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
@@ -4,16 +4,20 @@ Status + verlinkt das standalone hermes-webui. Voller Zugriff + Tools/MCP werden
|
||||
Hermes' eigener Config verdrahtet (siehe docs/HERMES_SETUP.md).
|
||||
"""
|
||||
|
||||
import logging
|
||||
|
||||
import httpx
|
||||
|
||||
from config import HERMES_API_URL, HERMES_HOME, HERMES_WEBUI_URL, yaml
|
||||
from config import HERMES_API_URL, HERMES_HOME, HERMES_WEBUI_URL
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _reach(url: str, path: str = "") -> bool:
|
||||
try:
|
||||
with httpx.Client(timeout=3.0) as c:
|
||||
return c.get(f"{url}{path}").status_code < 500
|
||||
except Exception:
|
||||
except httpx.HTTPError:
|
||||
return False
|
||||
|
||||
|
||||
@@ -31,7 +35,7 @@ def agent_status() -> dict:
|
||||
if isinstance(cfg, dict):
|
||||
brain_model = cfg.get("model", {}).get("model", "auto")
|
||||
except Exception:
|
||||
pass
|
||||
log.debug("agent_status: Hermes-config.yaml nicht lesbar", exc_info=True)
|
||||
|
||||
|
||||
return {
|
||||
@@ -64,6 +68,7 @@ def update_brain_model(new_model: str) -> bool:
|
||||
with config_path.open("r", encoding="utf-8") as f:
|
||||
cfg = r_yaml.load(f) or {}
|
||||
except Exception:
|
||||
log.debug("update_brain_model: bestehende config.yaml nicht lesbar", exc_info=True)
|
||||
cfg = {}
|
||||
|
||||
if not isinstance(cfg, dict):
|
||||
@@ -85,8 +90,9 @@ def update_brain_model(new_model: str) -> bool:
|
||||
import services.maintenance as maintenance
|
||||
maintenance.restart_service("hermes-gateway")
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
log.warning("update_brain_model: hermes-gateway-Restart fehlgeschlagen", exc_info=True)
|
||||
|
||||
return True
|
||||
except Exception:
|
||||
log.warning("update_brain_model: Schreiben der config.yaml fehlgeschlagen", exc_info=True)
|
||||
return False
|
||||
|
||||
@@ -14,11 +14,15 @@ import time
|
||||
|
||||
import httpx
|
||||
|
||||
import logging
|
||||
|
||||
from config import DISCOVER_CACHE_PATH, DISCOVER_TTL
|
||||
from services.caps import capabilities
|
||||
from services.fit import evaluate_fit, extract_params_b, max_ctx_for
|
||||
from services.sources import CATEGORIES, SKIP_TOKENS, TRUSTED_AUTHORS
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
_FIT_ORDER = {"perfect": 0, "marginal": 1, "too_tight": 2}
|
||||
|
||||
|
||||
@@ -38,6 +42,7 @@ def _fetch_author_models(author: str) -> list:
|
||||
data = c.get(url).json()
|
||||
return data if isinstance(data, list) else []
|
||||
except Exception:
|
||||
log.debug("discover: Abfrage für Autor %s fehlgeschlagen", author, exc_info=True)
|
||||
return []
|
||||
|
||||
|
||||
@@ -109,7 +114,7 @@ def refresh_discover(ram_gb: float) -> dict:
|
||||
tmp.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
|
||||
os.replace(tmp, DISCOVER_CACHE_PATH)
|
||||
except Exception:
|
||||
pass # Cache ist nur Beschleunigung
|
||||
log.debug("discover: Cache-Schreiben fehlgeschlagen (nur Beschleunigung)", exc_info=True)
|
||||
return data
|
||||
|
||||
|
||||
@@ -118,7 +123,7 @@ def load_discover() -> dict | None:
|
||||
if DISCOVER_CACHE_PATH.exists():
|
||||
return json.loads(DISCOVER_CACHE_PATH.read_text(encoding="utf-8"))
|
||||
except Exception:
|
||||
pass
|
||||
log.debug("discover: Cache-Lesen fehlgeschlagen", exc_info=True)
|
||||
return None
|
||||
|
||||
|
||||
@@ -130,4 +135,5 @@ def safe_discover(ram_gb: float) -> dict | None:
|
||||
try:
|
||||
return refresh_discover(ram_gb)
|
||||
except Exception:
|
||||
log.warning("discover: Live-Refresh fehlgeschlagen, nutze Cache", exc_info=True)
|
||||
return cached
|
||||
|
||||
@@ -0,0 +1,41 @@
|
||||
"""Token-Erfassung für den Builtin-Gateway.
|
||||
|
||||
Parst die `usage`-Felder aus llama-swap-Antworten (Stream + Non-Stream) und meldet
|
||||
sie an token_stats. Hält den gateway_proxy-Router dünn und ersetzt die zuvor inline
|
||||
verstreute, still scheiternde String-Suche durch einen testbaren SSE-Zeilenparser.
|
||||
"""
|
||||
|
||||
import json
|
||||
import logging
|
||||
|
||||
from services.token_stats import increment_tokens
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def record_usage(usage: dict | None, model: str) -> None:
|
||||
"""Ein usage-Objekt verbuchen (no-op bei None/leer)."""
|
||||
if not usage:
|
||||
return
|
||||
prompt = usage.get("prompt_tokens", 0)
|
||||
completion = usage.get("completion_tokens", 0)
|
||||
if prompt or completion:
|
||||
increment_tokens(prompt, completion, model=model)
|
||||
|
||||
|
||||
def record_stream_chunk(chunk: bytes, model: str) -> None:
|
||||
"""Rohen SSE-Chunk auf `usage` prüfen und Tokens verbuchen. Fehler werden
|
||||
geloggt (debug) statt verschluckt — ein defekter Chunk bricht den Stream nicht."""
|
||||
if b'"usage"' not in chunk:
|
||||
return
|
||||
text = chunk.decode("utf-8", errors="ignore")
|
||||
for line in text.splitlines():
|
||||
if not line.startswith("data:"):
|
||||
continue
|
||||
data_str = line[5:].strip()
|
||||
if not data_str or data_str == "[DONE]":
|
||||
continue
|
||||
try:
|
||||
record_usage(json.loads(data_str).get("usage"), model)
|
||||
except json.JSONDecodeError:
|
||||
log.debug("gateway stream: usage-Parsing fehlgeschlagen: %s", data_str[:120])
|
||||
@@ -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)
|
||||
|
||||
Reference in New Issue
Block a user