Merge PR #1351 to add reasoning_effort config to enable LLM thinking mode

feat: add reasoning_effort config to enable LLM thinking mode

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: **3,927 lines** (run `bash core_agent_lines.sh` to verify anytime)
+📏 Real-time line count: **3,935 lines** (run `bash core_agent_lines.sh` to verify anytime)
 
 ## 📢 News
 

nanobot/agent/loop.py

@@ -56,6 +56,7 @@ class AgentLoop:
         temperature: float = 0.1,
         max_tokens: int = 4096,
         memory_window: int = 100,
+        reasoning_effort: str | None = None,
         brave_api_key: str | None = None,
         exec_config: ExecToolConfig | None = None,
         cron_service: CronService | None = None,
@@ -74,6 +75,7 @@ class AgentLoop:
         self.temperature = temperature
         self.max_tokens = max_tokens
         self.memory_window = memory_window
+        self.reasoning_effort = reasoning_effort
         self.brave_api_key = brave_api_key
         self.exec_config = exec_config or ExecToolConfig()
         self.cron_service = cron_service
@@ -89,6 +91,7 @@ class AgentLoop:
             model=self.model,
             temperature=self.temperature,
             max_tokens=self.max_tokens,
+            reasoning_effort=reasoning_effort,
             brave_api_key=brave_api_key,
             exec_config=self.exec_config,
             restrict_to_workspace=restrict_to_workspace,
@@ -191,6 +194,7 @@ class AgentLoop:
                 model=self.model,
                 temperature=self.temperature,
                 max_tokens=self.max_tokens,
+                reasoning_effort=self.reasoning_effort,
             )
 
             if response.has_tool_calls:

nanobot/agent/subagent.py

@@ -28,6 +28,7 @@ class SubagentManager:
         model: str | None = None,
         temperature: float = 0.7,
         max_tokens: int = 4096,
+        reasoning_effort: str | None = None,
         brave_api_key: str | None = None,
         exec_config: "ExecToolConfig | None" = None,
         restrict_to_workspace: bool = False,
@@ -39,6 +40,7 @@ class SubagentManager:
         self.model = model or provider.get_default_model()
         self.temperature = temperature
         self.max_tokens = max_tokens
+        self.reasoning_effort = reasoning_effort
         self.brave_api_key = brave_api_key
         self.exec_config = exec_config or ExecToolConfig()
         self.restrict_to_workspace = restrict_to_workspace
@@ -124,6 +126,7 @@ class SubagentManager:
                     model=self.model,
                     temperature=self.temperature,
                     max_tokens=self.max_tokens,
+                    reasoning_effort=self.reasoning_effort,
                 )
                 
                 if response.has_tool_calls:

nanobot/cli/commands.py

@@ -283,6 +283,7 @@ def gateway(
         max_tokens=config.agents.defaults.max_tokens,
         max_iterations=config.agents.defaults.max_tool_iterations,
         memory_window=config.agents.defaults.memory_window,
+        reasoning_effort=config.agents.defaults.reasoning_effort,
         brave_api_key=config.tools.web.search.api_key or None,
         exec_config=config.tools.exec,
         cron_service=cron,
@@ -441,6 +442,7 @@ def agent(
         max_tokens=config.agents.defaults.max_tokens,
         max_iterations=config.agents.defaults.max_tool_iterations,
         memory_window=config.agents.defaults.memory_window,
+        reasoning_effort=config.agents.defaults.reasoning_effort,
         brave_api_key=config.tools.web.search.api_key or None,
         exec_config=config.tools.exec,
         cron_service=cron,
@@ -932,6 +934,7 @@ def cron_run(
         max_tokens=config.agents.defaults.max_tokens,
         max_iterations=config.agents.defaults.max_tool_iterations,
         memory_window=config.agents.defaults.memory_window,
+        reasoning_effort=config.agents.defaults.reasoning_effort,
         brave_api_key=config.tools.web.search.api_key or None,
         exec_config=config.tools.exec,
         restrict_to_workspace=config.tools.restrict_to_workspace,

nanobot/config/schema.py

@@ -226,6 +226,7 @@ class AgentDefaults(Base):
     temperature: float = 0.1
     max_tool_iterations: int = 40
     memory_window: int = 100
+    reasoning_effort: str | None = None  # low / medium / high — enables LLM thinking mode
 
 
 class AgentsConfig(Base):

nanobot/providers/base.py

@@ -88,6 +88,7 @@ class LLMProvider(ABC):
         model: str | None = None,
         max_tokens: int = 4096,
         temperature: float = 0.7,
+        reasoning_effort: str | None = None,
     ) -> LLMResponse:
         """
         Send a chat completion request.

nanobot/providers/custom_provider.py

@@ -18,13 +18,16 @@ class CustomProvider(LLMProvider):
         self._client = AsyncOpenAI(api_key=api_key, base_url=api_base)
 
     async def chat(self, messages: list[dict[str, Any]], tools: list[dict[str, Any]] | None = None,
-                   model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7) -> LLMResponse:
+                   model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7,
+                   reasoning_effort: str | None = None) -> LLMResponse:
         kwargs: dict[str, Any] = {
             "model": model or self.default_model,
             "messages": self._sanitize_empty_content(messages),
             "max_tokens": max(1, max_tokens),
             "temperature": temperature,
         }
+        if reasoning_effort:
+            kwargs["reasoning_effort"] = reasoning_effort
         if tools:
             kwargs.update(tools=tools, tool_choice="auto")
         try:

nanobot/providers/litellm_provider.py

@@ -178,6 +178,7 @@ class LiteLLMProvider(LLMProvider):
         model: str | None = None,
         max_tokens: int = 4096,
         temperature: float = 0.7,
+        reasoning_effort: str | None = None,
     ) -> LLMResponse:
         """
         Send a chat completion request via LiteLLM.
@@ -224,6 +225,10 @@ class LiteLLMProvider(LLMProvider):
         if self.extra_headers:
             kwargs["extra_headers"] = self.extra_headers
         
+        if reasoning_effort:
+            kwargs["reasoning_effort"] = reasoning_effort
+            kwargs["drop_params"] = True
+        
         if tools:
             kwargs["tools"] = tools
             kwargs["tool_choice"] = "auto"

nanobot/providers/openai_codex_provider.py

@@ -31,6 +31,7 @@ class OpenAICodexProvider(LLMProvider):
         model: str | None = None,
         max_tokens: int = 4096,
         temperature: float = 0.7,
+        reasoning_effort: str | None = None,
     ) -> LLMResponse:
         model = model or self.default_model
         system_prompt, input_items = _convert_messages(messages)