> ## Documentation Index
> Fetch the complete documentation index at: https://allhandsai-fix-security-analyzer-examples.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# openhands.sdk.agent

> API reference for openhands.sdk.agent module

### class Agent

Bases: [`AgentBase`](#class-agentbase)

Main agent implementation for OpenHands.

The Agent class provides the core functionality for running AI agents that can
interact with tools, process messages, and execute actions. It inherits from
AgentBase and implements the agent execution logic.

#### Example

```pycon theme={null}
>>> from openhands.sdk import LLM, Agent, Tool
>>> llm = LLM(model="claude-sonnet-4-20250514", api_key=SecretStr("key"))
>>> tools = [Tool(name="BashTool"), Tool(name="FileEditorTool")]
>>> agent = Agent(llm=llm, tools=tools)
```

#### Properties

* `agent_context`: AgentContext | None
* `condenser`: CondenserBase | None
* `filter_tools_regex`: str | None
* `kind`: Literal\['Agent']
* `llm`: LLM
* `mcp_config`: dict\[str, Any]
* `model_config`: ClassVar\[ConfigDict] = (configuration object)
  Configuration for the model, should be a dictionary conforming to \[ConfigDict]\[pydantic.config.ConfigDict].
* `security_analyzer`: analyzer.SecurityAnalyzerBase | None
* `system_prompt_filename`: str
* `system_prompt_kwargs`: dict\[str, object]
* `tools`: list\[Tool]

#### Methods

#### init\_state()

Initialize the empty conversation state to prepare the agent for user
messages.

Typically this involves adding system message

NOTE: state will be mutated in-place.

#### model\_post\_init()

Override this method to perform additional initialization after **init** and model\_construct.
This is useful if you want to do some validation that requires the entire model to be initialized.

#### step()

Taking a step in the conversation.

Typically this involves:

1. Making a LLM call
2. Executing the tool
3. Updating the conversation state with

LLM calls (role=”assistant”) and tool results (role=”tool”)

4.1 If conversation is finished, set state.execution\_status to FINISHED
4.2 Otherwise, just return, Conversation will kick off the next step

NOTE: state will be mutated in-place.

### class AgentBase

Bases: `DiscriminatedUnionMixin`, `ABC`

Abstract base class for OpenHands agents.

Agents are stateless and should be fully defined by their configuration.
This base class provides the common interface and functionality that all
agent implementations must follow.

#### Properties

* `agent_context`: AgentContext | None
* `condenser`: CondenserBase | None
* `filter_tools_regex`: str | None
* `kind`: str
* `llm`: LLM
* `mcp_config`: dict\[str, Any]
* `model_config`: ClassVar\[ConfigDict] = (configuration object)
  Configuration for the model, should be a dictionary conforming to \[ConfigDict]\[pydantic.config.ConfigDict].
* `name`: str
  Returns the name of the Agent.
* `prompt_dir`: str
  Returns the directory where this class’s module file is located.
* `security_analyzer`: SecurityAnalyzerBase | None
* `system_message`: str
  Compute system message on-demand to maintain statelessness.
* `system_prompt_filename`: str
* `system_prompt_kwargs`: dict\[str, object]
* `tools`: list\[Tool]
* `tools_map`: dictstr, \[ToolDefinition]
  Get the initialized tools map.
  :raises RuntimeError: If the agent has not been initialized.

#### Methods

#### get\_all\_llms()

Recursively yield unique base-class LLM objects reachable from self.

* Returns actual object references (not copies).
* De-dupes by id(LLM).
* Cycle-safe via a visited set for all traversed objects.
* Only yields objects whose type is exactly LLM (no subclasses).
* Does not handle dataclasses.

#### init\_state()

Initialize the empty conversation state to prepare the agent for user
messages.

Typically this involves adding system message

NOTE: state will be mutated in-place.

#### model\_dump\_succint()

Like model\_dump, but excludes None fields by default.

#### model\_post\_init()

Override this method to perform additional initialization after **init** and model\_construct.
This is useful if you want to do some validation that requires the entire model to be initialized.

#### resolve\_diff\_from\_deserialized()

Return a new AgentBase instance equivalent to persisted but with
explicitly whitelisted fields (e.g. api\_key, security\_analyzer) taken from
self.

#### abstractmethod step()

Taking a step in the conversation.

Typically this involves:

1. Making a LLM call
2. Executing the tool
3. Updating the conversation state with

LLM calls (role=”assistant”) and tool results (role=”tool”)

4.1 If conversation is finished, set state.execution\_status to FINISHED
4.2 Otherwise, just return, Conversation will kick off the next step

NOTE: state will be mutated in-place.