v2.1: Switch to voice-assistant profile

- Use voice-assistant profile (minimal chatbot, max_turns=10, nous provider)
- Remove /fast prefix and model override - handled by profile config
- Use messaging toolset for send_message tool (Telegram delivery)
- Add hardcoded TELEGRAM_BOT_TOKEN and TELEGRAM_HOME_CHANNEL to relay env
- Telegram delivery now works via gateway's send_message_tool
- Version bump to 2.1
- Health endpoint shows profile: voice-assistant

app.py

@@ -1,22 +1,19 @@
 """
 Hermes Relay v2 — Flask bridge tussen Node-RED en Hermes Agent.
 
-Gebruikt een warme Hermes agent (directe Python import) in plaats van
+Gebruikt de voice-assistant profiel (minimale chatbot, max_turns=10).
-subprocess per query. Dit bespaart ~3-5 seconden startup tijd per query.
+Geen prefix/model override nodig — profiel handelt dit af.
 
-Node-RED stuurt POST met msg.payload → Hermes (direct) → Antwoord + Telegram.
+Node-RED stuurt POST met msg.payload → Hermes (direct) → Alleen antwoord terug.
-
-Endpoints:
-  POST /ask       — main relay endpoint
-  GET  /health    — health check
 """
+
 import os
 import sys
 import time
 import logging
 
 # ── Hermes path toevoegen (zodat we Hermes direct kunnen importeren) ───
-_HERMES_SITE = '/usr/local/lib/hermes-agent/venv/lib/python3.11/site-packages'
+_HERMES_SITE = "/usr/local/lib/hermes-agent/venv/lib/python3.11/site-packages"
 if _HERMES_SITE not in sys.path:
     sys.path.insert(0, _HERMES_SITE)
 
@@ -24,9 +21,7 @@ from flask import Flask, request, jsonify
 
 # ── Config ──────────────────────────────────────────────────────────────
 TIMEOUT = 120          # max seconden voor Hermes query
-TG_TARGET = "telegram" # hermes send target
+TG_TARGET = "telegram"  # hermes send target
-PROMPT_PREFIX = "/fast" # wordt aan elke prompt toegevoegd
-MODEL = "qwen3.7-max"   # model override (leeg = default uit config)
 
 # ── Logging ─────────────────────────────────────────────────────────────
 logging.basicConfig(
@@ -40,24 +35,53 @@ logger = logging.getLogger(__name__)
 app = Flask(__name__)
 
 # ── Hermes warm houden ──────────────────────────────────────────────────
-# Import de Hermes client (triggert eenmalige module laden)
-HERMES_BIN = "/usr/local/bin/hermes"  # nog steeds nodig voor hermes send
 from hermes_client import call_hermes as _hermes_query
 
+# Laad gateway config eenmalig voor Telegram verzenden
+_gw_config_loaded = False
+_gw_config = None
+
+def _ensure_gw_config():
+    """Laad gateway config eenmalig."""
+    global _gw_config_loaded, _gw_config
+    if _gw_config_loaded:
+        return _gw_config
+    # Forceer default profiel voor gateway config
+    import os
+    os.environ["HERMES_HOME"] = "/root/.hermes"
+    # Zet de echte Telegram token in environment zodat gateway config deze kan laden
+    os.environ["TELEGRAM_BOT_TOKEN"] = "8736787405:AAGbtAtTPT7Kf3SWdPIhGbiiDVjnAUB_a5c"
+    os.environ["TELEGRAM_HOME_CHANNEL"] = "5453608010"
+    from gateway.config import load_gateway_config
+    _gw_config = load_gateway_config()
+    _gw_config_loaded = True
+    return _gw_config
+
 
 def send_telegram(text):
-    """Stuur bericht via hermes send subprocess."""
+    """Stuur bericht via gateway's send_message_tool (gebruikt gateway config met echte token)."""
-    import subprocess
     try:
-        result = subprocess.run(
+        logger.info("Telegram send: starting...")
-            [HERMES_BIN, "send", "--to", TG_TARGET, "--quiet", text],
+        _ensure_gw_config()
-            capture_output=True,
+        logger.info("Telegram send: gw config loaded")
-            text=True,
+        from tools.send_message_tool import send_message_tool
-            timeout=30,
+        import json
-        )
+
-        return result.returncode == 0
+        # Stuur via home channel (telegram = default target)
+        result_json = send_message_tool({
+            "action": "send",
+            "target": "telegram",
+            "message": text,
+        })
+        logger.info("Telegram send: send_message_tool returned")
+        result = json.loads(result_json)
+        if result.get("error"):
+            logger.error("Telegram send failed: %s", result["error"])
+            return False
+        logger.info("Telegram send: success=%s", result.get("success", False))
+        return result.get("success", False)
     except Exception as e:
-        logger.error("Telegram send failed: %s", e)
+        logger.error("Telegram send failed with exception: %s", e, exc_info=True)
         return False
 
 
@@ -65,7 +89,7 @@ def send_telegram(text):
 
 @app.route("/ask", methods=["POST"])
 def ask():
-    """Main relay endpoint."""
+    """Main relay endpoint — retourneert alleen het antwoord."""
     start = time.time()
 
     # Parse input
@@ -104,13 +128,12 @@ def health():
     return jsonify({
         "status": "ok",
         "service": "hermes-relay",
-        "version": "2.0",
+        "version": "2.1",
         "mode": "python-import",
-        "model": MODEL or "(default)",
+        "profile": "voice-assistant",
-        "prompt_prefix": PROMPT_PREFIX or "(none)",
     })
 
 
 if __name__ == "__main__":
-    logger.info("Starting Hermes Relay v2.0 (warme agent)...")
+    logger.info("Starting Hermes Relay v2.1 (voice-assistant profiel)...")
-    app.run(host="0.0.0.0", port=8650, debug=False)
+    app.run(host="0.0.0.0", port=8650, debug=False)

hermes_client.py

@@ -3,6 +3,9 @@ Hermes Client — directe Python import (geen subprocess overhead).
 
 Warme agent: eenmalig initialiseren, daarna hergebruiken voor elke query.
 Dit bespaart de subprocess + Python startup overhead van 2-5 seconden per query.
+
+Gebruikt het 'voice-assistant' profiel (minimale chatbot: alleen memory tool,
+deepseek-v4-flash/opencode-go, max_turns=10).
 """
 import io
 import os
@@ -17,8 +20,8 @@ logger = logging.getLogger(__name__)
 _HERMES_LOADED = False
 _cli = None
 
-# Model override voor relay (leeg = default uit config)
+# Voice-assistant profiel home directory
-MODEL_OVERRIDE = "qwen3.7-plus"
+_HERMES_HOME = "/root/.hermes/profiles/voice-assistant"
 
 
 def _ensure_hermes_loaded():
@@ -29,52 +32,50 @@ def _ensure_hermes_loaded():
 
     start = time.time()
 
+    # Forceer voice-assistant profiel via HERMES_HOME
+    os.environ["HERMES_HOME"] = _HERMES_HOME
+
     # Zorg dat Hermes in de Python path zit
-    hermes_path = '/usr/local/lib/hermes-agent/venv/lib/python3.11/site-packages'
+    hermes_path = "/usr/local/lib/hermes-agent/venv/lib/python3.11/site-packages"
     if hermes_path not in sys.path:
         sys.path.insert(0, hermes_path)
 
     # Force UTF-8
-    os.environ.setdefault('PYTHONIOENCODING', 'utf-8')
+    os.environ.setdefault("PYTHONIOENCODING", "utf-8")
 
     # Laad .env via Hermes' eigen loader
     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(hermes_path), '.env')
+    _project_env = os.path.join(os.path.dirname(hermes_path), ".env")
     load_hermes_dotenv(hermes_home=_hermes_home, project_env=_project_env)
 
-    # Load config
+    # Load config (nu vanuit voice-assistant profiel)
     from hermes_cli.config import load_config
     config = load_config()
 
-    # Resolve toolsets (geen tools voor snelle relay)
+    # Gebruik messaging toolset zodat agent send_message tool kan gebruiken
-    from hermes_cli.tools_config import _get_platform_tools
+    toolsets = ["messaging"]
-    if MODEL_OVERRIDE:
-        # Geen tools laden bij model override (DeepSeek heeft incompatible tool schema)
-        toolsets = []
-    else:
-        toolsets = sorted(_get_platform_tools(config, 'cli'))
 
     # YOLO mode + interactive mode
-    os.environ['HERMES_YOLO_MODE'] = '1'
+    os.environ["HERMES_YOLO_MODE"] = "1"
-    os.environ['HERMES_INTERACTIVE'] = '1'
+    os.environ["HERMES_INTERACTIVE"] = "1"
-    os.environ['HERMES_SESSION_SOURCE'] = 'relay'
+    os.environ["HERMES_SESSION_SOURCE"] = "relay"
 
     # Import HermesCLI
     from cli import HermesCLI
 
     # Maak CLI instantie (nog géén agent init — dat gebeurt pas bij eerste query)
     _cli = HermesCLI(
-        model=config.get('model', {}).get('default', ''),
+        model=config.get("model", {}).get("default", ""),
         toolsets=toolsets,
     )
     # Onderdruk banner/status output
-    _cli.tool_progress_mode = 'off'
+    _cli.tool_progress_mode = "off"
 
     elapsed = time.time() - start
     logger.info(
-        "Hermes loaded in %.2fs (toolsets: %s)",
+        "Hermes loaded in %.2fs (toolsets: %s, profile: voice-assistant)",
         elapsed, toolsets
     )
     _HERMES_LOADED = True
@@ -90,24 +91,20 @@ def call_hermes(prompt):
     """
     _ensure_hermes_loaded()
 
-    # Prefix (zoals /fast)
+    # Geen prefix meer — voice-assistant profiel handelt dit af via config
-    prefix = os.environ.get('HERMES_RELAY_PREFIX', '/fast')
+    full_prompt = prompt.strip()
-    full_prompt = (prefix + " " + prompt).strip() if prefix else prompt
 
     start = time.time()
 
-    # ── Agent initialiseren met model override ──
+    # ── Agent initialiseren ──
     turn_route = _cli._resolve_turn_agent_config(full_prompt)
-    
+
-    # Override model als MODEL_OVERRIDE is ingesteld
+    if turn_route["signature"] != _cli._active_agent_route_signature:
-    model_override = MODEL_OVERRIDE if MODEL_OVERRIDE else turn_route['model']
-    
-    if turn_route['signature'] != _cli._active_agent_route_signature:
         _cli.agent = None
     init_ok = _cli._init_agent(
-        model_override=model_override,
+        model_override=turn_route["model"],
-        runtime_override=turn_route['runtime'],
+        runtime_override=turn_route["runtime"],
-        request_overrides=turn_route.get('request_overrides'),
+        request_overrides=turn_route.get("request_overrides"),
     )
     if not init_ok:
         return "⚠️ Kon Hermes agent niet initialiseren."
@@ -137,11 +134,11 @@ def call_hermes(prompt):
         return "⚠️ Hermes error: " + str(e)
 
     elapsed = time.time() - start
-    
+
     # Fallback als Hermes None teruggeeft (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
+    return result