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

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)
-MODEL_OVERRIDE = "qwen3.7-plus"
+# Voice-assistant profiel home directory
+_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)
-    from hermes_cli.tools_config import _get_platform_tools
-    if MODEL_OVERRIDE:
-        # Geen tools laden bij model override (DeepSeek heeft incompatible tool schema)
-        toolsets = []
-    else:
-        toolsets = sorted(_get_platform_tools(config, 'cli'))
+    # Gebruik messaging toolset zodat agent send_message tool kan gebruiken
+    toolsets = ["messaging"]
 
     # YOLO mode + interactive mode
-    os.environ['HERMES_YOLO_MODE'] = '1'
-    os.environ['HERMES_INTERACTIVE'] = '1'
-    os.environ['HERMES_SESSION_SOURCE'] = 'relay'
+    os.environ["HERMES_YOLO_MODE"] = "1"
+    os.environ["HERMES_INTERACTIVE"] = "1"
+    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)
-    prefix = os.environ.get('HERMES_RELAY_PREFIX', '/fast')
-    full_prompt = (prefix + " " + prompt).strip() if prefix else prompt
+    # Geen prefix meer — voice-assistant profiel handelt dit af via config
+    full_prompt = prompt.strip()
 
     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
-    model_override = MODEL_OVERRIDE if MODEL_OVERRIDE else turn_route['model']
-    
-    if turn_route['signature'] != _cli._active_agent_route_signature:
+
+    if turn_route["signature"] != _cli._active_agent_route_signature:
         _cli.agent = None
     init_ok = _cli._init_agent(
-        model_override=model_override,
-        runtime_override=turn_route['runtime'],
-        request_overrides=turn_route.get('request_overrides'),
+        model_override=turn_route["model"],
+        runtime_override=turn_route["runtime"],
+        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