diff --git a/README.md b/README.md
index bf19298..4f170a9 100644
--- a/README.md
+++ b/README.md
@@ -16,7 +16,7 @@
 
 ⚡️ Delivers core agent functionality in just **~4,000** lines of code — **99% smaller** than Clawdbot's 430k+ lines.
 
-📏 Real-time line count: **3,431 lines** (run `bash core_agent_lines.sh` to verify anytime)
+📏 Real-time line count: **3,422 lines** (run `bash core_agent_lines.sh` to verify anytime)
 
 ## 📢 News
 
@@ -352,6 +352,7 @@ Config file: `~/.nanobot/config.json`
 | `deepseek` | LLM (DeepSeek direct) | [platform.deepseek.com](https://platform.deepseek.com) |
 | `groq` | LLM + **Voice transcription** (Whisper) | [console.groq.com](https://console.groq.com) |
 | `gemini` | LLM (Gemini direct) | [aistudio.google.com](https://aistudio.google.com) |
+| `aihubmix` | LLM (API gateway, access to all models) | [aihubmix.com](https://aihubmix.com) |
 | `dashscope` | LLM (Qwen) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) |
 
 
diff --git a/nanobot/agent/loop.py b/nanobot/agent/loop.py
index e4193ec..b13113f 100644
--- a/nanobot/agent/loop.py
+++ b/nanobot/agent/loop.py
@@ -155,7 +155,8 @@ class AgentLoop:
         if msg.channel == "system":
             return await self._process_system_message(msg)
         
-        logger.info(f"Processing message from {msg.channel}:{msg.sender_id}")
+        preview = msg.content[:80] + "..." if len(msg.content) > 80 else msg.content
+        logger.info(f"Processing message from {msg.channel}:{msg.sender_id}: {preview}")
         
         # Get or create session
         session = self.sessions.get_or_create(msg.session_key)
@@ -216,8 +217,8 @@ class AgentLoop:
                 
                 # Execute tools
                 for tool_call in response.tool_calls:
-                    args_str = json.dumps(tool_call.arguments)
-                    logger.debug(f"Executing tool: {tool_call.name} with arguments: {args_str}")
+                    args_str = json.dumps(tool_call.arguments, ensure_ascii=False)
+                    logger.info(f"Tool call: {tool_call.name}({args_str[:200]})")
                     result = await self.tools.execute(tool_call.name, tool_call.arguments)
                     messages = self.context.add_tool_result(
                         messages, tool_call.id, tool_call.name, result
@@ -230,6 +231,10 @@ class AgentLoop:
         if final_content is None:
             final_content = "I've completed processing but have no response to give."
         
+        # Log response preview
+        preview = final_content[:120] + "..." if len(final_content) > 120 else final_content
+        logger.info(f"Response to {msg.channel}:{msg.sender_id}: {preview}")
+        
         # Save to session
         session.add_message("user", msg.content)
         session.add_message("assistant", final_content)
@@ -315,8 +320,8 @@ class AgentLoop:
                 )
                 
                 for tool_call in response.tool_calls:
-                    args_str = json.dumps(tool_call.arguments)
-                    logger.debug(f"Executing tool: {tool_call.name} with arguments: {args_str}")
+                    args_str = json.dumps(tool_call.arguments, ensure_ascii=False)
+                    logger.info(f"Tool call: {tool_call.name}({args_str[:200]})")
                     result = await self.tools.execute(tool_call.name, tool_call.arguments)
                     messages = self.context.add_tool_result(
                         messages, tool_call.id, tool_call.name, result
diff --git a/nanobot/cli/commands.py b/nanobot/cli/commands.py
index 2ae6e05..19e62e9 100644
--- a/nanobot/cli/commands.py
+++ b/nanobot/cli/commands.py
@@ -147,6 +147,23 @@ This file stores important information that should persist across sessions.
         console.print("  [dim]Created memory/MEMORY.md[/dim]")
 
 
+def _make_provider(config):
+    """Create LiteLLMProvider from config. Exits if no API key found."""
+    from nanobot.providers.litellm_provider import LiteLLMProvider
+    p = config.get_provider()
+    model = config.agents.defaults.model
+    if not (p and p.api_key) and not model.startswith("bedrock/"):
+        console.print("[red]Error: No API key configured.[/red]")
+        console.print("Set one in ~/.nanobot/config.json under providers section")
+        raise typer.Exit(1)
+    return LiteLLMProvider(
+        api_key=p.api_key if p else None,
+        api_base=config.get_api_base(),
+        default_model=model,
+        extra_headers=p.extra_headers if p else None,
+    )
+
+
 # ============================================================================
 # Gateway / Server
 # ============================================================================
@@ -160,7 +177,6 @@ def gateway(
     """Start the nanobot gateway."""
     from nanobot.config.loader import load_config, get_data_dir
     from nanobot.bus.queue import MessageBus
-    from nanobot.providers.litellm_provider import LiteLLMProvider
     from nanobot.agent.loop import AgentLoop
     from nanobot.channels.manager import ChannelManager
     from nanobot.cron.service import CronService
@@ -174,26 +190,8 @@ def gateway(
     console.print(f"{__logo__} Starting nanobot gateway on port {port}...")
     
     config = load_config()
-    
-    # Create components
     bus = MessageBus()
-    
-    # Create provider (supports OpenRouter, Anthropic, OpenAI, Bedrock)
-    api_key = config.get_api_key()
-    api_base = config.get_api_base()
-    model = config.agents.defaults.model
-    is_bedrock = model.startswith("bedrock/")
-
-    if not api_key and not is_bedrock:
-        console.print("[red]Error: No API key configured.[/red]")
-        console.print("Set one in ~/.nanobot/config.json under providers.openrouter.apiKey")
-        raise typer.Exit(1)
-    
-    provider = LiteLLMProvider(
-        api_key=api_key,
-        api_base=api_base,
-        default_model=config.agents.defaults.model
-    )
+    provider = _make_provider(config)
     
     # Create cron service first (callback set after agent creation)
     cron_store_path = get_data_dir() / "cron" / "jobs.json"
@@ -290,26 +288,12 @@ def agent(
     """Interact with the agent directly."""
     from nanobot.config.loader import load_config
     from nanobot.bus.queue import MessageBus
-    from nanobot.providers.litellm_provider import LiteLLMProvider
     from nanobot.agent.loop import AgentLoop
     
     config = load_config()
     
-    api_key = config.get_api_key()
-    api_base = config.get_api_base()
-    model = config.agents.defaults.model
-    is_bedrock = model.startswith("bedrock/")
-
-    if not api_key and not is_bedrock:
-        console.print("[red]Error: No API key configured.[/red]")
-        raise typer.Exit(1)
-
     bus = MessageBus()
-    provider = LiteLLMProvider(
-        api_key=api_key,
-        api_base=api_base,
-        default_model=config.agents.defaults.model
-    )
+    provider = _make_provider(config)
     
     agent_loop = AgentLoop(
         bus=bus,
@@ -657,12 +641,14 @@ def status():
         has_gemini = bool(config.providers.gemini.api_key)
         has_zhipu = bool(config.providers.zhipu.api_key)
         has_vllm = bool(config.providers.vllm.api_base)
+        has_aihubmix = bool(config.providers.aihubmix.api_key)
         
         console.print(f"OpenRouter API: {'[green]✓[/green]' if has_openrouter else '[dim]not set[/dim]'}")
         console.print(f"Anthropic API: {'[green]✓[/green]' if has_anthropic else '[dim]not set[/dim]'}")
         console.print(f"OpenAI API: {'[green]✓[/green]' if has_openai else '[dim]not set[/dim]'}")
         console.print(f"Gemini API: {'[green]✓[/green]' if has_gemini else '[dim]not set[/dim]'}")
         console.print(f"Zhipu AI API: {'[green]✓[/green]' if has_zhipu else '[dim]not set[/dim]'}")
+        console.print(f"AiHubMix API: {'[green]✓[/green]' if has_aihubmix else '[dim]not set[/dim]'}")
         vllm_status = f"[green]✓ {config.providers.vllm.api_base}[/green]" if has_vllm else "[dim]not set[/dim]"
         console.print(f"vLLM/Local: {vllm_status}")
 
diff --git a/nanobot/config/schema.py b/nanobot/config/schema.py
index 9af6ee2..7724288 100644
--- a/nanobot/config/schema.py
+++ b/nanobot/config/schema.py
@@ -65,6 +65,7 @@ class ProviderConfig(BaseModel):
     """LLM provider configuration."""
     api_key: str = ""
     api_base: str | None = None
+    extra_headers: dict[str, str] | None = None  # Custom headers (e.g. APP-Code for AiHubMix)
 
 
 class ProvidersConfig(BaseModel):
@@ -79,6 +80,7 @@ class ProvidersConfig(BaseModel):
     vllm: ProviderConfig = Field(default_factory=ProviderConfig)
     gemini: ProviderConfig = Field(default_factory=ProviderConfig)
     moonshot: ProviderConfig = Field(default_factory=ProviderConfig)
+    aihubmix: ProviderConfig = Field(default_factory=ProviderConfig)  # AiHubMix API gateway
 
 
 class GatewayConfig(BaseModel):
@@ -123,60 +125,44 @@ class Config(BaseSettings):
         """Get expanded workspace path."""
         return Path(self.agents.defaults.workspace).expanduser()
     
-    def _match_provider(self, model: str | None = None) -> ProviderConfig | None:
-        """Match a provider based on model name."""
+    # Default base URLs for API gateways
+    _GATEWAY_DEFAULTS = {"openrouter": "https://openrouter.ai/api/v1", "aihubmix": "https://aihubmix.com/v1"}
+
+    def get_provider(self, model: str | None = None) -> ProviderConfig | None:
+        """Get matched provider config (api_key, api_base, extra_headers). Falls back to first available."""
         model = (model or self.agents.defaults.model).lower()
-        # Map of keywords to provider configs
-        providers = {
-            "openrouter": self.providers.openrouter,
-            "deepseek": self.providers.deepseek,
-            "anthropic": self.providers.anthropic,
-            "claude": self.providers.anthropic,
-            "openai": self.providers.openai,
-            "gpt": self.providers.openai,
-            "gemini": self.providers.gemini,
-            "zhipu": self.providers.zhipu,
-            "glm": self.providers.zhipu,
-            "zai": self.providers.zhipu,
-            "dashscope": self.providers.dashscope,
-            "qwen": self.providers.dashscope,
-            "groq": self.providers.groq,
-            "moonshot": self.providers.moonshot,
-            "kimi": self.providers.moonshot,
-            "vllm": self.providers.vllm,
+        p = self.providers
+        # Keyword → provider mapping (order matters: gateways first)
+        keyword_map = {
+            "aihubmix": p.aihubmix, "openrouter": p.openrouter,
+            "deepseek": p.deepseek, "anthropic": p.anthropic, "claude": p.anthropic,
+            "openai": p.openai, "gpt": p.openai, "gemini": p.gemini,
+            "zhipu": p.zhipu, "glm": p.zhipu, "zai": p.zhipu,
+            "dashscope": p.dashscope, "qwen": p.dashscope,
+            "groq": p.groq, "moonshot": p.moonshot, "kimi": p.moonshot, "vllm": p.vllm,
         }
-        for keyword, provider in providers.items():
-            if keyword in model and provider.api_key:
+        for kw, provider in keyword_map.items():
+            if kw in model and provider.api_key:
                 return provider
-        return None
+        # Fallback: gateways first (can serve any model), then specific providers
+        all_providers = [p.openrouter, p.aihubmix, p.anthropic, p.openai, p.deepseek,
+                         p.gemini, p.zhipu, p.dashscope, p.moonshot, p.vllm, p.groq]
+        return next((pr for pr in all_providers if pr.api_key), None)
 
     def get_api_key(self, model: str | None = None) -> str | None:
-        """Get API key for the given model (or default model). Falls back to first available key."""
-        # Try matching by model name first
-        matched = self._match_provider(model)
-        if matched:
-            return matched.api_key
-        # Fallback: return first available key
-        for provider in [
-            self.providers.openrouter, self.providers.deepseek,
-            self.providers.anthropic, self.providers.openai,
-            self.providers.gemini, self.providers.zhipu,
-            self.providers.dashscope, self.providers.moonshot,
-            self.providers.vllm, self.providers.groq,
-        ]:
-            if provider.api_key:
-                return provider.api_key
-        return None
+        """Get API key for the given model. Falls back to first available key."""
+        p = self.get_provider(model)
+        return p.api_key if p else None
     
     def get_api_base(self, model: str | None = None) -> str | None:
-        """Get API base URL based on model name."""
-        model = (model or self.agents.defaults.model).lower()
-        if "openrouter" in model:
-            return self.providers.openrouter.api_base or "https://openrouter.ai/api/v1"
-        if any(k in model for k in ("zhipu", "glm", "zai")):
-            return self.providers.zhipu.api_base
-        if "vllm" in model:
-            return self.providers.vllm.api_base
+        """Get API base URL for the given model. Applies default URLs for known gateways."""
+        p = self.get_provider(model)
+        if p and p.api_base:
+            return p.api_base
+        # Default URLs for known gateways (openrouter, aihubmix)
+        for name, url in self._GATEWAY_DEFAULTS.items():
+            if p == getattr(self.providers, name):
+                return url
         return None
     
     class Config:
diff --git a/nanobot/providers/litellm_provider.py b/nanobot/providers/litellm_provider.py
index 7a2d373..7a52e7c 100644
--- a/nanobot/providers/litellm_provider.py
+++ b/nanobot/providers/litellm_provider.py
@@ -21,10 +21,12 @@ class LiteLLMProvider(LLMProvider):
         self, 
         api_key: str | None = None, 
         api_base: str | None = None,
-        default_model: str = "anthropic/claude-opus-4-5"
+        default_model: str = "anthropic/claude-opus-4-5",
+        extra_headers: dict[str, str] | None = None,
     ):
         super().__init__(api_key, api_base)
         self.default_model = default_model
+        self.extra_headers = extra_headers or {}
         
         # Detect OpenRouter by api_key prefix or explicit api_base
         self.is_openrouter = (
@@ -32,14 +34,20 @@ class LiteLLMProvider(LLMProvider):
             (api_base and "openrouter" in api_base)
         )
         
+        # Detect AiHubMix by api_base
+        self.is_aihubmix = bool(api_base and "aihubmix" in api_base)
+        
         # Track if using custom endpoint (vLLM, etc.)
-        self.is_vllm = bool(api_base) and not self.is_openrouter
+        self.is_vllm = bool(api_base) and not self.is_openrouter and not self.is_aihubmix
         
         # Configure LiteLLM based on provider
         if api_key:
             if self.is_openrouter:
                 # OpenRouter mode - set key
                 os.environ["OPENROUTER_API_KEY"] = api_key
+            elif self.is_aihubmix:
+                # AiHubMix gateway - OpenAI-compatible
+                os.environ["OPENAI_API_KEY"] = api_key
             elif self.is_vllm:
                 # vLLM/custom endpoint - uses OpenAI-compatible API
                 os.environ["HOSTED_VLLM_API_KEY"] = api_key
@@ -91,41 +99,26 @@ class LiteLLMProvider(LLMProvider):
         """
         model = model or self.default_model
         
-        # For OpenRouter, prefix model name if not already prefixed
+        # Auto-prefix model names for known providers
+        # (keywords, target_prefix, skip_if_starts_with)
+        _prefix_rules = [
+            (("glm", "zhipu"), "zai", ("zhipu/", "zai/", "openrouter/", "hosted_vllm/")),
+            (("qwen", "dashscope"), "dashscope", ("dashscope/", "openrouter/")),
+            (("moonshot", "kimi"), "moonshot", ("moonshot/", "openrouter/")),
+            (("gemini",), "gemini", ("gemini/",)),
+        ]
+        model_lower = model.lower()
+        for keywords, prefix, skip in _prefix_rules:
+            if any(kw in model_lower for kw in keywords) and not any(model.startswith(s) for s in skip):
+                model = f"{prefix}/{model}"
+                break
+
+        # Gateway/endpoint-specific prefixes (detected by api_base/api_key, not model name)
         if self.is_openrouter and not model.startswith("openrouter/"):
             model = f"openrouter/{model}"
-        
-        # For Zhipu/Z.ai, ensure prefix is present
-        # Handle cases like "glm-4.7-flash" -> "zai/glm-4.7-flash"
-        if ("glm" in model.lower() or "zhipu" in model.lower()) and not (
-            model.startswith("zhipu/") or 
-            model.startswith("zai/") or 
-            model.startswith("openrouter/") or
-            model.startswith("hosted_vllm/")
-        ):
-            model = f"zai/{model}"
-
-        # For DashScope/Qwen, ensure dashscope/ prefix
-        if ("qwen" in model.lower() or "dashscope" in model.lower()) and not (
-            model.startswith("dashscope/") or
-            model.startswith("openrouter/")
-        ):
-            model = f"dashscope/{model}"
-
-        # For Moonshot/Kimi, ensure moonshot/ prefix (before vLLM check)
-        if ("moonshot" in model.lower() or "kimi" in model.lower()) and not (
-            model.startswith("moonshot/") or model.startswith("openrouter/")
-        ):
-            model = f"moonshot/{model}"
-
-        # For Gemini, ensure gemini/ prefix if not already present
-        if "gemini" in model.lower() and not model.startswith("gemini/"):
-            model = f"gemini/{model}"
-
-
-        # For vLLM, use hosted_vllm/ prefix per LiteLLM docs
-        # Convert openai/ prefix to hosted_vllm/ if user specified it
-        if self.is_vllm:
+        elif self.is_aihubmix:
+            model = f"openai/{model.split('/')[-1]}"
+        elif self.is_vllm:
             model = f"hosted_vllm/{model}"
         
         # kimi-k2.5 only supports temperature=1.0
@@ -143,6 +136,10 @@ class LiteLLMProvider(LLMProvider):
         if self.api_base:
             kwargs["api_base"] = self.api_base
         
+        # Pass extra headers (e.g. APP-Code for AiHubMix)
+        if self.extra_headers:
+            kwargs["extra_headers"] = self.extra_headers
+        
         if tools:
             kwargs["tools"] = tools
             kwargs["tool_choice"] = "auto"