x

config.json

@@ -36,7 +36,7 @@
       "max_tokens": "65536",
       "gpu_util": "0.95",
       "tool_call_parser": "qwen3_xml",
-      "enable_auto_tool_choice": false,
+      "enable_auto_tool_choice": true,
       "served_model_name": "Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit",
       "hf_model_id": "cpatonn/Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit"
     },
@@ -50,7 +50,7 @@
       "enforce_eager": false,
       "env": {"VLLM_USE_TRITON_AWQ": "1"},
       "tool_call_parser": "qwen3_xml",
-      "enable_auto_tool_choice": false,
+      "enable_auto_tool_choice": true,
       "served_model_name": "Qwen3-Next-80B-A3B-Instruct-AWQ-4bit",
       "hf_model_id": "cpatonn/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit"
     },

scripts/start_vllm.py

@@ -159,12 +159,19 @@ def launch_model(model_id, config, model_path, gpu_count):
     
     # Add tool call parser if specified
     tool_call_parser = config.get("tool_call_parser")
+    openclaw_compat = os.getenv("OPENCLAW_COMPAT", "false").lower() == "true"
+    if openclaw_compat and not tool_call_parser:
+        tool_call_parser = os.getenv("OPENCLAW_TOOL_CALL_PARSER", "qwen3_xml")
     if tool_call_parser:
         cmd.extend(["--tool-call-parser", tool_call_parser])
-        openclaw_compat = os.getenv("OPENCLAW_COMPAT", "false").lower() == "true"
         enable_auto_tool_choice = config.get("enable_auto_tool_choice")
+        auto_tool_choice_env = os.getenv("ENABLE_AUTO_TOOL_CHOICE")
+        if auto_tool_choice_env is not None:
+            enable_auto_tool_choice = auto_tool_choice_env.lower() == "true"
         if enable_auto_tool_choice is None:
-            enable_auto_tool_choice = not openclaw_compat
+            enable_auto_tool_choice = True
+        if openclaw_compat:
+            enable_auto_tool_choice = True
         if enable_auto_tool_choice:
             cmd.extend(["--enable-auto-tool-choice"])
             log("Added auto tool choice enabled")