Feat: Hermes PC-Zugriff via MCP (executor + mcp_pc)

- mcp/mcp_pc.py: MCP-Server der PC-Tools an den Executor proxied
  (pc_shell, pc_screenshot, pc_type, pc_key, pc_open, pc_status)
- client/hermes-pc/executor.py: FastAPI auf Port 7777 (Daemon-Reg entfernt)
- client/hermes-pc/start.bat, install.bat, requirements.txt
- client/hermes-voice/agent_client.py, main.py: agent_client integration

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Hitonabi
2026-06-26 23:32:18 +02:00
parent a64b30c429
commit 483eb0b2fb
7 changed files with 307 additions and 2 deletions
+31
View File
@@ -0,0 +1,31 @@
"""Spricht mit dem Hermes Agent Daemon auf der AI Box."""
import httpx
TIMEOUT = 120
def ask_agent(text: str, screenshot_b64: str | None, settings: dict) -> tuple[str, list]:
"""Schickt Nachricht an den Daemon, gibt (response, tool_calls) zurück."""
daemon_url = settings.get("agent_daemon_url", "http://192.168.178.151:8765")
try:
with httpx.Client(timeout=TIMEOUT) as c:
resp = c.post(f"{daemon_url}/chat", json={
"message": text,
"screenshot": screenshot_b64,
})
resp.raise_for_status()
data = resp.json()
return data.get("response", ""), data.get("tool_calls", [])
except httpx.TimeoutException:
return "Antwort hat zu lange gedauert.", []
except Exception as e:
return f"Agent nicht erreichbar: {e}", []
def get_agent_status(settings: dict) -> dict:
daemon_url = settings.get("agent_daemon_url", "http://192.168.178.151:8765")
try:
with httpx.Client(timeout=5) as c:
return c.get(f"{daemon_url}/status").json()
except Exception:
return {"alive": False}
+7 -2
View File
@@ -12,7 +12,7 @@ import config_manager as cfg
from audio_input import start_recording, stop_recording, transcribe
from audio_output import speak, stop_speaking, play_ding
from screen_capture import capture_screen
from ai_client import ask
from agent_client import ask_agent, get_agent_status
from hotkey_listener import HotkeyListener, KeyCapturer, str_to_display
ctk.set_appearance_mode("dark")
@@ -145,7 +145,12 @@ class HermesApp(ctk.CTk):
ui_event("log_user", text)
screenshot = (capture_screen()
if self.settings["screenshot_enabled"] else None)
response = ask(text, screenshot, self.settings)
ui_event("status", ("thinking", "💭 Denke…", "#3b82f6"))
response, tool_calls = ask_agent(text, screenshot, self.settings)
for tc in tool_calls:
ui_event("log_tool", tc)
ui_event("log_hermes", response)
ui_event("status", ("speaking", "🔊 Spricht…", "#a855f7"))