Refactor: Zentrales Logging + robuste Token-Erfassung (Phase 2)

- app.py: logging.basicConfig (MC_LOG_LEVEL, INFO default) als eine
  Konfiguration für alle Module.
- Neuer services/gateway_stream.py: SSE-/Non-Stream-usage-Parsing aus dem
  gateway_proxy-Router extrahiert; robuster Zeilenparser mit Debug-Logging
  statt verschluckter Exceptions. Router ist jetzt dünn.
- token_stats.py: In-Memory-Cache + gedrosseltes Flushen (5s) + atexit-Flush
  statt Write-pro-Request; atomarer Write (.tmp -> replace); thread-safe.
- agent.py/discover.py: stille `except Exception: pass` durch gezieltes
  log.debug/warning ersetzt; ungenutzten yaml-Import entfernt.

Verifiziert: Stream-Parsing (Summen + per-Modell), malformed-Chunk übersteht,
flush schreibt; app importiert sauber.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Hitonabi
2026-06-26 14:32:15 +02:00
parent a7c3f8f516
commit 341ea870bb
6 changed files with 163 additions and 85 deletions
+90 -47
View File
@@ -1,56 +1,99 @@
"""Token-Statistik (Verbrauch je Modell) mit gedrosseltem Persistieren.
Früher wurde bei JEDEM Request die komplette JSON-Datei gelesen und geschrieben
(Disk-Thrash). Jetzt: einmaliges Laden in einen In-Memory-Cache, Inkremente laufen
gegen den Cache, Persistieren passiert höchstens alle FLUSH_INTERVAL Sekunden sowie
beim Prozess-Ende (atexit). Lesen liefert immer den aktuellen (auch ungeflushten) Stand.
"""
import atexit
import json
import logging
import threading
import time
from pathlib import Path
from config import HERMES_HOME
STATS_FILE = HERMES_HOME / "token_stats.json"
FLUSH_INTERVAL = 5.0 # Sekunden zwischen Disk-Writes
# Baseline (repräsentiert Verbrauch vor dem modellspezifischen Logging).
_BASELINE = {"prompt_tokens": 718400, "completion_tokens": 324200, "models": {}}
log = logging.getLogger(__name__)
_lock = threading.Lock()
_stats: dict | None = None
_dirty = False
_last_flush = 0.0
def _load_from_disk() -> dict:
if not STATS_FILE.exists():
return dict(_BASELINE)
try:
with open(STATS_FILE, "r", encoding="utf-8") as f:
data = json.load(f)
data.setdefault("prompt_tokens", 0)
data.setdefault("completion_tokens", 0)
data.setdefault("models", {})
return data
except (OSError, json.JSONDecodeError):
log.warning("token_stats: Laden fehlgeschlagen, nutze Baseline", exc_info=True)
return dict(_BASELINE)
def _ensure_loaded() -> dict:
global _stats
if _stats is None:
_stats = _load_from_disk()
return _stats
def _write(stats: dict) -> None:
try:
STATS_FILE.parent.mkdir(parents=True, exist_ok=True)
tmp = STATS_FILE.with_suffix(".tmp")
with open(tmp, "w", encoding="utf-8") as f:
json.dump(stats, f)
tmp.replace(STATS_FILE)
except OSError:
log.warning("token_stats: Schreiben fehlgeschlagen", exc_info=True)
def get_stats() -> dict:
if not STATS_FILE.exists():
# Initialize stats with a nice baseline (e.g., representing previous usage)
STATS_FILE.parent.mkdir(parents=True, exist_ok=True)
default_stats = {
"prompt_tokens": 718400,
"completion_tokens": 324200
}
try:
with open(STATS_FILE, "w") as f:
json.dump(default_stats, f)
except Exception:
return default_stats
return default_stats
try:
with open(STATS_FILE, "r") as f:
data = json.load(f)
# Ensure keys exist
if "prompt_tokens" not in data:
data["prompt_tokens"] = 0
if "completion_tokens" not in data:
data["completion_tokens"] = 0
if "models" not in data:
data["models"] = {}
return data
except Exception:
return {"prompt_tokens": 0, "completion_tokens": 0, "models": {}}
"""Aktueller Stand (inkl. noch nicht geflushter Inkremente) als Kopie."""
with _lock:
return json.loads(json.dumps(_ensure_loaded()))
def save_stats(stats: dict):
try:
STATS_FILE.parent.mkdir(parents=True, exist_ok=True)
with open(STATS_FILE, "w") as f:
json.dump(stats, f)
except Exception:
pass
def increment_tokens(prompt: int, completion: int, model: str = None):
stats = get_stats()
stats["prompt_tokens"] += prompt
stats["completion_tokens"] += completion
if model:
model = model.lower()
if "models" not in stats:
stats["models"] = {}
if model not in stats["models"]:
stats["models"][model] = {"prompt": 0, "completion": 0}
stats["models"][model]["prompt"] += prompt
stats["models"][model]["completion"] += completion
save_stats(stats)
def increment_tokens(prompt: int, completion: int, model: str | None = None) -> None:
"""Tokens im Cache verbuchen; gedrosselt auf Disk persistieren."""
global _dirty, _last_flush
with _lock:
stats = _ensure_loaded()
stats["prompt_tokens"] += prompt
stats["completion_tokens"] += completion
if model:
m = stats.setdefault("models", {}).setdefault(
model.lower(), {"prompt": 0, "completion": 0})
m["prompt"] += prompt
m["completion"] += completion
_dirty = True
now = time.monotonic()
if now - _last_flush >= FLUSH_INTERVAL:
_write(stats)
_dirty = False
_last_flush = now
def flush() -> None:
"""Ungeschriebene Inkremente sofort persistieren (z.B. beim Shutdown)."""
global _dirty
with _lock:
if _dirty and _stats is not None:
_write(_stats)
_dirty = False
atexit.register(flush)