Merge branch 'main' of github.com:NousResearch/hermes-agent into bb/gui

hermes_cli/config.py

@@ -400,7 +400,12 @@ DEFAULT_CONFIG = {
         # The gateway stops accepting new work, waits for running agents
         # to finish, then interrupts any remaining runs after the timeout.
         # 0 = no drain, interrupt immediately.
-        "restart_drain_timeout": 60,
+        #
+        # 180s is calibrated for realistic in-flight agent turns: a typical
+        # coding conversation mid-reasoning runs 60–150s per call, so a 60s
+        # budget routinely interrupted legitimate work on /restart. Raise
+        # further in config.yaml if you run very-long-reasoning models.
+        "restart_drain_timeout": 180,
         # Max app-level retry attempts for API errors (connection drops,
         # provider timeouts, 5xx, etc.) before the agent surfaces the
         # failure.  The OpenAI SDK already does its own low-level retries
@@ -639,6 +644,18 @@ DEFAULT_CONFIG = {
         "cache_ttl": "5m",
     },
 
+    # OpenRouter-specific settings.
+    # response_cache: enable OpenRouter response caching (X-OpenRouter-Cache header).
+    #   When enabled, identical requests return cached responses for free (zero billing).
+    #   This is separate from Anthropic prompt caching and works alongside it.
+    #   See: https://openrouter.ai/docs/guides/features/response-caching
+    # response_cache_ttl: how long cached responses remain valid, in seconds (1-86400).
+    #   Default 300 (5 minutes). Only used when response_cache is enabled.
+    "openrouter": {
+        "response_cache": True,
+        "response_cache_ttl": 300,
+    },
+
     # AWS Bedrock provider configuration.
     # Only used when model.provider is "bedrock".
     "bedrock": {
@@ -825,7 +842,7 @@ DEFAULT_CONFIG = {
             # Voices: alloy, echo, fable, onyx, nova, shimmer
         },
         "xai": {
-            "voice_id": "eve",
+            "voice_id": "eve",  # or custom voice ID — see https://docs.x.ai/developers/model-capabilities/audio/custom-voices
             "language": "en",
             "sample_rate": 24000,
             "bit_rate": 128000,