fix: raise tool result history limit to 16k and force save_memory in consolidation

nanobot/agent/memory.py

@@ -120,6 +120,7 @@ class MemoryStore:
                 ],
                 tools=_SAVE_MEMORY_TOOL,
                 model=model,
+                tool_choice="required",
             )
 
             if not response.has_tool_calls:

nanobot/providers/azure_openai_provider.py

@@ -88,6 +88,7 @@ class AzureOpenAIProvider(LLMProvider):
         max_tokens: int = 4096,
         temperature: float = 0.7,
         reasoning_effort: str | None = None,
+        tool_choice: str | dict[str, Any] | None = None,
     ) -> dict[str, Any]:
         """Prepare the request payload with Azure OpenAI 2024-10-21 compliance."""
         payload: dict[str, Any] = {
@@ -106,7 +107,7 @@ class AzureOpenAIProvider(LLMProvider):
 
         if tools:
             payload["tools"] = tools
-            payload["tool_choice"] = "auto"
+            payload["tool_choice"] = tool_choice or "auto"
 
         return payload
 
@@ -118,6 +119,7 @@ class AzureOpenAIProvider(LLMProvider):
         max_tokens: int = 4096,
         temperature: float = 0.7,
         reasoning_effort: str | None = None,
+        tool_choice: str | dict[str, Any] | None = None,
     ) -> LLMResponse:
         """
         Send a chat completion request to Azure OpenAI.
@@ -137,7 +139,8 @@ class AzureOpenAIProvider(LLMProvider):
         url = self._build_chat_url(deployment_name)
         headers = self._build_headers()
         payload = self._prepare_request_payload(
-            deployment_name, messages, tools, max_tokens, temperature, reasoning_effort
+            deployment_name, messages, tools, max_tokens, temperature, reasoning_effort,
+            tool_choice=tool_choice,
         )
 
         try:

nanobot/providers/base.py

@@ -166,6 +166,7 @@ class LLMProvider(ABC):
         max_tokens: int = 4096,
         temperature: float = 0.7,
         reasoning_effort: str | None = None,
+        tool_choice: str | dict[str, Any] | None = None,
     ) -> LLMResponse:
         """
         Send a chat completion request.
@@ -176,6 +177,7 @@ class LLMProvider(ABC):
             model: Model identifier (provider-specific).
             max_tokens: Maximum tokens in response.
             temperature: Sampling temperature.
+            tool_choice: Tool selection strategy ("auto", "required", or specific tool dict).
         
         Returns:
             LLMResponse with content and/or tool calls.
@@ -195,6 +197,7 @@ class LLMProvider(ABC):
         max_tokens: object = _SENTINEL,
         temperature: object = _SENTINEL,
         reasoning_effort: object = _SENTINEL,
+        tool_choice: str | dict[str, Any] | None = None,
     ) -> LLMResponse:
         """Call chat() with retry on transient provider failures.
 
@@ -218,6 +221,7 @@ class LLMProvider(ABC):
                     max_tokens=max_tokens,
                     temperature=temperature,
                     reasoning_effort=reasoning_effort,
+                    tool_choice=tool_choice,
                 )
             except asyncio.CancelledError:
                 raise
@@ -250,6 +254,7 @@ class LLMProvider(ABC):
                 max_tokens=max_tokens,
                 temperature=temperature,
                 reasoning_effort=reasoning_effort,
+                tool_choice=tool_choice,
             )
         except asyncio.CancelledError:
             raise

nanobot/providers/custom_provider.py

@@ -25,7 +25,8 @@ class CustomProvider(LLMProvider):
 
     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,
-                   reasoning_effort: str | None = None) -> LLMResponse:
+                   reasoning_effort: str | None = None,
+                   tool_choice: str | dict[str, Any] | None = None) -> LLMResponse:
         kwargs: dict[str, Any] = {
             "model": model or self.default_model,
             "messages": self._sanitize_empty_content(messages),
@@ -35,7 +36,7 @@ class CustomProvider(LLMProvider):
         if reasoning_effort:
             kwargs["reasoning_effort"] = reasoning_effort
         if tools:
-            kwargs.update(tools=tools, tool_choice="auto")
+            kwargs.update(tools=tools, tool_choice=tool_choice or "auto")
         try:
             return self._parse(await self._client.chat.completions.create(**kwargs))
         except Exception as e:

nanobot/providers/litellm_provider.py

@@ -214,6 +214,7 @@ class LiteLLMProvider(LLMProvider):
         max_tokens: int = 4096,
         temperature: float = 0.7,
         reasoning_effort: str | None = None,
+        tool_choice: str | dict[str, Any] | None = None,
     ) -> LLMResponse:
         """
         Send a chat completion request via LiteLLM.
@@ -267,7 +268,7 @@ class LiteLLMProvider(LLMProvider):
         
         if tools:
             kwargs["tools"] = tools
-            kwargs["tool_choice"] = "auto"
+            kwargs["tool_choice"] = tool_choice or "auto"
 
         try:
             response = await acompletion(**kwargs)

nanobot/providers/openai_codex_provider.py

@@ -32,6 +32,7 @@ class OpenAICodexProvider(LLMProvider):
         max_tokens: int = 4096,
         temperature: float = 0.7,
         reasoning_effort: str | None = None,
+        tool_choice: str | dict[str, Any] | None = None,
     ) -> LLMResponse:
         model = model or self.default_model
         system_prompt, input_items = _convert_messages(messages)
@@ -48,7 +49,7 @@ class OpenAICodexProvider(LLMProvider):
             "text": {"verbosity": "medium"},
             "include": ["reasoning.encrypted_content"],
             "prompt_cache_key": _prompt_cache_key(messages),
-            "tool_choice": "auto",
+            "tool_choice": tool_choice or "auto",
             "parallel_tool_calls": True,
         }