chore: import upstream snapshot with attribution

agentlightning/litagent/__init__.py

@@ -0,0 +1,11 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+from .decorator import *
+from .litagent import *
+
+__all__ = [
+    "LitAgent",
+    "llm_rollout",
+    "prompt_rollout",
+    "rollout",
+]

agentlightning/litagent/decorator.py

@@ -0,0 +1,536 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""Convenience decorators for building lightweight `LitAgent` implementations."""
+
+from __future__ import annotations
+
+import functools
+import inspect
+import logging
+from typing import Any, Awaitable, Callable, Dict, Protocol, TypeGuard, TypeVar, Union, overload
+
+from agentlightning.types import (
+    LLM,
+    AttemptedRollout,
+    NamedResources,
+    PromptTemplate,
+    ProxyLLM,
+    Rollout,
+    RolloutRawResult,
+)
+
+from .litagent import LitAgent
+
+logger = logging.getLogger(__name__)
+
+T = TypeVar("T")
+
+__all__ = [
+    "llm_rollout",
+    "prompt_rollout",
+    "rollout",
+]
+
+
+T_contra = TypeVar("T_contra", contravariant=True)
+
+
+class LlmRolloutFuncSync2(Protocol[T_contra]):
+    def __call__(self, task: T_contra, llm: LLM) -> RolloutRawResult: ...
+
+
+class LlmRolloutFuncSync3(Protocol[T_contra]):
+    def __call__(self, task: T_contra, llm: LLM, rollout: Rollout) -> RolloutRawResult: ...
+
+
+class LlmRolloutFuncAsync2(Protocol[T_contra]):
+    def __call__(self, task: T_contra, llm: LLM) -> Awaitable[RolloutRawResult]: ...
+
+
+class LlmRolloutFuncAsync3(Protocol[T_contra]):
+    def __call__(self, task: T_contra, llm: LLM, rollout: Rollout) -> Awaitable[RolloutRawResult]: ...
+
+
+LlmRolloutFunc = Union[
+    LlmRolloutFuncSync2[T_contra],
+    LlmRolloutFuncSync3[T_contra],
+    LlmRolloutFuncAsync2[T_contra],
+    LlmRolloutFuncAsync3[T_contra],
+]
+
+
+class PromptRolloutFuncSync2(Protocol[T_contra]):
+    def __call__(self, task: T_contra, prompt_template: PromptTemplate) -> RolloutRawResult: ...
+
+
+class PromptRolloutFuncAsync2(Protocol[T_contra]):
+    def __call__(self, task: T_contra, prompt_template: PromptTemplate) -> Awaitable[RolloutRawResult]: ...
+
+
+class PromptRolloutFuncSync3(Protocol[T_contra]):
+    def __call__(self, task: T_contra, prompt_template: PromptTemplate, rollout: Rollout) -> RolloutRawResult: ...
+
+
+class PromptRolloutFuncAsync3(Protocol[T_contra]):
+    def __call__(
+        self, task: T_contra, prompt_template: PromptTemplate, rollout: Rollout
+    ) -> Awaitable[RolloutRawResult]: ...
+
+
+PromptRolloutFunc = Union[
+    PromptRolloutFuncSync2[T_contra],
+    PromptRolloutFuncSync3[T_contra],
+    PromptRolloutFuncAsync2[T_contra],
+    PromptRolloutFuncAsync3[T_contra],
+]
+
+
+class FunctionalLitAgentFunc(Protocol[T_contra]):
+    def __call__(
+        self, task: T_contra, *args: Any, **kwargs: Any
+    ) -> Union[RolloutRawResult, Awaitable[RolloutRawResult]]: ...
+
+
+class FunctionalLitAgent(LitAgent[T]):
+    """Adapter that turns plain rollout functions into [`LitAgent`][agentlightning.LitAgent] instances.
+
+    The helper inspects the wrapped function to determine which resources to
+    inject, allowing both synchronous and asynchronous callables to participate
+    in the training loop without writing a dedicated subclass.
+    """
+
+    def __init__(self, rollout_func: FunctionalLitAgentFunc[T], *, strip_proxy: bool = True) -> None:
+        """Initialize the wrapper around a rollout function.
+
+        Args:
+            rollout_func: Callable that implements the rollout. It may be synchronous
+                or asynchronous and can optionally receive a
+                [`Rollout`][agentlightning.Rollout] alongside resources such as
+                `llm` or `prompt_template`.
+            strip_proxy: When ``True``, convert
+                [`ProxyLLM`][agentlightning.ProxyLLM] inputs into
+                [`LLM`][agentlightning.LLM] instances before calling the
+                rollout function. Defaults to `True`.
+        """
+        super().__init__()
+        self._rollout_func = rollout_func
+        self._strip_proxy = strip_proxy
+        self._is_async = inspect.iscoroutinefunction(rollout_func)
+        self._sig = inspect.signature(rollout_func)
+
+        # Copy function metadata to preserve type hints and other attributes
+        functools.update_wrapper(self, rollout_func)  # type: ignore
+
+    def _accepts_rollout(self) -> bool:
+        return "rollout" in self._sig.parameters
+
+    def _accepts_llm(self) -> bool:
+        return "llm" in self._sig.parameters
+
+    def _accepts_prompt_template(self) -> bool:
+        return "prompt_template" in self._sig.parameters
+
+    def __call__(self, *args: Any, **kwargs: Any) -> Any:
+        """Make the agent instance callable, preserving the original function behavior."""
+        return self._rollout_func(*args, **kwargs)  # type: ignore
+
+    def is_async(self) -> bool:
+        return self._is_async
+
+    def rollout(self, task: T, resources: NamedResources, rollout: Rollout) -> RolloutRawResult:
+        """Execute a synchronous rollout using the wrapped function.
+
+        Args:
+            task: Task input data.
+            resources: Mapping of named resources available to the agent.
+            rollout: Rollout metadata provided by the runtime.
+
+        Returns:
+            Result produced by the wrapped rollout function.
+
+        Raises:
+            RuntimeError: If the wrapped function is asynchronous.
+        """
+        if self._is_async:
+            raise RuntimeError(f"{self._rollout_func} is asynchronous. Use rollout_async instead.")
+
+        kwargs = self._get_kwargs(resources, rollout)
+        return self._rollout_func(task, **kwargs)  # type: ignore
+
+    async def rollout_async(self, task: T, resources: NamedResources, rollout: Rollout) -> RolloutRawResult:
+        """Execute an asynchronous rollout using the wrapped function.
+
+        Args:
+            task: Task input data.
+            resources: Mapping of named resources available to the agent.
+            rollout: Rollout metadata provided by the runtime.
+
+        Returns:
+            Result produced by the wrapped rollout coroutine.
+
+        Raises:
+            RuntimeError: If the wrapped function is synchronous.
+        """
+        if not self._is_async:
+            raise RuntimeError(f"{self._rollout_func} is synchronous. Use rollout instead.")
+
+        kwargs = self._get_kwargs(resources, rollout)
+        return await self._rollout_func(task, **kwargs)  # type: ignore
+
+    def _get_kwargs(self, resources: NamedResources, rollout: Rollout) -> Dict[str, Any]:
+        """Prepare keyword arguments expected by the wrapped rollout function.
+
+
+        It dynamically builds the `kwargs` dictionary by inspecting the function signature and
+        including only the parameters the function accepts. This allows flexible function
+        signatures that can request any combination of: rollout, llm, and/or prompt_template.
+
+        Args:
+            resources: Mapping of named resources available for the rollout.
+            rollout: Rollout metadata provided by the runtime.
+
+        Returns:
+            Dictionary of keyword arguments to forward to the rollout function.
+        """
+
+        kwargs: Dict[str, Any] = {}
+        if self._accepts_rollout():
+            kwargs["rollout"] = rollout
+        if self._accepts_llm():
+            kwargs["llm"] = self._get_llm_resource(resources, rollout)
+        if self._accepts_prompt_template():
+            kwargs["prompt_template"] = self._get_prompt_template_resource(resources, rollout)
+
+        return kwargs
+
+    def _get_llm_resource(self, resources: NamedResources, rollout: Rollout) -> LLM:
+        """Retrieve the first LLM resource from the available resources.
+
+        Strip the ProxyLLM resource into a LLM resource if needed.
+
+        Args:
+            resources: Mapping of named resources.
+            rollout: Rollout metadata used when stripping proxy endpoints.
+
+        Returns:
+            First [`LLM`][agentlightning.LLM] resource encountered.
+
+        Raises:
+            ValueError: If no LLM resource is present.
+        """
+        resource_found: LLM | None = None
+        for name, resource in resources.items():
+            if isinstance(resource, LLM):
+                if resource_found is not None:
+                    logger.warning(f"Multiple LLM resources found in resources. Using the first one: '{name}'.")
+                    break
+                resource_found = resource
+
+        if resource_found is None:
+            raise ValueError("No LLM resource found in the provided resources.")
+
+        if self._strip_proxy:
+            resource_found = self._strip_proxy_helper(resource_found, rollout)
+
+        return resource_found
+
+    def _get_prompt_template_resource(self, resources: NamedResources, rollout: Rollout) -> PromptTemplate:
+        """Retrieve the first prompt template resource from the available resources.
+
+        Args:
+            resources: Mapping of named resources.
+            rollout: Rollout metadata (unused).
+
+        Returns:
+            First [`PromptTemplate`][agentlightning.PromptTemplate] resource encountered.
+
+        Raises:
+            ValueError: If no prompt template resource is present.
+        """
+        resource_found: PromptTemplate | None = None
+        for name, resource in resources.items():
+            if isinstance(resource, PromptTemplate):
+                if resource_found is not None:
+                    logger.warning(
+                        f"Multiple prompt template resources found in resources. Using the first one: '{name}'."
+                    )
+                    break
+                resource_found = resource
+
+        if resource_found is None:
+            raise ValueError("No prompt template resource found in the provided resources.")
+
+        return resource_found
+
+    def _strip_proxy_helper(self, proxy_llm: LLM, rollout: Rollout) -> LLM:
+        """Convert [`ProxyLLM`][agentlightning.ProxyLLM] instances into concrete LLMs.
+
+        It resolves ProxyLLM instances to their concrete LLM implementation
+        by attaching the attempted rollout context. This is only used when the function
+        signature accepts an `llm` parameter and strip_proxy is True.
+
+        Args:
+            proxy_llm: Candidate LLM resource.
+            rollout: Rollout metadata that provides rollout and attempt identifiers.
+
+        Returns:
+            [`LLM`][agentlightning.LLM] with rollout context baked into the endpoint.
+
+        Raises:
+            ValueError: If the rollout is not an
+                [`AttemptedRollout`][agentlightning.AttemptedRollout].
+        """
+
+        if not isinstance(proxy_llm, ProxyLLM):
+            # Not a ProxyLLM, nothing to strip here.
+            return proxy_llm
+
+        # Rollout is still a Rollout here because API is not stabilized yet.
+        # In practice, it must be an AttemptedRollout.
+        if not isinstance(rollout, AttemptedRollout):
+            raise ValueError("Rollout is not an AttemptedRollout.")
+
+        return proxy_llm.with_attempted_rollout(rollout)
+
+
+@overload
+def llm_rollout(func: LlmRolloutFunc[T]) -> FunctionalLitAgent[T]: ...
+
+
+@overload
+def llm_rollout(*, strip_proxy: bool = True) -> Callable[[LlmRolloutFunc[T]], FunctionalLitAgent[T]]: ...
+
+
+def llm_rollout(
+    func: LlmRolloutFunc[T] | None = None, *, strip_proxy: bool = True
+) -> FunctionalLitAgent[T] | Callable[[LlmRolloutFunc[T]], FunctionalLitAgent[T]]:
+    """Create a [`FunctionalLitAgent`][agentlightning.litagent.decorator.FunctionalLitAgent] for LLM-based rollouts.
+
+    Args:
+        func: Callable defining the agent's behaviour. Supported signatures include:
+
+            * `(task, llm) -> result`
+            * `(task, llm, rollout) -> result`
+            * `async (task, llm) -> result`
+            * `async (task, llm, rollout) -> result`
+
+        strip_proxy: When `True`, convert proxy resources into concrete
+            [`LLM`][agentlightning.LLM] instances before calling the
+            function. Defaults to `True`.
+
+    Returns:
+        [`FunctionalLitAgent`][agentlightning.litagent.decorator.FunctionalLitAgent] that
+        wraps the supplied function.
+
+    Examples:
+        ```python
+        @llm_rollout
+        def my_agent(task, llm):
+            return llm.endpoint
+
+        @llm_rollout(strip_proxy=False)
+        def my_agent_no_strip(task, llm):
+            return llm.model
+
+        result = my_agent(task, llm)
+        result = my_agent.rollout(task, resources, rollout)
+        ```
+    """
+
+    def decorator(f: LlmRolloutFunc[T]) -> FunctionalLitAgent[T]:
+        _validate_llm_rollout_func(f)
+        return FunctionalLitAgent(f, strip_proxy=strip_proxy)
+
+    if func is None:
+        # Called with arguments: @llm_rollout(strip_proxy=False)
+        return decorator
+    else:
+        # Called without arguments: @llm_rollout
+        return decorator(func)
+
+
+def _validate_llm_rollout_func(func: Any) -> TypeGuard[LlmRolloutFunc[Any]]:
+    """Validate the function signature of an LLM rollout function.
+
+    Ensures the function follows the expected pattern for LLM-based rollouts:
+
+    - Must have at least 2 parameters
+    - First parameter must be named 'task'
+    - Must have a parameter named 'llm'
+    - Optionally can have a 'rollout' parameter
+
+    Args:
+        func: Function to inspect.
+
+    Returns:
+        `True` when the signature matches the supported patterns.
+
+    Raises:
+        ValueError: If the function signature does not match the expected pattern.
+    """
+    sig = inspect.signature(func)
+    params = list(sig.parameters.keys())
+    if len(params) < 2:
+        raise ValueError(f"Function {func} must have at least 2 parameters.")
+    if params[0] != "task":
+        raise ValueError(f"Function {func} must be a positional parameter called 'task'.")
+    if "llm" not in params:
+        raise ValueError(f"Function {func} must have a positional parameter called 'llm'.")
+
+    return True
+
+
+@overload
+def prompt_rollout(func: PromptRolloutFunc[T]) -> FunctionalLitAgent[T]: ...
+
+
+@overload
+def prompt_rollout() -> Callable[[PromptRolloutFunc[T]], FunctionalLitAgent[T]]: ...
+
+
+def prompt_rollout(
+    func: PromptRolloutFunc[T] | None = None,
+) -> FunctionalLitAgent[T] | Callable[[PromptRolloutFunc[T]], FunctionalLitAgent[T]]:
+    """Create a [`FunctionalLitAgent`][agentlightning.litagent.decorator.FunctionalLitAgent] for prompt-based rollouts.
+
+    This decorator is designed for agents that work with tunable prompt templates. It enables
+    a workflow where algorithms manage and optimize the prompt template, while agents consume
+    the template to perform rollouts. This is particularly useful for prompt optimization scenarios.
+
+    Args:
+        func: Callable defining the agent's behavior. Supported signatures include:
+
+            * `(task, prompt_template) -> result`
+            * `(task, prompt_template, rollout) -> result`
+            * `async (task, prompt_template) -> result`
+            * `async (task, prompt_template, rollout) -> result`
+
+    Returns:
+        [`FunctionalLitAgent`][agentlightning.litagent.decorator.FunctionalLitAgent] that
+        wraps the supplied function.
+
+    Examples:
+        ```python
+        @prompt_rollout
+        def my_agent(task, prompt_template):
+            messages = prompt_template.format(task=task.input)
+            return messages
+
+        result = my_agent(task, prompt_template)
+        result = my_agent.rollout(task, resources, rollout)
+        ```
+    """
+
+    def decorator(f: PromptRolloutFunc[T]) -> FunctionalLitAgent[T]:
+        _validate_prompt_rollout_func(f)
+        return FunctionalLitAgent(f)
+
+    if func is None:
+        return decorator
+    else:
+        return decorator(func)
+
+
+def _validate_prompt_rollout_func(func: Any) -> TypeGuard[PromptRolloutFunc[Any]]:
+    """Validate the function signature of a prompt rollout function.
+
+    Ensures the function follows the expected pattern for prompt-template-based rollouts:
+
+    - Must have at least 2 parameters
+    - First parameter must be named 'task'
+    - Must have a parameter named 'prompt_template'
+    - Optionally can have a 'rollout' parameter
+
+    Args:
+        func: Function to inspect.
+
+    Returns:
+        `True` when the signature matches the supported patterns.
+
+    Raises:
+        ValueError: If the function signature does not match the expected pattern.
+    """
+    sig = inspect.signature(func)
+    params = list(sig.parameters.keys())
+    if len(params) < 2:
+        raise ValueError(f"Function {func} must have at least 2 parameters.")
+    if params[0] != "task":
+        raise ValueError(f"Function {func} must be a positional parameter called 'task'.")
+    if "prompt_template" not in params:
+        raise ValueError(f"Function {func} must have a positional parameter called 'prompt_template'.")
+
+    return True
+
+
+def rollout(func: Union[LlmRolloutFunc[T], PromptRolloutFunc[T], Callable[..., Any]]) -> FunctionalLitAgent[T]:
+    """Create a [`FunctionalLitAgent`][agentlightning.litagent.decorator.FunctionalLitAgent] from an arbitrary rollout function.
+
+    This function inspects the provided callable and creates the appropriate
+    agent type based on its signature. It supports both LLM-based and prompt-template-based
+    agents. The returned agent instance is callable, preserving the original function's
+    behavior and type hints.
+
+    See [`llm_rollout`][agentlightning.litagent.decorator.llm_rollout] and
+    [`prompt_rollout`][agentlightning.litagent.decorator.prompt_rollout] for more details.
+
+    Args:
+        func: Callable that implements the rollout. Supported signatures:
+
+            - `[async ](task, llm[, rollout])` for LLM-based agents
+            - `[async ](task, prompt_template[, rollout])` for prompt-template-based agents
+
+            The supported output types of `func` is same as the return type of [`rollout`][agentlightning.LitAgent.rollout].
+
+    Returns:
+        [`FunctionalLitAgent`][agentlightning.litagent.decorator.FunctionalLitAgent] that
+        wraps the supplied function.
+
+    Examples:
+        ```python
+        # LLM-based agent
+        @rollout
+        def my_llm_agent(task, llm):
+            client = OpenAI(base_url=llm.endpoint)
+            response = client.chat.completions.create(
+                model=llm.model,
+                messages=[{"role": "user", "content": task.input}],
+            )
+            return response
+
+        # Prompt-template-based agent
+        @rollout
+        def my_prompt_agent(task, prompt_template):
+            messages = prompt_template.format(task=task.input)
+            # ... perform rollout with the formatted prompt
+            return response
+
+        # Function is still callable with original behavior
+        result = my_llm_agent(task, llm)
+
+        # Agent methods are also available
+        result = my_llm_agent.rollout(task, resources, rollout)
+        ```
+
+    Raises:
+        NotImplementedError: If the function signature doesn't match any known patterns.
+    """
+    # Check if it matches the LLM rollout API pattern
+    sig = inspect.signature(func)
+
+    try:
+        if _validate_llm_rollout_func(func):
+            return llm_rollout(func)
+    except ValueError:
+        pass
+
+    try:
+        if _validate_prompt_rollout_func(func):
+            return prompt_rollout(func)
+    except ValueError:
+        pass
+
+    raise NotImplementedError(
+        f"Function signature {sig} does not match any known agent patterns. "
+        "Expected signatures: (task, llm[, rollout]) or (task, prompt_template[, rollout]). "
+        "Functions can be sync or async."
+    )

agentlightning/litagent/litagent.py

@@ -0,0 +1,252 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+"""Base abstractions for building agents that plug into Agent Lightning."""
+
+from __future__ import annotations
+
+import inspect
+import logging
+import warnings
+import weakref
+from typing import TYPE_CHECKING, Any, Callable, Generic, Optional, TypeVar
+
+from agentlightning.types import NamedResources, Rollout, RolloutRawResult, Task
+
+if TYPE_CHECKING:
+    from agentlightning.runner import Runner
+    from agentlightning.tracer import Tracer
+    from agentlightning.trainer import Trainer
+
+
+logger = logging.getLogger(__name__)
+
+T = TypeVar("T")
+
+__all__ = [
+    "LitAgent",
+]
+
+
+def is_v0_1_rollout_api(func: Callable[..., Any]) -> bool:
+    """Return `True` when the rollout function uses the deprecated v0.1 signature.
+
+    The helper inspects the callable's signature to detect whether a `rollout_id`
+    parameter is present, which indicates the legacy API.
+
+    Args:
+        func: Function to analyze.
+
+    Returns:
+        `True` if the callable exposes a `rollout_id` parameter.
+    """
+    return "rollout_id" in inspect.signature(func).parameters
+
+
+class LitAgent(Generic[T]):
+    """Base class for implementing agent rollouts.
+
+    Subclasses override the rollout methods to process tasks while the trainer and
+    runner infrastructure manages orchestration, tracing, and persistence.
+    """
+
+    def __init__(self, *, trained_agents: Optional[str] = None) -> None:  # FIXME: str | None won't work for cli
+        """Initialize the agent instance.
+
+        Args:
+            trained_agents: Optional identifier used by legacy tooling to mark trained
+                agents.
+
+        !!! warning "Deprecated"
+            The `trained_agents` flag is deprecated. Configure `agent_match` in the adapter
+            layer instead. See [`TracerTraceToTriplet`][agentlightning.TracerTraceToTriplet]
+            for more details.
+        """
+        if trained_agents is not None:
+            warnings.warn(
+                "`trained_agents` is deprecated. Configure `agent_match` in adapter instead.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+        self.trained_agents = trained_agents
+
+        self._trainer_ref: weakref.ReferenceType[Trainer] | None = None
+        self._runner_ref: weakref.ReferenceType[Runner[T]] | None = None
+
+    def is_async(self) -> bool:
+        """Return `True` when the agent overrides any asynchronous rollout methods.
+
+        Override this method for customized async detection logic.
+        """
+        return (
+            (
+                hasattr(self, "training_rollout_async")
+                and self.__class__.training_rollout_async is not LitAgent.training_rollout_async  # type: ignore
+            )
+            or (
+                hasattr(self, "validation_rollout_async")
+                and self.__class__.validation_rollout_async is not LitAgent.validation_rollout_async  # type: ignore
+            )
+            or (hasattr(self, "rollout_async") and self.__class__.rollout_async is not LitAgent.rollout_async)  # type: ignore
+        )
+
+    def set_trainer(self, trainer: Trainer) -> None:
+        """Attach the trainer responsible for orchestration.
+
+        Args:
+            trainer: [`Trainer`][agentlightning.Trainer] that manages the agent.
+        """
+        self._trainer_ref = weakref.ref(trainer)
+
+    def get_trainer(self) -> Trainer:
+        """Return the trainer associated with this agent."""
+        if self._trainer_ref is None:
+            raise ValueError("Trainer has not been set for this agent.")
+        trainer = self._trainer_ref()
+        if trainer is None:
+            raise ValueError("Trainer reference is no longer valid (object has been garbage collected).")
+        return trainer
+
+    @property
+    def trainer(self) -> Trainer:
+        """Return the trainer associated with this agent."""
+        return self.get_trainer()
+
+    def get_tracer(self) -> Tracer:
+        """Return the tracer configured for this agent."""
+        if hasattr(self.runner, "tracer"):
+            return self.runner.tracer  # type: ignore
+        else:
+            return self.trainer.tracer
+
+    @property
+    def tracer(self) -> Tracer:
+        """Return the tracer configured for this agent."""
+        return self.get_tracer()
+
+    def set_runner(self, runner: Runner[T]) -> None:
+        """Attach the runner responsible for executing rollouts.
+
+        Args:
+            runner: [`Runner`][agentlightning.Runner] coordinating execution.
+        """
+        self._runner_ref = weakref.ref(runner)
+
+    def get_runner(self) -> Runner[T]:
+        """Return the runner responsible for executing rollouts."""
+        if self._runner_ref is None:
+            raise ValueError("Runner has not been set for this agent.")
+        runner = self._runner_ref()
+        if runner is None:
+            raise ValueError("Runner reference is no longer valid (object has been garbage collected).")
+        return runner
+
+    @property
+    def runner(self) -> Runner[T]:
+        """Return the runner responsible for executing rollouts."""
+        return self.get_runner()
+
+    def on_rollout_start(self, task: Task, runner: Runner[T], tracer: Tracer) -> None:
+        """Hook invoked immediately before a rollout begins.
+
+        Subclasses can override this method to implement custom logic such as logging,
+        metric collection, or resource setup. The default implementation is a no-op.
+
+        Args:
+            task: [`Task`][agentlightning.Task] that will be processed.
+            runner: [`Runner`][agentlightning.Runner] managing the rollout.
+            tracer: [`Tracer`][agentlightning.Tracer] associated with the runner.
+
+        !!! warning "Deprecated"
+            Override [`Hook.on_rollout_start`][agentlightning.Hook.on_rollout_start]
+            instead of this method when extending agents.
+        """
+
+    def on_rollout_end(self, task: Task, rollout: Rollout, runner: Runner[T], tracer: Tracer) -> None:
+        """Hook invoked after a rollout completes.
+
+        Subclasses can override this method for cleanup or additional logging. The default
+        implementation is a no-op.
+
+        Args:
+            task: [`Task`][agentlightning.Task] that was processed.
+            rollout: Resulting [`Rollout`][agentlightning.Rollout].
+            runner: [`Runner`][agentlightning.Runner] managing the rollout.
+            tracer: [`Tracer`][agentlightning.Tracer] associated with the runner.
+
+        !!! warning "Deprecated"
+            Override [`Hook.on_rollout_end`][agentlightning.Hook.on_rollout_end]
+            instead of this method when extending agents.
+        """
+
+    def rollout(self, task: T, resources: NamedResources, rollout: Rollout) -> RolloutRawResult:
+        """Execute a rollout synchronously.
+
+
+        If you don't wish to implement both training rollout and validation
+        rollout separately, you can just implement `rollout` which will work for both.
+
+        Args:
+            task: Task payload provided by the scheduler.
+            resources: Mapping of named resources (for example LLMs or prompt templates).
+            rollout: Rollout metadata. Avoid mutating this object directly unless a
+                subclass needs to override defaults.
+
+        Returns:
+            One of the following values:
+
+            * `None` when tracing is handled by the runner.
+            * `float` representing the final reward.
+            * `List[ReadableSpan]` with OpenTelemetry spans.
+            * `List[Span]` with Agent Lightning spans.
+            * `List[SpanCoreFields]` with Agent Lightning spans.
+        """
+        raise NotImplementedError("Agents must implement the `rollout` method.")
+
+    async def rollout_async(self, task: T, resources: NamedResources, rollout: Rollout) -> RolloutRawResult:
+        """Execute a rollout asynchronously.
+
+        Args:
+            task: Task payload provided by the scheduler.
+            resources: Mapping of named resources (for example LLMs or prompt templates).
+            rollout: Rollout metadata. Avoid mutating this object directly unless a
+                subclass needs to override defaults.
+
+        Returns:
+            Same possible return values as
+            [`rollout`][agentlightning.LitAgent.rollout].
+        """
+        raise NotImplementedError("Agents must implement the `rollout_async` method for async operations.")
+
+    def training_rollout(self, task: T, resources: NamedResources, rollout: Rollout) -> RolloutRawResult:
+        """Process a single training task synchronously.
+
+        By default, this method delegates to
+        [`rollout`][agentlightning.LitAgent.rollout].
+        """
+        return self.rollout(task, resources, rollout)
+
+    def validation_rollout(self, task: T, resources: NamedResources, rollout: Rollout) -> RolloutRawResult:
+        """Process a single validation task synchronously.
+
+        Override this method when validation should differ from training. The default
+        implementation delegates to
+        [`training_rollout`][agentlightning.LitAgent.training_rollout].
+        """
+        return self.rollout(task, resources, rollout)
+
+    async def training_rollout_async(self, task: T, resources: NamedResources, rollout: Rollout) -> RolloutRawResult:
+        """Process a single training task asynchronously.
+
+        By default, this method delegates to
+        [`rollout_async`][agentlightning.LitAgent.rollout_async].
+        """
+        return await self.rollout_async(task, resources, rollout)
+
+    async def validation_rollout_async(self, task: T, resources: NamedResources, rollout: Rollout) -> RolloutRawResult:
+        """Process a single validation task asynchronously.
+
+        Override this method when validation should differ from training. The default
+        implementation delegates to
+        [`training_rollout_async`][agentlightning.LitAgent.training_rollout_async].
+        """
+        return await self.rollout_async(task, resources, rollout)