refactor: move generation settings to provider level, eliminate parameter passthrough

nanobot/agent/loop.py

@@ -52,9 +52,6 @@ class AgentLoop:
         workspace: Path,
         model: str | None = None,
         max_iterations: int = 40,
-        temperature: float = 0.1,
-        max_tokens: int = 4096,
-        reasoning_effort: str | None = None,
         context_window_tokens: int = 65_536,
         brave_api_key: str | None = None,
         web_proxy: str | None = None,
@@ -72,9 +69,6 @@ class AgentLoop:
         self.workspace = workspace
         self.model = model or provider.get_default_model()
         self.max_iterations = max_iterations
-        self.temperature = temperature
-        self.max_tokens = max_tokens
-        self.reasoning_effort = reasoning_effort
         self.context_window_tokens = context_window_tokens
         self.brave_api_key = brave_api_key
         self.web_proxy = web_proxy
@@ -90,9 +84,6 @@ class AgentLoop:
             workspace=workspace,
             bus=bus,
             model=self.model,
-            temperature=self.temperature,
-            max_tokens=self.max_tokens,
-            reasoning_effort=reasoning_effort,
             brave_api_key=brave_api_key,
             web_proxy=web_proxy,
             exec_config=self.exec_config,
@@ -114,9 +105,6 @@ class AgentLoop:
             context_window_tokens=context_window_tokens,
             build_messages=self.context.build_messages,
             get_tool_definitions=self.tools.get_definitions,
-            temperature=self.temperature,
-            max_tokens=self.max_tokens,
-            reasoning_effort=self.reasoning_effort,
         )
         self._register_default_tools()
 
@@ -205,9 +193,6 @@ class AgentLoop:
                 messages=messages,
                 tools=tool_defs,
                 model=self.model,
-                temperature=self.temperature,
-                max_tokens=self.max_tokens,
-                reasoning_effort=self.reasoning_effort,
             )
 
             if response.has_tool_calls:

nanobot/agent/memory.py

@@ -57,7 +57,6 @@ def _normalize_save_memory_args(args: Any) -> dict[str, Any] | None:
         return args[0] if args and isinstance(args[0], dict) else None
     return args if isinstance(args, dict) else None
 
-
 class MemoryStore:
     """Two-layer memory: MEMORY.md (long-term facts) + HISTORY.md (grep-searchable log)."""
 
@@ -99,9 +98,6 @@ class MemoryStore:
         messages: list[dict],
         provider: LLMProvider,
         model: str,
-        temperature: float | None = None,
-        max_tokens: int | None = None,
-        reasoning_effort: str | None = None,
     ) -> bool:
         """Consolidate the provided message chunk into MEMORY.md + HISTORY.md."""
         if not messages:
@@ -124,9 +120,6 @@ class MemoryStore:
                 ],
                 tools=_SAVE_MEMORY_TOOL,
                 model=model,
-                temperature=temperature,
-                max_tokens=max_tokens,
-                reasoning_effort=reasoning_effort,
             )
 
             if not response.has_tool_calls:
@@ -166,9 +159,6 @@ class MemoryConsolidator:
         context_window_tokens: int,
         build_messages: Callable[..., list[dict[str, Any]]],
         get_tool_definitions: Callable[[], list[dict[str, Any]]],
-        temperature: float | None = None,
-        max_tokens: int | None = None,
-        reasoning_effort: str | None = None,
     ):
         self.store = MemoryStore(workspace)
         self.provider = provider
@@ -177,9 +167,6 @@ class MemoryConsolidator:
         self.context_window_tokens = context_window_tokens
         self._build_messages = build_messages
         self._get_tool_definitions = get_tool_definitions
-        self._temperature = temperature
-        self._max_tokens = max_tokens
-        self._reasoning_effort = reasoning_effort
         self._locks: weakref.WeakValueDictionary[str, asyncio.Lock] = weakref.WeakValueDictionary()
 
     def get_lock(self, session_key: str) -> asyncio.Lock:
@@ -188,14 +175,7 @@ class MemoryConsolidator:
 
     async def consolidate_messages(self, messages: list[dict[str, object]]) -> bool:
         """Archive a selected message chunk into persistent memory."""
-        return await self.store.consolidate(
-            messages,
-            self.provider,
-            self.model,
-            temperature=self._temperature,
-            max_tokens=self._max_tokens,
-            reasoning_effort=self._reasoning_effort,
-        )
+        return await self.store.consolidate(messages, self.provider, self.model)
 
     def pick_consolidation_boundary(
         self,

nanobot/agent/subagent.py

@@ -28,9 +28,6 @@ class SubagentManager:
         workspace: Path,
         bus: MessageBus,
         model: str | None = None,
-        temperature: float = 0.7,
-        max_tokens: int = 4096,
-        reasoning_effort: str | None = None,
         brave_api_key: str | None = None,
         web_proxy: str | None = None,
         exec_config: "ExecToolConfig | None" = None,
@@ -41,9 +38,6 @@ class SubagentManager:
         self.workspace = workspace
         self.bus = bus
         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.web_proxy = web_proxy
         self.exec_config = exec_config or ExecToolConfig()
@@ -128,9 +122,6 @@ class SubagentManager:
                     messages=messages,
                     tools=tools.get_definitions(),
                     model=self.model,
-                    temperature=self.temperature,
-                    max_tokens=self.max_tokens,
-                    reasoning_effort=self.reasoning_effort,
                 )
 
                 if response.has_tool_calls: