> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentbasis.co/llms.txt
> Use this file to discover all available pages before exploring further.

# API Reference

> Complete list of all SDK functions and their signatures

This page lists all public functions exported by the AgentBasis SDK.

## agentbasis

Core module functions imported directly from `agentbasis`.

```python theme={null}
import agentbasis
```

### Initialization

| Function                                                        | Description                                                                                             |
| --------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- |
| `init(api_key: str = None, agent_id: str = None) -> AgentBasis` | Initialize the SDK. Reads from `AGENTBASIS_API_KEY` and `AGENTBASIS_AGENT_ID` env vars if not provided. |
| `flush(timeout_millis: int = 30000) -> bool`                    | Force flush all pending telemetry data. Returns `True` if successful.                                   |
| `shutdown() -> None`                                            | Shut down the SDK and flush pending data. Auto-called on exit.                                          |

### Context Management

| Function                                                 | Description                                             |
| -------------------------------------------------------- | ------------------------------------------------------- |
| `set_user(user_id: str \| None) -> None`                 | Set the current user ID globally.                       |
| `set_session(session_id: str \| None) -> None`           | Set the current session ID globally.                    |
| `set_conversation(conversation_id: str \| None) -> None` | Set the current conversation ID globally.               |
| `set_metadata(metadata: dict \| None) -> None`           | Set custom metadata globally (e.g., `{"plan": "pro"}`). |
| `get_user() -> str \| None`                              | Get the current user ID.                                |
| `get_session() -> str \| None`                           | Get the current session ID.                             |
| `get_conversation() -> str \| None`                      | Get the current conversation ID.                        |
| `get_metadata() -> dict \| None`                         | Get the current metadata.                               |

### Context Managers & Decorators

| Function                                                       | Description                                                                 |
| -------------------------------------------------------------- | --------------------------------------------------------------------------- |
| `context(user_id, session_id, conversation_id, metadata)`      | Context manager for scoped context.                                         |
| `with_context(user_id, session_id, conversation_id, metadata)` | Decorator for setting context on a function.                                |
| `trace`                                                        | Decorator to track function execution as a span. Works with sync and async. |

***

## agentbasis.llms.openai

```python theme={null}
from agentbasis.llms.openai import instrument
```

| Function               | Description                                                                 |
| ---------------------- | --------------------------------------------------------------------------- |
| `instrument() -> None` | Auto-instrument OpenAI SDK. Traces both `OpenAI` and `AsyncOpenAI` clients. |

***

## agentbasis.llms.anthropic

```python theme={null}
from agentbasis.llms.anthropic import instrument
```

| Function               | Description                                                                          |
| ---------------------- | ------------------------------------------------------------------------------------ |
| `instrument() -> None` | Auto-instrument Anthropic SDK. Traces both `Anthropic` and `AsyncAnthropic` clients. |

***

## agentbasis.llms.gemini

```python theme={null}
from agentbasis.llms.gemini import instrument
```

| Function               | Description                                                                                    |
| ---------------------- | ---------------------------------------------------------------------------------------------- |
| `instrument() -> None` | Auto-instrument Google Gemini SDK. Traces `GenerativeModel.generate_content()` sync and async. |

***

## agentbasis.frameworks.langchain

```python theme={null}
from agentbasis.frameworks.langchain import get_callback_handler, instrument, get_callback_config
```

| Function                                              | Description                                              |
| ----------------------------------------------------- | -------------------------------------------------------- |
| `get_callback_handler() -> AgentBasisCallbackHandler` | Get a new callback handler instance.                     |
| `instrument() -> AgentBasisCallbackHandler`           | Get the global singleton callback handler.               |
| `get_callback_config() -> dict`                       | Get a RunnableConfig dict with callbacks pre-configured. |

### AgentBasisCallbackHandler

Callback handler that traces:

* LLM calls (`on_llm_start/end/error`)
* Chain execution (`on_chain_start/end/error`)
* Tool invocations (`on_tool_start/end/error`)
* Retriever operations (`on_retriever_start/end/error`)

***

## agentbasis.frameworks.pydanticai

```python theme={null}
from agentbasis.frameworks.pydanticai import instrument, get_instrumentation_settings, get_metadata_callback, create_traced_agent
```

| Function                                                                                           | Description                                                 |
| -------------------------------------------------------------------------------------------------- | ----------------------------------------------------------- |
| `instrument(include_content: bool = True, include_binary_content: bool = False) -> None`           | Enable global instrumentation for all Pydantic AI agents.   |
| `get_instrumentation_settings(include_content, include_binary_content) -> InstrumentationSettings` | Get settings for per-agent instrumentation.                 |
| `get_metadata_callback() -> Callable`                                                              | Get a callback that injects AgentBasis context into traces. |
| `create_traced_agent(model: str, include_content: bool = True, **kwargs) -> Agent`                 | Create a Pydantic AI agent pre-configured with tracing.     |

### Parameters

| Parameter                | Description                                                                      |
| ------------------------ | -------------------------------------------------------------------------------- |
| `include_content`        | Whether to log prompts and completions. Set `False` for privacy. Default: `True` |
| `include_binary_content` | Whether to include binary content like images. Default: `False`                  |