feat: make Telegram relay delivery opt-in

app.py

@@ -19,11 +19,16 @@ if _HERMES_SITE not in sys.path:
 
 from quart import Quart, jsonify, request
 
-VERSION = "3.2.0"
+VERSION = "3.3.0"
 TIMEOUT = int(os.environ.get("HERMES_RELAY_TIMEOUT", "120"))
 TG_TARGET = os.environ.get("HERMES_RELAY_TELEGRAM_TARGET", "telegram")
 DELIVERY_WORKERS = int(os.environ.get("HERMES_RELAY_DELIVERY_WORKERS", "2"))
 MAX_PAYLOAD_CHARS = int(os.environ.get("HERMES_RELAY_MAX_PAYLOAD_CHARS", "12000"))
+# HTTP replies are the default.  Set this explicitly to true only when relay
+# answers should additionally be delivered through Telegram.
+TELEGRAM_DELIVERY_ENABLED = os.environ.get(
+    "HERMES_RELAY_TELEGRAM_DELIVERY_ENABLED", "false"
+).strip().lower() in {"1", "true", "yes", "on"}
 
 logging.basicConfig(
     level=logging.INFO,
@@ -114,7 +119,7 @@ def _queue_telegram(text: str) -> None:
 
 @app.route("/ask", methods=["POST"])
 async def ask():
-    """Answer a request; Telegram delivery is asynchronous and non-blocking."""
+    """Answer a request; optional Telegram delivery stays outside the HTTP path."""
     request_started = time.perf_counter()
 
     if request.is_json:
@@ -161,7 +166,8 @@ async def ask():
     request_elapsed = round(time.perf_counter() - request_started, 3)
     logger.info("Answer (llm=%.3fs, request=%.3fs): %s...", llm_elapsed, request_elapsed, answer[:200])
 
-    _queue_telegram(answer)
+    if TELEGRAM_DELIVERY_ENABLED:
+        _queue_telegram(answer)
     return jsonify({
         "status": "ok",
         "answer": answer,
@@ -169,7 +175,7 @@ async def ask():
         "elapsed_seconds": llm_elapsed,
         "llm_elapsed_seconds": llm_elapsed,
         "request_elapsed_seconds": request_elapsed,
-        "telegram_queued": True,
+        "telegram_queued": TELEGRAM_DELIVERY_ENABLED,
     })
 
 
@@ -181,6 +187,7 @@ async def health():
         "version": VERSION,
         "mode": "async-quart",
         "profile": "voice-assistant",
+        "telegram_delivery_enabled": TELEGRAM_DELIVERY_ENABLED,
         "pending_telegram_deliveries": len(_delivery_tasks),
     }
     if request.args.get("detail", "false").lower() == "true":
@@ -199,8 +206,8 @@ async def startup() -> None:
     global _hermes_lock
     _hermes_lock = asyncio.Lock()
     logger.info(
-        "Hermes Relay v%s startup complete (one serialized agent, delivery_workers=%d, timeout=%ds)",
-        VERSION, DELIVERY_WORKERS, TIMEOUT,
+        "Hermes Relay v%s startup complete (one serialized agent, telegram_delivery=%s, delivery_workers=%d, timeout=%ds)",
+        VERSION, TELEGRAM_DELIVERY_ENABLED, DELIVERY_WORKERS, TIMEOUT,
     )