chore: use base model for llms

docs/en/concepts/llms.mdx

@@ -1212,7 +1212,7 @@ Learn how to get the most out of your LLM configuration:
     ```python
 import httpx
 from crewai import LLM
-from crewai.llms.hooks import BaseInterceptor
+from crewai.llm.hooks import BaseInterceptor
 
 class CustomInterceptor(BaseInterceptor[httpx.Request, httpx.Response]):
     """Custom interceptor to modify requests and responses."""

lib/crewai/src/crewai/__init__.py

@@ -8,8 +8,8 @@
 from crewai.crews.crew_output import CrewOutput
 from crewai.flow.flow import Flow
 from crewai.knowledge.knowledge import Knowledge
-from crewai.llm import LLM
-from crewai.llms.base_llm import BaseLLM
+from crewai.llm.base_llm import BaseLLM
+from crewai.llm.core import LLM
 from crewai.process import Process
 from crewai.task import Task
 from crewai.tasks.llm_guardrail import LLMGuardrail

lib/crewai/src/crewai/agent/core.py

@@ -39,7 +39,7 @@
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.utils.knowledge_utils import extract_knowledge_context
 from crewai.lite_agent import LiteAgent
-from crewai.llms.base_llm import BaseLLM
+from crewai.llm.base_llm import BaseLLM
 from crewai.mcp import (
     MCPClient,
     MCPServerConfig,
@@ -633,7 +633,7 @@ def create_agent_executor(
             )
 
         self.agent_executor = CrewAgentExecutor(
-            llm=self.llm,
+            llm=self.llm,  # type: ignore[arg-type]
             task=task,  # type: ignore[arg-type]
             agent=self,
             crew=self.crew,
@@ -810,6 +810,7 @@ def _get_native_mcp_tools(
         from crewai.tools.base_tool import BaseTool
         from crewai.tools.mcp_native_tool import MCPNativeTool
 
+        transport: StdioTransport | HTTPTransport | SSETransport
         if isinstance(mcp_config, MCPServerStdio):
             transport = StdioTransport(
                 command=mcp_config.command,
@@ -903,10 +904,12 @@ async def _setup_client_and_list_tools() -> list[dict[str, Any]]:
                                 server_name=server_name,
                                 run_context=None,
                             )
-                            if mcp_config.tool_filter(context, tool):
+                            # Try new signature first
+                            if mcp_config.tool_filter(context, tool):  # type: ignore[arg-type,call-arg]
                                 filtered_tools.append(tool)
                         except (TypeError, AttributeError):
-                            if mcp_config.tool_filter(tool):
+                            # Fallback to old signature
+                            if mcp_config.tool_filter(tool):  # type: ignore[arg-type,call-arg]
                                 filtered_tools.append(tool)
                     else:
                         # Not callable - include tool
@@ -981,7 +984,9 @@ def _extract_server_name(server_url: str) -> str:
         path = parsed.path.replace("/", "_").strip("_")
         return f"{domain}_{path}" if path else domain
 
-    def _get_mcp_tool_schemas(self, server_params: dict) -> dict[str, dict]:
+    def _get_mcp_tool_schemas(
+        self, server_params: dict[str, Any]
+    ) -> dict[str, dict[str, Any]]:
         """Get tool schemas from MCP server for wrapper creation with caching."""
         server_url = server_params["url"]
 
@@ -995,7 +1000,7 @@ def _get_mcp_tool_schemas(self, server_params: dict) -> dict[str, dict]:
                 self._logger.log(
                     "debug", f"Using cached MCP tool schemas for {server_url}"
                 )
-                return cached_data
+                return cast(dict[str, dict[str, Any]], cached_data)
 
         try:
             schemas = asyncio.run(self._get_mcp_tool_schemas_async(server_params))
@@ -1013,15 +1018,15 @@ def _get_mcp_tool_schemas(self, server_params: dict) -> dict[str, dict]:
 
     async def _get_mcp_tool_schemas_async(
         self, server_params: dict[str, Any]
-    ) -> dict[str, dict]:
+    ) -> dict[str, dict[str, Any]]:
         """Async implementation of MCP tool schema retrieval with timeouts and retries."""
         server_url = server_params["url"]
         return await self._retry_mcp_discovery(
             self._discover_mcp_tools_with_timeout, server_url
         )
 
     async def _retry_mcp_discovery(
-        self, operation_func, server_url: str
+        self, operation_func: Any, server_url: str
     ) -> dict[str, dict[str, Any]]:
         """Retry MCP discovery operation with exponential backoff, avoiding try-except in loop."""
         last_error = None
@@ -1052,7 +1057,7 @@ async def _retry_mcp_discovery(
 
     @staticmethod
     async def _attempt_mcp_discovery(
-        operation_func, server_url: str
+        operation_func: Any, server_url: str
     ) -> tuple[dict[str, dict[str, Any]] | None, str, bool]:
         """Attempt single MCP discovery operation and return (result, error_message, should_retry)."""
         try:
@@ -1156,13 +1161,13 @@ def _json_schema_to_pydantic(
                     Field(..., description=field_description),
                 )
             else:
-                field_definitions[field_name] = (
+                field_definitions[field_name] = (  # type: ignore[assignment]
                     field_type | None,
                     Field(default=None, description=field_description),
                 )
 
         model_name = f"{tool_name.replace('-', '_').replace(' ', '_')}Schema"
-        return create_model(model_name, **field_definitions)
+        return create_model(model_name, **field_definitions)  # type: ignore[no-any-return,call-overload]
 
     def _json_type_to_python(self, field_schema: dict[str, Any]) -> type:
         """Convert JSON Schema type to Python type.
@@ -1182,16 +1187,16 @@ def _json_type_to_python(self, field_schema: dict[str, Any]) -> type:
                 if "const" in option:
                     types.append(str)
                 else:
-                    types.append(self._json_type_to_python(option))
+                    types.append(self._json_type_to_python(option))  # type: ignore[arg-type]
             unique_types = list(set(types))
             if len(unique_types) > 1:
                 result = unique_types[0]
                 for t in unique_types[1:]:
-                    result = result | t
+                    result = result | t  # type: ignore[assignment]
                 return result
             return unique_types[0]
 
-        type_mapping = {
+        type_mapping: dict[str, type] = {
             "string": str,
             "number": float,
             "integer": int,
@@ -1200,10 +1205,10 @@ def _json_type_to_python(self, field_schema: dict[str, Any]) -> type:
             "object": dict,
         }
 
-        return type_mapping.get(json_type, Any)
+        return type_mapping.get(json_type or "", Any)
 
     @staticmethod
-    def _fetch_amp_mcp_servers(mcp_name: str) -> list[dict]:
+    def _fetch_amp_mcp_servers(mcp_name: str) -> list[dict[str, Any]]:
         """Fetch MCP server configurations from CrewAI AMP API."""
         # TODO: Implement AMP API call to "integrations/mcps" endpoint
         # Should return list of server configs with URLs

lib/crewai/src/crewai/agents/agent_builder/base_agent.py

@@ -137,7 +137,7 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
         default=False,
         description="Enable agent to delegate and ask questions among each other.",
     )
-    tools: list[BaseTool] | None = Field(
+    tools: list[BaseTool] = Field(
         default_factory=list, description="Tools at agents' disposal"
     )
     max_iter: int = Field(
@@ -161,7 +161,7 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
         description="An instance of the ToolsHandler class.",
     )
     tools_results: list[dict[str, Any]] = Field(
-        default=[], description="Results of the tools used by the agent."
+        default_factory=list, description="Results of the tools used by the agent."
     )
     max_tokens: int | None = Field(
         default=None, description="Maximum number of tokens for the agent's execution."
@@ -265,7 +265,7 @@ def validate_mcps(
         if not mcps:
             return mcps
 
-        validated_mcps = []
+        validated_mcps: list[str | MCPServerConfig] = []
         for mcp in mcps:
             if isinstance(mcp, str):
                 if mcp.startswith(("https://", "crewai-amp:")):

lib/crewai/src/crewai/agents/crew_agent_executor.py

@@ -51,7 +51,7 @@
     from crewai.agent import Agent
     from crewai.agents.tools_handler import ToolsHandler
     from crewai.crew import Crew
-    from crewai.llms.base_llm import BaseLLM
+    from crewai.llm.base_llm import BaseLLM
     from crewai.task import Task
     from crewai.tools.base_tool import BaseTool
     from crewai.tools.structured_tool import CrewStructuredTool

lib/crewai/src/crewai/cli/crew_chat.py

@@ -14,7 +14,8 @@
 from crewai.cli.utils import read_toml
 from crewai.cli.version import get_crewai_version
 from crewai.crew import Crew
-from crewai.llm import LLM, BaseLLM
+from crewai.llm import LLM
+from crewai.llm.base_llm import BaseLLM
 from crewai.types.crew_chat import ChatInputField, ChatInputs
 from crewai.utilities.llm_utils import create_llm
 from crewai.utilities.printer import Printer

lib/crewai/src/crewai/crew.py

@@ -56,8 +56,8 @@
 from crewai.flow.flow_trackable import FlowTrackable
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
-from crewai.llm import LLM
-from crewai.llms.base_llm import BaseLLM
+from crewai.llm.base_llm import BaseLLM
+from crewai.llm.core import LLM
 from crewai.memory.entity.entity_memory import EntityMemory
 from crewai.memory.external.external_memory import ExternalMemory
 from crewai.memory.long_term.long_term_memory import LongTermMemory

lib/crewai/src/crewai/events/event_listener.py

@@ -89,7 +89,7 @@
     ToolUsageStartedEvent,
 )
 from crewai.events.utils.console_formatter import ConsoleFormatter
-from crewai.llm import LLM
+from crewai.llm.core import LLM
 from crewai.task import Task
 from crewai.telemetry.telemetry import Telemetry
 from crewai.utilities import Logger

lib/crewai/src/crewai/experimental/evaluation/base_evaluator.py

@@ -7,7 +7,7 @@
 
 from crewai.agent import Agent
 from crewai.agents.agent_builder.base_agent import BaseAgent
-from crewai.llm import BaseLLM
+from crewai.llm.base_llm import BaseLLM
 from crewai.task import Task
 from crewai.utilities.llm_utils import create_llm
 

lib/crewai/src/crewai/lite_agent.py

@@ -39,8 +39,8 @@
 from crewai.events.types.logging_events import AgentLogsExecutionEvent
 from crewai.flow.flow_trackable import FlowTrackable
 from crewai.lite_agent_output import LiteAgentOutput
-from crewai.llm import LLM
-from crewai.llms.base_llm import BaseLLM
+from crewai.llm.base_llm import BaseLLM
+from crewai.llm.core import LLM
 from crewai.tools.base_tool import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.utilities.agent_utils import (
@@ -504,7 +504,7 @@ def _invoke_loop(self) -> AgentFinish:
             AgentFinish: The final result of the agent execution.
         """
         # Execute the agent loop
-        formatted_answer = None
+        formatted_answer: AgentAction | AgentFinish | None = None
         while not isinstance(formatted_answer, AgentFinish):
             try:
                 if has_reached_max_iterations(self._iterations, self.max_iterations):
@@ -553,7 +553,8 @@ def _invoke_loop(self) -> AgentFinish:
                         show_logs=self._show_logs,
                     )
 
-                self._append_message(formatted_answer.text, role="assistant")
+                if formatted_answer is not None:
+                    self._append_message(formatted_answer.text, role="assistant")
             except OutputParserError as e:  # noqa: PERF203
                 self._printer.print(
                     content="Failed to parse LLM output. Retrying...",

lib/crewai/src/crewai/llm/__init__.py

@@ -0,0 +1,4 @@
+from crewai.llm.core import LLM
+
+
+__all__ = ["LLM"]