r in metrics:
-            caller = r.get("caller", "unknown")
-            if caller not in by_caller:
-                by_caller[caller] = {"count": 0, "success": 0, "errors": 0}
-            by_caller[caller]["count"] += 1
-            if r.get("success"):
-                by_caller[caller]["success"] += 1
-            else:
-                by_caller[caller]["errors"] += 1
-        for caller, stats in by_caller.items():
-            err = f"  {RED}err:{stats['errors']}{RST}" if stats["errors"] else ""
-            print(f"    {caller:25s}  calls:{stats['count']:4d}  "
-                  f"{GREEN}ok:{stats['success']}{RST}{err}")
+        print(f"    Tokens: {local_summary['input_tokens']} in  |  {local_summary['output_tokens']} out  |  {local_summary['total_tokens']} total")
+        if local_summary.get('avg_latency_s') is not None:
+            print(f"    Avg latency: {local_summary['avg_latency_s']:.2f}s")
+        if local_summary.get('avg_tokens_per_second') is not None:
+            print(f"    Avg throughput: {GREEN}{local_summary['avg_tokens_per_second']:.2f} tok/s{RST}")
+        for caller, stats in sorted(local_summary['by_caller'].items()):
+            err = f"  {RED}err:{stats['failed_calls']}{RST}" if stats['failed_calls'] else ""
+            print(f"    {caller:25s}  calls:{stats['calls']:4d}  tokens:{stats['total_tokens']:5d}  {GREEN}ok:{stats['successful_calls']}{RST}{err}")
 
-        by_model = {}
-        for r in metrics:
-            model = r.get("model", "unknown")
-            by_model[model] = by_model.get(model, 0) + 1
         print(f"\n    {DIM}Models used:{RST}")
-        for model, count in sorted(by_model.items(), key=lambda x: -x[1]):
-            print(f"      {model:30s}  {count} calls")
+        for model, stats in sorted(local_summary['by_model'].items(), key=lambda x: -x[1]['calls']):
+            print(f"      {model:30s}  {stats['calls']} calls  {stats['total_tokens']} tok")
     else:
         print(f"    {DIM}(no local calls recorded yet){RST}")
 
@@ -211,15 +235,18 @@ def render(hours=24):
     else:
         print(f"    {DIM}(no ticks today){RST}")
 
-    # ── HERMES SESSIONS ──
-    local_sessions = [s for s in sessions
-                     if "localhost:11434" in str(s.get("base_url", ""))]
+    # ── HERMES SESSIONS / SOVEREIGNTY LOAD ──
+    local_sessions = [s for s in sessions if "localhost:11434" in str(s.get("base_url", ""))]
     cloud_sessions = [s for s in sessions if s not in local_sessions]
-    print(f"\n  {BOLD}HERMES SESSIONS{RST}")
+    print(f"\n  {BOLD}HERMES SESSIONS / SOVEREIGNTY LOAD{RST}")
     print(f"  {DIM}{'-' * 55}{RST}")
-    print(f"    Total: {len(sessions)}  |  "
-          f"{GREEN}Local: {len(local_sessions)}{RST}  |  "
-          f"{YELLOW}Cloud: {len(cloud_sessions)}{RST}")
+    print(f"    Session cache: {len(sessions)} total  |  {GREEN}{len(local_sessions)} local{RST}  |  {YELLOW}{len(cloud_sessions)} cloud{RST}")
+    if session_rows:
+        print(f"    Session DB:    {session_summary['total_sessions']} total  |  {GREEN}{session_summary['local_sessions']} local{RST}  |  {YELLOW}{session_summary['cloud_sessions']} cloud{RST}")
+        print(f"    Token est:     {GREEN}{session_summary['local_est_tokens']} local{RST}  |  {YELLOW}{session_summary['cloud_est_tokens']} cloud{RST}")
+        print(f"    Est cloud cost: ${session_summary['cloud_est_cost_usd']:.4f}")
+    else:
+        print(f"    {DIM}(no session-db stats available){RST}")
 
     # ── ACTIVE LOOPS ──
     print(f"\n  {BOLD}ACTIVE LOOPS{RST}")