wouser
5daa338c78
- Migrate from Flask to Quart (async) for better concurrency - Add httpx with HTTP/2 connection pooling for Telegram - Add diskcache for caching health check responses - Increase ThreadPoolExecutor workers from 4 to 8 (configurable) - Remove hardcoded paths - use environment variables - Add circuit breaker pattern for resilient external calls - Add proper timeout handling for health checks - Pin all dependencies in requirements.txt - Add graceful startup/shutdown handlers - Pre-warm agent in background thread on startup
270 lines
9.3 KiB
Python
270 lines
9.3 KiB
Python
"""
|
|
Hermes Client — True warm agent for zero-latency queries.
|
|
|
|
Architecture:
|
|
- Agent is initialized ONCE at module load (or first use) and kept warm
|
|
- Only reinitialize if model/provider/runtime actually changes (route signature)
|
|
- No conversation history reset - each query is naturally stateless
|
|
- All config via environment variables for deployment flexibility
|
|
"""
|
|
|
|
import os
|
|
import sys
|
|
import time
|
|
import logging
|
|
import signal
|
|
import atexit
|
|
import threading
|
|
from typing import Optional, Dict, Any, Tuple, Union
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
# ── Configuration via environment variables ─────────────────────────────
|
|
HERMES_HOME = os.environ.get("HERMES_RELAY_HERMES_HOME", "/root/.hermes/profiles/voice-assistant")
|
|
HERMES_SITE_PACKAGES = os.environ.get("HERMES_RELAY_SITE_PACKAGES", "/usr/local/lib/hermes-agent/venv/lib/python3.11/site-packages")
|
|
HERMES_MODEL = os.environ.get("HERMES_RELAY_MODEL", "") # Empty = use profile default
|
|
HERMES_TOOLSETS = os.environ.get("HERMES_RELAY_TOOLSETS", "messaging").split(",")
|
|
HERMES_MAX_TURNS = int(os.environ.get("HERMES_RELAY_MAX_TURNS", "10"))
|
|
HERMES_TIMEOUT = int(os.environ.get("HERMES_RELAY_TIMEOUT", "120"))
|
|
LOG_LEVEL = os.environ.get("HERMES_RELAY_LOG_LEVEL", "INFO").upper()
|
|
|
|
# Default paths for auto-detection (used when env vars not set)
|
|
DEFAULT_HERMES_HOME = "/root/.hermes/profiles/voice-assistant"
|
|
DEFAULT_SITE_PACKAGES = "/usr/local/lib/hermes-agent/venv/lib/python3.11/site-packages"
|
|
|
|
# ── Module-level state (true warm agent) ────────────────────────────────
|
|
_HERMES_LOADED = False
|
|
_CLI = None
|
|
_ACTIVE_ROUTE_SIGNATURE = None
|
|
_SHUTTING_DOWN = False
|
|
|
|
# Thread lock for protecting global state modifications
|
|
_STATE_LOCK = threading.Lock()
|
|
|
|
|
|
def _setup_logging() -> None:
|
|
"""Configure logging once."""
|
|
logging.basicConfig(
|
|
level=getattr(logging, LOG_LEVEL, logging.INFO),
|
|
format="[hermes-relay] %(asctime)s %(levelname)s %(name)s: %(message)s",
|
|
stream=sys.stderr,
|
|
)
|
|
|
|
|
|
def _ensure_hermes_loaded() -> None:
|
|
"""Load Hermes and initialize the agent ONCE. This is the heavy lifting."""
|
|
global _HERMES_LOADED, _CLI, _ACTIVE_ROUTE_SIGNATURE
|
|
|
|
# Fast path - already loaded
|
|
if _HERMES_LOADED:
|
|
return
|
|
|
|
# Slow path - acquire lock and double-check
|
|
with _STATE_LOCK:
|
|
if _HERMES_LOADED:
|
|
return
|
|
|
|
start = time.time()
|
|
_setup_logging()
|
|
|
|
# Force voice-assistant profile via HERMES_HOME
|
|
os.environ["HERMES_HOME"] = HERMES_HOME or DEFAULT_HERMES_HOME
|
|
|
|
# Ensure Hermes is in Python path
|
|
site_packages = HERMES_SITE_PACKAGES or DEFAULT_SITE_PACKAGES
|
|
if site_packages not in sys.path:
|
|
sys.path.insert(0, site_packages)
|
|
|
|
# Force UTF-8
|
|
os.environ.setdefault("PYTHONIOENCODING", "utf-8")
|
|
|
|
# Load .env via Hermes' own loader (loads profile .env + project .env)
|
|
from hermes_cli.env_loader import load_hermes_dotenv
|
|
from hermes_constants import get_hermes_home
|
|
|
|
_hermes_home = get_hermes_home()
|
|
_project_env = os.path.join(os.path.dirname(site_packages), ".env")
|
|
load_hermes_dotenv(hermes_home=_hermes_home, project_env=_project_env)
|
|
|
|
# Load config from voice-assistant profile
|
|
from hermes_cli.config import load_config
|
|
config = load_config()
|
|
|
|
# YOLO mode + interactive mode (required for agent tools)
|
|
os.environ["HERMES_YOLO_MODE"] = "1"
|
|
os.environ["HERMES_INTERACTIVE"] = "1"
|
|
os.environ["HERMES_SESSION_SOURCE"] = "relay"
|
|
|
|
# Import HermesCLI
|
|
from cli import HermesCLI
|
|
|
|
# Determine model (env override > profile default)
|
|
model = HERMES_MODEL or config.get("model", {}).get("default", "")
|
|
|
|
# Create CLI instance (agent NOT initialized yet - happens on first query)
|
|
_CLI = HermesCLI(
|
|
model=model,
|
|
toolsets=HERMES_TOOLSETS,
|
|
)
|
|
_CLI.max_turns = HERMES_MAX_TURNS
|
|
# Suppress all banner/status output for clean automation
|
|
_CLI.tool_progress_mode = "off"
|
|
_CLI.verbose = False
|
|
_CLI.streaming_enabled = False
|
|
|
|
elapsed = time.time() - start
|
|
logger.info(
|
|
"Hermes client loaded in %.2fs (toolsets=%s, model=%s, max_turns=%d, profile=voice-assistant)",
|
|
elapsed, HERMES_TOOLSETS, model or "profile-default", HERMES_MAX_TURNS
|
|
)
|
|
_HERMES_LOADED = True
|
|
|
|
|
|
def _initialize_agent() -> bool:
|
|
"""
|
|
Initialize the agent if not already initialized, or if route signature changed.
|
|
Returns True on success, False on failure.
|
|
"""
|
|
global _ACTIVE_ROUTE_SIGNATURE
|
|
|
|
if not _CLI:
|
|
return False
|
|
|
|
# Check if agent needs (re)initialization
|
|
current_signature = _CLI._resolve_turn_agent_config("")["signature"]
|
|
|
|
if _CLI.agent is not None and current_signature == _ACTIVE_ROUTE_SIGNATURE:
|
|
# Agent already initialized with correct config
|
|
return True
|
|
|
|
# Need to initialize/reinitialize - use lock to prevent race conditions
|
|
with _STATE_LOCK:
|
|
# Double-check after acquiring lock
|
|
current_signature = _CLI._resolve_turn_agent_config("")["signature"]
|
|
if _CLI.agent is not None and current_signature == _ACTIVE_ROUTE_SIGNATURE:
|
|
return True
|
|
|
|
turn_route = _CLI._resolve_turn_agent_config("")
|
|
init_ok = _CLI._init_agent(
|
|
model_override=turn_route["model"],
|
|
runtime_override=turn_route["runtime"],
|
|
request_overrides=turn_route.get("request_overrides"),
|
|
)
|
|
|
|
if not init_ok:
|
|
logger.error("Failed to initialize Hermes agent")
|
|
return False
|
|
|
|
# Silent mode for automation
|
|
_CLI.agent.quiet_mode = True
|
|
_CLI.agent.suppress_status_output = True
|
|
_CLI.agent.stream_delta_callback = None
|
|
_CLI.agent.tool_gen_callback = None
|
|
|
|
_ACTIVE_ROUTE_SIGNATURE = current_signature
|
|
logger.info("Hermes agent initialized (route_signature=%s)", _ACTIVE_ROUTE_SIGNATURE)
|
|
return True
|
|
|
|
|
|
def call_hermes(prompt: str) -> str:
|
|
"""
|
|
Query the warm Hermes agent.
|
|
|
|
The agent is initialized once at startup and reused for all queries.
|
|
Only reinitializes if model/provider/base_url actually changes.
|
|
"""
|
|
if _SHUTTING_DOWN:
|
|
return "⚠️ Service shutting down, please retry."
|
|
_ensure_hermes_loaded()
|
|
|
|
if not _initialize_agent():
|
|
return "⚠️ Kon Hermes agent niet initialiseren."
|
|
|
|
full_prompt = prompt.strip()
|
|
if not full_prompt:
|
|
return "⚠️ Lege prompt ontvangen."
|
|
|
|
start = time.time()
|
|
|
|
try:
|
|
# Each query is a fresh conversation - reset messages
|
|
# This is intentional: we want stateless queries for the relay
|
|
_CLI.agent.messages = []
|
|
result = _CLI.agent.chat(full_prompt)
|
|
|
|
except KeyboardInterrupt:
|
|
logger.warning("Hermes query interrupted")
|
|
raise # Re-raise to allow proper shutdown
|
|
except SystemExit as e:
|
|
# Hermes calls sys.exit() in some error paths
|
|
logger.warning("Hermes called sys.exit() during query: %s", e)
|
|
return "⚠️ Hermes error: process exited unexpectedly"
|
|
except Exception as e:
|
|
logger.error("Hermes error: %s", e, exc_info=True)
|
|
# Return user-friendly message but log full traceback
|
|
return f"⚠️ Hermes error: {type(e).__name__}"
|
|
|
|
elapsed = time.time() - start
|
|
|
|
# Fallback if Hermes returns None (error path)
|
|
if result is None:
|
|
logger.warning("Hermes returned None — possible error during query")
|
|
return "⚠️ Geen antwoord van Hermes. Probeer opnieuw."
|
|
|
|
logger.info("Hermes responded in %.1fs (%d chars)", elapsed, len(result))
|
|
return result
|
|
|
|
|
|
def health_check() -> Dict[str, Any]:
|
|
"""
|
|
Check if Hermes agent is healthy and responsive.
|
|
Returns a dict with status details.
|
|
|
|
This is a LIGHTWEIGHT check - no actual LLM query is made.
|
|
For deep health checking, use the /health endpoint with detail=true.
|
|
"""
|
|
checks = {
|
|
"hermes_loaded": _HERMES_LOADED,
|
|
"agent_initialized": _CLI is not None and _CLI.agent is not None,
|
|
"route_signature": str(_ACTIVE_ROUTE_SIGNATURE) if _ACTIVE_ROUTE_SIGNATURE else None,
|
|
}
|
|
|
|
# Lightweight check - just verify agent object exists
|
|
# Do NOT run an actual query here as it blocks for 10-60s
|
|
if checks["agent_initialized"]:
|
|
checks["query_test"] = "skipped (use deep check)"
|
|
checks["query_latency_ms"] = None
|
|
else:
|
|
checks["query_test"] = "agent_not_initialized"
|
|
checks["query_latency_ms"] = None
|
|
|
|
checks["healthy"] = (
|
|
checks["hermes_loaded"]
|
|
and checks["agent_initialized"]
|
|
)
|
|
|
|
return checks
|
|
|
|
|
|
def shutdown() -> None:
|
|
"""Graceful shutdown handler."""
|
|
global _SHUTTING_DOWN
|
|
with _STATE_LOCK:
|
|
_SHUTTING_DOWN = True
|
|
logger.info("Shutdown initiated")
|
|
|
|
if _CLI and _CLI.agent:
|
|
try:
|
|
# Give agent a chance to clean up
|
|
if hasattr(_CLI.agent, "shutdown"):
|
|
_CLI.agent.shutdown()
|
|
except Exception as e:
|
|
logger.error("Error during agent shutdown: %s", e, exc_info=True)
|
|
|
|
logger.info("Shutdown complete")
|
|
|
|
|
|
# Register shutdown handlers
|
|
signal.signal(signal.SIGTERM, lambda s, f: shutdown())
|
|
signal.signal(signal.SIGINT, lambda s, f: shutdown())
|
|
atexit.register(shutdown) |