space: add /api/probe to verify live Warden generation end-to-end

space/app.py

@@ -148,6 +148,36 @@ def whisper() -> dict:
     return {"line": random.choice(WHISPERS)}
 
 
+@router.get("/api/probe")
+def probe(q: str = "A new process woke up in your machine. Greet it in one short line, in voice.") -> dict:
+    """Verification/health: ask the live Warden one line through the internal
+    llama-server. Confirms generation actually works end-to-end."""
+    import time
+
+    if not warden_ready():
+        return {"ok": False, "state": WARDEN_ERR}
+    body = json.dumps({
+        "messages": [
+            {"role": "system", "content": "You are the Warden, the malevolent operating system of SCRYPTOS. Terse, menacing, Unix-flavored."},
+            {"role": "user", "content": q},
+        ],
+        "max_tokens": 60,
+        "temperature": 0.6,
+    }).encode()
+    req = urllib.request.Request(
+        f"http://127.0.0.1:{LLAMA_PORT}/v1/chat/completions",
+        data=body, headers={"Content-Type": "application/json"},
+    )
+    t0 = time.time()
+    try:
+        with urllib.request.urlopen(req, timeout=150) as r:
+            data = json.loads(r.read())
+        line = data["choices"][0]["message"]["content"].strip()
+        return {"ok": True, "line": line, "seconds": round(time.time() - t0, 1)}
+    except Exception as err:
+        return {"ok": False, "error": f"{type(err).__name__}: {err}"}
+
+
 @router.get("/")
 def landing() -> FileResponse:
     return FileResponse(STATIC / "index.html")
@@ -292,7 +322,7 @@ if __name__ == "__main__":
     fastapi_app.mount("/static", StaticFiles(directory=STATIC), name="static")
     # include_router appends; move our routes ahead of gradio's catch-alls.
     our = [r for r in fastapi_app.router.routes if getattr(r, "name", "") in {
-        "status", "whisper", "landing", "play", "pty_bridge",
+        "status", "whisper", "probe", "landing", "play", "pty_bridge",
     }]
     for r in our:
         fastapi_app.router.routes.remove(r)