pydantic_ai.agent

Agent dataclass

Bases: AbstractAgent[AgentDepsT, OutputDataT]

Class for defining "agents" - a way to have a specific type of "conversation" with an LLM.

Agents are generic in the dependency type they take AgentDepsT and the output type they return, OutputDataT.

By default, if neither generic parameter is customised, agents have type Agent[None, str].

Minimal usage example:

from pydantic_ai import Agent

agent = Agent('openai:gpt-5.2')
result = agent.run_sync('What is the capital of France?')
print(result.output)
#> The capital of France is Paris.

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

@dataclasses.dataclass(init=False)
class Agent(AbstractAgent[AgentDepsT, OutputDataT]):
    """Class for defining "agents" - a way to have a specific type of "conversation" with an LLM.

    Agents are generic in the dependency type they take [`AgentDepsT`][pydantic_ai.tools.AgentDepsT]
    and the output type they return, [`OutputDataT`][pydantic_ai.output.OutputDataT].

    By default, if neither generic parameter is customised, agents have type `Agent[None, str]`.

    Minimal usage example:

    ```python
    from pydantic_ai import Agent

    agent = Agent('openai:gpt-5.2')
    result = agent.run_sync('What is the capital of France?')
    print(result.output)
    #> The capital of France is Paris.
    ```
    """

    _model: models.Model | models.KnownModelName | str | None

    _name: str | None
    _description: TemplateStr[AgentDepsT] | str | None
    end_strategy: EndStrategy
    """The strategy for handling multiple tool calls when a final result is found.

    - `'early'` (default): Output tools are executed first. Once a valid final result is found, remaining function and output tool calls are skipped
    - `'exhaustive'`: Output tools are executed first, then all function tools are executed. The first valid output tool result becomes the final output
    """

    model_settings: AgentModelSettings[AgentDepsT] | None
    """Optional model request settings to use for this agent's runs, by default.

    Can be a static `ModelSettings` dict or a callable that takes a
    [`RunContext`][pydantic_ai.tools.RunContext] and returns `ModelSettings`.
    Callables are called before each model request, allowing dynamic per-step settings.

    Note, if `model_settings` is also provided at run time, those settings will be merged
    on top of the agent-level settings, with the run-level argument taking priority.
    """

    _output_type: OutputSpec[OutputDataT]

    instrument: InstrumentationSettings | bool | None
    """Options to automatically instrument with OpenTelemetry."""

    _instrument_default: ClassVar[InstrumentationSettings | bool] = False
    _metadata: AgentMetadata[AgentDepsT] | None = dataclasses.field(repr=False)

    _deps_type: type[AgentDepsT] = dataclasses.field(repr=False)
    _output_schema: _output.OutputSchema[OutputDataT] = dataclasses.field(repr=False)
    _output_validators: list[_output.OutputValidator[AgentDepsT, OutputDataT]] = dataclasses.field(repr=False)
    _instructions: list[str | _system_prompt.SystemPromptFunc[AgentDepsT]] = dataclasses.field(repr=False)
    _system_prompts: tuple[str, ...] = dataclasses.field(repr=False)
    _system_prompt_functions: list[_system_prompt.SystemPromptRunner[AgentDepsT]] = dataclasses.field(repr=False)
    _system_prompt_dynamic_functions: dict[str, _system_prompt.SystemPromptRunner[AgentDepsT]] = dataclasses.field(
        repr=False
    )
    _function_toolset: FunctionToolset[AgentDepsT] = dataclasses.field(repr=False)
    _output_toolset: OutputToolset[AgentDepsT] | None = dataclasses.field(repr=False)
    _user_toolsets: list[AbstractToolset[AgentDepsT]] = dataclasses.field(repr=False)
    _prepare_tools: ToolsPrepareFunc[AgentDepsT] | None = dataclasses.field(repr=False)
    _prepare_output_tools: ToolsPrepareFunc[AgentDepsT] | None = dataclasses.field(repr=False)
    _max_result_retries: int = dataclasses.field(repr=False)
    _max_tool_retries: int = dataclasses.field(repr=False)
    _tool_timeout: float | None = dataclasses.field(repr=False)
    _validation_context: Any | Callable[[RunContext[AgentDepsT]], Any] = dataclasses.field(repr=False)

    _event_stream_handler: EventStreamHandler[AgentDepsT] | None = dataclasses.field(repr=False)

    _concurrency_limiter: _concurrency.AbstractConcurrencyLimiter | None = dataclasses.field(repr=False)

    _enter_lock: Lock = dataclasses.field(repr=False)
    _entered_count: int = dataclasses.field(repr=False)
    _exit_stack: AsyncExitStack | None = dataclasses.field(repr=False)

    @overload
    def __init__(
        self,
        model: models.Model | models.KnownModelName | str | None = None,
        *,
        output_type: OutputSpec[OutputDataT] = str,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        system_prompt: str | Sequence[str] = (),
        deps_type: type[AgentDepsT] = NoneType,
        name: str | None = None,
        description: TemplateStr[AgentDepsT] | str | None = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        retries: int = 1,
        validation_context: Any | Callable[[RunContext[AgentDepsT]], Any] = None,
        output_retries: int | None = None,
        tools: Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] = (),
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] = (),
        prepare_tools: ToolsPrepareFunc[AgentDepsT] | None = None,
        prepare_output_tools: ToolsPrepareFunc[AgentDepsT] | None = None,
        toolsets: Sequence[AgentToolset[AgentDepsT]] | None = None,
        defer_model_check: bool = False,
        end_strategy: EndStrategy = 'early',
        instrument: InstrumentationSettings | bool | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        history_processors: Sequence[HistoryProcessor[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        tool_timeout: float | None = None,
        max_concurrency: _concurrency.AnyConcurrencyLimit = None,
        capabilities: Sequence[AbstractCapability[AgentDepsT]] | None = None,
    ) -> None: ...

    @overload
    @deprecated('`mcp_servers` is deprecated, use `toolsets` instead.')
    def __init__(
        self,
        model: models.Model | models.KnownModelName | str | None = None,
        *,
        output_type: OutputSpec[OutputDataT] = str,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        system_prompt: str | Sequence[str] = (),
        deps_type: type[AgentDepsT] = NoneType,
        name: str | None = None,
        description: TemplateStr[AgentDepsT] | str | None = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        retries: int = 1,
        validation_context: Any | Callable[[RunContext[AgentDepsT]], Any] = None,
        output_retries: int | None = None,
        tools: Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] = (),
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] = (),
        prepare_tools: ToolsPrepareFunc[AgentDepsT] | None = None,
        prepare_output_tools: ToolsPrepareFunc[AgentDepsT] | None = None,
        mcp_servers: Sequence[MCPServer] = (),
        defer_model_check: bool = False,
        end_strategy: EndStrategy = 'early',
        instrument: InstrumentationSettings | bool | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        history_processors: Sequence[HistoryProcessor[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        tool_timeout: float | None = None,
        max_concurrency: _concurrency.AnyConcurrencyLimit = None,
        capabilities: Sequence[AbstractCapability[AgentDepsT]] | None = None,
    ) -> None: ...

    def __init__(
        self,
        model: models.Model | models.KnownModelName | str | None = None,
        *,
        output_type: OutputSpec[OutputDataT] = str,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        system_prompt: str | Sequence[str] = (),
        deps_type: type[AgentDepsT] = NoneType,
        name: str | None = None,
        description: TemplateStr[AgentDepsT] | str | None = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        retries: int = 1,
        validation_context: Any | Callable[[RunContext[AgentDepsT]], Any] = None,
        output_retries: int | None = None,
        tools: Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] = (),
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] = (),
        prepare_tools: ToolsPrepareFunc[AgentDepsT] | None = None,
        prepare_output_tools: ToolsPrepareFunc[AgentDepsT] | None = None,
        toolsets: Sequence[AgentToolset[AgentDepsT]] | None = None,
        defer_model_check: bool = False,
        end_strategy: EndStrategy = 'early',
        instrument: InstrumentationSettings | bool | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        history_processors: Sequence[HistoryProcessor[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        tool_timeout: float | None = None,
        max_concurrency: _concurrency.AnyConcurrencyLimit = None,
        capabilities: Sequence[AbstractCapability[AgentDepsT]] | None = None,
        **_deprecated_kwargs: Any,
    ):
        """Create an agent.

        Args:
            model: The default model to use for this agent, if not provided,
                you must provide the model when calling it. We allow `str` here since the actual list of allowed models changes frequently.
            output_type: The type of the output data, used to validate the data returned by the model,
                defaults to `str`.
            instructions: Instructions to use for this agent, you can also register instructions via a function with
                [`instructions`][pydantic_ai.agent.Agent.instructions] or pass additional, temporary, instructions when executing a run.
            system_prompt: Static system prompts to use for this agent, you can also register system
                prompts via a function with [`system_prompt`][pydantic_ai.agent.Agent.system_prompt].
            deps_type: The type used for dependency injection, this parameter exists solely to allow you to fully
                parameterize the agent, and therefore get the best out of static type checking.
                If you're not using deps, but want type checking to pass, you can set `deps=None` to satisfy Pyright
                or add a type hint `: Agent[None, <return type>]`.
            name: The name of the agent, used for logging. If `None`, we try to infer the agent name from the call frame
                when the agent is first run.
            description: A human-readable description of the agent, attached to the agent run span as
                `gen_ai.agent.description` when instrumentation is enabled.
            model_settings: Optional model request settings to use for this agent's runs, by default.
                Can be a static `ModelSettings` dict or a callable that takes a
                [`RunContext`][pydantic_ai.tools.RunContext] and returns `ModelSettings`.
                Callables are called before each model request, allowing dynamic per-step settings.
            retries: The default number of retries to allow for tool calls and output validation, before raising an error.
                For model request retries, see the [HTTP Request Retries](../retries.md) documentation.
            validation_context: Pydantic [validation context](https://docs.pydantic.dev/latest/concepts/validators/#validation-context) used to validate tool arguments and outputs.
            output_retries: The maximum number of retries to allow for output validation, defaults to `retries`.
            tools: Tools to register with the agent, you can also register tools via the decorators
                [`@agent.tool`][pydantic_ai.agent.Agent.tool] and [`@agent.tool_plain`][pydantic_ai.agent.Agent.tool_plain].
            builtin_tools: The builtin tools that the agent will use. This depends on the model, as some models may not
                support certain tools. If the model doesn't support the builtin tools, an error will be raised.
            prepare_tools: Custom function to prepare the tool definition of all tools for each step, except output tools.
                This is useful if you want to customize the definition of multiple tools or you want to register
                a subset of tools for a given step. See [`ToolsPrepareFunc`][pydantic_ai.tools.ToolsPrepareFunc]
            prepare_output_tools: Custom function to prepare the tool definition of all output tools for each step.
                This is useful if you want to customize the definition of multiple output tools or you want to register
                a subset of output tools for a given step. See [`ToolsPrepareFunc`][pydantic_ai.tools.ToolsPrepareFunc]
            toolsets: Toolsets to register with the agent, including MCP servers and functions which take a run context
                and return a toolset. See [`ToolsetFunc`][pydantic_ai.toolsets.ToolsetFunc] for more information.
            defer_model_check: by default, if you provide a [named][pydantic_ai.models.KnownModelName] model,
                it's evaluated to create a [`Model`][pydantic_ai.models.Model] instance immediately,
                which checks for the necessary environment variables. Set this to `false`
                to defer the evaluation until the first run. Useful if you want to
                [override the model][pydantic_ai.agent.Agent.override] for testing.
            end_strategy: Strategy for handling tool calls that are requested alongside a final result.
                See [`EndStrategy`][pydantic_ai.agent.EndStrategy] for more information.
            instrument: Set to True to automatically instrument with OpenTelemetry,
                which will use Logfire if it's configured.
                Set to an instance of [`InstrumentationSettings`][pydantic_ai.agent.InstrumentationSettings] to customize.
                If this isn't set, then the last value set by
                [`Agent.instrument_all()`][pydantic_ai.agent.Agent.instrument_all]
                will be used, which defaults to False.
                See the [Debugging and Monitoring guide](https://ai.pydantic.dev/logfire/) for more info.
            metadata: Optional metadata to store with each run.
                Provide a dictionary of primitives, or a callable returning one
                computed from the [`RunContext`][pydantic_ai.tools.RunContext] on each run.
                Metadata is resolved when a run starts and recomputed after a successful run finishes so it
                can reflect the final state.
                Resolved metadata can be read after the run completes via
                [`AgentRun.metadata`][pydantic_ai.agent.AgentRun],
                [`AgentRunResult.metadata`][pydantic_ai.agent.AgentRunResult], and
                [`StreamedRunResult.metadata`][pydantic_ai.result.StreamedRunResult],
                and is attached to the agent run span when instrumentation is enabled.
            history_processors: Optional list of callables to process the message history before sending it to the model.
                Each processor takes a list of messages and returns a modified list of messages.
                Processors can be sync or async and are applied in sequence.
            event_stream_handler: Optional handler for events from the model's streaming response and the agent's execution of tools.
            tool_timeout: Default timeout in seconds for tool execution. If a tool takes longer than this,
                the tool is considered to have failed and a retry prompt is returned to the model (counting towards the retry limit).
                Individual tools can override this with their own timeout. Defaults to None (no timeout).
            max_concurrency: Optional limit on concurrent agent runs. Can be an integer for simple limiting,
                a [`ConcurrencyLimit`][pydantic_ai.ConcurrencyLimit] for advanced configuration with backpressure,
                a [`ConcurrencyLimiter`][pydantic_ai.ConcurrencyLimiter] for sharing limits across
                multiple agents, or None (default) for no limiting. When the limit is reached, additional calls
                to `run()` or `iter()` will wait until a slot becomes available.
            capabilities: Optional list of capabilities to configure the agent with.
                Built-in capabilities include [`Instructions`][pydantic_ai.capabilities.Instructions],
                [`Thinking`][pydantic_ai.capabilities.Thinking],
                [`ModelSettings`][pydantic_ai.capabilities.ModelSettings],
                [`WebSearch`][pydantic_ai.capabilities.WebSearch],
                [`HistoryProcessor`][pydantic_ai.capabilities.HistoryProcessor], and
                [`Toolset`][pydantic_ai.capabilities.Toolset].
                Custom capabilities can be created by subclassing
                [`AbstractCapability`][pydantic_ai.capabilities.AbstractCapability].
        """
        if model is None or defer_model_check:
            self._model = model
        else:
            self._model = models.infer_model(model)

        self._name = name
        self._description = description
        self.end_strategy = end_strategy

        self.history_processors: list[HistoryProcessor[AgentDepsT]] = list(history_processors or [])

        capabilities = list(capabilities or [])
        for history_processor in self.history_processors:
            capabilities.append(HistoryProcessorCap(history_processor))

        self._root_capability = CombinedCapability(capabilities)

        self.model_settings = model_settings

        self._output_type = output_type
        self.instrument = instrument
        self._metadata = metadata
        self._deps_type = deps_type

        if mcp_servers := _deprecated_kwargs.pop('mcp_servers', None):
            if toolsets is not None:  # pragma: no cover
                raise TypeError('`mcp_servers` and `toolsets` cannot be set at the same time.')
            warnings.warn('`mcp_servers` is deprecated, use `toolsets` instead', DeprecationWarning)
            toolsets = mcp_servers

        _utils.validate_empty_kwargs(_deprecated_kwargs)

        self._output_schema = _output.OutputSchema[OutputDataT].build(output_type)
        self._output_validators = []

        self._instructions = _instructions.normalize_instructions(instructions)
        self._cap_instructions = _instructions.normalize_instructions(self._root_capability.get_instructions())

        self._system_prompts = (system_prompt,) if isinstance(system_prompt, str) else tuple(system_prompt)
        self._system_prompt_functions = []
        self._system_prompt_dynamic_functions = {}

        self._max_result_retries = output_retries if output_retries is not None else retries
        self._max_tool_retries = retries
        self._tool_timeout = tool_timeout

        self._validation_context = validation_context

        self._builtin_tools = list(builtin_tools)
        self._cap_builtin_tools = list(self._root_capability.get_builtin_tools())

        self._cap_model_settings = self._root_capability.get_model_settings()

        self._prepare_tools = prepare_tools
        self._prepare_output_tools = prepare_output_tools

        self._output_toolset = self._output_schema.toolset
        if self._output_toolset:
            self._output_toolset.max_retries = self._max_result_retries

        self._function_toolset = _AgentFunctionToolset(
            tools,
            max_retries=self._max_tool_retries,
            timeout=self._tool_timeout,
            output_schema=self._output_schema,
        )

        # Agent-direct toolsets
        agent_toolsets = list(toolsets or [])
        self._dynamic_toolsets = [
            DynamicToolset[AgentDepsT](toolset_func=toolset)
            for toolset in agent_toolsets
            if not isinstance(toolset, AbstractToolset)
        ]
        self._user_toolsets = [toolset for toolset in agent_toolsets if isinstance(toolset, AbstractToolset)]

        # Capability-contributed toolsets (stored separately for per-run re-extraction)
        cap_toolset = self._root_capability.get_toolset()
        self._cap_toolsets: list[AgentToolset[AgentDepsT]] = [cap_toolset] if cap_toolset is not None else []

        self._event_stream_handler = event_stream_handler

        self._concurrency_limiter = _concurrency.normalize_to_limiter(max_concurrency)

        self._override_name: ContextVar[_utils.Option[str]] = ContextVar('_override_name', default=None)
        self._override_deps: ContextVar[_utils.Option[AgentDepsT]] = ContextVar('_override_deps', default=None)
        self._override_model: ContextVar[_utils.Option[models.Model]] = ContextVar('_override_model', default=None)
        self._override_toolsets: ContextVar[_utils.Option[Sequence[AbstractToolset[AgentDepsT]]]] = ContextVar(
            '_override_toolsets', default=None
        )
        self._override_tools: ContextVar[
            _utils.Option[Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]]]
        ] = ContextVar('_override_tools', default=None)
        self._override_instructions: ContextVar[
            _utils.Option[list[str | _system_prompt.SystemPromptFunc[AgentDepsT]]]
        ] = ContextVar('_override_instructions', default=None)
        self._override_metadata: ContextVar[_utils.Option[AgentMetadata[AgentDepsT]]] = ContextVar(
            '_override_metadata', default=None
        )
        self._override_model_settings: ContextVar[_utils.Option[AgentModelSettings[AgentDepsT]]] = ContextVar(
            '_override_model_settings', default=None
        )
        self._override_root_capability: ContextVar[_utils.Option[CombinedCapability[AgentDepsT]]] = ContextVar(
            '_override_root_capability', default=None
        )
        self._enter_lock = Lock()
        self._entered_count = 0
        self._exit_stack = None

    @overload
    @classmethod
    def from_spec(
        cls,
        spec: dict[str, Any] | AgentSpec,
        *,
        custom_capability_types: Sequence[type[AbstractCapability[Any]]] = (),
        model: models.Model | models.KnownModelName | str | None = None,
        output_type: OutputSpec[Any] = str,
        instructions: _instructions.AgentInstructions[Any] = None,
        system_prompt: str | Sequence[str] = (),
        name: str | None = None,
        description: str | None = None,
        model_settings: ModelSettings | None = None,
        retries: int | None = None,
        validation_context: Any = None,
        output_retries: int | None = None,
        tools: Sequence[Tool[Any] | ToolFuncEither[Any, ...]] = (),
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[Any]] = (),
        prepare_tools: ToolsPrepareFunc[Any] | None = None,
        prepare_output_tools: ToolsPrepareFunc[Any] | None = None,
        toolsets: Sequence[AgentToolset[Any]] | None = None,
        defer_model_check: bool = False,
        end_strategy: EndStrategy | None = None,
        instrument: InstrumentationSettings | bool | None = None,
        metadata: AgentMetadata[Any] | None = None,
        history_processors: Sequence[HistoryProcessor[Any]] | None = None,
        event_stream_handler: EventStreamHandler[Any] | None = None,
        tool_timeout: float | None = None,
        max_concurrency: _concurrency.AnyConcurrencyLimit = None,
        capabilities: Sequence[AbstractCapability[Any]] | None = None,
    ) -> Agent[None, str]: ...

    @overload
    @classmethod
    def from_spec(
        cls,
        spec: dict[str, Any] | AgentSpec,
        *,
        deps_type: type[T],
        custom_capability_types: Sequence[type[AbstractCapability[Any]]] = (),
        model: models.Model | models.KnownModelName | str | None = None,
        output_type: OutputSpec[Any] = str,
        instructions: _instructions.AgentInstructions[Any] = None,
        system_prompt: str | Sequence[str] = (),
        name: str | None = None,
        description: str | None = None,
        model_settings: ModelSettings | None = None,
        retries: int | None = None,
        validation_context: Any = None,
        output_retries: int | None = None,
        tools: Sequence[Tool[Any] | ToolFuncEither[Any, ...]] = (),
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[Any]] = (),
        prepare_tools: ToolsPrepareFunc[Any] | None = None,
        prepare_output_tools: ToolsPrepareFunc[Any] | None = None,
        toolsets: Sequence[AgentToolset[Any]] | None = None,
        defer_model_check: bool = False,
        end_strategy: EndStrategy | None = None,
        instrument: InstrumentationSettings | bool | None = None,
        metadata: AgentMetadata[Any] | None = None,
        history_processors: Sequence[HistoryProcessor[Any]] | None = None,
        event_stream_handler: EventStreamHandler[Any] | None = None,
        tool_timeout: float | None = None,
        max_concurrency: _concurrency.AnyConcurrencyLimit = None,
        capabilities: Sequence[AbstractCapability[Any]] | None = None,
    ) -> Agent[T, str]: ...

    @classmethod
    def from_spec(
        cls,
        spec: dict[str, Any] | AgentSpec,
        *,
        deps_type: type[Any] = type(None),
        custom_capability_types: Sequence[type[AbstractCapability[Any]]] = (),
        model: models.Model | models.KnownModelName | str | None = None,
        output_type: OutputSpec[Any] = str,
        instructions: _instructions.AgentInstructions[Any] = None,
        system_prompt: str | Sequence[str] = (),
        name: str | None = None,
        description: str | None = None,
        model_settings: ModelSettings | None = None,
        retries: int | None = None,
        validation_context: Any = None,
        output_retries: int | None = None,
        tools: Sequence[Tool[Any] | ToolFuncEither[Any, ...]] = (),
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[Any]] = (),
        prepare_tools: ToolsPrepareFunc[Any] | None = None,
        prepare_output_tools: ToolsPrepareFunc[Any] | None = None,
        toolsets: Sequence[AgentToolset[Any]] | None = None,
        defer_model_check: bool = False,
        end_strategy: EndStrategy | None = None,
        instrument: InstrumentationSettings | bool | None = None,
        metadata: AgentMetadata[Any] | None = None,
        history_processors: Sequence[HistoryProcessor[Any]] | None = None,
        event_stream_handler: EventStreamHandler[Any] | None = None,
        tool_timeout: float | None = None,
        max_concurrency: _concurrency.AnyConcurrencyLimit = None,
        capabilities: Sequence[AbstractCapability[Any]] | None = None,
    ) -> Agent[Any, Any]:
        """Construct an Agent from a spec dict or `AgentSpec`.

        This allows defining agents declaratively in YAML/JSON/dict form.
        Keyword arguments supplement the spec: scalar spec fields (like `name`,
        `retries`) are used as defaults that explicit arguments override, while
        `capabilities` from both sources are merged.

        Args:
            spec: The agent specification, either a dict or an `AgentSpec` instance.
            deps_type: The type of the dependencies for the agent. When provided,
                template strings in capabilities (e.g. ``"Hello {{name}}"``) are
                compiled and validated against this type.
            custom_capability_types: Additional capability classes to make available
                beyond the built-in defaults.
            model: Override the model from the spec.
            output_type: The type of the output data, defaults to `str`.
            instructions: Instructions for the agent.
            system_prompt: Static system prompts.
            name: The agent name, overrides spec `name` if provided.
            description: The agent description, overrides spec `description` if provided.
            model_settings: Model request settings.
            retries: Default retries for tool calls and output validation, overrides spec `retries` if provided.
            validation_context: Pydantic validation context for tool arguments and outputs.
            output_retries: Max retries for output validation, overrides spec `output_retries` if provided.
            tools: Tools to register with the agent.
            builtin_tools: Builtin tools for the agent.
            prepare_tools: Custom function to prepare tool definitions.
            prepare_output_tools: Custom function to prepare output tool definitions.
            toolsets: Toolsets to register with the agent.
            defer_model_check: Defer model evaluation until first run.
            end_strategy: Strategy for tool calls alongside a final result, overrides spec `end_strategy` if provided.
            instrument: Instrumentation settings, overrides spec `instrument` if provided.
            metadata: Metadata to store with each run, overrides spec `metadata` if provided.
            history_processors: Processors for message history.
            event_stream_handler: Handler for streaming events.
            tool_timeout: Default timeout for tool execution, overrides spec `tool_timeout` if provided.
            max_concurrency: Limit on concurrent agent runs.
            capabilities: Additional capabilities merged with those from the spec.

        Returns:
            A new Agent instance.
        """
        from pydantic_ai.agent.spec import AgentSpec as _AgentSpecModel

        template_context: dict[str, Any] = {
            'deps_type': deps_type if deps_type is not type(None) else None,
        }
        if isinstance(spec, dict):
            validated_spec = _AgentSpecModel.model_validate(spec, context=template_context)
        else:
            validated_spec = spec
        template_context['deps_schema'] = validated_spec.deps_schema

        effective_output_type: OutputSpec[Any]
        if output_type is not str:
            effective_output_type = output_type
        elif validated_spec.output_schema is not None:
            from pydantic_ai.output import StructuredDict

            effective_output_type = StructuredDict(validated_spec.output_schema)
        else:
            effective_output_type = str

        # Merge instructions from spec and arg
        merged_instructions = _instructions.normalize_instructions(validated_spec.instructions)
        merged_instructions.extend(_instructions.normalize_instructions(instructions))

        all_capabilities = _capabilities_from_spec(validated_spec, custom_capability_types, template_context)
        if capabilities:
            all_capabilities.extend(capabilities)

        effective_model = model or validated_spec.model
        if effective_model is None:
            raise exceptions.UserError(
                '`model` must be provided either in the spec or as a keyword argument to `from_spec()`.'
            )

        return Agent(
            model=effective_model,
            output_type=effective_output_type,
            instructions=merged_instructions or None,
            system_prompt=system_prompt,
            deps_type=deps_type,
            name=name or validated_spec.name,
            description=description or validated_spec.description,
            model_settings=merge_model_settings(
                cast(ModelSettings, validated_spec.model_settings) if validated_spec.model_settings else None,
                model_settings,
            ),
            retries=retries if retries is not None else validated_spec.retries,
            validation_context=validation_context,
            output_retries=output_retries if output_retries is not None else validated_spec.output_retries,
            tools=tools,
            builtin_tools=builtin_tools,
            prepare_tools=prepare_tools,
            prepare_output_tools=prepare_output_tools,
            toolsets=toolsets,
            defer_model_check=defer_model_check,
            end_strategy=end_strategy if end_strategy is not None else validated_spec.end_strategy,
            instrument=instrument if instrument is not None else validated_spec.instrument,
            metadata=metadata if metadata is not None else validated_spec.metadata,
            history_processors=history_processors,
            event_stream_handler=event_stream_handler,
            tool_timeout=tool_timeout if tool_timeout is not None else validated_spec.tool_timeout,
            max_concurrency=max_concurrency,
            capabilities=all_capabilities,
        )

    @overload
    @classmethod
    def from_file(
        cls,
        path: Path | str,
        *,
        custom_capability_types: Sequence[type[AbstractCapability[Any]]] = (),
        model: models.Model | models.KnownModelName | str | None = None,
        output_type: OutputSpec[Any] = str,
        instructions: _instructions.AgentInstructions[Any] = None,
        system_prompt: str | Sequence[str] = (),
        name: str | None = None,
        description: str | None = None,
        model_settings: ModelSettings | None = None,
        retries: int | None = None,
        validation_context: Any = None,
        output_retries: int | None = None,
        tools: Sequence[Tool[Any] | ToolFuncEither[Any, ...]] = (),
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[Any]] = (),
        prepare_tools: ToolsPrepareFunc[Any] | None = None,
        prepare_output_tools: ToolsPrepareFunc[Any] | None = None,
        toolsets: Sequence[AgentToolset[Any]] | None = None,
        defer_model_check: bool = False,
        end_strategy: EndStrategy | None = None,
        instrument: InstrumentationSettings | bool | None = None,
        metadata: AgentMetadata[Any] | None = None,
        history_processors: Sequence[HistoryProcessor[Any]] | None = None,
        event_stream_handler: EventStreamHandler[Any] | None = None,
        tool_timeout: float | None = None,
        max_concurrency: _concurrency.AnyConcurrencyLimit = None,
        capabilities: Sequence[AbstractCapability[Any]] | None = None,
    ) -> Agent[None, str]: ...

    @overload
    @classmethod
    def from_file(
        cls,
        path: Path | str,
        *,
        deps_type: type[T],
        custom_capability_types: Sequence[type[AbstractCapability[Any]]] = (),
        model: models.Model | models.KnownModelName | str | None = None,
        output_type: OutputSpec[Any] = str,
        instructions: _instructions.AgentInstructions[Any] = None,
        system_prompt: str | Sequence[str] = (),
        name: str | None = None,
        description: str | None = None,
        model_settings: ModelSettings | None = None,
        retries: int | None = None,
        validation_context: Any = None,
        output_retries: int | None = None,
        tools: Sequence[Tool[Any] | ToolFuncEither[Any, ...]] = (),
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[Any]] = (),
        prepare_tools: ToolsPrepareFunc[Any] | None = None,
        prepare_output_tools: ToolsPrepareFunc[Any] | None = None,
        toolsets: Sequence[AgentToolset[Any]] | None = None,
        defer_model_check: bool = False,
        end_strategy: EndStrategy | None = None,
        instrument: InstrumentationSettings | bool | None = None,
        metadata: AgentMetadata[Any] | None = None,
        history_processors: Sequence[HistoryProcessor[Any]] | None = None,
        event_stream_handler: EventStreamHandler[Any] | None = None,
        tool_timeout: float | None = None,
        max_concurrency: _concurrency.AnyConcurrencyLimit = None,
        capabilities: Sequence[AbstractCapability[Any]] | None = None,
    ) -> Agent[T, str]: ...

    @classmethod
    def from_file(
        cls,
        path: Path | str,
        **kwargs: Any,
    ) -> Agent[Any, Any]:
        """Construct an Agent from a YAML or JSON spec file.

        This is a convenience method equivalent to
        ``Agent.from_spec(AgentSpec.from_file(path), ...)``.

        The file format is inferred from the extension (`.yaml`/`.yml` or `.json`).

        Args:
            path: Path to the spec file.
            **kwargs: All other arguments are forwarded to [`from_spec`][pydantic_ai.Agent.from_spec].

        Returns:
            A new Agent instance.
        """
        from pydantic_ai.agent.spec import AgentSpec as _AgentSpecModel

        spec = _AgentSpecModel.from_file(path)
        return cls.from_spec(spec, **kwargs)

    @staticmethod
    def instrument_all(instrument: InstrumentationSettings | bool = True) -> None:
        """Set the instrumentation options for all agents where `instrument` is not set."""
        Agent._instrument_default = instrument

    @property
    def model(self) -> models.Model | models.KnownModelName | str | None:
        """The default model configured for this agent."""
        return self._model

    @model.setter
    def model(self, value: models.Model | models.KnownModelName | str | None) -> None:
        """Set the default model configured for this agent.

        We allow `str` here since the actual list of allowed models changes frequently.
        """
        self._model = value

    @property
    def name(self) -> str | None:
        """The name of the agent, used for logging.

        If `None`, we try to infer the agent name from the call frame when the agent is first run.
        """
        name_ = self._override_name.get()
        return name_.value if name_ else self._name

    @name.setter
    def name(self, value: str | None) -> None:
        """Set the name of the agent, used for logging."""
        self._name = value

    @property
    def description(self) -> str | None:
        """A human-readable description of the agent.

        If the description is a TemplateStr, returns the raw template source.
        The rendered description is available at runtime via OTel span attributes.
        """
        if self._description is None:
            return None
        return str(self._description)

    @description.setter
    def description(self, value: TemplateStr[AgentDepsT] | str | None) -> None:
        """Set the description of the agent."""
        self._description = value

    @property
    def deps_type(self) -> type:
        """The type of dependencies used by the agent."""
        return self._deps_type

    @property
    def output_type(self) -> OutputSpec[OutputDataT]:
        """The type of data output by agent runs, used to validate the data returned by the model, defaults to `str`."""
        return self._output_type

    @property
    def event_stream_handler(self) -> EventStreamHandler[AgentDepsT] | None:
        """Optional handler for events from the model's streaming response and the agent's execution of tools."""
        return self._event_stream_handler

    def __repr__(self) -> str:
        return f'{type(self).__name__}(model={self.model!r}, name={self.name!r}, end_strategy={self.end_strategy!r}, model_settings={self.model_settings!r}, output_type={self.output_type!r}, instrument={self.instrument!r})'

    @overload
    def iter(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AbstractAsyncContextManager[AgentRun[AgentDepsT, OutputDataT]]: ...

    @overload
    def iter(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT],
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AbstractAsyncContextManager[AgentRun[AgentDepsT, RunOutputDataT]]: ...

    @asynccontextmanager
    async def iter(  # noqa: C901
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[Any] | None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AsyncIterator[AgentRun[AgentDepsT, Any]]:
        """A contextmanager which can be used to iterate over the agent graph's nodes as they are executed.

        This method builds an internal agent graph (using system prompts, tools and output schemas) and then returns an
        `AgentRun` object. The `AgentRun` can be used to async-iterate over the nodes of the graph as they are
        executed. This is the API to use if you want to consume the outputs coming from each LLM model response, or the
        stream of events coming from the execution of tools.

        The `AgentRun` also provides methods to access the full message history, new messages, and usage statistics,
        and the final result of the run once it has completed.

        For more details, see the documentation of `AgentRun`.

        Example:
        ```python
        from pydantic_ai import Agent

        agent = Agent('openai:gpt-5.2')

        async def main():
            nodes = []
            async with agent.iter('What is the capital of France?') as agent_run:
                async for node in agent_run:
                    nodes.append(node)
            print(nodes)
            '''
            [
                ModelRequestNode(
                    request=ModelRequest(
                        parts=[
                            UserPromptPart(
                                content='What is the capital of France?',
                                timestamp=datetime.datetime(...),
                            )
                        ],
                        timestamp=datetime.datetime(...),
                        run_id='...',
                    )
                ),
                CallToolsNode(
                    model_response=ModelResponse(
                        parts=[TextPart(content='The capital of France is Paris.')],
                        usage=RequestUsage(input_tokens=56, output_tokens=7),
                        model_name='gpt-5.2',
                        timestamp=datetime.datetime(...),
                        run_id='...',
                    )
                ),
                End(data=FinalResult(output='The capital of France is Paris.')),
            ]
            '''
            print(agent_run.result.output)
            #> The capital of France is Paris.
        ```

        Args:
            user_prompt: User input to start/continue the conversation.
            output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
                output validators since output validators would expect an argument that matches the agent's output type.
            message_history: History of the conversation so far.
            deferred_tool_results: Optional results for deferred tool calls in the message history.
            model: Optional model to use for this run, required if `model` was not set when creating the agent.
            instructions: Optional additional instructions to use for this run.
            deps: Optional dependencies to use for this run.
            model_settings: Optional settings to use for this model's request, or a callable
                that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
                Callables are called before each model request, allowing dynamic per-step settings.
            usage_limits: Optional limits on model request count or token usage.
            usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
            metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
                [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
            infer_name: Whether to try to infer the agent name from the call frame if it's not set.
            toolsets: Optional additional toolsets for this run.
            builtin_tools: Optional additional builtin tools for this run.
            spec: Optional agent spec to apply for this run. At run time, spec values are additive.

        Returns:
            The result of the run.
        """
        if infer_name and self.name is None:
            self._infer_name(inspect.currentframe())

        # Resolve spec contributions (additive at run time)
        resolved = self._resolve_spec(spec)
        if resolved is not None:
            # Model: spec as fallback (run param > spec > agent)
            if model is None and resolved.model is not None:
                model = resolved.model
            # Instructions: spec instructions are additional
            if resolved.instructions:
                extra = resolved.instructions
                if instructions is not None:
                    existing = _instructions.normalize_instructions(instructions)
                    existing.extend(extra)
                    instructions = existing
                else:
                    instructions = extra
            # Model settings: merge spec settings under run settings (only static dicts)
            if resolved.model_settings is not None:
                if model_settings is None or not callable(model_settings):
                    model_settings = merge_model_settings(resolved.model_settings, model_settings)
                # If model_settings is a callable, spec model_settings are handled via the capability layer
            # Metadata: merge spec metadata under run metadata
            if resolved.metadata is not None:
                if metadata is not None:
                    if callable(metadata):
                        _spec_meta = resolved.metadata
                        _orig_metadata = metadata

                        def _merged_meta(ctx: RunContext[AgentDepsT]) -> dict[str, Any]:
                            return {**(_spec_meta or {}), **_orig_metadata(ctx)}

                        metadata = _merged_meta
                    else:
                        metadata = {**resolved.metadata, **metadata}
                else:
                    metadata = resolved.metadata

        model_used = self._get_model(model)
        del model

        deps = self._get_deps(deps)
        output_schema = self._prepare_output_schema(output_type)

        output_type_ = output_type or self.output_type

        # We consider it a user error if a user tries to restrict the result type while having an output validator that
        # may change the result type from the restricted type to something else. Therefore, we consider the following
        # typecast reasonable, even though it is possible to violate it with otherwise-type-checked code.
        output_validators = self._output_validators

        output_toolset = self._output_toolset
        if output_schema != self._output_schema or output_validators:
            output_toolset = output_schema.toolset
            if output_toolset:
                output_toolset.max_retries = self._max_result_retries
                output_toolset.output_validators = output_validators

        # Build the graph
        graph = _agent_graph.build_agent_graph(self.name, self._deps_type, output_type_)

        # Build the initial state
        usage = usage or _usage.RunUsage()
        state = _agent_graph.GraphAgentState(
            message_history=list(message_history) if message_history else [],
            usage=usage,
            retries=0,
            run_step=0,
        )

        # Build a resolver that computes model settings per-step, in order of precedence: run > agent > model
        model_settings_override = self._override_model_settings.get()
        agent_model_settings = (
            model_settings_override.value if model_settings_override is not None else self.model_settings
        )
        run_model_settings = model_settings if model_settings_override is None else None

        usage_limits = usage_limits or _usage.UsageLimits()

        if isinstance(model_used, InstrumentedModel):
            instrumentation_settings = model_used.instrumentation_settings
            tracer = model_used.instrumentation_settings.tracer
        else:
            instrumentation_settings = None
            tracer = NoOpTracer()

        # Build initial RunContext for for_run lifecycle hooks
        initial_ctx = RunContext[AgentDepsT](
            deps=deps,
            model=model_used,
            usage=usage,
            prompt=user_prompt,
            messages=state.message_history,
            tracer=tracer,
            run_step=0,
        )

        # Determine root capability: override > agent default
        override_cap = self._override_root_capability.get()
        base_capability = override_cap.value if override_cap is not None else self._root_capability

        # Merge spec capability additively with base capability
        if resolved is not None and resolved.capability is not None:
            effective_capability = CombinedCapability([base_capability, resolved.capability])
        else:
            effective_capability = base_capability

        # Per-run capability: re-extract get_*() if for_run returns a different instance
        run_capability = await effective_capability.for_run(initial_ctx)
        cap_toolsets: list[AgentToolset[AgentDepsT]] | None
        if run_capability is not effective_capability:
            cap_instructions = _instructions.normalize_instructions(run_capability.get_instructions())
            cap_builtin_tools = list(run_capability.get_builtin_tools())
            cap_model_settings = run_capability.get_model_settings()
            cap_ts = run_capability.get_toolset()
            cap_toolsets = [cap_ts] if cap_ts is not None else []
        elif override_cap is not None or (resolved is not None and resolved.capability is not None):
            # Re-extract from effective_capability since it differs from self._root_capability
            cap_instructions = _instructions.normalize_instructions(effective_capability.get_instructions())
            cap_builtin_tools = list(effective_capability.get_builtin_tools())
            cap_model_settings = effective_capability.get_model_settings()
            cap_ts = effective_capability.get_toolset()
            cap_toolsets = [cap_ts] if cap_ts is not None else []
        else:
            cap_instructions = None  # use init-time defaults
            cap_builtin_tools = self._cap_builtin_tools
            cap_model_settings = self._cap_model_settings
            cap_toolsets = None

        # Build model settings resolver using per-run capability
        def get_model_settings(run_context: RunContext[AgentDepsT]) -> ModelSettings | None:
            # Resolve settings in layers, each merged on top of the previous.
            # Before calling each callable, set run_context.model_settings so it
            # can see the merged result of all previous layers.
            merged = model_used.settings

            run_context.model_settings = merged
            resolved_agent = (
                agent_model_settings(run_context) if callable(agent_model_settings) else agent_model_settings
            )
            merged = merge_model_settings(merged, resolved_agent)

            # Capability settings (e.g. from Thinking, ModelSettings capabilities), cached at init
            run_context.model_settings = merged
            cap_settings = cap_model_settings
            resolved_cap = cap_settings(run_context) if callable(cap_settings) else cap_settings
            merged = merge_model_settings(merged, resolved_cap)

            run_context.model_settings = merged
            resolved_run = run_model_settings(run_context) if callable(run_model_settings) else run_model_settings
            merged = merge_model_settings(merged, resolved_run)

            run_context.model_settings = merged
            return merged

        # Build toolset with per-run capability contributions
        toolset = self._get_toolset(
            output_toolset=output_toolset,
            additional_toolsets=toolsets,
            cap_toolsets=cap_toolsets,
        )
        toolset = await toolset.for_run(initial_ctx)
        tool_manager = ToolManager[AgentDepsT](
            toolset, root_capability=run_capability, default_max_retries=self._max_tool_retries
        )

        # Build instructions with per-run capability contributions
        instructions_literal, instructions_functions = self._get_instructions(
            additional_instructions=instructions,
            cap_instructions=cap_instructions,
        )

        async def get_instructions(run_context: RunContext[AgentDepsT]) -> str | None:
            parts = [
                instructions_literal,
                *[await func.run(run_context) for func in instructions_functions],
            ]

            parts = [p for p in parts if p]
            if not parts:
                return None
            return '\n\n'.join(parts).strip()

        graph_deps = _agent_graph.GraphAgentDeps[AgentDepsT, OutputDataT](
            user_deps=deps,
            prompt=user_prompt,
            new_message_index=len(message_history) if message_history else 0,
            resumed_request=None,
            model=model_used,
            get_model_settings=get_model_settings,
            usage_limits=usage_limits,
            max_result_retries=self._max_result_retries,
            end_strategy=self.end_strategy,
            output_schema=output_schema,
            output_validators=output_validators,
            validation_context=self._validation_context,
            root_capability=run_capability,
            builtin_tools=[
                *self._builtin_tools,
                *cap_builtin_tools,
                *(builtin_tools or []),
            ],
            tool_manager=tool_manager,
            tracer=tracer,
            get_instructions=get_instructions,
            instrumentation_settings=instrumentation_settings,
        )

        user_prompt_node = _agent_graph.UserPromptNode[AgentDepsT](
            user_prompt=user_prompt,
            deferred_tool_results=deferred_tool_results,
            instructions=instructions_literal,
            instructions_functions=instructions_functions,
            system_prompts=self._system_prompts,
            system_prompt_functions=self._system_prompt_functions,
            system_prompt_dynamic_functions=self._system_prompt_dynamic_functions,
        )

        agent_name = self.name or 'agent'
        instrumentation_names = InstrumentationNames.for_version(
            instrumentation_settings.version if instrumentation_settings else DEFAULT_INSTRUMENTATION_VERSION
        )

        span_attributes: dict[str, str] = {
            'model_name': model_used.model_name if model_used else 'no-model',
            'agent_name': agent_name,
            'gen_ai.agent.name': agent_name,
            'logfire.msg': f'{agent_name} run',
        }
        if self._description is not None:
            if isinstance(self._description, TemplateStr):
                span_attributes['gen_ai.agent.description'] = self._description.render(deps)
            else:
                span_attributes['gen_ai.agent.description'] = self._description

        run_span = tracer.start_span(
            instrumentation_names.get_agent_run_span_name(agent_name),
            attributes=span_attributes,
        )

        run_metadata: dict[str, Any] | None = None
        try:
            async with (
                _concurrency.get_concurrency_context(self._concurrency_limiter, f'agent:{agent_name}'),
                graph.iter(
                    inputs=user_prompt_node,
                    state=state,
                    deps=graph_deps,
                    span=use_span(run_span) if run_span.is_recording() else None,
                    infer_name=False,
                ) as graph_run,
            ):
                async with toolset:
                    agent_run = AgentRun(graph_run)
                    run_metadata = self._resolve_and_store_metadata(agent_run.ctx, metadata)

                    # Build RunContext for run lifecycle hooks
                    run_ctx = _agent_graph.build_run_context(agent_run.ctx)

                    # wrap_run cooperative hand-off protocol:
                    #
                    # 1. _do_run() calls before_run, sets _run_ready, then awaits _run_done.
                    # 2. wrap_run wraps _do_run via the capability middleware chain.
                    # 3. We await either _run_ready (handler started) or _wrap_task completion
                    #    (short-circuit: wrap_run returned without calling handler).
                    # 4. We yield agent_run to the caller for iteration.
                    # 5. When the caller finishes (or an error occurs), we set _run_done.
                    # 6. _do_run resumes: returns the result (success) or re-raises the error.
                    # 7. If wrap_run catches the error and returns a recovery result, we use it.
                    #    Otherwise the original error propagates.
                    _run_ready = asyncio.Event()
                    _run_done = asyncio.Event()
                    _run_error: BaseException | None = None

                    async def _do_run() -> AgentRunResult[Any]:
                        await run_capability.before_run(run_ctx)
                        _run_ready.set()
                        await _run_done.wait()
                        if _run_error is not None:
                            # Raise the original node error, not the potentially
                            # transformed version from context manager __aexit__ chains.
                            raise agent_run._node_error or _run_error  # pyright: ignore[reportPrivateUsage]
                        r = agent_run.result
                        assert r is not None
                        return r

                    _wrap_task = asyncio.create_task(run_capability.wrap_run(run_ctx, handler=_do_run))

                    # Wait for handler to start or wrap_run to complete (short-circuit)
                    _ready_waiter = asyncio.create_task(_run_ready.wait())
                    await asyncio.wait({_ready_waiter, _wrap_task}, return_when=asyncio.FIRST_COMPLETED)
                    _ready_waiter.cancel()

                    _short_circuited = _wrap_task.done() and not _run_ready.is_set()
                    if _short_circuited:
                        _result = _wrap_task.result()
                        _result = await run_capability.after_run(run_ctx, result=_result)
                        agent_run._result_override = _result  # pyright: ignore[reportPrivateUsage]

                    try:
                        yield agent_run
                    except BaseException as _exc:
                        # Use the original node error if available, since context manager
                        # __aexit__ chains (GraphRun → anyio TaskGroup) may transform
                        # the exception (e.g. into CancelledError or ExceptionGroup).
                        _run_error = agent_run._node_error or _exc  # pyright: ignore[reportPrivateUsage]
                        # Don't re-raise yet — give wrap_run a chance to recover.
                        # If wrap_run catches the error from handler() and returns
                        # a recovery result, the exception will be suppressed.
                    finally:
                        if agent_run.result is not None:
                            run_metadata = self._resolve_and_store_metadata(agent_run.ctx, metadata)
                        else:
                            run_metadata = graph_run.state.metadata

                        if not _short_circuited:
                            _run_done.set()
                            if _run_error is None and agent_run.result is not None:
                                _result = await _wrap_task
                                _result = await run_capability.after_run(run_ctx, result=_result)
                                agent_run._result_override = _result  # pyright: ignore[reportPrivateUsage]
                            elif _run_error is not None:
                                # Error path: await wrap_run to see if it recovers.
                                # _do_run() re-raises _run_error; if wrap_run catches
                                # it and returns a result, recovery succeeds.
                                try:
                                    _result = await _wrap_task
                                    _result = await run_capability.after_run(run_ctx, result=_result)
                                    agent_run._result_override = _result  # pyright: ignore[reportPrivateUsage]
                                    _run_error = None  # Recovery succeeded
                                except BaseException:
                                    pass  # wrap_run didn't recover
                            elif not _wrap_task.done():
                                _wrap_task.cancel()
                                try:
                                    await _wrap_task
                                except (asyncio.CancelledError, BaseException):
                                    pass

                    # If wrap_run didn't recover from the error, re-raise.
                    # In an @asynccontextmanager, not re-raising suppresses the exception.
                    if _run_error is not None:
                        raise _run_error

                    final_result = agent_run.result
                    if (
                        instrumentation_settings
                        and instrumentation_settings.include_content
                        and run_span.is_recording()
                        and final_result is not None
                    ):
                        run_span.set_attribute(
                            'final_result',
                            (
                                final_result.output
                                if isinstance(final_result.output, str)
                                else json.dumps(InstrumentedModel.serialize_any(final_result.output))
                            ),
                        )
        finally:
            try:
                if instrumentation_settings and run_span.is_recording():
                    run_span.set_attributes(
                        self._run_span_end_attributes(
                            instrumentation_settings,
                            usage,
                            state.message_history,
                            graph_deps.new_message_index,
                            run_metadata,
                        )
                    )
            finally:
                run_span.end()

    def _get_metadata(
        self,
        ctx: RunContext[AgentDepsT],
        additional_metadata: AgentMetadata[AgentDepsT] | None = None,
    ) -> dict[str, Any] | None:
        metadata_override = self._override_metadata.get()
        if metadata_override is not None:
            return self._resolve_metadata_config(metadata_override.value, ctx)

        base_metadata = self._resolve_metadata_config(self._metadata, ctx)
        run_metadata = self._resolve_metadata_config(additional_metadata, ctx)

        if base_metadata and run_metadata:
            return {**base_metadata, **run_metadata}
        return run_metadata or base_metadata

    def _resolve_metadata_config(
        self,
        config: AgentMetadata[AgentDepsT] | None,
        ctx: RunContext[AgentDepsT],
    ) -> dict[str, Any] | None:
        if config is None:
            return None
        metadata = config(ctx) if callable(config) else config
        return metadata

    def _resolve_and_store_metadata(
        self,
        graph_run_ctx: GraphRunContext[_agent_graph.GraphAgentState, _agent_graph.GraphAgentDeps[AgentDepsT, Any]],
        metadata: AgentMetadata[AgentDepsT] | None,
    ) -> dict[str, Any] | None:
        run_context = build_run_context(graph_run_ctx)
        resolved_metadata = self._get_metadata(run_context, metadata)
        graph_run_ctx.state.metadata = resolved_metadata
        return resolved_metadata

    def _run_span_end_attributes(
        self,
        settings: InstrumentationSettings,
        usage: _usage.RunUsage,
        message_history: list[_messages.ModelMessage],
        new_message_index: int,
        metadata: dict[str, Any] | None = None,
    ) -> dict[str, str | int | float | bool]:
        if settings.version == 1:
            attrs = {
                'all_messages_events': json.dumps(
                    [InstrumentedModel.event_to_dict(e) for e in settings.messages_to_otel_events(message_history)]
                )
            }
        else:
            # Store the last instructions here for convenience
            last_instructions = InstrumentedModel._get_instructions(message_history)  # pyright: ignore[reportPrivateUsage]
            attrs: dict[str, Any] = {
                'pydantic_ai.all_messages': json.dumps(settings.messages_to_otel_messages(list(message_history))),
                **settings.system_instructions_attributes(last_instructions),
            }

            # If this agent run was provided with existing history, store an attribute indicating the point at which the
            # new messages begin.
            if new_message_index > 0:
                attrs['pydantic_ai.new_message_index'] = new_message_index

            # If the instructions for this agent run were not always the same, store an attribute that indicates that.
            # This can signal to an observability UI that different steps in the agent run had different instructions.
            # Note: We purposely only look at "new" messages because they are the only ones produced by this agent run.
            if any(
                (
                    isinstance(m, _messages.ModelRequest)
                    and m.instructions is not None
                    and m.instructions != last_instructions
                )
                for m in message_history[new_message_index:]
            ):
                attrs['pydantic_ai.variable_instructions'] = True

        if metadata is not None:
            attrs['metadata'] = json.dumps(InstrumentedModel.serialize_any(metadata))

        usage_attrs = (
            {
                k.replace('gen_ai.usage.', 'gen_ai.aggregated_usage.', 1): v
                for k, v in usage.opentelemetry_attributes().items()
            }
            if settings.use_aggregated_usage_attribute_names
            else usage.opentelemetry_attributes()
        )

        return {
            **usage_attrs,
            **attrs,
            'logfire.json_schema': json.dumps(
                {
                    'type': 'object',
                    'properties': {
                        **{k: {'type': 'array'} if isinstance(v, str) else {} for k, v in attrs.items()},
                        'final_result': {'type': 'object'},
                    },
                }
            ),
        }

    def _resolve_spec(
        self,
        spec: dict[str, Any] | AgentSpec | None,
        custom_capability_types: Sequence[type[AbstractCapability[Any]]] = (),
    ) -> _ResolvedSpec | None:
        """Validate and instantiate capabilities from a spec, returning contributions.

        Returns None if spec is None.
        """
        if spec is None:
            return None

        from pydantic_ai.agent.spec import AgentSpec as _AgentSpecModel

        deps_type = self._deps_type
        template_context: dict[str, Any] = {
            'deps_type': deps_type if deps_type is not type(None) else None,
        }
        if isinstance(spec, dict):
            validated_spec = _AgentSpecModel.model_validate(spec, context=template_context)
        else:
            validated_spec = spec
        template_context['deps_schema'] = validated_spec.deps_schema

        capabilities = _capabilities_from_spec(validated_spec, custom_capability_types, template_context)
        combined = CombinedCapability(capabilities) if capabilities else None

        # Warn for unsupported fields with non-default values
        _unsupported_fields = {
            'end_strategy': 'early',
            'retries': 1,
            'output_retries': None,
            'tool_timeout': None,
            'output_schema': None,
            'deps_schema': None,
        }
        for field_name, default_val in _unsupported_fields.items():
            val = getattr(validated_spec, field_name, default_val)
            if val != default_val:
                warnings.warn(
                    f'AgentSpec field {field_name!r} is not supported at run/override time and will be ignored',
                    UserWarning,
                    stacklevel=3,
                )

        return _ResolvedSpec(
            spec=validated_spec,
            capability=combined,
            instructions=_instructions.normalize_instructions(validated_spec.instructions)
            if validated_spec.instructions
            else [],
            model=validated_spec.model,
            model_settings=cast(ModelSettings, validated_spec.model_settings)
            if validated_spec.model_settings
            else None,
            metadata=validated_spec.metadata,
            name=validated_spec.name,
        )

    @contextmanager
    def override(  # noqa: C901
        self,
        *,
        name: str | _utils.Unset = _utils.UNSET,
        deps: AgentDepsT | _utils.Unset = _utils.UNSET,
        model: models.Model | models.KnownModelName | str | _utils.Unset = _utils.UNSET,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | _utils.Unset = _utils.UNSET,
        tools: Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] | _utils.Unset = _utils.UNSET,
        instructions: _instructions.AgentInstructions[AgentDepsT] | _utils.Unset = _utils.UNSET,
        metadata: AgentMetadata[AgentDepsT] | _utils.Unset = _utils.UNSET,
        model_settings: AgentModelSettings[AgentDepsT] | _utils.Unset = _utils.UNSET,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> Iterator[None]:
        """Context manager to temporarily override agent name, dependencies, model, toolsets, tools, or instructions.

        This is particularly useful when testing.
        You can find an example of this [here](../testing.md#overriding-model-via-pytest-fixtures).

        Args:
            name: The name to use instead of the name passed to the agent constructor and agent run.
            deps: The dependencies to use instead of the dependencies passed to the agent run.
            model: The model to use instead of the model passed to the agent run.
            toolsets: The toolsets to use instead of the toolsets passed to the agent constructor and agent run.
            tools: The tools to use instead of the tools registered with the agent.
            instructions: The instructions to use instead of the instructions registered with the agent.
            metadata: The metadata to use instead of the metadata passed to the agent constructor. When set, any
                per-run `metadata` argument is ignored.
            model_settings: The model settings to use instead of the model settings passed to the agent constructor.
                When set, any per-run `model_settings` argument is ignored.
            spec: Optional agent spec providing defaults for override. Explicit params take precedence over spec values.
        """
        resolved = self._resolve_spec(spec)

        # Apply spec values as defaults where explicit params are not set
        if resolved is not None:
            if not _utils.is_set(name) and resolved.name is not None:
                name = resolved.name
            if not _utils.is_set(model) and resolved.model is not None:
                model = resolved.model
            if not _utils.is_set(instructions) and resolved.instructions:
                instructions = resolved.instructions
            if not _utils.is_set(model_settings) and resolved.model_settings is not None:
                model_settings = resolved.model_settings
            if not _utils.is_set(metadata) and resolved.metadata is not None:
                metadata = resolved.metadata

        if _utils.is_set(name):
            name_token = self._override_name.set(_utils.Some(name))
        else:
            name_token = None

        if _utils.is_set(deps):
            deps_token = self._override_deps.set(_utils.Some(deps))
        else:
            deps_token = None

        if _utils.is_set(model):
            model_token = self._override_model.set(_utils.Some(models.infer_model(model)))
        else:
            model_token = None

        if _utils.is_set(toolsets):
            toolsets_token = self._override_toolsets.set(_utils.Some(toolsets))
        else:
            toolsets_token = None

        if _utils.is_set(tools):
            tools_token = self._override_tools.set(_utils.Some(tools))
        else:
            tools_token = None

        if _utils.is_set(instructions):
            normalized_instructions = _instructions.normalize_instructions(instructions)
            instructions_token = self._override_instructions.set(_utils.Some(normalized_instructions))
        else:
            instructions_token = None

        if _utils.is_set(metadata):
            metadata_token = self._override_metadata.set(_utils.Some(metadata))
        else:
            metadata_token = None

        if _utils.is_set(model_settings):
            model_settings_token = self._override_model_settings.set(_utils.Some(model_settings))
        else:
            model_settings_token = None

        # Set capability from spec, combining with agent's existing root capability
        if resolved is not None and resolved.capability is not None:
            cap_token = self._override_root_capability.set(_utils.Some(resolved.capability))
        else:
            cap_token = None

        try:
            yield
        finally:
            if name_token is not None:
                self._override_name.reset(name_token)
            if deps_token is not None:
                self._override_deps.reset(deps_token)
            if model_token is not None:
                self._override_model.reset(model_token)
            if toolsets_token is not None:
                self._override_toolsets.reset(toolsets_token)
            if tools_token is not None:
                self._override_tools.reset(tools_token)
            if instructions_token is not None:
                self._override_instructions.reset(instructions_token)
            if metadata_token is not None:
                self._override_metadata.reset(metadata_token)
            if model_settings_token is not None:
                self._override_model_settings.reset(model_settings_token)
            if cap_token is not None:
                self._override_root_capability.reset(cap_token)

    @overload
    def instructions(
        self, func: Callable[[RunContext[AgentDepsT]], str | None], /
    ) -> Callable[[RunContext[AgentDepsT]], str | None]: ...

    @overload
    def instructions(
        self, func: Callable[[RunContext[AgentDepsT]], Awaitable[str | None]], /
    ) -> Callable[[RunContext[AgentDepsT]], Awaitable[str | None]]: ...

    @overload
    def instructions(self, func: Callable[[], str | None], /) -> Callable[[], str | None]: ...

    @overload
    def instructions(self, func: Callable[[], Awaitable[str | None]], /) -> Callable[[], Awaitable[str | None]]: ...

    @overload
    def instructions(
        self, /
    ) -> Callable[[_system_prompt.SystemPromptFunc[AgentDepsT]], _system_prompt.SystemPromptFunc[AgentDepsT]]: ...

    def instructions(
        self,
        func: _system_prompt.SystemPromptFunc[AgentDepsT] | None = None,
        /,
    ) -> (
        Callable[[_system_prompt.SystemPromptFunc[AgentDepsT]], _system_prompt.SystemPromptFunc[AgentDepsT]]
        | _system_prompt.SystemPromptFunc[AgentDepsT]
    ):
        """Decorator to register an instructions function.

        Optionally takes [`RunContext`][pydantic_ai.tools.RunContext] as its only argument.
        Can decorate a sync or async functions.

        The decorator can be used bare (`agent.instructions`).

        Overloads for every possible signature of `instructions` are included so the decorator doesn't obscure
        the type of the function.

        Example:
        ```python
        from pydantic_ai import Agent, RunContext

        agent = Agent('test', deps_type=str)

        @agent.instructions
        def simple_instructions() -> str:
            return 'foobar'

        @agent.instructions
        async def async_instructions(ctx: RunContext[str]) -> str:
            return f'{ctx.deps} is the best'
        ```
        """
        if func is None:

            def decorator(
                func_: _system_prompt.SystemPromptFunc[AgentDepsT],
            ) -> _system_prompt.SystemPromptFunc[AgentDepsT]:
                self._instructions.append(func_)
                return func_

            return decorator
        else:
            self._instructions.append(func)
            return func

    @overload
    def system_prompt(
        self, func: Callable[[RunContext[AgentDepsT]], str | None], /
    ) -> Callable[[RunContext[AgentDepsT]], str | None]: ...

    @overload
    def system_prompt(
        self, func: Callable[[RunContext[AgentDepsT]], Awaitable[str | None]], /
    ) -> Callable[[RunContext[AgentDepsT]], Awaitable[str | None]]: ...

    @overload
    def system_prompt(self, func: Callable[[], str | None], /) -> Callable[[], str | None]: ...

    @overload
    def system_prompt(self, func: Callable[[], Awaitable[str | None]], /) -> Callable[[], Awaitable[str | None]]: ...

    @overload
    def system_prompt(
        self, /, *, dynamic: bool = False
    ) -> Callable[[_system_prompt.SystemPromptFunc[AgentDepsT]], _system_prompt.SystemPromptFunc[AgentDepsT]]: ...

    def system_prompt(
        self,
        func: _system_prompt.SystemPromptFunc[AgentDepsT] | None = None,
        /,
        *,
        dynamic: bool = False,
    ) -> (
        Callable[[_system_prompt.SystemPromptFunc[AgentDepsT]], _system_prompt.SystemPromptFunc[AgentDepsT]]
        | _system_prompt.SystemPromptFunc[AgentDepsT]
    ):
        """Decorator to register a system prompt function.

        Optionally takes [`RunContext`][pydantic_ai.tools.RunContext] as its only argument.
        Can decorate a sync or async functions.

        The decorator can be used either bare (`agent.system_prompt`) or as a function call
        (`agent.system_prompt(...)`), see the examples below.

        Overloads for every possible signature of `system_prompt` are included so the decorator doesn't obscure
        the type of the function, see `tests/typed_agent.py` for tests.

        Args:
            func: The function to decorate
            dynamic: If True, the system prompt will be reevaluated even when `messages_history` is provided,
                see [`SystemPromptPart.dynamic_ref`][pydantic_ai.messages.SystemPromptPart.dynamic_ref]

        Example:
        ```python
        from pydantic_ai import Agent, RunContext

        agent = Agent('test', deps_type=str)

        @agent.system_prompt
        def simple_system_prompt() -> str:
            return 'foobar'

        @agent.system_prompt(dynamic=True)
        async def async_system_prompt(ctx: RunContext[str]) -> str:
            return f'{ctx.deps} is the best'
        ```
        """
        if func is None:

            def decorator(
                func_: _system_prompt.SystemPromptFunc[AgentDepsT],
            ) -> _system_prompt.SystemPromptFunc[AgentDepsT]:
                runner = _system_prompt.SystemPromptRunner[AgentDepsT](func_, dynamic=dynamic)
                self._system_prompt_functions.append(runner)
                if dynamic:  # pragma: lax no cover
                    self._system_prompt_dynamic_functions[func_.__qualname__] = runner
                return func_

            return decorator
        else:
            assert not dynamic, "dynamic can't be True in this case"
            self._system_prompt_functions.append(_system_prompt.SystemPromptRunner[AgentDepsT](func, dynamic=dynamic))
            return func

    @overload
    def output_validator(
        self, func: Callable[[RunContext[AgentDepsT], OutputDataT], OutputDataT], /
    ) -> Callable[[RunContext[AgentDepsT], OutputDataT], OutputDataT]: ...

    @overload
    def output_validator(
        self, func: Callable[[RunContext[AgentDepsT], OutputDataT], Awaitable[OutputDataT]], /
    ) -> Callable[[RunContext[AgentDepsT], OutputDataT], Awaitable[OutputDataT]]: ...

    @overload
    def output_validator(
        self, func: Callable[[OutputDataT], OutputDataT], /
    ) -> Callable[[OutputDataT], OutputDataT]: ...

    @overload
    def output_validator(
        self, func: Callable[[OutputDataT], Awaitable[OutputDataT]], /
    ) -> Callable[[OutputDataT], Awaitable[OutputDataT]]: ...

    def output_validator(
        self, func: _output.OutputValidatorFunc[AgentDepsT, OutputDataT], /
    ) -> _output.OutputValidatorFunc[AgentDepsT, OutputDataT]:
        """Decorator to register an output validator function.

        Optionally takes [`RunContext`][pydantic_ai.tools.RunContext] as its first argument.
        Can decorate a sync or async functions.

        Overloads for every possible signature of `output_validator` are included so the decorator doesn't obscure
        the type of the function, see `tests/typed_agent.py` for tests.

        Example:
        ```python
        from pydantic_ai import Agent, ModelRetry, RunContext

        agent = Agent('test', deps_type=str)

        @agent.output_validator
        def output_validator_simple(data: str) -> str:
            if 'wrong' in data:
                raise ModelRetry('wrong response')
            return data

        @agent.output_validator
        async def output_validator_deps(ctx: RunContext[str], data: str) -> str:
            if ctx.deps in data:
                raise ModelRetry('wrong response')
            return data

        result = agent.run_sync('foobar', deps='spam')
        print(result.output)
        #> success (no tool calls)
        ```
        """
        self._output_validators.append(_output.OutputValidator[AgentDepsT, Any](func))
        return func

    @overload
    def tool(self, func: ToolFuncContext[AgentDepsT, ToolParams], /) -> ToolFuncContext[AgentDepsT, ToolParams]: ...

    @overload
    def tool(
        self,
        /,
        *,
        name: str | None = None,
        description: str | None = None,
        retries: int | None = None,
        prepare: ToolPrepareFunc[AgentDepsT] | None = None,
        args_validator: ArgsValidatorFunc[AgentDepsT, ToolParams] | None = None,
        docstring_format: DocstringFormat = 'auto',
        require_parameter_descriptions: bool = False,
        schema_generator: type[GenerateJsonSchema] = GenerateToolJsonSchema,
        strict: bool | None = None,
        sequential: bool = False,
        requires_approval: bool = False,
        metadata: dict[str, Any] | None = None,
        timeout: float | None = None,
    ) -> Callable[[ToolFuncContext[AgentDepsT, ToolParams]], ToolFuncContext[AgentDepsT, ToolParams]]: ...

    def tool(
        self,
        func: ToolFuncContext[AgentDepsT, ToolParams] | None = None,
        /,
        *,
        name: str | None = None,
        description: str | None = None,
        retries: int | None = None,
        prepare: ToolPrepareFunc[AgentDepsT] | None = None,
        args_validator: ArgsValidatorFunc[AgentDepsT, ToolParams] | None = None,
        docstring_format: DocstringFormat = 'auto',
        require_parameter_descriptions: bool = False,
        schema_generator: type[GenerateJsonSchema] = GenerateToolJsonSchema,
        strict: bool | None = None,
        sequential: bool = False,
        requires_approval: bool = False,
        metadata: dict[str, Any] | None = None,
        timeout: float | None = None,
    ) -> Any:
        """Decorator to register a tool function which takes [`RunContext`][pydantic_ai.tools.RunContext] as its first argument.

        Can decorate a sync or async functions.

        The docstring is inspected to extract both the tool description and description of each parameter,
        [learn more](../tools.md#function-tools-and-schema).

        We can't add overloads for every possible signature of tool, since the return type is a recursive union
        so the signature of functions decorated with `@agent.tool` is obscured.

        Example:
        ```python
        from pydantic_ai import Agent, RunContext

        agent = Agent('test', deps_type=int)

        @agent.tool
        def foobar(ctx: RunContext[int], x: int) -> int:
            return ctx.deps + x

        @agent.tool(retries=2)
        async def spam(ctx: RunContext[str], y: float) -> float:
            return ctx.deps + y

        result = agent.run_sync('foobar', deps=1)
        print(result.output)
        #> {"foobar":1,"spam":1.0}
        ```

        Args:
            func: The tool function to register.
            name: The name of the tool, defaults to the function name.
            description: The description of the tool, defaults to the function docstring.
            retries: The number of retries to allow for this tool, defaults to the agent's default retries,
                which defaults to 1.
            prepare: custom method to prepare the tool definition for each step, return `None` to omit this
                tool from a given step. This is useful if you want to customise a tool at call time,
                or omit it completely from a step. See [`ToolPrepareFunc`][pydantic_ai.tools.ToolPrepareFunc].
            args_validator: custom method to validate tool arguments after schema validation has passed,
                before execution. The validator receives the already-validated and type-converted parameters,
                with `RunContext` as the first argument.
                Should raise [`ModelRetry`][pydantic_ai.exceptions.ModelRetry] on validation failure,
                return `None` on success.
                See [`ArgsValidatorFunc`][pydantic_ai.tools.ArgsValidatorFunc].
            docstring_format: The format of the docstring, see [`DocstringFormat`][pydantic_ai.tools.DocstringFormat].
                Defaults to `'auto'`, such that the format is inferred from the structure of the docstring.
            require_parameter_descriptions: If True, raise an error if a parameter description is missing. Defaults to False.
            schema_generator: The JSON schema generator class to use for this tool. Defaults to `GenerateToolJsonSchema`.
            strict: Whether to enforce JSON schema compliance (only affects OpenAI).
                See [`ToolDefinition`][pydantic_ai.tools.ToolDefinition] for more info.
            sequential: Whether the function requires a sequential/serial execution environment. Defaults to False.
            requires_approval: Whether this tool requires human-in-the-loop approval. Defaults to False.
                See the [tools documentation](../deferred-tools.md#human-in-the-loop-tool-approval) for more info.
            metadata: Optional metadata for the tool. This is not sent to the model but can be used for filtering and tool behavior customization.
            timeout: Timeout in seconds for tool execution. If the tool takes longer, a retry prompt is returned to the model.
                Overrides the agent-level `tool_timeout` if set. Defaults to None (no timeout).
        """

        def tool_decorator(
            func_: ToolFuncContext[AgentDepsT, ToolParams],
        ) -> ToolFuncContext[AgentDepsT, ToolParams]:
            # noinspection PyTypeChecker
            self._function_toolset.add_function(
                func_,
                takes_ctx=True,
                name=name,
                description=description,
                retries=retries,
                prepare=prepare,
                args_validator=args_validator,
                docstring_format=docstring_format,
                require_parameter_descriptions=require_parameter_descriptions,
                schema_generator=schema_generator,
                strict=strict,
                sequential=sequential,
                requires_approval=requires_approval,
                metadata=metadata,
                timeout=timeout,
            )
            return func_

        return tool_decorator if func is None else tool_decorator(func)

    @overload
    def tool_plain(self, func: ToolFuncPlain[ToolParams], /) -> ToolFuncPlain[ToolParams]: ...

    @overload
    def tool_plain(
        self,
        /,
        *,
        name: str | None = None,
        description: str | None = None,
        retries: int | None = None,
        prepare: ToolPrepareFunc[AgentDepsT] | None = None,
        args_validator: ArgsValidatorFunc[AgentDepsT, ToolParams] | None = None,
        docstring_format: DocstringFormat = 'auto',
        require_parameter_descriptions: bool = False,
        schema_generator: type[GenerateJsonSchema] = GenerateToolJsonSchema,
        strict: bool | None = None,
        sequential: bool = False,
        requires_approval: bool = False,
        metadata: dict[str, Any] | None = None,
        timeout: float | None = None,
    ) -> Callable[[ToolFuncPlain[ToolParams]], ToolFuncPlain[ToolParams]]: ...

    def tool_plain(
        self,
        func: ToolFuncPlain[ToolParams] | None = None,
        /,
        *,
        name: str | None = None,
        description: str | None = None,
        retries: int | None = None,
        prepare: ToolPrepareFunc[AgentDepsT] | None = None,
        args_validator: ArgsValidatorFunc[AgentDepsT, ToolParams] | None = None,
        docstring_format: DocstringFormat = 'auto',
        require_parameter_descriptions: bool = False,
        schema_generator: type[GenerateJsonSchema] = GenerateToolJsonSchema,
        strict: bool | None = None,
        sequential: bool = False,
        requires_approval: bool = False,
        metadata: dict[str, Any] | None = None,
        timeout: float | None = None,
    ) -> Any:
        """Decorator to register a tool function which DOES NOT take `RunContext` as an argument.

        Can decorate a sync or async functions.

        The docstring is inspected to extract both the tool description and description of each parameter,
        [learn more](../tools.md#function-tools-and-schema).

        We can't add overloads for every possible signature of tool, since the return type is a recursive union
        so the signature of functions decorated with `@agent.tool` is obscured.

        Example:
        ```python
        from pydantic_ai import Agent, RunContext

        agent = Agent('test')

        @agent.tool
        def foobar(ctx: RunContext[int]) -> int:
            return 123

        @agent.tool(retries=2)
        async def spam(ctx: RunContext[str]) -> float:
            return 3.14

        result = agent.run_sync('foobar', deps=1)
        print(result.output)
        #> {"foobar":123,"spam":3.14}
        ```

        Args:
            func: The tool function to register.
            name: The name of the tool, defaults to the function name.
            description: The description of the tool, defaults to the function docstring.
            retries: The number of retries to allow for this tool, defaults to the agent's default retries,
                which defaults to 1.
            prepare: custom method to prepare the tool definition for each step, return `None` to omit this
                tool from a given step. This is useful if you want to customise a tool at call time,
                or omit it completely from a step. See [`ToolPrepareFunc`][pydantic_ai.tools.ToolPrepareFunc].
            args_validator: custom method to validate tool arguments after schema validation has passed,
                before execution. The validator receives the already-validated and type-converted parameters,
                with [`RunContext`][pydantic_ai.tools.RunContext] as the first argument — even though the
                tool function itself does not take `RunContext` when using `tool_plain`.
                Should raise [`ModelRetry`][pydantic_ai.exceptions.ModelRetry] on validation failure,
                return `None` on success.
                See [`ArgsValidatorFunc`][pydantic_ai.tools.ArgsValidatorFunc].
            docstring_format: The format of the docstring, see [`DocstringFormat`][pydantic_ai.tools.DocstringFormat].
                Defaults to `'auto'`, such that the format is inferred from the structure of the docstring.
            require_parameter_descriptions: If True, raise an error if a parameter description is missing. Defaults to False.
            schema_generator: The JSON schema generator class to use for this tool. Defaults to `GenerateToolJsonSchema`.
            strict: Whether to enforce JSON schema compliance (only affects OpenAI).
                See [`ToolDefinition`][pydantic_ai.tools.ToolDefinition] for more info.
            sequential: Whether the function requires a sequential/serial execution environment. Defaults to False.
            requires_approval: Whether this tool requires human-in-the-loop approval. Defaults to False.
                See the [tools documentation](../deferred-tools.md#human-in-the-loop-tool-approval) for more info.
            metadata: Optional metadata for the tool. This is not sent to the model but can be used for filtering and tool behavior customization.
            timeout: Timeout in seconds for tool execution. If the tool takes longer, a retry prompt is returned to the model.
                Overrides the agent-level `tool_timeout` if set. Defaults to None (no timeout).
        """

        def tool_decorator(func_: ToolFuncPlain[ToolParams]) -> ToolFuncPlain[ToolParams]:
            # noinspection PyTypeChecker
            self._function_toolset.add_function(
                func_,
                takes_ctx=False,
                name=name,
                description=description,
                retries=retries,
                prepare=prepare,
                args_validator=args_validator,
                docstring_format=docstring_format,
                require_parameter_descriptions=require_parameter_descriptions,
                schema_generator=schema_generator,
                strict=strict,
                sequential=sequential,
                requires_approval=requires_approval,
                metadata=metadata,
                timeout=timeout,
            )
            return func_

        return tool_decorator if func is None else tool_decorator(func)

    @overload
    def toolset(self, func: ToolsetFunc[AgentDepsT], /) -> ToolsetFunc[AgentDepsT]: ...

    @overload
    def toolset(
        self,
        /,
        *,
        per_run_step: bool = True,
        id: str | None = None,
    ) -> Callable[[ToolsetFunc[AgentDepsT]], ToolsetFunc[AgentDepsT]]: ...

    def toolset(
        self,
        func: ToolsetFunc[AgentDepsT] | None = None,
        /,
        *,
        per_run_step: bool = True,
        id: str | None = None,
    ) -> Any:
        """Decorator to register a toolset function which takes [`RunContext`][pydantic_ai.tools.RunContext] as its only argument.

        Can decorate a sync or async functions.

        The decorator can be used bare (`agent.toolset`).

        Example:
        ```python
        from pydantic_ai import AbstractToolset, Agent, FunctionToolset, RunContext

        agent = Agent('test', deps_type=str)

        @agent.toolset
        async def simple_toolset(ctx: RunContext[str]) -> AbstractToolset[str]:
            return FunctionToolset()
        ```

        Args:
            func: The toolset function to register.
            per_run_step: Whether to re-evaluate the toolset for each run step. Defaults to True.
            id: An optional unique ID for the dynamic toolset. Required for use with durable execution
                environments like Temporal, where the ID identifies the toolset's activities within the workflow.
        """

        def toolset_decorator(func_: ToolsetFunc[AgentDepsT]) -> ToolsetFunc[AgentDepsT]:
            self._dynamic_toolsets.append(DynamicToolset(func_, per_run_step=per_run_step, id=id))
            return func_

        return toolset_decorator if func is None else toolset_decorator(func)

    def _get_model(self, model: models.Model | models.KnownModelName | str | None) -> models.Model:
        """Create a model configured for this agent.

        Args:
            model: model to use for this run, required if `model` was not set when creating the agent.

        Returns:
            The model used
        """
        model_: models.Model
        if some_model := self._override_model.get():
            # we don't want `override()` to cover up errors from the model not being defined, hence this check
            if model is None and self.model is None:
                raise exceptions.UserError(
                    '`model` must either be set on the agent or included when calling it. '
                    '(Even when `override(model=...)` is customizing the model that will actually be called)'
                )
            model_ = some_model.value
        elif model is not None:
            model_ = models.infer_model(model)
        elif self.model is not None:
            # noinspection PyTypeChecker
            model_ = self.model = models.infer_model(self.model)
        else:
            raise exceptions.UserError('`model` must either be set on the agent or included when calling it.')

        instrument = self.instrument
        if instrument is None:
            instrument = self._instrument_default

        return instrument_model(model_, instrument)

    def _get_deps(self: Agent[T, OutputDataT], deps: T) -> T:
        """Get deps for a run.

        If we've overridden deps via `_override_deps`, use that, otherwise use the deps passed to the call.

        We could do runtime type checking of deps against `self._deps_type`, but that's a slippery slope.
        """
        if some_deps := self._override_deps.get():
            return some_deps.value
        else:
            return deps

    def _get_instructions(
        self,
        additional_instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        cap_instructions: list[str | _system_prompt.SystemPromptFunc[AgentDepsT]] | None = None,
    ) -> tuple[str | None, list[_system_prompt.SystemPromptRunner[AgentDepsT]]]:
        override_instructions = self._override_instructions.get()
        if override_instructions:
            # Override replaces all instructions, including capability contributions.
            instructions = override_instructions.value
        else:
            instructions = self._instructions.copy()
            instructions.extend(cap_instructions if cap_instructions is not None else self._cap_instructions)
            if additional_instructions is not None:
                instructions.extend(_instructions.normalize_instructions(additional_instructions))

        literal_parts: list[str] = []
        functions: list[_system_prompt.SystemPromptRunner[AgentDepsT]] = []

        for instruction in instructions:
            if isinstance(instruction, str):
                literal_parts.append(instruction)
            else:
                # TemplateStr instances land here too: they are callable with a
                # RunContext parameter, so SystemPromptRunner handles them like
                # any other system prompt function.
                functions.append(_system_prompt.SystemPromptRunner[AgentDepsT](instruction))

        literal = '\n'.join(literal_parts).strip() or None
        return literal, functions

    def _get_toolset(
        self,
        output_toolset: AbstractToolset[AgentDepsT] | None | _utils.Unset = _utils.UNSET,
        additional_toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        cap_toolsets: Sequence[AgentToolset[AgentDepsT]] | None = None,
    ) -> AbstractToolset[AgentDepsT]:
        """Get the complete toolset.

        Args:
            output_toolset: The output toolset to use instead of the one built at agent construction time.
            additional_toolsets: Additional toolsets to add, unless toolsets have been overridden.
            cap_toolsets: Per-run capability toolsets to use instead of the init-time capability toolsets.
        """
        toolsets = list(self._build_toolset_list(cap_toolsets=cap_toolsets))
        # Don't add additional toolsets if the toolsets have been overridden
        if additional_toolsets and self._override_toolsets.get() is None:
            toolsets = [*toolsets, *additional_toolsets]

        toolset = CombinedToolset(toolsets)

        if self._prepare_tools:
            toolset = PreparedToolset(toolset, self._prepare_tools)

        output_toolset = output_toolset if _utils.is_set(output_toolset) else self._output_toolset
        if output_toolset is not None:
            if self._prepare_output_tools:
                output_toolset = PreparedToolset(output_toolset, self._prepare_output_tools)
            toolset = CombinedToolset([output_toolset, toolset])

        return toolset

    @property
    def toolsets(self) -> Sequence[AbstractToolset[AgentDepsT]]:
        """All toolsets registered on the agent, including a function toolset holding tools that were registered on the agent directly.

        Output tools are not included.
        """
        return self._build_toolset_list()

    def _build_toolset_list(
        self,
        cap_toolsets: Sequence[AgentToolset[AgentDepsT]] | None = None,
    ) -> list[AbstractToolset[AgentDepsT]]:
        """Build the list of toolsets, optionally with per-run capability toolsets."""
        toolsets: list[AbstractToolset[AgentDepsT]] = []

        if some_tools := self._override_tools.get():
            function_toolset = _AgentFunctionToolset(
                some_tools.value,
                max_retries=self._max_tool_retries,
                timeout=self._tool_timeout,
                output_schema=self._output_schema,
            )
        else:
            function_toolset = self._function_toolset
        toolsets.append(function_toolset)

        if some_user_toolsets := self._override_toolsets.get():
            toolsets.extend(some_user_toolsets.value)
        else:
            toolsets.extend(self._user_toolsets)
            toolsets.extend(self._dynamic_toolsets)
            for cap_ts in cap_toolsets if cap_toolsets is not None else self._cap_toolsets:
                if isinstance(cap_ts, AbstractToolset):
                    toolsets.append(cap_ts)  # pyright: ignore[reportUnknownArgumentType]
                else:
                    toolsets.append(DynamicToolset(cap_ts))

        return toolsets

    @overload
    def _prepare_output_schema(self, output_type: None) -> _output.OutputSchema[OutputDataT]: ...

    @overload
    def _prepare_output_schema(
        self, output_type: OutputSpec[RunOutputDataT]
    ) -> _output.OutputSchema[RunOutputDataT]: ...

    def _prepare_output_schema(self, output_type: OutputSpec[Any] | None) -> _output.OutputSchema[Any]:
        if output_type is not None:
            if self._output_validators:
                raise exceptions.UserError('Cannot set a custom run `output_type` when the agent has output validators')
            schema = _output.OutputSchema.build(output_type)
        else:
            schema = self._output_schema

        return schema

    async def __aenter__(self) -> Self:
        """Enter the agent context.

        This will start all [`MCPServerStdio`s][pydantic_ai.mcp.MCPServerStdio] registered as `toolsets` so they are ready to be used.

        This is a no-op if the agent has already been entered.
        """
        async with self._enter_lock:
            if self._entered_count == 0:
                async with AsyncExitStack() as exit_stack:
                    toolset = self._get_toolset()
                    await exit_stack.enter_async_context(toolset)

                    self._exit_stack = exit_stack.pop_all()
            self._entered_count += 1
        return self

    async def __aexit__(self, *args: Any) -> bool | None:
        async with self._enter_lock:
            self._entered_count -= 1
            if self._entered_count == 0 and self._exit_stack is not None:
                await self._exit_stack.aclose()
                self._exit_stack = None

    def set_mcp_sampling_model(self, model: models.Model | models.KnownModelName | str | None = None) -> None:
        """Set the sampling model on all MCP servers registered with the agent.

        If no sampling model is provided, the agent's model will be used.
        """
        try:
            sampling_model = models.infer_model(model) if model else self._get_model(None)
        except exceptions.UserError as e:
            raise exceptions.UserError('No sampling model provided and no model set on the agent.') from e

        from ..mcp import MCPServer

        def _set_sampling_model(toolset: AbstractToolset[AgentDepsT]) -> None:
            if isinstance(toolset, MCPServer):
                toolset.sampling_model = sampling_model

        self._get_toolset().apply(_set_sampling_model)

    def to_web(
        self,
        *,
        models: ModelsParam = None,
        builtin_tools: list[AbstractBuiltinTool] | None = None,
        deps: AgentDepsT = None,
        model_settings: ModelSettings | None = None,
        instructions: str | None = None,
        html_source: str | Path | None = None,
    ) -> Starlette:
        """Create a Starlette app that serves a web chat UI for this agent.

        This method returns a pre-configured Starlette application that provides a web-based
        chat interface for interacting with the agent. By default, the UI is fetched from a
        CDN and cached on first use.

        The returned Starlette application can be mounted into a FastAPI app or run directly
        with any ASGI server (uvicorn, hypercorn, etc.).

        Note that the `deps` and `model_settings` will be the same for each request.
        To provide different `deps` for each request use the lower-level adapters directly.

        Args:
            models: Additional models to make available in the UI. Can be:
                - A sequence of model names/instances (e.g., `['openai:gpt-5', 'anthropic:claude-sonnet-4-6']`)
                - A dict mapping display labels to model names/instances
                  (e.g., `{'GPT 5': 'openai:gpt-5', 'Claude': 'anthropic:claude-sonnet-4-6'}`)
                The agent's model is always included. Builtin tool support is automatically
                determined from each model's profile.
            builtin_tools: Additional builtin tools to make available in the UI.
                The agent's configured builtin tools are always included. Tool labels
                in the UI are derived from the tool's `label` property.
            deps: Optional dependencies to use for all requests.
            model_settings: Optional settings to use for all model requests.
            instructions: Optional extra instructions to pass to each agent run.
            html_source: Path or URL for the chat UI HTML. Can be:
                - None (default): Fetches from CDN and caches locally
                - A Path instance: Reads from the local file
                - A URL string (http:// or https://): Fetches from the URL
                - A file path string: Reads from the local file

        Returns:
            A configured Starlette application ready to be served (e.g., with uvicorn)

        Example:
            ```python
            from pydantic_ai import Agent
            from pydantic_ai.builtin_tools import WebSearchTool

            agent = Agent('openai:gpt-5', builtin_tools=[WebSearchTool()])

            # Simple usage - uses agent's model and builtin tools
            app = agent.to_web()

            # Or provide additional models for UI selection
            app = agent.to_web(models=['openai:gpt-5', 'anthropic:claude-sonnet-4-6'])

            # Then run with: uvicorn app:app --reload
            ```
        """
        from ..ui._web import create_web_app

        return create_web_app(
            self,
            models=models,
            builtin_tools=builtin_tools,
            deps=deps,
            model_settings=model_settings,
            instructions=instructions,
            html_source=html_source,
        )

    @asynccontextmanager
    @deprecated(
        '`run_mcp_servers` is deprecated, use `async with agent:` instead. If you need to set a sampling model on all MCP servers, use `agent.set_mcp_sampling_model()`.'
    )
    async def run_mcp_servers(
        self, model: models.Model | models.KnownModelName | str | None = None
    ) -> AsyncIterator[None]:
        """Run [`MCPServerStdio`s][pydantic_ai.mcp.MCPServerStdio] so they can be used by the agent.

        Deprecated: use [`async with agent`][pydantic_ai.agent.Agent.__aenter__] instead.
        If you need to set a sampling model on all MCP servers, use [`agent.set_mcp_sampling_model()`][pydantic_ai.agent.Agent.set_mcp_sampling_model].

        Returns: a context manager to start and shutdown the servers.
        """
        try:
            self.set_mcp_sampling_model(model)
        except exceptions.UserError:
            if model is not None:
                raise

        async with self:
            yield

__init__

__init__(
    model: Model | KnownModelName | str | None = None,
    *,
    output_type: OutputSpec[OutputDataT] = str,
    instructions: AgentInstructions[AgentDepsT] = None,
    system_prompt: str | Sequence[str] = (),
    deps_type: type[AgentDepsT] = NoneType,
    name: str | None = None,
    description: (
        TemplateStr[AgentDepsT] | str | None
    ) = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    retries: int = 1,
    validation_context: (
        Any | Callable[[RunContext[AgentDepsT]], Any]
    ) = None,
    output_retries: int | None = None,
    tools: Sequence[
        Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]
    ] = (),
    builtin_tools: Sequence[
        AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]
    ] = (),
    prepare_tools: (
        ToolsPrepareFunc[AgentDepsT] | None
    ) = None,
    prepare_output_tools: (
        ToolsPrepareFunc[AgentDepsT] | None
    ) = None,
    toolsets: (
        Sequence[AgentToolset[AgentDepsT]] | None
    ) = None,
    defer_model_check: bool = False,
    end_strategy: EndStrategy = "early",
    instrument: (
        InstrumentationSettings | bool | None
    ) = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    history_processors: (
        Sequence[HistoryProcessor[AgentDepsT]] | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    tool_timeout: float | None = None,
    max_concurrency: AnyConcurrencyLimit = None,
    capabilities: (
        Sequence[AbstractCapability[AgentDepsT]] | None
    ) = None
) -> None

__init__(
    model: Model | KnownModelName | str | None = None,
    *,
    output_type: OutputSpec[OutputDataT] = str,
    instructions: AgentInstructions[AgentDepsT] = None,
    system_prompt: str | Sequence[str] = (),
    deps_type: type[AgentDepsT] = NoneType,
    name: str | None = None,
    description: (
        TemplateStr[AgentDepsT] | str | None
    ) = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    retries: int = 1,
    validation_context: (
        Any | Callable[[RunContext[AgentDepsT]], Any]
    ) = None,
    output_retries: int | None = None,
    tools: Sequence[
        Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]
    ] = (),
    builtin_tools: Sequence[
        AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]
    ] = (),
    prepare_tools: (
        ToolsPrepareFunc[AgentDepsT] | None
    ) = None,
    prepare_output_tools: (
        ToolsPrepareFunc[AgentDepsT] | None
    ) = None,
    mcp_servers: Sequence[MCPServer] = (),
    defer_model_check: bool = False,
    end_strategy: EndStrategy = "early",
    instrument: (
        InstrumentationSettings | bool | None
    ) = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    history_processors: (
        Sequence[HistoryProcessor[AgentDepsT]] | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    tool_timeout: float | None = None,
    max_concurrency: AnyConcurrencyLimit = None,
    capabilities: (
        Sequence[AbstractCapability[AgentDepsT]] | None
    ) = None
) -> None

__init__(
    model: Model | KnownModelName | str | None = None,
    *,
    output_type: OutputSpec[OutputDataT] = str,
    instructions: AgentInstructions[AgentDepsT] = None,
    system_prompt: str | Sequence[str] = (),
    deps_type: type[AgentDepsT] = NoneType,
    name: str | None = None,
    description: (
        TemplateStr[AgentDepsT] | str | None
    ) = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    retries: int = 1,
    validation_context: (
        Any | Callable[[RunContext[AgentDepsT]], Any]
    ) = None,
    output_retries: int | None = None,
    tools: Sequence[
        Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]
    ] = (),
    builtin_tools: Sequence[
        AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]
    ] = (),
    prepare_tools: (
        ToolsPrepareFunc[AgentDepsT] | None
    ) = None,
    prepare_output_tools: (
        ToolsPrepareFunc[AgentDepsT] | None
    ) = None,
    toolsets: (
        Sequence[AgentToolset[AgentDepsT]] | None
    ) = None,
    defer_model_check: bool = False,
    end_strategy: EndStrategy = "early",
    instrument: (
        InstrumentationSettings | bool | None
    ) = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    history_processors: (
        Sequence[HistoryProcessor[AgentDepsT]] | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    tool_timeout: float | None = None,
    max_concurrency: AnyConcurrencyLimit = None,
    capabilities: (
        Sequence[AbstractCapability[AgentDepsT]] | None
    ) = None,
    **_deprecated_kwargs: Any
)

Create an agent.

Parameters:

Name	Type	Description	Default
model	Model | KnownModelName | str | None	The default model to use for this agent, if not provided, you must provide the model when calling it. We allow str here since the actual list of allowed models changes frequently.	None
output_type	OutputSpec[OutputDataT]	The type of the output data, used to validate the data returned by the model, defaults to str.	str
instructions	AgentInstructions[AgentDepsT]	Instructions to use for this agent, you can also register instructions via a function with instructions or pass additional, temporary, instructions when executing a run.	None
system_prompt	str | Sequence[str]	Static system prompts to use for this agent, you can also register system prompts via a function with system_prompt.	()
deps_type	type[AgentDepsT]	The type used for dependency injection, this parameter exists solely to allow you to fully parameterize the agent, and therefore get the best out of static type checking. If you're not using deps, but want type checking to pass, you can set deps=None to satisfy Pyright or add a type hint : Agent[None, <return type>].	NoneType
name	str | None	The name of the agent, used for logging. If None, we try to infer the agent name from the call frame when the agent is first run.	None
description	TemplateStr[AgentDepsT] | str | None	A human-readable description of the agent, attached to the agent run span as gen_ai.agent.description when instrumentation is enabled.	None
model_settings	AgentModelSettings[AgentDepsT] | None	Optional model request settings to use for this agent's runs, by default. Can be a static ModelSettings dict or a callable that takes a RunContext and returns ModelSettings. Callables are called before each model request, allowing dynamic per-step settings.	None
retries	int	The default number of retries to allow for tool calls and output validation, before raising an error. For model request retries, see the HTTP Request Retries documentation.	1
validation_context	Any | Callable[[RunContext[AgentDepsT]], Any]	Pydantic validation context used to validate tool arguments and outputs.	None
output_retries	int | None	The maximum number of retries to allow for output validation, defaults to retries.	None
tools	Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]]	Tools to register with the agent, you can also register tools via the decorators @agent.tool and @agent.tool_plain.	()
builtin_tools	Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]]	The builtin tools that the agent will use. This depends on the model, as some models may not support certain tools. If the model doesn't support the builtin tools, an error will be raised.	()
prepare_tools	ToolsPrepareFunc[AgentDepsT] | None	Custom function to prepare the tool definition of all tools for each step, except output tools. This is useful if you want to customize the definition of multiple tools or you want to register a subset of tools for a given step. See ToolsPrepareFunc	None
prepare_output_tools	ToolsPrepareFunc[AgentDepsT] | None	Custom function to prepare the tool definition of all output tools for each step. This is useful if you want to customize the definition of multiple output tools or you want to register a subset of output tools for a given step. See ToolsPrepareFunc	None
toolsets	Sequence[AgentToolset[AgentDepsT]] | None	Toolsets to register with the agent, including MCP servers and functions which take a run context and return a toolset. See ToolsetFunc for more information.	None
defer_model_check	bool	by default, if you provide a named model, it's evaluated to create a Model instance immediately, which checks for the necessary environment variables. Set this to false to defer the evaluation until the first run. Useful if you want to override the model for testing.	False
end_strategy	EndStrategy	Strategy for handling tool calls that are requested alongside a final result. See EndStrategy for more information.	'early'
instrument	InstrumentationSettings | bool | None	Set to True to automatically instrument with OpenTelemetry, which will use Logfire if it's configured. Set to an instance of InstrumentationSettings to customize. If this isn't set, then the last value set by Agent.instrument_all() will be used, which defaults to False. See the Debugging and Monitoring guide for more info.	None
metadata	AgentMetadata[AgentDepsT] | None	Optional metadata to store with each run. Provide a dictionary of primitives, or a callable returning one computed from the RunContext on each run. Metadata is resolved when a run starts and recomputed after a successful run finishes so it can reflect the final state. Resolved metadata can be read after the run completes via AgentRun.metadata, AgentRunResult.metadata, and StreamedRunResult.metadata, and is attached to the agent run span when instrumentation is enabled.	None
history_processors	Sequence[HistoryProcessor[AgentDepsT]] | None	Optional list of callables to process the message history before sending it to the model. Each processor takes a list of messages and returns a modified list of messages. Processors can be sync or async and are applied in sequence.	None
event_stream_handler	EventStreamHandler[AgentDepsT] | None	Optional handler for events from the model's streaming response and the agent's execution of tools.	None
tool_timeout	float | None	Default timeout in seconds for tool execution. If a tool takes longer than this, the tool is considered to have failed and a retry prompt is returned to the model (counting towards the retry limit). Individual tools can override this with their own timeout. Defaults to None (no timeout).	None
max_concurrency	AnyConcurrencyLimit	Optional limit on concurrent agent runs. Can be an integer for simple limiting, a ConcurrencyLimit for advanced configuration with backpressure, a ConcurrencyLimiter for sharing limits across multiple agents, or None (default) for no limiting. When the limit is reached, additional calls to run() or iter() will wait until a slot becomes available.	None
capabilities	Sequence[AbstractCapability[AgentDepsT]] | None	Optional list of capabilities to configure the agent with. Built-in capabilities include [Instructions][pydantic_ai.capabilities.Instructions], [Thinking][pydantic_ai.capabilities.Thinking], [ModelSettings][pydantic_ai.capabilities.ModelSettings], [WebSearch][pydantic_ai.capabilities.WebSearch], [HistoryProcessor][pydantic_ai.capabilities.HistoryProcessor], and [Toolset][pydantic_ai.capabilities.Toolset]. Custom capabilities can be created by subclassing [AbstractCapability][pydantic_ai.capabilities.AbstractCapability].	None

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

def __init__(
    self,
    model: models.Model | models.KnownModelName | str | None = None,
    *,
    output_type: OutputSpec[OutputDataT] = str,
    instructions: _instructions.AgentInstructions[AgentDepsT] = None,
    system_prompt: str | Sequence[str] = (),
    deps_type: type[AgentDepsT] = NoneType,
    name: str | None = None,
    description: TemplateStr[AgentDepsT] | str | None = None,
    model_settings: AgentModelSettings[AgentDepsT] | None = None,
    retries: int = 1,
    validation_context: Any | Callable[[RunContext[AgentDepsT]], Any] = None,
    output_retries: int | None = None,
    tools: Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] = (),
    builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] = (),
    prepare_tools: ToolsPrepareFunc[AgentDepsT] | None = None,
    prepare_output_tools: ToolsPrepareFunc[AgentDepsT] | None = None,
    toolsets: Sequence[AgentToolset[AgentDepsT]] | None = None,
    defer_model_check: bool = False,
    end_strategy: EndStrategy = 'early',
    instrument: InstrumentationSettings | bool | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    history_processors: Sequence[HistoryProcessor[AgentDepsT]] | None = None,
    event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
    tool_timeout: float | None = None,
    max_concurrency: _concurrency.AnyConcurrencyLimit = None,
    capabilities: Sequence[AbstractCapability[AgentDepsT]] | None = None,
    **_deprecated_kwargs: Any,
):
    """Create an agent.

    Args:
        model: The default model to use for this agent, if not provided,
            you must provide the model when calling it. We allow `str` here since the actual list of allowed models changes frequently.
        output_type: The type of the output data, used to validate the data returned by the model,
            defaults to `str`.
        instructions: Instructions to use for this agent, you can also register instructions via a function with
            [`instructions`][pydantic_ai.agent.Agent.instructions] or pass additional, temporary, instructions when executing a run.
        system_prompt: Static system prompts to use for this agent, you can also register system
            prompts via a function with [`system_prompt`][pydantic_ai.agent.Agent.system_prompt].
        deps_type: The type used for dependency injection, this parameter exists solely to allow you to fully
            parameterize the agent, and therefore get the best out of static type checking.
            If you're not using deps, but want type checking to pass, you can set `deps=None` to satisfy Pyright
            or add a type hint `: Agent[None, <return type>]`.
        name: The name of the agent, used for logging. If `None`, we try to infer the agent name from the call frame
            when the agent is first run.
        description: A human-readable description of the agent, attached to the agent run span as
            `gen_ai.agent.description` when instrumentation is enabled.
        model_settings: Optional model request settings to use for this agent's runs, by default.
            Can be a static `ModelSettings` dict or a callable that takes a
            [`RunContext`][pydantic_ai.tools.RunContext] and returns `ModelSettings`.
            Callables are called before each model request, allowing dynamic per-step settings.
        retries: The default number of retries to allow for tool calls and output validation, before raising an error.
            For model request retries, see the [HTTP Request Retries](../retries.md) documentation.
        validation_context: Pydantic [validation context](https://docs.pydantic.dev/latest/concepts/validators/#validation-context) used to validate tool arguments and outputs.
        output_retries: The maximum number of retries to allow for output validation, defaults to `retries`.
        tools: Tools to register with the agent, you can also register tools via the decorators
            [`@agent.tool`][pydantic_ai.agent.Agent.tool] and [`@agent.tool_plain`][pydantic_ai.agent.Agent.tool_plain].
        builtin_tools: The builtin tools that the agent will use. This depends on the model, as some models may not
            support certain tools. If the model doesn't support the builtin tools, an error will be raised.
        prepare_tools: Custom function to prepare the tool definition of all tools for each step, except output tools.
            This is useful if you want to customize the definition of multiple tools or you want to register
            a subset of tools for a given step. See [`ToolsPrepareFunc`][pydantic_ai.tools.ToolsPrepareFunc]
        prepare_output_tools: Custom function to prepare the tool definition of all output tools for each step.
            This is useful if you want to customize the definition of multiple output tools or you want to register
            a subset of output tools for a given step. See [`ToolsPrepareFunc`][pydantic_ai.tools.ToolsPrepareFunc]
        toolsets: Toolsets to register with the agent, including MCP servers and functions which take a run context
            and return a toolset. See [`ToolsetFunc`][pydantic_ai.toolsets.ToolsetFunc] for more information.
        defer_model_check: by default, if you provide a [named][pydantic_ai.models.KnownModelName] model,
            it's evaluated to create a [`Model`][pydantic_ai.models.Model] instance immediately,
            which checks for the necessary environment variables. Set this to `false`
            to defer the evaluation until the first run. Useful if you want to
            [override the model][pydantic_ai.agent.Agent.override] for testing.
        end_strategy: Strategy for handling tool calls that are requested alongside a final result.
            See [`EndStrategy`][pydantic_ai.agent.EndStrategy] for more information.
        instrument: Set to True to automatically instrument with OpenTelemetry,
            which will use Logfire if it's configured.
            Set to an instance of [`InstrumentationSettings`][pydantic_ai.agent.InstrumentationSettings] to customize.
            If this isn't set, then the last value set by
            [`Agent.instrument_all()`][pydantic_ai.agent.Agent.instrument_all]
            will be used, which defaults to False.
            See the [Debugging and Monitoring guide](https://ai.pydantic.dev/logfire/) for more info.
        metadata: Optional metadata to store with each run.
            Provide a dictionary of primitives, or a callable returning one
            computed from the [`RunContext`][pydantic_ai.tools.RunContext] on each run.
            Metadata is resolved when a run starts and recomputed after a successful run finishes so it
            can reflect the final state.
            Resolved metadata can be read after the run completes via
            [`AgentRun.metadata`][pydantic_ai.agent.AgentRun],
            [`AgentRunResult.metadata`][pydantic_ai.agent.AgentRunResult], and
            [`StreamedRunResult.metadata`][pydantic_ai.result.StreamedRunResult],
            and is attached to the agent run span when instrumentation is enabled.
        history_processors: Optional list of callables to process the message history before sending it to the model.
            Each processor takes a list of messages and returns a modified list of messages.
            Processors can be sync or async and are applied in sequence.
        event_stream_handler: Optional handler for events from the model's streaming response and the agent's execution of tools.
        tool_timeout: Default timeout in seconds for tool execution. If a tool takes longer than this,
            the tool is considered to have failed and a retry prompt is returned to the model (counting towards the retry limit).
            Individual tools can override this with their own timeout. Defaults to None (no timeout).
        max_concurrency: Optional limit on concurrent agent runs. Can be an integer for simple limiting,
            a [`ConcurrencyLimit`][pydantic_ai.ConcurrencyLimit] for advanced configuration with backpressure,
            a [`ConcurrencyLimiter`][pydantic_ai.ConcurrencyLimiter] for sharing limits across
            multiple agents, or None (default) for no limiting. When the limit is reached, additional calls
            to `run()` or `iter()` will wait until a slot becomes available.
        capabilities: Optional list of capabilities to configure the agent with.
            Built-in capabilities include [`Instructions`][pydantic_ai.capabilities.Instructions],
            [`Thinking`][pydantic_ai.capabilities.Thinking],
            [`ModelSettings`][pydantic_ai.capabilities.ModelSettings],
            [`WebSearch`][pydantic_ai.capabilities.WebSearch],
            [`HistoryProcessor`][pydantic_ai.capabilities.HistoryProcessor], and
            [`Toolset`][pydantic_ai.capabilities.Toolset].
            Custom capabilities can be created by subclassing
            [`AbstractCapability`][pydantic_ai.capabilities.AbstractCapability].
    """
    if model is None or defer_model_check:
        self._model = model
    else:
        self._model = models.infer_model(model)

    self._name = name
    self._description = description
    self.end_strategy = end_strategy

    self.history_processors: list[HistoryProcessor[AgentDepsT]] = list(history_processors or [])

    capabilities = list(capabilities or [])
    for history_processor in self.history_processors:
        capabilities.append(HistoryProcessorCap(history_processor))

    self._root_capability = CombinedCapability(capabilities)

    self.model_settings = model_settings

    self._output_type = output_type
    self.instrument = instrument
    self._metadata = metadata
    self._deps_type = deps_type

    if mcp_servers := _deprecated_kwargs.pop('mcp_servers', None):
        if toolsets is not None:  # pragma: no cover
            raise TypeError('`mcp_servers` and `toolsets` cannot be set at the same time.')
        warnings.warn('`mcp_servers` is deprecated, use `toolsets` instead', DeprecationWarning)
        toolsets = mcp_servers

    _utils.validate_empty_kwargs(_deprecated_kwargs)

    self._output_schema = _output.OutputSchema[OutputDataT].build(output_type)
    self._output_validators = []

    self._instructions = _instructions.normalize_instructions(instructions)
    self._cap_instructions = _instructions.normalize_instructions(self._root_capability.get_instructions())

    self._system_prompts = (system_prompt,) if isinstance(system_prompt, str) else tuple(system_prompt)
    self._system_prompt_functions = []
    self._system_prompt_dynamic_functions = {}

    self._max_result_retries = output_retries if output_retries is not None else retries
    self._max_tool_retries = retries
    self._tool_timeout = tool_timeout

    self._validation_context = validation_context

    self._builtin_tools = list(builtin_tools)
    self._cap_builtin_tools = list(self._root_capability.get_builtin_tools())

    self._cap_model_settings = self._root_capability.get_model_settings()

    self._prepare_tools = prepare_tools
    self._prepare_output_tools = prepare_output_tools

    self._output_toolset = self._output_schema.toolset
    if self._output_toolset:
        self._output_toolset.max_retries = self._max_result_retries

    self._function_toolset = _AgentFunctionToolset(
        tools,
        max_retries=self._max_tool_retries,
        timeout=self._tool_timeout,
        output_schema=self._output_schema,
    )

    # Agent-direct toolsets
    agent_toolsets = list(toolsets or [])
    self._dynamic_toolsets = [
        DynamicToolset[AgentDepsT](toolset_func=toolset)
        for toolset in agent_toolsets
        if not isinstance(toolset, AbstractToolset)
    ]
    self._user_toolsets = [toolset for toolset in agent_toolsets if isinstance(toolset, AbstractToolset)]

    # Capability-contributed toolsets (stored separately for per-run re-extraction)
    cap_toolset = self._root_capability.get_toolset()
    self._cap_toolsets: list[AgentToolset[AgentDepsT]] = [cap_toolset] if cap_toolset is not None else []

    self._event_stream_handler = event_stream_handler

    self._concurrency_limiter = _concurrency.normalize_to_limiter(max_concurrency)

    self._override_name: ContextVar[_utils.Option[str]] = ContextVar('_override_name', default=None)
    self._override_deps: ContextVar[_utils.Option[AgentDepsT]] = ContextVar('_override_deps', default=None)
    self._override_model: ContextVar[_utils.Option[models.Model]] = ContextVar('_override_model', default=None)
    self._override_toolsets: ContextVar[_utils.Option[Sequence[AbstractToolset[AgentDepsT]]]] = ContextVar(
        '_override_toolsets', default=None
    )
    self._override_tools: ContextVar[
        _utils.Option[Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]]]
    ] = ContextVar('_override_tools', default=None)
    self._override_instructions: ContextVar[
        _utils.Option[list[str | _system_prompt.SystemPromptFunc[AgentDepsT]]]
    ] = ContextVar('_override_instructions', default=None)
    self._override_metadata: ContextVar[_utils.Option[AgentMetadata[AgentDepsT]]] = ContextVar(
        '_override_metadata', default=None
    )
    self._override_model_settings: ContextVar[_utils.Option[AgentModelSettings[AgentDepsT]]] = ContextVar(
        '_override_model_settings', default=None
    )
    self._override_root_capability: ContextVar[_utils.Option[CombinedCapability[AgentDepsT]]] = ContextVar(
        '_override_root_capability', default=None
    )
    self._enter_lock = Lock()
    self._entered_count = 0
    self._exit_stack = None

end_strategy instance-attribute

end_strategy: EndStrategy = end_strategy

The strategy for handling multiple tool calls when a final result is found.

• 'early' (default): Output tools are executed first. Once a valid final result is found, remaining function and output tool calls are skipped
• 'exhaustive': Output tools are executed first, then all function tools are executed. The first valid output tool result becomes the final output

model_settings instance-attribute

model_settings: AgentModelSettings[AgentDepsT] | None = (
    model_settings
)

Optional model request settings to use for this agent's runs, by default.

Can be a static ModelSettings dict or a callable that takes a RunContext and returns ModelSettings. Callables are called before each model request, allowing dynamic per-step settings.

Note, if model_settings is also provided at run time, those settings will be merged on top of the agent-level settings, with the run-level argument taking priority.

instrument instance-attribute

instrument: InstrumentationSettings | bool | None = (
    instrument
)

Options to automatically instrument with OpenTelemetry.

from_spec classmethod

from_spec(
    spec: dict[str, Any] | AgentSpec,
    *,
    custom_capability_types: Sequence[
        type[AbstractCapability[Any]]
    ] = (),
    model: Model | KnownModelName | str | None = None,
    output_type: OutputSpec[Any] = str,
    instructions: AgentInstructions[Any] = None,
    system_prompt: str | Sequence[str] = (),
    name: str | None = None,
    description: str | None = None,
    model_settings: ModelSettings | None = None,
    retries: int | None = None,
    validation_context: Any = None,
    output_retries: int | None = None,
    tools: Sequence[
        Tool[Any] | ToolFuncEither[Any, ...]
    ] = (),
    builtin_tools: Sequence[
        AbstractBuiltinTool | BuiltinToolFunc[Any]
    ] = (),
    prepare_tools: ToolsPrepareFunc[Any] | None = None,
    prepare_output_tools: (
        ToolsPrepareFunc[Any] | None
    ) = None,
    toolsets: Sequence[AgentToolset[Any]] | None = None,
    defer_model_check: bool = False,
    end_strategy: EndStrategy | None = None,
    instrument: (
        InstrumentationSettings | bool | None
    ) = None,
    metadata: AgentMetadata[Any] | None = None,
    history_processors: (
        Sequence[HistoryProcessor[Any]] | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[Any] | None
    ) = None,
    tool_timeout: float | None = None,
    max_concurrency: AnyConcurrencyLimit = None,
    capabilities: (
        Sequence[AbstractCapability[Any]] | None
    ) = None
) -> Agent[None, str]

from_spec(
    spec: dict[str, Any] | AgentSpec,
    *,
    deps_type: type[T],
    custom_capability_types: Sequence[
        type[AbstractCapability[Any]]
    ] = (),
    model: Model | KnownModelName | str | None = None,
    output_type: OutputSpec[Any] = str,
    instructions: AgentInstructions[Any] = None,
    system_prompt: str | Sequence[str] = (),
    name: str | None = None,
    description: str | None = None,
    model_settings: ModelSettings | None = None,
    retries: int | None = None,
    validation_context: Any = None,
    output_retries: int | None = None,
    tools: Sequence[
        Tool[Any] | ToolFuncEither[Any, ...]
    ] = (),
    builtin_tools: Sequence[
        AbstractBuiltinTool | BuiltinToolFunc[Any]
    ] = (),
    prepare_tools: ToolsPrepareFunc[Any] | None = None,
    prepare_output_tools: (
        ToolsPrepareFunc[Any] | None
    ) = None,
    toolsets: Sequence[AgentToolset[Any]] | None = None,
    defer_model_check: bool = False,
    end_strategy: EndStrategy | None = None,
    instrument: (
        InstrumentationSettings | bool | None
    ) = None,
    metadata: AgentMetadata[Any] | None = None,
    history_processors: (
        Sequence[HistoryProcessor[Any]] | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[Any] | None
    ) = None,
    tool_timeout: float | None = None,
    max_concurrency: AnyConcurrencyLimit = None,
    capabilities: (
        Sequence[AbstractCapability[Any]] | None
    ) = None
) -> Agent[T, str]

from_spec(
    spec: dict[str, Any] | AgentSpec,
    *,
    deps_type: type[Any] = type(None),
    custom_capability_types: Sequence[
        type[AbstractCapability[Any]]
    ] = (),
    model: Model | KnownModelName | str | None = None,
    output_type: OutputSpec[Any] = str,
    instructions: AgentInstructions[Any] = None,
    system_prompt: str | Sequence[str] = (),
    name: str | None = None,
    description: str | None = None,
    model_settings: ModelSettings | None = None,
    retries: int | None = None,
    validation_context: Any = None,
    output_retries: int | None = None,
    tools: Sequence[
        Tool[Any] | ToolFuncEither[Any, ...]
    ] = (),
    builtin_tools: Sequence[
        AbstractBuiltinTool | BuiltinToolFunc[Any]
    ] = (),
    prepare_tools: ToolsPrepareFunc[Any] | None = None,
    prepare_output_tools: (
        ToolsPrepareFunc[Any] | None
    ) = None,
    toolsets: Sequence[AgentToolset[Any]] | None = None,
    defer_model_check: bool = False,
    end_strategy: EndStrategy | None = None,
    instrument: (
        InstrumentationSettings | bool | None
    ) = None,
    metadata: AgentMetadata[Any] | None = None,
    history_processors: (
        Sequence[HistoryProcessor[Any]] | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[Any] | None
    ) = None,
    tool_timeout: float | None = None,
    max_concurrency: AnyConcurrencyLimit = None,
    capabilities: (
        Sequence[AbstractCapability[Any]] | None
    ) = None
) -> Agent[Any, Any]

Construct an Agent from a spec dict or AgentSpec.

This allows defining agents declaratively in YAML/JSON/dict form. Keyword arguments supplement the spec: scalar spec fields (like name, retries) are used as defaults that explicit arguments override, while capabilities from both sources are merged.

Parameters:

Name	Type	Description	Default
spec	dict[str, Any] | AgentSpec	The agent specification, either a dict or an AgentSpec instance.	required
deps_type	type[Any]	The type of the dependencies for the agent. When provided, template strings in capabilities (e.g. "Hello {{name}}") are compiled and validated against this type.	type(None)
custom_capability_types	Sequence[type[AbstractCapability[Any]]]	Additional capability classes to make available beyond the built-in defaults.	()
model	Model | KnownModelName | str | None	Override the model from the spec.	None
output_type	OutputSpec[Any]	The type of the output data, defaults to str.	str
instructions	AgentInstructions[Any]	Instructions for the agent.	None
system_prompt	str | Sequence[str]	Static system prompts.	()
name	str | None	The agent name, overrides spec name if provided.	None
description	str | None	The agent description, overrides spec description if provided.	None
model_settings	ModelSettings | None	Model request settings.	None
retries	int | None	Default retries for tool calls and output validation, overrides spec retries if provided.	None
validation_context	Any	Pydantic validation context for tool arguments and outputs.	None
output_retries	int | None	Max retries for output validation, overrides spec output_retries if provided.	None
tools	Sequence[Tool[Any] | ToolFuncEither[Any, ...]]	Tools to register with the agent.	()
builtin_tools	Sequence[AbstractBuiltinTool | BuiltinToolFunc[Any]]	Builtin tools for the agent.	()
prepare_tools	ToolsPrepareFunc[Any] | None	Custom function to prepare tool definitions.	None
prepare_output_tools	ToolsPrepareFunc[Any] | None	Custom function to prepare output tool definitions.	None
toolsets	Sequence[AgentToolset[Any]] | None	Toolsets to register with the agent.	None
defer_model_check	bool	Defer model evaluation until first run.	False
end_strategy	EndStrategy | None	Strategy for tool calls alongside a final result, overrides spec end_strategy if provided.	None
instrument	InstrumentationSettings | bool | None	Instrumentation settings, overrides spec instrument if provided.	None
metadata	AgentMetadata[Any] | None	Metadata to store with each run, overrides spec metadata if provided.	None
history_processors	Sequence[HistoryProcessor[Any]] | None	Processors for message history.	None
event_stream_handler	EventStreamHandler[Any] | None	Handler for streaming events.	None
tool_timeout	float | None	Default timeout for tool execution, overrides spec tool_timeout if provided.	None
max_concurrency	AnyConcurrencyLimit	Limit on concurrent agent runs.	None
capabilities	Sequence[AbstractCapability[Any]] | None	Additional capabilities merged with those from the spec.	None

Returns:

Type	Description
Agent[Any, Any]	A new Agent instance.

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

@classmethod
def from_spec(
    cls,
    spec: dict[str, Any] | AgentSpec,
    *,
    deps_type: type[Any] = type(None),
    custom_capability_types: Sequence[type[AbstractCapability[Any]]] = (),
    model: models.Model | models.KnownModelName | str | None = None,
    output_type: OutputSpec[Any] = str,
    instructions: _instructions.AgentInstructions[Any] = None,
    system_prompt: str | Sequence[str] = (),
    name: str | None = None,
    description: str | None = None,
    model_settings: ModelSettings | None = None,
    retries: int | None = None,
    validation_context: Any = None,
    output_retries: int | None = None,
    tools: Sequence[Tool[Any] | ToolFuncEither[Any, ...]] = (),
    builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[Any]] = (),
    prepare_tools: ToolsPrepareFunc[Any] | None = None,
    prepare_output_tools: ToolsPrepareFunc[Any] | None = None,
    toolsets: Sequence[AgentToolset[Any]] | None = None,
    defer_model_check: bool = False,
    end_strategy: EndStrategy | None = None,
    instrument: InstrumentationSettings | bool | None = None,
    metadata: AgentMetadata[Any] | None = None,
    history_processors: Sequence[HistoryProcessor[Any]] | None = None,
    event_stream_handler: EventStreamHandler[Any] | None = None,
    tool_timeout: float | None = None,
    max_concurrency: _concurrency.AnyConcurrencyLimit = None,
    capabilities: Sequence[AbstractCapability[Any]] | None = None,
) -> Agent[Any, Any]:
    """Construct an Agent from a spec dict or `AgentSpec`.

    This allows defining agents declaratively in YAML/JSON/dict form.
    Keyword arguments supplement the spec: scalar spec fields (like `name`,
    `retries`) are used as defaults that explicit arguments override, while
    `capabilities` from both sources are merged.

    Args:
        spec: The agent specification, either a dict or an `AgentSpec` instance.
        deps_type: The type of the dependencies for the agent. When provided,
            template strings in capabilities (e.g. ``"Hello {{name}}"``) are
            compiled and validated against this type.
        custom_capability_types: Additional capability classes to make available
            beyond the built-in defaults.
        model: Override the model from the spec.
        output_type: The type of the output data, defaults to `str`.
        instructions: Instructions for the agent.
        system_prompt: Static system prompts.
        name: The agent name, overrides spec `name` if provided.
        description: The agent description, overrides spec `description` if provided.
        model_settings: Model request settings.
        retries: Default retries for tool calls and output validation, overrides spec `retries` if provided.
        validation_context: Pydantic validation context for tool arguments and outputs.
        output_retries: Max retries for output validation, overrides spec `output_retries` if provided.
        tools: Tools to register with the agent.
        builtin_tools: Builtin tools for the agent.
        prepare_tools: Custom function to prepare tool definitions.
        prepare_output_tools: Custom function to prepare output tool definitions.
        toolsets: Toolsets to register with the agent.
        defer_model_check: Defer model evaluation until first run.
        end_strategy: Strategy for tool calls alongside a final result, overrides spec `end_strategy` if provided.
        instrument: Instrumentation settings, overrides spec `instrument` if provided.
        metadata: Metadata to store with each run, overrides spec `metadata` if provided.
        history_processors: Processors for message history.
        event_stream_handler: Handler for streaming events.
        tool_timeout: Default timeout for tool execution, overrides spec `tool_timeout` if provided.
        max_concurrency: Limit on concurrent agent runs.
        capabilities: Additional capabilities merged with those from the spec.

    Returns:
        A new Agent instance.
    """
    from pydantic_ai.agent.spec import AgentSpec as _AgentSpecModel

    template_context: dict[str, Any] = {
        'deps_type': deps_type if deps_type is not type(None) else None,
    }
    if isinstance(spec, dict):
        validated_spec = _AgentSpecModel.model_validate(spec, context=template_context)
    else:
        validated_spec = spec
    template_context['deps_schema'] = validated_spec.deps_schema

    effective_output_type: OutputSpec[Any]
    if output_type is not str:
        effective_output_type = output_type
    elif validated_spec.output_schema is not None:
        from pydantic_ai.output import StructuredDict

        effective_output_type = StructuredDict(validated_spec.output_schema)
    else:
        effective_output_type = str

    # Merge instructions from spec and arg
    merged_instructions = _instructions.normalize_instructions(validated_spec.instructions)
    merged_instructions.extend(_instructions.normalize_instructions(instructions))

    all_capabilities = _capabilities_from_spec(validated_spec, custom_capability_types, template_context)
    if capabilities:
        all_capabilities.extend(capabilities)

    effective_model = model or validated_spec.model
    if effective_model is None:
        raise exceptions.UserError(
            '`model` must be provided either in the spec or as a keyword argument to `from_spec()`.'
        )

    return Agent(
        model=effective_model,
        output_type=effective_output_type,
        instructions=merged_instructions or None,
        system_prompt=system_prompt,
        deps_type=deps_type,
        name=name or validated_spec.name,
        description=description or validated_spec.description,
        model_settings=merge_model_settings(
            cast(ModelSettings, validated_spec.model_settings) if validated_spec.model_settings else None,
            model_settings,
        ),
        retries=retries if retries is not None else validated_spec.retries,
        validation_context=validation_context,
        output_retries=output_retries if output_retries is not None else validated_spec.output_retries,
        tools=tools,
        builtin_tools=builtin_tools,
        prepare_tools=prepare_tools,
        prepare_output_tools=prepare_output_tools,
        toolsets=toolsets,
        defer_model_check=defer_model_check,
        end_strategy=end_strategy if end_strategy is not None else validated_spec.end_strategy,
        instrument=instrument if instrument is not None else validated_spec.instrument,
        metadata=metadata if metadata is not None else validated_spec.metadata,
        history_processors=history_processors,
        event_stream_handler=event_stream_handler,
        tool_timeout=tool_timeout if tool_timeout is not None else validated_spec.tool_timeout,
        max_concurrency=max_concurrency,
        capabilities=all_capabilities,
    )

from_file classmethod

from_file(
    path: Path | str,
    *,
    custom_capability_types: Sequence[
        type[AbstractCapability[Any]]
    ] = (),
    model: Model | KnownModelName | str | None = None,
    output_type: OutputSpec[Any] = str,
    instructions: AgentInstructions[Any] = None,
    system_prompt: str | Sequence[str] = (),
    name: str | None = None,
    description: str | None = None,
    model_settings: ModelSettings | None = None,
    retries: int | None = None,
    validation_context: Any = None,
    output_retries: int | None = None,
    tools: Sequence[
        Tool[Any] | ToolFuncEither[Any, ...]
    ] = (),
    builtin_tools: Sequence[
        AbstractBuiltinTool | BuiltinToolFunc[Any]
    ] = (),
    prepare_tools: ToolsPrepareFunc[Any] | None = None,
    prepare_output_tools: (
        ToolsPrepareFunc[Any] | None
    ) = None,
    toolsets: Sequence[AgentToolset[Any]] | None = None,
    defer_model_check: bool = False,
    end_strategy: EndStrategy | None = None,
    instrument: (
        InstrumentationSettings | bool | None
    ) = None,
    metadata: AgentMetadata[Any] | None = None,
    history_processors: (
        Sequence[HistoryProcessor[Any]] | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[Any] | None
    ) = None,
    tool_timeout: float | None = None,
    max_concurrency: AnyConcurrencyLimit = None,
    capabilities: (
        Sequence[AbstractCapability[Any]] | None
    ) = None
) -> Agent[None, str]

from_file(
    path: Path | str,
    *,
    deps_type: type[T],
    custom_capability_types: Sequence[
        type[AbstractCapability[Any]]
    ] = (),
    model: Model | KnownModelName | str | None = None,
    output_type: OutputSpec[Any] = str,
    instructions: AgentInstructions[Any] = None,
    system_prompt: str | Sequence[str] = (),
    name: str | None = None,
    description: str | None = None,
    model_settings: ModelSettings | None = None,
    retries: int | None = None,
    validation_context: Any = None,
    output_retries: int | None = None,
    tools: Sequence[
        Tool[Any] | ToolFuncEither[Any, ...]
    ] = (),
    builtin_tools: Sequence[
        AbstractBuiltinTool | BuiltinToolFunc[Any]
    ] = (),
    prepare_tools: ToolsPrepareFunc[Any] | None = None,
    prepare_output_tools: (
        ToolsPrepareFunc[Any] | None
    ) = None,
    toolsets: Sequence[AgentToolset[Any]] | None = None,
    defer_model_check: bool = False,
    end_strategy: EndStrategy | None = None,
    instrument: (
        InstrumentationSettings | bool | None
    ) = None,
    metadata: AgentMetadata[Any] | None = None,
    history_processors: (
        Sequence[HistoryProcessor[Any]] | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[Any] | None
    ) = None,
    tool_timeout: float | None = None,
    max_concurrency: AnyConcurrencyLimit = None,
    capabilities: (
        Sequence[AbstractCapability[Any]] | None
    ) = None
) -> Agent[T, str]

from_file(
    path: Path | str, **kwargs: Any
) -> Agent[Any, Any]

Construct an Agent from a YAML or JSON spec file.

This is a convenience method equivalent to Agent.from_spec(AgentSpec.from_file(path), ...).

The file format is inferred from the extension (.yaml/.yml or .json).

Parameters:

Name	Type	Description	Default
path	Path | str	Path to the spec file.	required
**kwargs	Any	All other arguments are forwarded to [from_spec][pydantic_ai.Agent.from_spec].	{}

Returns:

Type	Description
Agent[Any, Any]	A new Agent instance.

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

@classmethod
def from_file(
    cls,
    path: Path | str,
    **kwargs: Any,
) -> Agent[Any, Any]:
    """Construct an Agent from a YAML or JSON spec file.

    This is a convenience method equivalent to
    ``Agent.from_spec(AgentSpec.from_file(path), ...)``.

    The file format is inferred from the extension (`.yaml`/`.yml` or `.json`).

    Args:
        path: Path to the spec file.
        **kwargs: All other arguments are forwarded to [`from_spec`][pydantic_ai.Agent.from_spec].

    Returns:
        A new Agent instance.
    """
    from pydantic_ai.agent.spec import AgentSpec as _AgentSpecModel

    spec = _AgentSpecModel.from_file(path)
    return cls.from_spec(spec, **kwargs)

instrument_all staticmethod

instrument_all(
    instrument: InstrumentationSettings | bool = True,
) -> None

Set the instrumentation options for all agents where instrument is not set.

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

@staticmethod
def instrument_all(instrument: InstrumentationSettings | bool = True) -> None:
    """Set the instrumentation options for all agents where `instrument` is not set."""
    Agent._instrument_default = instrument

model property writable

model: Model | KnownModelName | str | None

The default model configured for this agent.

name property writable

name: str | None

The name of the agent, used for logging.

If None, we try to infer the agent name from the call frame when the agent is first run.

description property writable

description: str | None

A human-readable description of the agent.

If the description is a TemplateStr, returns the raw template source. The rendered description is available at runtime via OTel span attributes.

deps_type property

deps_type: type

The type of dependencies used by the agent.

output_type property

output_type: OutputSpec[OutputDataT]

The type of data output by agent runs, used to validate the data returned by the model, defaults to str.

event_stream_handler property

event_stream_handler: EventStreamHandler[AgentDepsT] | None

Optional handler for events from the model's streaming response and the agent's execution of tools.

iter async

iter(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AbstractAsyncContextManager[
    AgentRun[AgentDepsT, OutputDataT]
]

iter(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT],
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AbstractAsyncContextManager[
    AgentRun[AgentDepsT, RunOutputDataT]
]

iter(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[Any] | None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AsyncIterator[AgentRun[AgentDepsT, Any]]

A contextmanager which can be used to iterate over the agent graph's nodes as they are executed.

This method builds an internal agent graph (using system prompts, tools and output schemas) and then returns an AgentRun object. The AgentRun can be used to async-iterate over the nodes of the graph as they are executed. This is the API to use if you want to consume the outputs coming from each LLM model response, or the stream of events coming from the execution of tools.

The AgentRun also provides methods to access the full message history, new messages, and usage statistics, and the final result of the run once it has completed.

For more details, see the documentation of AgentRun.

Example:

from pydantic_ai import Agent

agent = Agent('openai:gpt-5.2')

async def main():
    nodes = []
    async with agent.iter('What is the capital of France?') as agent_run:
        async for node in agent_run:
            nodes.append(node)
    print(nodes)
    '''
    [
        ModelRequestNode(
            request=ModelRequest(
                parts=[
                    UserPromptPart(
                        content='What is the capital of France?',
                        timestamp=datetime.datetime(...),
                    )
                ],
                timestamp=datetime.datetime(...),
                run_id='...',
            )
        ),
        CallToolsNode(
            model_response=ModelResponse(
                parts=[TextPart(content='The capital of France is Paris.')],
                usage=RequestUsage(input_tokens=56, output_tokens=7),
                model_name='gpt-5.2',
                timestamp=datetime.datetime(...),
                run_id='...',
            )
        ),
        End(data=FinalResult(output='The capital of France is Paris.')),
    ]
    '''
    print(agent_run.result.output)
    #> The capital of France is Paris.

Parameters:

Name	Type	Description	Default
user_prompt	str | Sequence[UserContent] | None	User input to start/continue the conversation.	None
output_type	OutputSpec[Any] | None	Custom output type to use for this run, output_type may only be used if the agent has no output validators since output validators would expect an argument that matches the agent's output type.	None
message_history	Sequence[ModelMessage] | None	History of the conversation so far.	None
deferred_tool_results	DeferredToolResults | None	Optional results for deferred tool calls in the message history.	None
model	Model | KnownModelName | str | None	Optional model to use for this run, required if model was not set when creating the agent.	None
instructions	AgentInstructions[AgentDepsT]	Optional additional instructions to use for this run.	None
deps	AgentDepsT	Optional dependencies to use for this run.	None
model_settings	AgentModelSettings[AgentDepsT] | None	Optional settings to use for this model's request, or a callable that receives RunContext and returns settings. Callables are called before each model request, allowing dynamic per-step settings.	None
usage_limits	UsageLimits | None	Optional limits on model request count or token usage.	None
usage	RunUsage | None	Optional usage to start with, useful for resuming a conversation or agents used in tools.	None
metadata	AgentMetadata[AgentDepsT] | None	Optional metadata to attach to this run. Accepts a dictionary or a callable taking RunContext; merged with the agent's configured metadata.	None
infer_name	bool	Whether to try to infer the agent name from the call frame if it's not set.	True
toolsets	Sequence[AbstractToolset[AgentDepsT]] | None	Optional additional toolsets for this run.	None
builtin_tools	Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None	Optional additional builtin tools for this run.	None
spec	dict[str, Any] | AgentSpec | None	Optional agent spec to apply for this run. At run time, spec values are additive.	None

Returns:

Type	Description
AsyncIterator[AgentRun[AgentDepsT, Any]]	The result of the run.

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

@asynccontextmanager
async def iter(  # noqa: C901
    self,
    user_prompt: str | Sequence[_messages.UserContent] | None = None,
    *,
    output_type: OutputSpec[Any] | None = None,
    message_history: Sequence[_messages.ModelMessage] | None = None,
    deferred_tool_results: DeferredToolResults | None = None,
    model: models.Model | models.KnownModelName | str | None = None,
    instructions: _instructions.AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: AgentModelSettings[AgentDepsT] | None = None,
    usage_limits: _usage.UsageLimits | None = None,
    usage: _usage.RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
    builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
    spec: dict[str, Any] | AgentSpec | None = None,
) -> AsyncIterator[AgentRun[AgentDepsT, Any]]:
    """A contextmanager which can be used to iterate over the agent graph's nodes as they are executed.

    This method builds an internal agent graph (using system prompts, tools and output schemas) and then returns an
    `AgentRun` object. The `AgentRun` can be used to async-iterate over the nodes of the graph as they are
    executed. This is the API to use if you want to consume the outputs coming from each LLM model response, or the
    stream of events coming from the execution of tools.

    The `AgentRun` also provides methods to access the full message history, new messages, and usage statistics,
    and the final result of the run once it has completed.

    For more details, see the documentation of `AgentRun`.

    Example:
    ```python
    from pydantic_ai import Agent

    agent = Agent('openai:gpt-5.2')

    async def main():
        nodes = []
        async with agent.iter('What is the capital of France?') as agent_run:
            async for node in agent_run:
                nodes.append(node)
        print(nodes)
        '''
        [
            ModelRequestNode(
                request=ModelRequest(
                    parts=[
                        UserPromptPart(
                            content='What is the capital of France?',
                            timestamp=datetime.datetime(...),
                        )
                    ],
                    timestamp=datetime.datetime(...),
                    run_id='...',
                )
            ),
            CallToolsNode(
                model_response=ModelResponse(
                    parts=[TextPart(content='The capital of France is Paris.')],
                    usage=RequestUsage(input_tokens=56, output_tokens=7),
                    model_name='gpt-5.2',
                    timestamp=datetime.datetime(...),
                    run_id='...',
                )
            ),
            End(data=FinalResult(output='The capital of France is Paris.')),
        ]
        '''
        print(agent_run.result.output)
        #> The capital of France is Paris.
    ```

    Args:
        user_prompt: User input to start/continue the conversation.
        output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
            output validators since output validators would expect an argument that matches the agent's output type.
        message_history: History of the conversation so far.
        deferred_tool_results: Optional results for deferred tool calls in the message history.
        model: Optional model to use for this run, required if `model` was not set when creating the agent.
        instructions: Optional additional instructions to use for this run.
        deps: Optional dependencies to use for this run.
        model_settings: Optional settings to use for this model's request, or a callable
            that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
            Callables are called before each model request, allowing dynamic per-step settings.
        usage_limits: Optional limits on model request count or token usage.
        usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
        metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
            [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
        infer_name: Whether to try to infer the agent name from the call frame if it's not set.
        toolsets: Optional additional toolsets for this run.
        builtin_tools: Optional additional builtin tools for this run.
        spec: Optional agent spec to apply for this run. At run time, spec values are additive.

    Returns:
        The result of the run.
    """
    if infer_name and self.name is None:
        self._infer_name(inspect.currentframe())

    # Resolve spec contributions (additive at run time)
    resolved = self._resolve_spec(spec)
    if resolved is not None:
        # Model: spec as fallback (run param > spec > agent)
        if model is None and resolved.model is not None:
            model = resolved.model
        # Instructions: spec instructions are additional
        if resolved.instructions:
            extra = resolved.instructions
            if instructions is not None:
                existing = _instructions.normalize_instructions(instructions)
                existing.extend(extra)
                instructions = existing
            else:
                instructions = extra
        # Model settings: merge spec settings under run settings (only static dicts)
        if resolved.model_settings is not None:
            if model_settings is None or not callable(model_settings):
                model_settings = merge_model_settings(resolved.model_settings, model_settings)
            # If model_settings is a callable, spec model_settings are handled via the capability layer
        # Metadata: merge spec metadata under run metadata
        if resolved.metadata is not None:
            if metadata is not None:
                if callable(metadata):
                    _spec_meta = resolved.metadata
                    _orig_metadata = metadata

                    def _merged_meta(ctx: RunContext[AgentDepsT]) -> dict[str, Any]:
                        return {**(_spec_meta or {}), **_orig_metadata(ctx)}

                    metadata = _merged_meta
                else:
                    metadata = {**resolved.metadata, **metadata}
            else:
                metadata = resolved.metadata

    model_used = self._get_model(model)
    del model

    deps = self._get_deps(deps)
    output_schema = self._prepare_output_schema(output_type)

    output_type_ = output_type or self.output_type

    # We consider it a user error if a user tries to restrict the result type while having an output validator that
    # may change the result type from the restricted type to something else. Therefore, we consider the following
    # typecast reasonable, even though it is possible to violate it with otherwise-type-checked code.
    output_validators = self._output_validators

    output_toolset = self._output_toolset
    if output_schema != self._output_schema or output_validators:
        output_toolset = output_schema.toolset
        if output_toolset:
            output_toolset.max_retries = self._max_result_retries
            output_toolset.output_validators = output_validators

    # Build the graph
    graph = _agent_graph.build_agent_graph(self.name, self._deps_type, output_type_)

    # Build the initial state
    usage = usage or _usage.RunUsage()
    state = _agent_graph.GraphAgentState(
        message_history=list(message_history) if message_history else [],
        usage=usage,
        retries=0,
        run_step=0,
    )

    # Build a resolver that computes model settings per-step, in order of precedence: run > agent > model
    model_settings_override = self._override_model_settings.get()
    agent_model_settings = (
        model_settings_override.value if model_settings_override is not None else self.model_settings
    )
    run_model_settings = model_settings if model_settings_override is None else None

    usage_limits = usage_limits or _usage.UsageLimits()

    if isinstance(model_used, InstrumentedModel):
        instrumentation_settings = model_used.instrumentation_settings
        tracer = model_used.instrumentation_settings.tracer
    else:
        instrumentation_settings = None
        tracer = NoOpTracer()

    # Build initial RunContext for for_run lifecycle hooks
    initial_ctx = RunContext[AgentDepsT](
        deps=deps,
        model=model_used,
        usage=usage,
        prompt=user_prompt,
        messages=state.message_history,
        tracer=tracer,
        run_step=0,
    )

    # Determine root capability: override > agent default
    override_cap = self._override_root_capability.get()
    base_capability = override_cap.value if override_cap is not None else self._root_capability

    # Merge spec capability additively with base capability
    if resolved is not None and resolved.capability is not None:
        effective_capability = CombinedCapability([base_capability, resolved.capability])
    else:
        effective_capability = base_capability

    # Per-run capability: re-extract get_*() if for_run returns a different instance
    run_capability = await effective_capability.for_run(initial_ctx)
    cap_toolsets: list[AgentToolset[AgentDepsT]] | None
    if run_capability is not effective_capability:
        cap_instructions = _instructions.normalize_instructions(run_capability.get_instructions())
        cap_builtin_tools = list(run_capability.get_builtin_tools())
        cap_model_settings = run_capability.get_model_settings()
        cap_ts = run_capability.get_toolset()
        cap_toolsets = [cap_ts] if cap_ts is not None else []
    elif override_cap is not None or (resolved is not None and resolved.capability is not None):
        # Re-extract from effective_capability since it differs from self._root_capability
        cap_instructions = _instructions.normalize_instructions(effective_capability.get_instructions())
        cap_builtin_tools = list(effective_capability.get_builtin_tools())
        cap_model_settings = effective_capability.get_model_settings()
        cap_ts = effective_capability.get_toolset()
        cap_toolsets = [cap_ts] if cap_ts is not None else []
    else:
        cap_instructions = None  # use init-time defaults
        cap_builtin_tools = self._cap_builtin_tools
        cap_model_settings = self._cap_model_settings
        cap_toolsets = None

    # Build model settings resolver using per-run capability
    def get_model_settings(run_context: RunContext[AgentDepsT]) -> ModelSettings | None:
        # Resolve settings in layers, each merged on top of the previous.
        # Before calling each callable, set run_context.model_settings so it
        # can see the merged result of all previous layers.
        merged = model_used.settings

        run_context.model_settings = merged
        resolved_agent = (
            agent_model_settings(run_context) if callable(agent_model_settings) else agent_model_settings
        )
        merged = merge_model_settings(merged, resolved_agent)

        # Capability settings (e.g. from Thinking, ModelSettings capabilities), cached at init
        run_context.model_settings = merged
        cap_settings = cap_model_settings
        resolved_cap = cap_settings(run_context) if callable(cap_settings) else cap_settings
        merged = merge_model_settings(merged, resolved_cap)

        run_context.model_settings = merged
        resolved_run = run_model_settings(run_context) if callable(run_model_settings) else run_model_settings
        merged = merge_model_settings(merged, resolved_run)

        run_context.model_settings = merged
        return merged

    # Build toolset with per-run capability contributions
    toolset = self._get_toolset(
        output_toolset=output_toolset,
        additional_toolsets=toolsets,
        cap_toolsets=cap_toolsets,
    )
    toolset = await toolset.for_run(initial_ctx)
    tool_manager = ToolManager[AgentDepsT](
        toolset, root_capability=run_capability, default_max_retries=self._max_tool_retries
    )

    # Build instructions with per-run capability contributions
    instructions_literal, instructions_functions = self._get_instructions(
        additional_instructions=instructions,
        cap_instructions=cap_instructions,
    )

    async def get_instructions(run_context: RunContext[AgentDepsT]) -> str | None:
        parts = [
            instructions_literal,
            *[await func.run(run_context) for func in instructions_functions],
        ]

        parts = [p for p in parts if p]
        if not parts:
            return None
        return '\n\n'.join(parts).strip()

    graph_deps = _agent_graph.GraphAgentDeps[AgentDepsT, OutputDataT](
        user_deps=deps,
        prompt=user_prompt,
        new_message_index=len(message_history) if message_history else 0,
        resumed_request=None,
        model=model_used,
        get_model_settings=get_model_settings,
        usage_limits=usage_limits,
        max_result_retries=self._max_result_retries,
        end_strategy=self.end_strategy,
        output_schema=output_schema,
        output_validators=output_validators,
        validation_context=self._validation_context,
        root_capability=run_capability,
        builtin_tools=[
            *self._builtin_tools,
            *cap_builtin_tools,
            *(builtin_tools or []),
        ],
        tool_manager=tool_manager,
        tracer=tracer,
        get_instructions=get_instructions,
        instrumentation_settings=instrumentation_settings,
    )

    user_prompt_node = _agent_graph.UserPromptNode[AgentDepsT](
        user_prompt=user_prompt,
        deferred_tool_results=deferred_tool_results,
        instructions=instructions_literal,
        instructions_functions=instructions_functions,
        system_prompts=self._system_prompts,
        system_prompt_functions=self._system_prompt_functions,
        system_prompt_dynamic_functions=self._system_prompt_dynamic_functions,
    )

    agent_name = self.name or 'agent'
    instrumentation_names = InstrumentationNames.for_version(
        instrumentation_settings.version if instrumentation_settings else DEFAULT_INSTRUMENTATION_VERSION
    )

    span_attributes: dict[str, str] = {
        'model_name': model_used.model_name if model_used else 'no-model',
        'agent_name': agent_name,
        'gen_ai.agent.name': agent_name,
        'logfire.msg': f'{agent_name} run',
    }
    if self._description is not None:
        if isinstance(self._description, TemplateStr):
            span_attributes['gen_ai.agent.description'] = self._description.render(deps)
        else:
            span_attributes['gen_ai.agent.description'] = self._description

    run_span = tracer.start_span(
        instrumentation_names.get_agent_run_span_name(agent_name),
        attributes=span_attributes,
    )

    run_metadata: dict[str, Any] | None = None
    try:
        async with (
            _concurrency.get_concurrency_context(self._concurrency_limiter, f'agent:{agent_name}'),
            graph.iter(
                inputs=user_prompt_node,
                state=state,
                deps=graph_deps,
                span=use_span(run_span) if run_span.is_recording() else None,
                infer_name=False,
            ) as graph_run,
        ):
            async with toolset:
                agent_run = AgentRun(graph_run)
                run_metadata = self._resolve_and_store_metadata(agent_run.ctx, metadata)

                # Build RunContext for run lifecycle hooks
                run_ctx = _agent_graph.build_run_context(agent_run.ctx)

                # wrap_run cooperative hand-off protocol:
                #
                # 1. _do_run() calls before_run, sets _run_ready, then awaits _run_done.
                # 2. wrap_run wraps _do_run via the capability middleware chain.
                # 3. We await either _run_ready (handler started) or _wrap_task completion
                #    (short-circuit: wrap_run returned without calling handler).
                # 4. We yield agent_run to the caller for iteration.
                # 5. When the caller finishes (or an error occurs), we set _run_done.
                # 6. _do_run resumes: returns the result (success) or re-raises the error.
                # 7. If wrap_run catches the error and returns a recovery result, we use it.
                #    Otherwise the original error propagates.
                _run_ready = asyncio.Event()
                _run_done = asyncio.Event()
                _run_error: BaseException | None = None

                async def _do_run() -> AgentRunResult[Any]:
                    await run_capability.before_run(run_ctx)
                    _run_ready.set()
                    await _run_done.wait()
                    if _run_error is not None:
                        # Raise the original node error, not the potentially
                        # transformed version from context manager __aexit__ chains.
                        raise agent_run._node_error or _run_error  # pyright: ignore[reportPrivateUsage]
                    r = agent_run.result
                    assert r is not None
                    return r

                _wrap_task = asyncio.create_task(run_capability.wrap_run(run_ctx, handler=_do_run))

                # Wait for handler to start or wrap_run to complete (short-circuit)
                _ready_waiter = asyncio.create_task(_run_ready.wait())
                await asyncio.wait({_ready_waiter, _wrap_task}, return_when=asyncio.FIRST_COMPLETED)
                _ready_waiter.cancel()

                _short_circuited = _wrap_task.done() and not _run_ready.is_set()
                if _short_circuited:
                    _result = _wrap_task.result()
                    _result = await run_capability.after_run(run_ctx, result=_result)
                    agent_run._result_override = _result  # pyright: ignore[reportPrivateUsage]

                try:
                    yield agent_run
                except BaseException as _exc:
                    # Use the original node error if available, since context manager
                    # __aexit__ chains (GraphRun → anyio TaskGroup) may transform
                    # the exception (e.g. into CancelledError or ExceptionGroup).
                    _run_error = agent_run._node_error or _exc  # pyright: ignore[reportPrivateUsage]
                    # Don't re-raise yet — give wrap_run a chance to recover.
                    # If wrap_run catches the error from handler() and returns
                    # a recovery result, the exception will be suppressed.
                finally:
                    if agent_run.result is not None:
                        run_metadata = self._resolve_and_store_metadata(agent_run.ctx, metadata)
                    else:
                        run_metadata = graph_run.state.metadata

                    if not _short_circuited:
                        _run_done.set()
                        if _run_error is None and agent_run.result is not None:
                            _result = await _wrap_task
                            _result = await run_capability.after_run(run_ctx, result=_result)
                            agent_run._result_override = _result  # pyright: ignore[reportPrivateUsage]
                        elif _run_error is not None:
                            # Error path: await wrap_run to see if it recovers.
                            # _do_run() re-raises _run_error; if wrap_run catches
                            # it and returns a result, recovery succeeds.
                            try:
                                _result = await _wrap_task
                                _result = await run_capability.after_run(run_ctx, result=_result)
                                agent_run._result_override = _result  # pyright: ignore[reportPrivateUsage]
                                _run_error = None  # Recovery succeeded
                            except BaseException:
                                pass  # wrap_run didn't recover
                        elif not _wrap_task.done():
                            _wrap_task.cancel()
                            try:
                                await _wrap_task
                            except (asyncio.CancelledError, BaseException):
                                pass

                # If wrap_run didn't recover from the error, re-raise.
                # In an @asynccontextmanager, not re-raising suppresses the exception.
                if _run_error is not None:
                    raise _run_error

                final_result = agent_run.result
                if (
                    instrumentation_settings
                    and instrumentation_settings.include_content
                    and run_span.is_recording()
                    and final_result is not None
                ):
                    run_span.set_attribute(
                        'final_result',
                        (
                            final_result.output
                            if isinstance(final_result.output, str)
                            else json.dumps(InstrumentedModel.serialize_any(final_result.output))
                        ),
                    )
    finally:
        try:
            if instrumentation_settings and run_span.is_recording():
                run_span.set_attributes(
                    self._run_span_end_attributes(
                        instrumentation_settings,
                        usage,
                        state.message_history,
                        graph_deps.new_message_index,
                        run_metadata,
                    )
                )
        finally:
            run_span.end()

override

override(
    *,
    name: str | Unset = UNSET,
    deps: AgentDepsT | Unset = UNSET,
    model: Model | KnownModelName | str | Unset = UNSET,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | Unset
    ) = UNSET,
    tools: (
        Sequence[
            Tool[AgentDepsT]
            | ToolFuncEither[AgentDepsT, ...]
        ]
        | Unset
    ) = UNSET,
    instructions: (
        AgentInstructions[AgentDepsT] | Unset
    ) = UNSET,
    metadata: AgentMetadata[AgentDepsT] | Unset = UNSET,
    model_settings: (
        AgentModelSettings[AgentDepsT] | Unset
    ) = UNSET,
    spec: dict[str, Any] | AgentSpec | None = None
) -> Iterator[None]

Context manager to temporarily override agent name, dependencies, model, toolsets, tools, or instructions.

This is particularly useful when testing. You can find an example of this here.

Parameters:

Name	Type	Description	Default
name	str | Unset	The name to use instead of the name passed to the agent constructor and agent run.	UNSET
deps	AgentDepsT | Unset	The dependencies to use instead of the dependencies passed to the agent run.	UNSET
model	Model | KnownModelName | str | Unset	The model to use instead of the model passed to the agent run.	UNSET
toolsets	Sequence[AbstractToolset[AgentDepsT]] | Unset	The toolsets to use instead of the toolsets passed to the agent constructor and agent run.	UNSET
tools	Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] | Unset	The tools to use instead of the tools registered with the agent.	UNSET
instructions	AgentInstructions[AgentDepsT] | Unset	The instructions to use instead of the instructions registered with the agent.	UNSET
metadata	AgentMetadata[AgentDepsT] | Unset	The metadata to use instead of the metadata passed to the agent constructor. When set, any per-run metadata argument is ignored.	UNSET
model_settings	AgentModelSettings[AgentDepsT] | Unset	The model settings to use instead of the model settings passed to the agent constructor. When set, any per-run model_settings argument is ignored.	UNSET
spec	dict[str, Any] | AgentSpec | None	Optional agent spec providing defaults for override. Explicit params take precedence over spec values.	None

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

@contextmanager
def override(  # noqa: C901
    self,
    *,
    name: str | _utils.Unset = _utils.UNSET,
    deps: AgentDepsT | _utils.Unset = _utils.UNSET,
    model: models.Model | models.KnownModelName | str | _utils.Unset = _utils.UNSET,
    toolsets: Sequence[AbstractToolset[AgentDepsT]] | _utils.Unset = _utils.UNSET,
    tools: Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] | _utils.Unset = _utils.UNSET,
    instructions: _instructions.AgentInstructions[AgentDepsT] | _utils.Unset = _utils.UNSET,
    metadata: AgentMetadata[AgentDepsT] | _utils.Unset = _utils.UNSET,
    model_settings: AgentModelSettings[AgentDepsT] | _utils.Unset = _utils.UNSET,
    spec: dict[str, Any] | AgentSpec | None = None,
) -> Iterator[None]:
    """Context manager to temporarily override agent name, dependencies, model, toolsets, tools, or instructions.

    This is particularly useful when testing.
    You can find an example of this [here](../testing.md#overriding-model-via-pytest-fixtures).

    Args:
        name: The name to use instead of the name passed to the agent constructor and agent run.
        deps: The dependencies to use instead of the dependencies passed to the agent run.
        model: The model to use instead of the model passed to the agent run.
        toolsets: The toolsets to use instead of the toolsets passed to the agent constructor and agent run.
        tools: The tools to use instead of the tools registered with the agent.
        instructions: The instructions to use instead of the instructions registered with the agent.
        metadata: The metadata to use instead of the metadata passed to the agent constructor. When set, any
            per-run `metadata` argument is ignored.
        model_settings: The model settings to use instead of the model settings passed to the agent constructor.
            When set, any per-run `model_settings` argument is ignored.
        spec: Optional agent spec providing defaults for override. Explicit params take precedence over spec values.
    """
    resolved = self._resolve_spec(spec)

    # Apply spec values as defaults where explicit params are not set
    if resolved is not None:
        if not _utils.is_set(name) and resolved.name is not None:
            name = resolved.name
        if not _utils.is_set(model) and resolved.model is not None:
            model = resolved.model
        if not _utils.is_set(instructions) and resolved.instructions:
            instructions = resolved.instructions
        if not _utils.is_set(model_settings) and resolved.model_settings is not None:
            model_settings = resolved.model_settings
        if not _utils.is_set(metadata) and resolved.metadata is not None:
            metadata = resolved.metadata

    if _utils.is_set(name):
        name_token = self._override_name.set(_utils.Some(name))
    else:
        name_token = None

    if _utils.is_set(deps):
        deps_token = self._override_deps.set(_utils.Some(deps))
    else:
        deps_token = None

    if _utils.is_set(model):
        model_token = self._override_model.set(_utils.Some(models.infer_model(model)))
    else:
        model_token = None

    if _utils.is_set(toolsets):
        toolsets_token = self._override_toolsets.set(_utils.Some(toolsets))
    else:
        toolsets_token = None

    if _utils.is_set(tools):
        tools_token = self._override_tools.set(_utils.Some(tools))
    else:
        tools_token = None

    if _utils.is_set(instructions):
        normalized_instructions = _instructions.normalize_instructions(instructions)
        instructions_token = self._override_instructions.set(_utils.Some(normalized_instructions))
    else:
        instructions_token = None

    if _utils.is_set(metadata):
        metadata_token = self._override_metadata.set(_utils.Some(metadata))
    else:
        metadata_token = None

    if _utils.is_set(model_settings):
        model_settings_token = self._override_model_settings.set(_utils.Some(model_settings))
    else:
        model_settings_token = None

    # Set capability from spec, combining with agent's existing root capability
    if resolved is not None and resolved.capability is not None:
        cap_token = self._override_root_capability.set(_utils.Some(resolved.capability))
    else:
        cap_token = None

    try:
        yield
    finally:
        if name_token is not None:
            self._override_name.reset(name_token)
        if deps_token is not None:
            self._override_deps.reset(deps_token)
        if model_token is not None:
            self._override_model.reset(model_token)
        if toolsets_token is not None:
            self._override_toolsets.reset(toolsets_token)
        if tools_token is not None:
            self._override_tools.reset(tools_token)
        if instructions_token is not None:
            self._override_instructions.reset(instructions_token)
        if metadata_token is not None:
            self._override_metadata.reset(metadata_token)
        if model_settings_token is not None:
            self._override_model_settings.reset(model_settings_token)
        if cap_token is not None:
            self._override_root_capability.reset(cap_token)

instructions

instructions(
    func: Callable[[RunContext[AgentDepsT]], str | None],
) -> Callable[[RunContext[AgentDepsT]], str | None]

instructions(
    func: Callable[
        [RunContext[AgentDepsT]], Awaitable[str | None]
    ],
) -> Callable[
    [RunContext[AgentDepsT]], Awaitable[str | None]
]

instructions(
    func: Callable[[], str | None],
) -> Callable[[], str | None]

instructions(
    func: Callable[[], Awaitable[str | None]],
) -> Callable[[], Awaitable[str | None]]

instructions() -> Callable[
    [SystemPromptFunc[AgentDepsT]],
    SystemPromptFunc[AgentDepsT],
]

instructions(
    func: SystemPromptFunc[AgentDepsT] | None = None,
) -> (
    Callable[
        [SystemPromptFunc[AgentDepsT]],
        SystemPromptFunc[AgentDepsT],
    ]
    | SystemPromptFunc[AgentDepsT]
)

Decorator to register an instructions function.

Optionally takes RunContext as its only argument. Can decorate a sync or async functions.

The decorator can be used bare (agent.instructions).

Overloads for every possible signature of instructions are included so the decorator doesn't obscure the type of the function.

Example:

from pydantic_ai import Agent, RunContext

agent = Agent('test', deps_type=str)

@agent.instructions
def simple_instructions() -> str:
    return 'foobar'

@agent.instructions
async def async_instructions(ctx: RunContext[str]) -> str:
    return f'{ctx.deps} is the best'

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

def instructions(
    self,
    func: _system_prompt.SystemPromptFunc[AgentDepsT] | None = None,
    /,
) -> (
    Callable[[_system_prompt.SystemPromptFunc[AgentDepsT]], _system_prompt.SystemPromptFunc[AgentDepsT]]
    | _system_prompt.SystemPromptFunc[AgentDepsT]
):
    """Decorator to register an instructions function.

    Optionally takes [`RunContext`][pydantic_ai.tools.RunContext] as its only argument.
    Can decorate a sync or async functions.

    The decorator can be used bare (`agent.instructions`).

    Overloads for every possible signature of `instructions` are included so the decorator doesn't obscure
    the type of the function.

    Example:
    ```python
    from pydantic_ai import Agent, RunContext

    agent = Agent('test', deps_type=str)

    @agent.instructions
    def simple_instructions() -> str:
        return 'foobar'

    @agent.instructions
    async def async_instructions(ctx: RunContext[str]) -> str:
        return f'{ctx.deps} is the best'
    ```
    """
    if func is None:

        def decorator(
            func_: _system_prompt.SystemPromptFunc[AgentDepsT],
        ) -> _system_prompt.SystemPromptFunc[AgentDepsT]:
            self._instructions.append(func_)
            return func_

        return decorator
    else:
        self._instructions.append(func)
        return func

system_prompt

system_prompt(
    func: Callable[[RunContext[AgentDepsT]], str | None],
) -> Callable[[RunContext[AgentDepsT]], str | None]

system_prompt(
    func: Callable[
        [RunContext[AgentDepsT]], Awaitable[str | None]
    ],
) -> Callable[
    [RunContext[AgentDepsT]], Awaitable[str | None]
]

system_prompt(
    func: Callable[[], str | None],
) -> Callable[[], str | None]

system_prompt(
    func: Callable[[], Awaitable[str | None]],
) -> Callable[[], Awaitable[str | None]]

system_prompt(*, dynamic: bool = False) -> Callable[
    [SystemPromptFunc[AgentDepsT]],
    SystemPromptFunc[AgentDepsT],
]

system_prompt(
    func: SystemPromptFunc[AgentDepsT] | None = None,
    /,
    *,
    dynamic: bool = False,
) -> (
    Callable[
        [SystemPromptFunc[AgentDepsT]],
        SystemPromptFunc[AgentDepsT],
    ]
    | SystemPromptFunc[AgentDepsT]
)

Decorator to register a system prompt function.

Optionally takes RunContext as its only argument. Can decorate a sync or async functions.

The decorator can be used either bare (agent.system_prompt) or as a function call (agent.system_prompt(...)), see the examples below.

Overloads for every possible signature of system_prompt are included so the decorator doesn't obscure the type of the function, see tests/typed_agent.py for tests.

Parameters:

Name	Type	Description	Default
func	SystemPromptFunc[AgentDepsT] | None	The function to decorate	None
dynamic	bool	If True, the system prompt will be reevaluated even when messages_history is provided, see SystemPromptPart.dynamic_ref	False

Example:

from pydantic_ai import Agent, RunContext

agent = Agent('test', deps_type=str)

@agent.system_prompt
def simple_system_prompt() -> str:
    return 'foobar'

@agent.system_prompt(dynamic=True)
async def async_system_prompt(ctx: RunContext[str]) -> str:
    return f'{ctx.deps} is the best'

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

def system_prompt(
    self,
    func: _system_prompt.SystemPromptFunc[AgentDepsT] | None = None,
    /,
    *,
    dynamic: bool = False,
) -> (
    Callable[[_system_prompt.SystemPromptFunc[AgentDepsT]], _system_prompt.SystemPromptFunc[AgentDepsT]]
    | _system_prompt.SystemPromptFunc[AgentDepsT]
):
    """Decorator to register a system prompt function.

    Optionally takes [`RunContext`][pydantic_ai.tools.RunContext] as its only argument.
    Can decorate a sync or async functions.

    The decorator can be used either bare (`agent.system_prompt`) or as a function call
    (`agent.system_prompt(...)`), see the examples below.

    Overloads for every possible signature of `system_prompt` are included so the decorator doesn't obscure
    the type of the function, see `tests/typed_agent.py` for tests.

    Args:
        func: The function to decorate
        dynamic: If True, the system prompt will be reevaluated even when `messages_history` is provided,
            see [`SystemPromptPart.dynamic_ref`][pydantic_ai.messages.SystemPromptPart.dynamic_ref]

    Example:
    ```python
    from pydantic_ai import Agent, RunContext

    agent = Agent('test', deps_type=str)

    @agent.system_prompt
    def simple_system_prompt() -> str:
        return 'foobar'

    @agent.system_prompt(dynamic=True)
    async def async_system_prompt(ctx: RunContext[str]) -> str:
        return f'{ctx.deps} is the best'
    ```
    """
    if func is None:

        def decorator(
            func_: _system_prompt.SystemPromptFunc[AgentDepsT],
        ) -> _system_prompt.SystemPromptFunc[AgentDepsT]:
            runner = _system_prompt.SystemPromptRunner[AgentDepsT](func_, dynamic=dynamic)
            self._system_prompt_functions.append(runner)
            if dynamic:  # pragma: lax no cover
                self._system_prompt_dynamic_functions[func_.__qualname__] = runner
            return func_

        return decorator
    else:
        assert not dynamic, "dynamic can't be True in this case"
        self._system_prompt_functions.append(_system_prompt.SystemPromptRunner[AgentDepsT](func, dynamic=dynamic))
        return func

output_validator

output_validator(
    func: Callable[
        [RunContext[AgentDepsT], OutputDataT], OutputDataT
    ],
) -> Callable[
    [RunContext[AgentDepsT], OutputDataT], OutputDataT
]

output_validator(
    func: Callable[
        [RunContext[AgentDepsT], OutputDataT],
        Awaitable[OutputDataT],
    ],
) -> Callable[
    [RunContext[AgentDepsT], OutputDataT],
    Awaitable[OutputDataT],
]

output_validator(
    func: Callable[[OutputDataT], OutputDataT],
) -> Callable[[OutputDataT], OutputDataT]

output_validator(
    func: Callable[[OutputDataT], Awaitable[OutputDataT]],
) -> Callable[[OutputDataT], Awaitable[OutputDataT]]

output_validator(
    func: OutputValidatorFunc[AgentDepsT, OutputDataT],
) -> OutputValidatorFunc[AgentDepsT, OutputDataT]

Decorator to register an output validator function.

Optionally takes RunContext as its first argument. Can decorate a sync or async functions.

Overloads for every possible signature of output_validator are included so the decorator doesn't obscure the type of the function, see tests/typed_agent.py for tests.

Example:

from pydantic_ai import Agent, ModelRetry, RunContext

agent = Agent('test', deps_type=str)

@agent.output_validator
def output_validator_simple(data: str) -> str:
    if 'wrong' in data:
        raise ModelRetry('wrong response')
    return data

@agent.output_validator
async def output_validator_deps(ctx: RunContext[str], data: str) -> str:
    if ctx.deps in data:
        raise ModelRetry('wrong response')
    return data

result = agent.run_sync('foobar', deps='spam')
print(result.output)
#> success (no tool calls)

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

def output_validator(
    self, func: _output.OutputValidatorFunc[AgentDepsT, OutputDataT], /
) -> _output.OutputValidatorFunc[AgentDepsT, OutputDataT]:
    """Decorator to register an output validator function.

    Optionally takes [`RunContext`][pydantic_ai.tools.RunContext] as its first argument.
    Can decorate a sync or async functions.

    Overloads for every possible signature of `output_validator` are included so the decorator doesn't obscure
    the type of the function, see `tests/typed_agent.py` for tests.

    Example:
    ```python
    from pydantic_ai import Agent, ModelRetry, RunContext

    agent = Agent('test', deps_type=str)

    @agent.output_validator
    def output_validator_simple(data: str) -> str:
        if 'wrong' in data:
            raise ModelRetry('wrong response')
        return data

    @agent.output_validator
    async def output_validator_deps(ctx: RunContext[str], data: str) -> str:
        if ctx.deps in data:
            raise ModelRetry('wrong response')
        return data

    result = agent.run_sync('foobar', deps='spam')
    print(result.output)
    #> success (no tool calls)
    ```
    """
    self._output_validators.append(_output.OutputValidator[AgentDepsT, Any](func))
    return func

tool

tool(
    func: ToolFuncContext[AgentDepsT, ToolParams],
) -> ToolFuncContext[AgentDepsT, ToolParams]

tool(
    *,
    name: str | None = None,
    description: str | None = None,
    retries: int | None = None,
    prepare: ToolPrepareFunc[AgentDepsT] | None = None,
    args_validator: (
        ArgsValidatorFunc[AgentDepsT, ToolParams] | None
    ) = None,
    docstring_format: DocstringFormat = "auto",
    require_parameter_descriptions: bool = False,
    schema_generator: type[
        GenerateJsonSchema
    ] = GenerateToolJsonSchema,
    strict: bool | None = None,
    sequential: bool = False,
    requires_approval: bool = False,
    metadata: dict[str, Any] | None = None,
    timeout: float | None = None
) -> Callable[
    [ToolFuncContext[AgentDepsT, ToolParams]],
    ToolFuncContext[AgentDepsT, ToolParams],
]

tool(
    func: (
        ToolFuncContext[AgentDepsT, ToolParams] | None
    ) = None,
    /,
    *,
    name: str | None = None,
    description: str | None = None,
    retries: int | None = None,
    prepare: ToolPrepareFunc[AgentDepsT] | None = None,
    args_validator: (
        ArgsValidatorFunc[AgentDepsT, ToolParams] | None
    ) = None,
    docstring_format: DocstringFormat = "auto",
    require_parameter_descriptions: bool = False,
    schema_generator: type[
        GenerateJsonSchema
    ] = GenerateToolJsonSchema,
    strict: bool | None = None,
    sequential: bool = False,
    requires_approval: bool = False,
    metadata: dict[str, Any] | None = None,
    timeout: float | None = None,
) -> Any

Decorator to register a tool function which takes RunContext as its first argument.

Can decorate a sync or async functions.

The docstring is inspected to extract both the tool description and description of each parameter, learn more.

We can't add overloads for every possible signature of tool, since the return type is a recursive union so the signature of functions decorated with @agent.tool is obscured.

Example:

from pydantic_ai import Agent, RunContext

agent = Agent('test', deps_type=int)

@agent.tool
def foobar(ctx: RunContext[int], x: int) -> int:
    return ctx.deps + x

@agent.tool(retries=2)
async def spam(ctx: RunContext[str], y: float) -> float:
    return ctx.deps + y

result = agent.run_sync('foobar', deps=1)
print(result.output)
#> {"foobar":1,"spam":1.0}

Parameters:

Name	Type	Description	Default
func	ToolFuncContext[AgentDepsT, ToolParams] | None	The tool function to register.	None
name	str | None	The name of the tool, defaults to the function name.	None
description	str | None	The description of the tool, defaults to the function docstring.	None
retries	int | None	The number of retries to allow for this tool, defaults to the agent's default retries, which defaults to 1.	None
prepare	ToolPrepareFunc[AgentDepsT] | None	custom method to prepare the tool definition for each step, return None to omit this tool from a given step. This is useful if you want to customise a tool at call time, or omit it completely from a step. See ToolPrepareFunc.	None
args_validator	ArgsValidatorFunc[AgentDepsT, ToolParams] | None	custom method to validate tool arguments after schema validation has passed, before execution. The validator receives the already-validated and type-converted parameters, with RunContext as the first argument. Should raise ModelRetry on validation failure, return None on success. See ArgsValidatorFunc.	None
docstring_format	DocstringFormat	The format of the docstring, see DocstringFormat. Defaults to 'auto', such that the format is inferred from the structure of the docstring.	'auto'
require_parameter_descriptions	bool	If True, raise an error if a parameter description is missing. Defaults to False.	False
schema_generator	type[GenerateJsonSchema]	The JSON schema generator class to use for this tool. Defaults to GenerateToolJsonSchema.	GenerateToolJsonSchema
strict	bool | None	Whether to enforce JSON schema compliance (only affects OpenAI). See ToolDefinition for more info.	None
sequential	bool	Whether the function requires a sequential/serial execution environment. Defaults to False.	False
requires_approval	bool	Whether this tool requires human-in-the-loop approval. Defaults to False. See the tools documentation for more info.	False
metadata	dict[str, Any] | None	Optional metadata for the tool. This is not sent to the model but can be used for filtering and tool behavior customization.	None
timeout	float | None	Timeout in seconds for tool execution. If the tool takes longer, a retry prompt is returned to the model. Overrides the agent-level tool_timeout if set. Defaults to None (no timeout).	None

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

def tool(
    self,
    func: ToolFuncContext[AgentDepsT, ToolParams] | None = None,
    /,
    *,
    name: str | None = None,
    description: str | None = None,
    retries: int | None = None,
    prepare: ToolPrepareFunc[AgentDepsT] | None = None,
    args_validator: ArgsValidatorFunc[AgentDepsT, ToolParams] | None = None,
    docstring_format: DocstringFormat = 'auto',
    require_parameter_descriptions: bool = False,
    schema_generator: type[GenerateJsonSchema] = GenerateToolJsonSchema,
    strict: bool | None = None,
    sequential: bool = False,
    requires_approval: bool = False,
    metadata: dict[str, Any] | None = None,
    timeout: float | None = None,
) -> Any:
    """Decorator to register a tool function which takes [`RunContext`][pydantic_ai.tools.RunContext] as its first argument.

    Can decorate a sync or async functions.

    The docstring is inspected to extract both the tool description and description of each parameter,
    [learn more](../tools.md#function-tools-and-schema).

    We can't add overloads for every possible signature of tool, since the return type is a recursive union
    so the signature of functions decorated with `@agent.tool` is obscured.

    Example:
    ```python
    from pydantic_ai import Agent, RunContext

    agent = Agent('test', deps_type=int)

    @agent.tool
    def foobar(ctx: RunContext[int], x: int) -> int:
        return ctx.deps + x

    @agent.tool(retries=2)
    async def spam(ctx: RunContext[str], y: float) -> float:
        return ctx.deps + y

    result = agent.run_sync('foobar', deps=1)
    print(result.output)
    #> {"foobar":1,"spam":1.0}
    ```

    Args:
        func: The tool function to register.
        name: The name of the tool, defaults to the function name.
        description: The description of the tool, defaults to the function docstring.
        retries: The number of retries to allow for this tool, defaults to the agent's default retries,
            which defaults to 1.
        prepare: custom method to prepare the tool definition for each step, return `None` to omit this
            tool from a given step. This is useful if you want to customise a tool at call time,
            or omit it completely from a step. See [`ToolPrepareFunc`][pydantic_ai.tools.ToolPrepareFunc].
        args_validator: custom method to validate tool arguments after schema validation has passed,
            before execution. The validator receives the already-validated and type-converted parameters,
            with `RunContext` as the first argument.
            Should raise [`ModelRetry`][pydantic_ai.exceptions.ModelRetry] on validation failure,
            return `None` on success.
            See [`ArgsValidatorFunc`][pydantic_ai.tools.ArgsValidatorFunc].
        docstring_format: The format of the docstring, see [`DocstringFormat`][pydantic_ai.tools.DocstringFormat].
            Defaults to `'auto'`, such that the format is inferred from the structure of the docstring.
        require_parameter_descriptions: If True, raise an error if a parameter description is missing. Defaults to False.
        schema_generator: The JSON schema generator class to use for this tool. Defaults to `GenerateToolJsonSchema`.
        strict: Whether to enforce JSON schema compliance (only affects OpenAI).
            See [`ToolDefinition`][pydantic_ai.tools.ToolDefinition] for more info.
        sequential: Whether the function requires a sequential/serial execution environment. Defaults to False.
        requires_approval: Whether this tool requires human-in-the-loop approval. Defaults to False.
            See the [tools documentation](../deferred-tools.md#human-in-the-loop-tool-approval) for more info.
        metadata: Optional metadata for the tool. This is not sent to the model but can be used for filtering and tool behavior customization.
        timeout: Timeout in seconds for tool execution. If the tool takes longer, a retry prompt is returned to the model.
            Overrides the agent-level `tool_timeout` if set. Defaults to None (no timeout).
    """

    def tool_decorator(
        func_: ToolFuncContext[AgentDepsT, ToolParams],
    ) -> ToolFuncContext[AgentDepsT, ToolParams]:
        # noinspection PyTypeChecker
        self._function_toolset.add_function(
            func_,
            takes_ctx=True,
            name=name,
            description=description,
            retries=retries,
            prepare=prepare,
            args_validator=args_validator,
            docstring_format=docstring_format,
            require_parameter_descriptions=require_parameter_descriptions,
            schema_generator=schema_generator,
            strict=strict,
            sequential=sequential,
            requires_approval=requires_approval,
            metadata=metadata,
            timeout=timeout,
        )
        return func_

    return tool_decorator if func is None else tool_decorator(func)

tool_plain

tool_plain(
    func: ToolFuncPlain[ToolParams],
) -> ToolFuncPlain[ToolParams]

tool_plain(
    *,
    name: str | None = None,
    description: str | None = None,
    retries: int | None = None,
    prepare: ToolPrepareFunc[AgentDepsT] | None = None,
    args_validator: (
        ArgsValidatorFunc[AgentDepsT, ToolParams] | None
    ) = None,
    docstring_format: DocstringFormat = "auto",
    require_parameter_descriptions: bool = False,
    schema_generator: type[
        GenerateJsonSchema
    ] = GenerateToolJsonSchema,
    strict: bool | None = None,
    sequential: bool = False,
    requires_approval: bool = False,
    metadata: dict[str, Any] | None = None,
    timeout: float | None = None
) -> Callable[
    [ToolFuncPlain[ToolParams]], ToolFuncPlain[ToolParams]
]

tool_plain(
    func: ToolFuncPlain[ToolParams] | None = None,
    /,
    *,
    name: str | None = None,
    description: str | None = None,
    retries: int | None = None,
    prepare: ToolPrepareFunc[AgentDepsT] | None = None,
    args_validator: (
        ArgsValidatorFunc[AgentDepsT, ToolParams] | None
    ) = None,
    docstring_format: DocstringFormat = "auto",
    require_parameter_descriptions: bool = False,
    schema_generator: type[
        GenerateJsonSchema
    ] = GenerateToolJsonSchema,
    strict: bool | None = None,
    sequential: bool = False,
    requires_approval: bool = False,
    metadata: dict[str, Any] | None = None,
    timeout: float | None = None,
) -> Any

Decorator to register a tool function which DOES NOT take RunContext as an argument.

Can decorate a sync or async functions.

The docstring is inspected to extract both the tool description and description of each parameter, learn more.

We can't add overloads for every possible signature of tool, since the return type is a recursive union so the signature of functions decorated with @agent.tool is obscured.

Example:

from pydantic_ai import Agent, RunContext

agent = Agent('test')

@agent.tool
def foobar(ctx: RunContext[int]) -> int:
    return 123

@agent.tool(retries=2)
async def spam(ctx: RunContext[str]) -> float:
    return 3.14

result = agent.run_sync('foobar', deps=1)
print(result.output)
#> {"foobar":123,"spam":3.14}

Parameters:

Name	Type	Description	Default
func	ToolFuncPlain[ToolParams] | None	The tool function to register.	None
name	str | None	The name of the tool, defaults to the function name.	None
description	str | None	The description of the tool, defaults to the function docstring.	None
retries	int | None	The number of retries to allow for this tool, defaults to the agent's default retries, which defaults to 1.	None
prepare	ToolPrepareFunc[AgentDepsT] | None	custom method to prepare the tool definition for each step, return None to omit this tool from a given step. This is useful if you want to customise a tool at call time, or omit it completely from a step. See ToolPrepareFunc.	None
args_validator	ArgsValidatorFunc[AgentDepsT, ToolParams] | None	custom method to validate tool arguments after schema validation has passed, before execution. The validator receives the already-validated and type-converted parameters, with RunContext as the first argument — even though the tool function itself does not take RunContext when using tool_plain. Should raise ModelRetry on validation failure, return None on success. See ArgsValidatorFunc.	None
docstring_format	DocstringFormat	The format of the docstring, see DocstringFormat. Defaults to 'auto', such that the format is inferred from the structure of the docstring.	'auto'
require_parameter_descriptions	bool	If True, raise an error if a parameter description is missing. Defaults to False.	False
schema_generator	type[GenerateJsonSchema]	The JSON schema generator class to use for this tool. Defaults to GenerateToolJsonSchema.	GenerateToolJsonSchema
strict	bool | None	Whether to enforce JSON schema compliance (only affects OpenAI). See ToolDefinition for more info.	None
sequential	bool	Whether the function requires a sequential/serial execution environment. Defaults to False.	False
requires_approval	bool	Whether this tool requires human-in-the-loop approval. Defaults to False. See the tools documentation for more info.	False
metadata	dict[str, Any] | None	Optional metadata for the tool. This is not sent to the model but can be used for filtering and tool behavior customization.	None
timeout	float | None	Timeout in seconds for tool execution. If the tool takes longer, a retry prompt is returned to the model. Overrides the agent-level tool_timeout if set. Defaults to None (no timeout).	None

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

def tool_plain(
    self,
    func: ToolFuncPlain[ToolParams] | None = None,
    /,
    *,
    name: str | None = None,
    description: str | None = None,
    retries: int | None = None,
    prepare: ToolPrepareFunc[AgentDepsT] | None = None,
    args_validator: ArgsValidatorFunc[AgentDepsT, ToolParams] | None = None,
    docstring_format: DocstringFormat = 'auto',
    require_parameter_descriptions: bool = False,
    schema_generator: type[GenerateJsonSchema] = GenerateToolJsonSchema,
    strict: bool | None = None,
    sequential: bool = False,
    requires_approval: bool = False,
    metadata: dict[str, Any] | None = None,
    timeout: float | None = None,
) -> Any:
    """Decorator to register a tool function which DOES NOT take `RunContext` as an argument.

    Can decorate a sync or async functions.

    The docstring is inspected to extract both the tool description and description of each parameter,
    [learn more](../tools.md#function-tools-and-schema).

    We can't add overloads for every possible signature of tool, since the return type is a recursive union
    so the signature of functions decorated with `@agent.tool` is obscured.

    Example:
    ```python
    from pydantic_ai import Agent, RunContext

    agent = Agent('test')

    @agent.tool
    def foobar(ctx: RunContext[int]) -> int:
        return 123

    @agent.tool(retries=2)
    async def spam(ctx: RunContext[str]) -> float:
        return 3.14

    result = agent.run_sync('foobar', deps=1)
    print(result.output)
    #> {"foobar":123,"spam":3.14}
    ```

    Args:
        func: The tool function to register.
        name: The name of the tool, defaults to the function name.
        description: The description of the tool, defaults to the function docstring.
        retries: The number of retries to allow for this tool, defaults to the agent's default retries,
            which defaults to 1.
        prepare: custom method to prepare the tool definition for each step, return `None` to omit this
            tool from a given step. This is useful if you want to customise a tool at call time,
            or omit it completely from a step. See [`ToolPrepareFunc`][pydantic_ai.tools.ToolPrepareFunc].
        args_validator: custom method to validate tool arguments after schema validation has passed,
            before execution. The validator receives the already-validated and type-converted parameters,
            with [`RunContext`][pydantic_ai.tools.RunContext] as the first argument — even though the
            tool function itself does not take `RunContext` when using `tool_plain`.
            Should raise [`ModelRetry`][pydantic_ai.exceptions.ModelRetry] on validation failure,
            return `None` on success.
            See [`ArgsValidatorFunc`][pydantic_ai.tools.ArgsValidatorFunc].
        docstring_format: The format of the docstring, see [`DocstringFormat`][pydantic_ai.tools.DocstringFormat].
            Defaults to `'auto'`, such that the format is inferred from the structure of the docstring.
        require_parameter_descriptions: If True, raise an error if a parameter description is missing. Defaults to False.
        schema_generator: The JSON schema generator class to use for this tool. Defaults to `GenerateToolJsonSchema`.
        strict: Whether to enforce JSON schema compliance (only affects OpenAI).
            See [`ToolDefinition`][pydantic_ai.tools.ToolDefinition] for more info.
        sequential: Whether the function requires a sequential/serial execution environment. Defaults to False.
        requires_approval: Whether this tool requires human-in-the-loop approval. Defaults to False.
            See the [tools documentation](../deferred-tools.md#human-in-the-loop-tool-approval) for more info.
        metadata: Optional metadata for the tool. This is not sent to the model but can be used for filtering and tool behavior customization.
        timeout: Timeout in seconds for tool execution. If the tool takes longer, a retry prompt is returned to the model.
            Overrides the agent-level `tool_timeout` if set. Defaults to None (no timeout).
    """

    def tool_decorator(func_: ToolFuncPlain[ToolParams]) -> ToolFuncPlain[ToolParams]:
        # noinspection PyTypeChecker
        self._function_toolset.add_function(
            func_,
            takes_ctx=False,
            name=name,
            description=description,
            retries=retries,
            prepare=prepare,
            args_validator=args_validator,
            docstring_format=docstring_format,
            require_parameter_descriptions=require_parameter_descriptions,
            schema_generator=schema_generator,
            strict=strict,
            sequential=sequential,
            requires_approval=requires_approval,
            metadata=metadata,
            timeout=timeout,
        )
        return func_

    return tool_decorator if func is None else tool_decorator(func)

toolset

toolset(
    func: ToolsetFunc[AgentDepsT],
) -> ToolsetFunc[AgentDepsT]

toolset(
    *, per_run_step: bool = True, id: str | None = None
) -> Callable[
    [ToolsetFunc[AgentDepsT]], ToolsetFunc[AgentDepsT]
]

toolset(
    func: ToolsetFunc[AgentDepsT] | None = None,
    /,
    *,
    per_run_step: bool = True,
    id: str | None = None,
) -> Any

Decorator to register a toolset function which takes RunContext as its only argument.

Can decorate a sync or async functions.

The decorator can be used bare (agent.toolset).

Example:

from pydantic_ai import AbstractToolset, Agent, FunctionToolset, RunContext

agent = Agent('test', deps_type=str)

@agent.toolset
async def simple_toolset(ctx: RunContext[str]) -> AbstractToolset[str]:
    return FunctionToolset()

Parameters:

Name	Type	Description	Default
func	ToolsetFunc[AgentDepsT] | None	The toolset function to register.	None
per_run_step	bool	Whether to re-evaluate the toolset for each run step. Defaults to True.	True
id	str | None	An optional unique ID for the dynamic toolset. Required for use with durable execution environments like Temporal, where the ID identifies the toolset's activities within the workflow.	None

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

def toolset(
    self,
    func: ToolsetFunc[AgentDepsT] | None = None,
    /,
    *,
    per_run_step: bool = True,
    id: str | None = None,
) -> Any:
    """Decorator to register a toolset function which takes [`RunContext`][pydantic_ai.tools.RunContext] as its only argument.

    Can decorate a sync or async functions.

    The decorator can be used bare (`agent.toolset`).

    Example:
    ```python
    from pydantic_ai import AbstractToolset, Agent, FunctionToolset, RunContext

    agent = Agent('test', deps_type=str)

    @agent.toolset
    async def simple_toolset(ctx: RunContext[str]) -> AbstractToolset[str]:
        return FunctionToolset()
    ```

    Args:
        func: The toolset function to register.
        per_run_step: Whether to re-evaluate the toolset for each run step. Defaults to True.
        id: An optional unique ID for the dynamic toolset. Required for use with durable execution
            environments like Temporal, where the ID identifies the toolset's activities within the workflow.
    """

    def toolset_decorator(func_: ToolsetFunc[AgentDepsT]) -> ToolsetFunc[AgentDepsT]:
        self._dynamic_toolsets.append(DynamicToolset(func_, per_run_step=per_run_step, id=id))
        return func_

    return toolset_decorator if func is None else toolset_decorator(func)

toolsets property

toolsets: Sequence[AbstractToolset[AgentDepsT]]

All toolsets registered on the agent, including a function toolset holding tools that were registered on the agent directly.

Output tools are not included.

__aenter__ async

__aenter__() -> Self

Enter the agent context.

This will start all MCPServerStdios registered as toolsets so they are ready to be used.

This is a no-op if the agent has already been entered.

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

async def __aenter__(self) -> Self:
    """Enter the agent context.

    This will start all [`MCPServerStdio`s][pydantic_ai.mcp.MCPServerStdio] registered as `toolsets` so they are ready to be used.

    This is a no-op if the agent has already been entered.
    """
    async with self._enter_lock:
        if self._entered_count == 0:
            async with AsyncExitStack() as exit_stack:
                toolset = self._get_toolset()
                await exit_stack.enter_async_context(toolset)

                self._exit_stack = exit_stack.pop_all()
        self._entered_count += 1
    return self

set_mcp_sampling_model

set_mcp_sampling_model(
    model: Model | KnownModelName | str | None = None,
) -> None

Set the sampling model on all MCP servers registered with the agent.

If no sampling model is provided, the agent's model will be used.

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

def set_mcp_sampling_model(self, model: models.Model | models.KnownModelName | str | None = None) -> None:
    """Set the sampling model on all MCP servers registered with the agent.

    If no sampling model is provided, the agent's model will be used.
    """
    try:
        sampling_model = models.infer_model(model) if model else self._get_model(None)
    except exceptions.UserError as e:
        raise exceptions.UserError('No sampling model provided and no model set on the agent.') from e

    from ..mcp import MCPServer

    def _set_sampling_model(toolset: AbstractToolset[AgentDepsT]) -> None:
        if isinstance(toolset, MCPServer):
            toolset.sampling_model = sampling_model

    self._get_toolset().apply(_set_sampling_model)

to_web

to_web(
    *,
    models: ModelsParam = None,
    builtin_tools: list[AbstractBuiltinTool] | None = None,
    deps: AgentDepsT = None,
    model_settings: ModelSettings | None = None,
    instructions: str | None = None,
    html_source: str | Path | None = None
) -> Starlette

Create a Starlette app that serves a web chat UI for this agent.

This method returns a pre-configured Starlette application that provides a web-based chat interface for interacting with the agent. By default, the UI is fetched from a CDN and cached on first use.

The returned Starlette application can be mounted into a FastAPI app or run directly with any ASGI server (uvicorn, hypercorn, etc.).

Note that the deps and model_settings will be the same for each request. To provide different deps for each request use the lower-level adapters directly.

Parameters:

Name	Type	Description	Default
models	ModelsParam	Additional models to make available in the UI. Can be: - A sequence of model names/instances (e.g., ['openai:gpt-5', 'anthropic:claude-sonnet-4-6']) - A dict mapping display labels to model names/instances (e.g., {'GPT 5': 'openai:gpt-5', 'Claude': 'anthropic:claude-sonnet-4-6'}) The agent's model is always included. Builtin tool support is automatically determined from each model's profile.	None
builtin_tools	list[AbstractBuiltinTool] | None	Additional builtin tools to make available in the UI. The agent's configured builtin tools are always included. Tool labels in the UI are derived from the tool's label property.	None
deps	AgentDepsT	Optional dependencies to use for all requests.	None
model_settings	ModelSettings | None	Optional settings to use for all model requests.	None
instructions	str | None	Optional extra instructions to pass to each agent run.	None
html_source	str | Path | None	Path or URL for the chat UI HTML. Can be: - None (default): Fetches from CDN and caches locally - A Path instance: Reads from the local file - A URL string (http:// or https://): Fetches from the URL - A file path string: Reads from the local file	None

Returns:

Type	Description
Starlette	A configured Starlette application ready to be served (e.g., with uvicorn)

Example

from pydantic_ai import Agent
from pydantic_ai.builtin_tools import WebSearchTool

agent = Agent('openai:gpt-5', builtin_tools=[WebSearchTool()])

# Simple usage - uses agent's model and builtin tools
app = agent.to_web()

# Or provide additional models for UI selection
app = agent.to_web(models=['openai:gpt-5', 'anthropic:claude-sonnet-4-6'])

# Then run with: uvicorn app:app --reload

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

def to_web(
    self,
    *,
    models: ModelsParam = None,
    builtin_tools: list[AbstractBuiltinTool] | None = None,
    deps: AgentDepsT = None,
    model_settings: ModelSettings | None = None,
    instructions: str | None = None,
    html_source: str | Path | None = None,
) -> Starlette:
    """Create a Starlette app that serves a web chat UI for this agent.

    This method returns a pre-configured Starlette application that provides a web-based
    chat interface for interacting with the agent. By default, the UI is fetched from a
    CDN and cached on first use.

    The returned Starlette application can be mounted into a FastAPI app or run directly
    with any ASGI server (uvicorn, hypercorn, etc.).

    Note that the `deps` and `model_settings` will be the same for each request.
    To provide different `deps` for each request use the lower-level adapters directly.

    Args:
        models: Additional models to make available in the UI. Can be:
            - A sequence of model names/instances (e.g., `['openai:gpt-5', 'anthropic:claude-sonnet-4-6']`)
            - A dict mapping display labels to model names/instances
              (e.g., `{'GPT 5': 'openai:gpt-5', 'Claude': 'anthropic:claude-sonnet-4-6'}`)
            The agent's model is always included. Builtin tool support is automatically
            determined from each model's profile.
        builtin_tools: Additional builtin tools to make available in the UI.
            The agent's configured builtin tools are always included. Tool labels
            in the UI are derived from the tool's `label` property.
        deps: Optional dependencies to use for all requests.
        model_settings: Optional settings to use for all model requests.
        instructions: Optional extra instructions to pass to each agent run.
        html_source: Path or URL for the chat UI HTML. Can be:
            - None (default): Fetches from CDN and caches locally
            - A Path instance: Reads from the local file
            - A URL string (http:// or https://): Fetches from the URL
            - A file path string: Reads from the local file

    Returns:
        A configured Starlette application ready to be served (e.g., with uvicorn)

    Example:
        ```python
        from pydantic_ai import Agent
        from pydantic_ai.builtin_tools import WebSearchTool

        agent = Agent('openai:gpt-5', builtin_tools=[WebSearchTool()])

        # Simple usage - uses agent's model and builtin tools
        app = agent.to_web()

        # Or provide additional models for UI selection
        app = agent.to_web(models=['openai:gpt-5', 'anthropic:claude-sonnet-4-6'])

        # Then run with: uvicorn app:app --reload
        ```
    """
    from ..ui._web import create_web_app

    return create_web_app(
        self,
        models=models,
        builtin_tools=builtin_tools,
        deps=deps,
        model_settings=model_settings,
        instructions=instructions,
        html_source=html_source,
    )

run_mcp_servers async deprecated

run_mcp_servers(
    model: Model | KnownModelName | str | None = None,
) -> AsyncIterator[None]

Deprecated

run_mcp_servers is deprecated, use async with agent: instead. If you need to set a sampling model on all MCP servers, use agent.set_mcp_sampling_model().

Run MCPServerStdios so they can be used by the agent.

Deprecated: use async with agent instead. If you need to set a sampling model on all MCP servers, use agent.set_mcp_sampling_model().

Returns: a context manager to start and shutdown the servers.

Source code in pydantic_ai_slim/pydantic_ai/agent/__init__.py

@asynccontextmanager
@deprecated(
    '`run_mcp_servers` is deprecated, use `async with agent:` instead. If you need to set a sampling model on all MCP servers, use `agent.set_mcp_sampling_model()`.'
)
async def run_mcp_servers(
    self, model: models.Model | models.KnownModelName | str | None = None
) -> AsyncIterator[None]:
    """Run [`MCPServerStdio`s][pydantic_ai.mcp.MCPServerStdio] so they can be used by the agent.

    Deprecated: use [`async with agent`][pydantic_ai.agent.Agent.__aenter__] instead.
    If you need to set a sampling model on all MCP servers, use [`agent.set_mcp_sampling_model()`][pydantic_ai.agent.Agent.set_mcp_sampling_model].

    Returns: a context manager to start and shutdown the servers.
    """
    try:
        self.set_mcp_sampling_model(model)
    except exceptions.UserError:
        if model is not None:
            raise

    async with self:
        yield

AbstractAgent

Bases: Generic[AgentDepsT, OutputDataT], ABC

Abstract superclass for Agent, WrapperAgent, and your own custom agent implementations.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

class AbstractAgent(Generic[AgentDepsT, OutputDataT], ABC):
    """Abstract superclass for [`Agent`][pydantic_ai.agent.Agent], [`WrapperAgent`][pydantic_ai.agent.WrapperAgent], and your own custom agent implementations."""

    @property
    @abstractmethod
    def model(self) -> models.Model | models.KnownModelName | str | None:
        """The default model configured for this agent."""
        raise NotImplementedError

    @property
    @abstractmethod
    def name(self) -> str | None:
        """The name of the agent, used for logging.

        If `None`, we try to infer the agent name from the call frame when the agent is first run.
        """
        raise NotImplementedError

    @name.setter
    @abstractmethod
    def name(self, value: str | None) -> None:
        """Set the name of the agent, used for logging."""
        raise NotImplementedError

    @property
    @abstractmethod
    def description(self) -> str | None:
        """A human-readable description of the agent."""
        raise NotImplementedError

    @description.setter
    @abstractmethod
    def description(self, value: TemplateStr[AgentDepsT] | str | None) -> None:
        """Set the description of the agent."""
        raise NotImplementedError

    @property
    @abstractmethod
    def deps_type(self) -> type:
        """The type of dependencies used by the agent."""
        raise NotImplementedError

    @property
    @abstractmethod
    def output_type(self) -> OutputSpec[OutputDataT]:
        """The type of data output by agent runs, used to validate the data returned by the model, defaults to `str`."""
        raise NotImplementedError

    @property
    @abstractmethod
    def event_stream_handler(self) -> EventStreamHandler[AgentDepsT] | None:
        """Optional handler for events from the model's streaming response and the agent's execution of tools."""
        raise NotImplementedError

    @property
    @abstractmethod
    def toolsets(self) -> Sequence[AbstractToolset[AgentDepsT]]:
        """All toolsets registered on the agent.

        Output tools are not included.
        """
        raise NotImplementedError

    def output_json_schema(self, output_type: OutputSpec[OutputDataT | RunOutputDataT] | None = None) -> JsonSchema:
        """The output return JSON schema."""
        if output_type is None:
            output_type = self.output_type

        return_types = types_from_output_spec(output_spec=output_type)

        json_schemas: list[JsonSchema] = []
        for return_type in return_types:
            json_schema = TypeAdapter(return_type).json_schema(mode='serialization')
            if json_schema not in json_schemas:
                json_schemas.append(json_schema)

        if len(json_schemas) == 1:
            return json_schemas[0]
        else:
            json_schemas, all_defs = _utils.merge_json_schema_defs(json_schemas)
            json_schema: JsonSchema = {'anyOf': json_schemas}
            if all_defs:
                json_schema['$defs'] = all_defs
            return json_schema

    @overload
    async def run(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AgentRunResult[OutputDataT]: ...

    @overload
    async def run(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT],
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AgentRunResult[RunOutputDataT]: ...

    async def run(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT] | None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AgentRunResult[Any]:
        """Run the agent with a user prompt in async mode.

        This method builds an internal agent graph (using system prompts, tools and output schemas) and then
        runs the graph to completion. The result of the run is returned.

        Example:
        ```python
        from pydantic_ai import Agent

        agent = Agent('openai:gpt-5.2')

        async def main():
            agent_run = await agent.run('What is the capital of France?')
            print(agent_run.output)
            #> The capital of France is Paris.
        ```

        Args:
            user_prompt: User input to start/continue the conversation.
            output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
                output validators since output validators would expect an argument that matches the agent's output type.
            message_history: History of the conversation so far.
            deferred_tool_results: Optional results for deferred tool calls in the message history.
            model: Optional model to use for this run, required if `model` was not set when creating the agent.
            instructions: Optional additional instructions to use for this run.
            deps: Optional dependencies to use for this run.
            model_settings: Optional settings to use for this model's request, or a callable
                that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
                Callables are called before each model request, allowing dynamic per-step settings.
            usage_limits: Optional limits on model request count or token usage.
            usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
            metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
                [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
            infer_name: Whether to try to infer the agent name from the call frame if it's not set.
            toolsets: Optional additional toolsets for this run.
            event_stream_handler: Optional handler for events from the model's streaming response and the agent's execution of tools to use for this run.
            builtin_tools: Optional additional builtin tools for this run.
            spec: Optional agent spec to apply for this run. At run time, spec values are additive.

        Returns:
            The result of the run.
        """
        if infer_name and self.name is None:
            self._infer_name(inspect.currentframe())

        event_stream_handler = event_stream_handler or self.event_stream_handler

        async with self.iter(
            user_prompt=user_prompt,
            output_type=output_type,
            message_history=message_history,
            deferred_tool_results=deferred_tool_results,
            model=model,
            instructions=instructions,
            deps=deps,
            model_settings=model_settings,
            usage_limits=usage_limits,
            usage=usage,
            metadata=metadata,
            toolsets=toolsets,
            builtin_tools=builtin_tools,
            spec=spec,
        ) as agent_run:
            async for node in agent_run:
                if event_stream_handler is not None and (
                    self.is_model_request_node(node) or self.is_call_tools_node(node)
                ):
                    async with node.stream(agent_run.ctx) as stream:
                        run_ctx = _agent_graph.build_run_context(agent_run.ctx)
                        wrapped = await agent_run.ctx.deps.root_capability.wrap_run_event_stream(run_ctx, stream=stream)
                        await event_stream_handler(run_ctx, wrapped)

        assert agent_run.result is not None, 'The graph run did not finish properly'
        return agent_run.result

    @overload
    def run_sync(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AgentRunResult[OutputDataT]: ...

    @overload
    def run_sync(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT],
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AgentRunResult[RunOutputDataT]: ...

    def run_sync(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT] | None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AgentRunResult[Any]:
        """Synchronously run the agent with a user prompt.

        This is a convenience method that wraps [`self.run`][pydantic_ai.agent.AbstractAgent.run] with `loop.run_until_complete(...)`.
        You therefore can't use this method inside async code or if there's an active event loop.

        Example:
        ```python
        from pydantic_ai import Agent

        agent = Agent('openai:gpt-5.2')

        result_sync = agent.run_sync('What is the capital of Italy?')
        print(result_sync.output)
        #> The capital of Italy is Rome.
        ```

        Args:
            user_prompt: User input to start/continue the conversation.
            output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
                output validators since output validators would expect an argument that matches the agent's output type.
            message_history: History of the conversation so far.
            deferred_tool_results: Optional results for deferred tool calls in the message history.
            model: Optional model to use for this run, required if `model` was not set when creating the agent.
            instructions: Optional additional instructions to use for this run.
            deps: Optional dependencies to use for this run.
            model_settings: Optional settings to use for this model's request, or a callable
                that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
                Callables are called before each model request, allowing dynamic per-step settings.
            usage_limits: Optional limits on model request count or token usage.
            usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
            metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
                [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
            infer_name: Whether to try to infer the agent name from the call frame if it's not set.
            toolsets: Optional additional toolsets for this run.
            event_stream_handler: Optional handler for events from the model's streaming response and the agent's execution of tools to use for this run.
            builtin_tools: Optional additional builtin tools for this run.
            spec: Optional agent spec to apply for this run. At run time, spec values are additive.

        Returns:
            The result of the run.
        """
        if infer_name and self.name is None:
            self._infer_name(inspect.currentframe())

        return _utils.get_event_loop().run_until_complete(
            self.run(
                user_prompt,
                output_type=output_type,
                message_history=message_history,
                deferred_tool_results=deferred_tool_results,
                model=model,
                instructions=instructions,
                deps=deps,
                model_settings=model_settings,
                usage_limits=usage_limits,
                usage=usage,
                metadata=metadata,
                infer_name=False,
                toolsets=toolsets,
                builtin_tools=builtin_tools,
                event_stream_handler=event_stream_handler,
                spec=spec,
            )
        )

    @overload
    def run_stream(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AbstractAsyncContextManager[result.StreamedRunResult[AgentDepsT, OutputDataT]]: ...

    @overload
    def run_stream(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT],
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AbstractAsyncContextManager[result.StreamedRunResult[AgentDepsT, RunOutputDataT]]: ...

    @asynccontextmanager
    async def run_stream(  # noqa: C901
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT] | None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AsyncIterator[result.StreamedRunResult[AgentDepsT, Any]]:
        """Run the agent with a user prompt in async streaming mode.

        This method builds an internal agent graph (using system prompts, tools and output schemas) and then
        runs the graph until the model produces output matching the `output_type`, for example text or structured data.
        At this point, a streaming run result object is yielded from which you can stream the output as it comes in,
        and -- once this output has completed streaming -- get the complete output, message history, and usage.

        As this method will consider the first output matching the `output_type` to be the final output,
        it will stop running the agent graph and will not execute any tool calls made by the model after this "final" output.
        If you want to always run the agent graph to completion and stream events and output at the same time,
        use [`agent.run()`][pydantic_ai.agent.AbstractAgent.run] with an `event_stream_handler` or [`agent.iter()`][pydantic_ai.agent.AbstractAgent.iter] instead.

        Example:
        ```python
        from pydantic_ai import Agent

        agent = Agent('openai:gpt-5.2')

        async def main():
            async with agent.run_stream('What is the capital of the UK?') as response:
                print(await response.get_output())
                #> The capital of the UK is London.
        ```

        Args:
            user_prompt: User input to start/continue the conversation.
            output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
                output validators since output validators would expect an argument that matches the agent's output type.
            message_history: History of the conversation so far.
            deferred_tool_results: Optional results for deferred tool calls in the message history.
            model: Optional model to use for this run, required if `model` was not set when creating the agent.
            instructions: Optional additional instructions to use for this run.
            deps: Optional dependencies to use for this run.
            model_settings: Optional settings to use for this model's request, or a callable
                that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
                Callables are called before each model request, allowing dynamic per-step settings.
            usage_limits: Optional limits on model request count or token usage.
            usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
            metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
                [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
            infer_name: Whether to try to infer the agent name from the call frame if it's not set.
            toolsets: Optional additional toolsets for this run.
            builtin_tools: Optional additional builtin tools for this run.
            event_stream_handler: Optional handler for events from the model's streaming response and the agent's execution of tools to use for this run.
                It will receive all the events up until the final result is found, which you can then read or stream from inside the context manager.
                Note that it does _not_ receive any events after the final result is found.
            spec: Optional agent spec to apply for this run. At run time, spec values are additive.

        Returns:
            The result of the run.
        """
        if infer_name and self.name is None:
            # f_back because `asynccontextmanager` adds one frame
            if frame := inspect.currentframe():  # pragma: no branch
                self._infer_name(frame.f_back)

        event_stream_handler = event_stream_handler or self.event_stream_handler

        yielded = False
        async with self.iter(
            user_prompt,
            output_type=output_type,
            message_history=message_history,
            deferred_tool_results=deferred_tool_results,
            model=model,
            deps=deps,
            instructions=instructions,
            model_settings=model_settings,
            usage_limits=usage_limits,
            usage=usage,
            metadata=metadata,
            infer_name=False,
            toolsets=toolsets,
            builtin_tools=builtin_tools,
            spec=spec,
        ) as agent_run:
            # Handle wrap_run short-circuit: result is already available
            if agent_run.result is not None:
                graph_ctx = agent_run.ctx
                yield StreamedRunResult(
                    graph_ctx.state.message_history,
                    graph_ctx.deps.new_message_index,
                    run_result=agent_run.result,
                )
                yielded = True

            first_node = agent_run.next_node  # start with the first node
            assert isinstance(first_node, _agent_graph.UserPromptNode)  # the first node should be a user prompt node
            node: _agent_graph.AgentNode[Any, Any] = first_node
            while not yielded:
                graph_ctx = agent_run.ctx
                if self.is_model_request_node(node):
                    async with node.stream(graph_ctx) as stream:
                        final_result_event = None

                        async def stream_to_final(
                            stream: AgentStream,
                        ) -> AsyncIterator[_messages.ModelResponseStreamEvent]:
                            nonlocal final_result_event
                            async for event in stream:
                                yield event
                                if isinstance(event, _messages.FinalResultEvent):
                                    final_result_event = event
                                    break

                        run_ctx = _agent_graph.build_run_context(graph_ctx)
                        wrapped = await graph_ctx.deps.root_capability.wrap_run_event_stream(
                            run_ctx, stream=stream_to_final(stream)
                        )
                        if event_stream_handler is not None:
                            await event_stream_handler(run_ctx, wrapped)
                        else:
                            async for _ in wrapped:
                                pass

                        if final_result_event is not None:
                            final_result = FinalResult(
                                None, final_result_event.tool_name, final_result_event.tool_call_id
                            )
                            if yielded:
                                raise exceptions.AgentRunError('Agent run produced final results')  # pragma: no cover
                            yielded = True

                            messages = graph_ctx.state.message_history.copy()

                            async def on_complete() -> None:
                                """Called when the stream has completed.

                                The model response will have been added to messages by now
                                by `StreamedRunResult._marked_completed`.
                                """
                                nonlocal final_result
                                final_result = FinalResult(
                                    await stream.get_output(), final_result.tool_name, final_result.tool_call_id
                                )

                                # When we get here, the `ModelRequestNode` has completed streaming after the final result was found.
                                # When running an agent with `agent.run`, we'd then move to `CallToolsNode` to execute the tool calls and
                                # find the final result.
                                # We also want to execute tool calls (in case `agent.end_strategy == 'exhaustive'`) here, but
                                # we don't want to use run the `CallToolsNode` logic to determine the final output, as it would be
                                # wasteful and could produce a different result (e.g. when text output is followed by tool calls).
                                # So we call `process_tool_calls` directly and then end the run with the found final result.

                                parts: list[_messages.ModelRequestPart] = []
                                async for _event in _agent_graph.process_tool_calls(
                                    tool_manager=graph_ctx.deps.tool_manager,
                                    tool_calls=stream.response.tool_calls,
                                    tool_call_results=None,
                                    tool_call_metadata=None,
                                    final_result=final_result,
                                    ctx=graph_ctx,
                                    output_parts=parts,
                                ):
                                    pass

                                # To allow this message history to be used in a future run without dangling tool calls,
                                # append a new ModelRequest using the tool returns and retries
                                if parts:
                                    messages.append(
                                        _messages.ModelRequest(
                                            parts, run_id=graph_ctx.state.run_id, timestamp=_utils.now_utc()
                                        )
                                    )

                                await agent_run.next(_agent_graph.SetFinalResult(final_result))

                            yield StreamedRunResult(
                                messages,
                                graph_ctx.deps.new_message_index,
                                stream,
                                on_complete,
                            )
                            break
                elif self.is_call_tools_node(node) and event_stream_handler is not None:
                    async with node.stream(agent_run.ctx) as stream:
                        run_ctx = _agent_graph.build_run_context(agent_run.ctx)
                        wrapped = await agent_run.ctx.deps.root_capability.wrap_run_event_stream(run_ctx, stream=stream)
                        await event_stream_handler(run_ctx, wrapped)

                next_node = await agent_run.next(node)
                if isinstance(next_node, End) and agent_run.result is not None:
                    # A final output could have been produced by the CallToolsNode rather than the ModelRequestNode,
                    # if a tool function raised CallDeferred or ApprovalRequired.
                    # In this case there's no response to stream, but we still let the user access the output etc as normal.
                    yield StreamedRunResult(
                        graph_ctx.state.message_history,
                        graph_ctx.deps.new_message_index,
                        run_result=agent_run.result,
                    )
                    yielded = True
                    break
                if not isinstance(next_node, _agent_graph.AgentNode):
                    raise exceptions.AgentRunError(  # pragma: no cover
                        'Should have produced a StreamedRunResult before getting here'
                    )
                node = cast(_agent_graph.AgentNode[Any, Any], next_node)

        if not yielded:
            raise exceptions.AgentRunError('Agent run finished without producing a final result')  # pragma: no cover

    @overload
    def run_stream_sync(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> result.StreamedRunResultSync[AgentDepsT, OutputDataT]: ...

    @overload
    def run_stream_sync(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT],
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> result.StreamedRunResultSync[AgentDepsT, RunOutputDataT]: ...

    def run_stream_sync(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT] | None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> result.StreamedRunResultSync[AgentDepsT, Any]:
        """Run the agent with a user prompt in sync streaming mode.

        This is a convenience method that wraps [`run_stream()`][pydantic_ai.agent.AbstractAgent.run_stream] with `loop.run_until_complete(...)`.
        You therefore can't use this method inside async code or if there's an active event loop.

        This method builds an internal agent graph (using system prompts, tools and output schemas) and then
        runs the graph until the model produces output matching the `output_type`, for example text or structured data.
        At this point, a streaming run result object is yielded from which you can stream the output as it comes in,
        and -- once this output has completed streaming -- get the complete output, message history, and usage.

        As this method will consider the first output matching the `output_type` to be the final output,
        it will stop running the agent graph and will not execute any tool calls made by the model after this "final" output.
        If you want to always run the agent graph to completion and stream events and output at the same time,
        use [`agent.run()`][pydantic_ai.agent.AbstractAgent.run] with an `event_stream_handler` or [`agent.iter()`][pydantic_ai.agent.AbstractAgent.iter] instead.

        Example:
        ```python
        from pydantic_ai import Agent

        agent = Agent('openai:gpt-5.2')

        def main():
            response = agent.run_stream_sync('What is the capital of the UK?')
            print(response.get_output())
            #> The capital of the UK is London.
        ```

        Args:
            user_prompt: User input to start/continue the conversation.
            output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
                output validators since output validators would expect an argument that matches the agent's output type.
            message_history: History of the conversation so far.
            deferred_tool_results: Optional results for deferred tool calls in the message history.
            model: Optional model to use for this run, required if `model` was not set when creating the agent.
            deps: Optional dependencies to use for this run.
            model_settings: Optional settings to use for this model's request, or a callable
                that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
                Callables are called before each model request, allowing dynamic per-step settings.
            usage_limits: Optional limits on model request count or token usage.
            usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
            metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
                [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
            infer_name: Whether to try to infer the agent name from the call frame if it's not set.
            toolsets: Optional additional toolsets for this run.
            builtin_tools: Optional additional builtin tools for this run.
            event_stream_handler: Optional handler for events from the model's streaming response and the agent's execution of tools to use for this run.
                It will receive all the events up until the final result is found, which you can then read or stream from inside the context manager.
                Note that it does _not_ receive any events after the final result is found.
            spec: Optional agent spec to apply for this run. At run time, spec values are additive.

        Returns:
            The result of the run.
        """
        if infer_name and self.name is None:
            self._infer_name(inspect.currentframe())

        async def _consume_stream():
            async with self.run_stream(
                user_prompt,
                output_type=output_type,
                message_history=message_history,
                deferred_tool_results=deferred_tool_results,
                model=model,
                deps=deps,
                model_settings=model_settings,
                usage_limits=usage_limits,
                usage=usage,
                metadata=metadata,
                infer_name=infer_name,
                toolsets=toolsets,
                builtin_tools=builtin_tools,
                event_stream_handler=event_stream_handler,
                spec=spec,
            ) as stream_result:
                yield stream_result

        async_result = _utils.get_event_loop().run_until_complete(anext(_consume_stream()))
        return result.StreamedRunResultSync(async_result)

    @overload
    def run_stream_events(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AsyncIterator[_messages.AgentStreamEvent | AgentRunResultEvent[OutputDataT]]: ...

    @overload
    def run_stream_events(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT],
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AsyncIterator[_messages.AgentStreamEvent | AgentRunResultEvent[RunOutputDataT]]: ...

    def run_stream_events(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT] | None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AsyncIterator[_messages.AgentStreamEvent | AgentRunResultEvent[Any]]:
        """Run the agent with a user prompt in async mode and stream events from the run.

        This is a convenience method that wraps [`self.run`][pydantic_ai.agent.AbstractAgent.run] and
        uses the `event_stream_handler` kwarg to get a stream of events from the run.

        Example:
        ```python
        from pydantic_ai import Agent, AgentRunResultEvent, AgentStreamEvent

        agent = Agent('openai:gpt-5.2')

        async def main():
            events: list[AgentStreamEvent | AgentRunResultEvent] = []
            async for event in agent.run_stream_events('What is the capital of France?'):
                events.append(event)
            print(events)
            '''
            [
                PartStartEvent(index=0, part=TextPart(content='The capital of ')),
                FinalResultEvent(tool_name=None, tool_call_id=None),
                PartDeltaEvent(index=0, delta=TextPartDelta(content_delta='France is Paris. ')),
                PartEndEvent(
                    index=0, part=TextPart(content='The capital of France is Paris. ')
                ),
                AgentRunResultEvent(
                    result=AgentRunResult(output='The capital of France is Paris. ')
                ),
            ]
            '''
        ```

        Arguments are the same as for [`self.run`][pydantic_ai.agent.AbstractAgent.run],
        except that `event_stream_handler` is now allowed.

        Args:
            user_prompt: User input to start/continue the conversation.
            output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
                output validators since output validators would expect an argument that matches the agent's output type.
            message_history: History of the conversation so far.
            deferred_tool_results: Optional results for deferred tool calls in the message history.
            model: Optional model to use for this run, required if `model` was not set when creating the agent.
            instructions: Optional additional instructions to use for this run.
            deps: Optional dependencies to use for this run.
            model_settings: Optional settings to use for this model's request, or a callable
                that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
                Callables are called before each model request, allowing dynamic per-step settings.
            usage_limits: Optional limits on model request count or token usage.
            usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
            metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
                [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
            infer_name: Whether to try to infer the agent name from the call frame if it's not set.
            toolsets: Optional additional toolsets for this run.
            builtin_tools: Optional additional builtin tools for this run.
            spec: Optional agent spec to apply for this run. At run time, spec values are additive.

        Returns:
            An async iterable of stream events `AgentStreamEvent` and finally a `AgentRunResultEvent` with the final
            run result.
        """
        if infer_name and self.name is None:
            self._infer_name(inspect.currentframe())

        # unfortunately this hack of returning a generator rather than defining it right here is
        # required to allow overloads of this method to work in python's typing system, or at least with pyright
        # or at least I couldn't make it work without
        return self._run_stream_events(
            user_prompt,
            output_type=output_type,
            message_history=message_history,
            deferred_tool_results=deferred_tool_results,
            model=model,
            instructions=instructions,
            deps=deps,
            model_settings=model_settings,
            usage_limits=usage_limits,
            usage=usage,
            metadata=metadata,
            toolsets=toolsets,
            builtin_tools=builtin_tools,
            spec=spec,
        )

    async def _run_stream_events(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT] | None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AsyncIterator[_messages.AgentStreamEvent | AgentRunResultEvent[Any]]:
        send_stream, receive_stream = anyio.create_memory_object_stream[
            _messages.AgentStreamEvent | AgentRunResultEvent[Any]
        ]()

        async def event_stream_handler(
            _: RunContext[AgentDepsT], events: AsyncIterable[_messages.AgentStreamEvent]
        ) -> None:
            async for event in events:
                await send_stream.send(event)

        async def run_agent() -> AgentRunResult[Any]:
            async with send_stream:
                return await self.run(
                    user_prompt,
                    output_type=output_type,
                    message_history=message_history,
                    deferred_tool_results=deferred_tool_results,
                    model=model,
                    instructions=instructions,
                    deps=deps,
                    model_settings=model_settings,
                    usage_limits=usage_limits,
                    usage=usage,
                    metadata=metadata,
                    infer_name=False,
                    toolsets=toolsets,
                    builtin_tools=builtin_tools,
                    event_stream_handler=event_stream_handler,
                    spec=spec,
                )

        task = asyncio.create_task(run_agent())

        try:
            async with receive_stream:
                async for message in receive_stream:
                    yield message

            result = await task

        except asyncio.CancelledError as e:
            task.cancel(msg=e.args[0] if len(e.args) != 0 else None)
            raise

        yield AgentRunResultEvent(result)

    @overload
    def iter(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AbstractAsyncContextManager[AgentRun[AgentDepsT, OutputDataT]]: ...

    @overload
    def iter(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT],
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AbstractAsyncContextManager[AgentRun[AgentDepsT, RunOutputDataT]]: ...

    @asynccontextmanager
    @abstractmethod
    async def iter(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT] | None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AsyncIterator[AgentRun[AgentDepsT, Any]]:
        """A contextmanager which can be used to iterate over the agent graph's nodes as they are executed.

        This method builds an internal agent graph (using system prompts, tools and output schemas) and then returns an
        `AgentRun` object. The `AgentRun` can be used to async-iterate over the nodes of the graph as they are
        executed. This is the API to use if you want to consume the outputs coming from each LLM model response, or the
        stream of events coming from the execution of tools.

        The `AgentRun` also provides methods to access the full message history, new messages, and usage statistics,
        and the final result of the run once it has completed.

        For more details, see the documentation of `AgentRun`.

        Example:
        ```python
        from pydantic_ai import Agent

        agent = Agent('openai:gpt-5.2')

        async def main():
            nodes = []
            async with agent.iter('What is the capital of France?') as agent_run:
                async for node in agent_run:
                    nodes.append(node)
            print(nodes)
            '''
            [
                ModelRequestNode(
                    request=ModelRequest(
                        parts=[
                            UserPromptPart(
                                content='What is the capital of France?',
                                timestamp=datetime.datetime(...),
                            )
                        ],
                        timestamp=datetime.datetime(...),
                        run_id='...',
                    )
                ),
                CallToolsNode(
                    model_response=ModelResponse(
                        parts=[TextPart(content='The capital of France is Paris.')],
                        usage=RequestUsage(input_tokens=56, output_tokens=7),
                        model_name='gpt-5.2',
                        timestamp=datetime.datetime(...),
                        run_id='...',
                    )
                ),
                End(data=FinalResult(output='The capital of France is Paris.')),
            ]
            '''
            print(agent_run.result.output)
            #> The capital of France is Paris.
        ```

        Args:
            user_prompt: User input to start/continue the conversation.
            output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
                output validators since output validators would expect an argument that matches the agent's output type.
            message_history: History of the conversation so far.
            deferred_tool_results: Optional results for deferred tool calls in the message history.
            model: Optional model to use for this run, required if `model` was not set when creating the agent.
            instructions: Optional additional instructions to use for this run.
            deps: Optional dependencies to use for this run.
            model_settings: Optional settings to use for this model's request, or a callable
                that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
                Callables are called before each model request, allowing dynamic per-step settings.
            usage_limits: Optional limits on model request count or token usage.
            usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
            metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
                [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
            infer_name: Whether to try to infer the agent name from the call frame if it's not set.
            toolsets: Optional additional toolsets for this run.
            builtin_tools: Optional additional builtin tools for this run.
            spec: Optional agent spec to apply for this run. At run time, spec values are additive.

        Returns:
            The result of the run.
        """
        raise NotImplementedError
        yield

    @contextmanager
    @abstractmethod
    def override(
        self,
        *,
        name: str | _utils.Unset = _utils.UNSET,
        deps: AgentDepsT | _utils.Unset = _utils.UNSET,
        model: models.Model | models.KnownModelName | str | _utils.Unset = _utils.UNSET,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | _utils.Unset = _utils.UNSET,
        tools: Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] | _utils.Unset = _utils.UNSET,
        instructions: _instructions.AgentInstructions[AgentDepsT] | _utils.Unset = _utils.UNSET,
        model_settings: AgentModelSettings[AgentDepsT] | _utils.Unset = _utils.UNSET,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> Iterator[None]:
        """Context manager to temporarily override agent name, dependencies, model, toolsets, tools, or instructions.

        This is particularly useful when testing.
        You can find an example of this [here](../testing.md#overriding-model-via-pytest-fixtures).

        Args:
            name: The name to use instead of the name passed to the agent constructor and agent run.
            deps: The dependencies to use instead of the dependencies passed to the agent run.
            model: The model to use instead of the model passed to the agent run.
            toolsets: The toolsets to use instead of the toolsets passed to the agent constructor and agent run.
            tools: The tools to use instead of the tools registered with the agent.
            instructions: The instructions to use instead of the instructions registered with the agent.
            model_settings: The model settings to use instead of the model settings passed to the agent constructor.
                When set, any per-run `model_settings` argument is ignored.
            spec: Optional agent spec providing defaults for override.
        """
        raise NotImplementedError
        yield

    def _infer_name(self, function_frame: FrameType | None) -> None:
        """Infer the agent name from the call frame.

        RunUsage should be `self._infer_name(inspect.currentframe())`.
        """
        assert self.name is None, 'Name already set'
        if function_frame is not None:  # pragma: no branch
            if parent_frame := function_frame.f_back:  # pragma: no branch
                for name, item in parent_frame.f_locals.items():
                    if item is self:
                        self.name = name
                        return
                if parent_frame.f_locals != parent_frame.f_globals:  # pragma: no branch
                    # if we couldn't find the agent in locals and globals are a different dict, try globals
                    for name, item in parent_frame.f_globals.items():
                        if item is self:
                            self.name = name
                            return

    @staticmethod
    @contextmanager
    def parallel_tool_call_execution_mode(mode: _tool_manager.ParallelExecutionMode = 'parallel') -> Iterator[None]:
        """Set the parallel execution mode during the context.

        Args:
            mode: The execution mode for tool calls:
                - 'parallel': Run tool calls in parallel, yielding events as they complete (default).
                - 'sequential': Run tool calls one at a time in order.
                - 'parallel_ordered_events': Run tool calls in parallel, but events are emitted in order, after all calls complete.
        """
        with ToolManager.parallel_execution_mode(mode):
            yield

    @staticmethod
    @contextmanager
    @deprecated('Use `parallel_execution_mode("sequential")` instead.')
    def sequential_tool_calls() -> Iterator[None]:
        """Run tool calls sequentially during the context."""
        with ToolManager.parallel_execution_mode('sequential'):
            yield

    @staticmethod
    def is_model_request_node(
        node: _agent_graph.AgentNode[T, S] | End[result.FinalResult[S]],
    ) -> TypeIs[_agent_graph.ModelRequestNode[T, S]]:
        """Check if the node is a `ModelRequestNode`, narrowing the type if it is.

        This method preserves the generic parameters while narrowing the type, unlike a direct call to `isinstance`.
        """
        return isinstance(node, _agent_graph.ModelRequestNode)

    @staticmethod
    def is_call_tools_node(
        node: _agent_graph.AgentNode[T, S] | End[result.FinalResult[S]],
    ) -> TypeIs[_agent_graph.CallToolsNode[T, S]]:
        """Check if the node is a `CallToolsNode`, narrowing the type if it is.

        This method preserves the generic parameters while narrowing the type, unlike a direct call to `isinstance`.
        """
        return isinstance(node, _agent_graph.CallToolsNode)

    @staticmethod
    def is_user_prompt_node(
        node: _agent_graph.AgentNode[T, S] | End[result.FinalResult[S]],
    ) -> TypeIs[_agent_graph.UserPromptNode[T, S]]:
        """Check if the node is a `UserPromptNode`, narrowing the type if it is.

        This method preserves the generic parameters while narrowing the type, unlike a direct call to `isinstance`.
        """
        return isinstance(node, _agent_graph.UserPromptNode)

    @staticmethod
    def is_end_node(
        node: _agent_graph.AgentNode[T, S] | End[result.FinalResult[S]],
    ) -> TypeIs[End[result.FinalResult[S]]]:
        """Check if the node is a `End`, narrowing the type if it is.

        This method preserves the generic parameters while narrowing the type, unlike a direct call to `isinstance`.
        """
        return isinstance(node, End)

    @abstractmethod
    async def __aenter__(self) -> AbstractAgent[AgentDepsT, OutputDataT]:
        raise NotImplementedError

    @abstractmethod
    async def __aexit__(self, *args: Any) -> bool | None:
        raise NotImplementedError

    # TODO (v2): Remove in favor of using `AGUIApp` directly -- we don't have `to_temporal()` or `to_vercel_ai()` either.
    def to_ag_ui(
        self,
        *,
        # Agent.iter parameters
        output_type: OutputSpec[OutputDataT] | None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        deps: AgentDepsT = None,
        model_settings: ModelSettings | None = None,
        usage_limits: UsageLimits | None = None,
        usage: RunUsage | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        # Starlette
        debug: bool = False,
        routes: Sequence[BaseRoute] | None = None,
        middleware: Sequence[Middleware] | None = None,
        exception_handlers: Mapping[Any, ExceptionHandler] | None = None,
        on_startup: Sequence[Callable[[], Any]] | None = None,
        on_shutdown: Sequence[Callable[[], Any]] | None = None,
        lifespan: Lifespan[AGUIApp[AgentDepsT, OutputDataT]] | None = None,
    ) -> AGUIApp[AgentDepsT, OutputDataT]:
        """Returns an ASGI application that handles every AG-UI request by running the agent.

        Note that the `deps` will be the same for each request, with the exception of the AG-UI state that's
        injected into the `state` field of a `deps` object that implements the [`StateHandler`][pydantic_ai.ag_ui.StateHandler] protocol.
        To provide different `deps` for each request (e.g. based on the authenticated user),
        use [`pydantic_ai.ag_ui.run_ag_ui`][pydantic_ai.ag_ui.run_ag_ui] or
        [`pydantic_ai.ag_ui.handle_ag_ui_request`][pydantic_ai.ag_ui.handle_ag_ui_request] instead.

        Example:
        ```python
        from pydantic_ai import Agent

        agent = Agent('openai:gpt-5.2')
        app = agent.to_ag_ui()
        ```

        The `app` is an ASGI application that can be used with any ASGI server.

        To run the application, you can use the following command:

        ```bash
        uvicorn app:app --host 0.0.0.0 --port 8000
        ```

        See [AG-UI docs](../ui/ag-ui.md) for more information.

        Args:
            output_type: Custom output type to use for this run, `output_type` may only be used if the agent has
                no output validators since output validators would expect an argument that matches the agent's
                output type.
            message_history: History of the conversation so far.
            deferred_tool_results: Optional results for deferred tool calls in the message history.
            model: Optional model to use for this run, required if `model` was not set when creating the agent.
            deps: Optional dependencies to use for this run.
            model_settings: Optional settings to use for this model's request.
            usage_limits: Optional limits on model request count or token usage.
            usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
            infer_name: Whether to try to infer the agent name from the call frame if it's not set.
            toolsets: Optional additional toolsets for this run.

            debug: Boolean indicating if debug tracebacks should be returned on errors.
            routes: A list of routes to serve incoming HTTP and WebSocket requests.
            middleware: A list of middleware to run for every request. A starlette application will always
                automatically include two middleware classes. `ServerErrorMiddleware` is added as the very
                outermost middleware, to handle any uncaught errors occurring anywhere in the entire stack.
                `ExceptionMiddleware` is added as the very innermost middleware, to deal with handled
                exception cases occurring in the routing or endpoints.
            exception_handlers: A mapping of either integer status codes, or exception class types onto
                callables which handle the exceptions. Exception handler callables should be of the form
                `handler(request, exc) -> response` and may be either standard functions, or async functions.
            on_startup: A list of callables to run on application startup. Startup handler callables do not
                take any arguments, and may be either standard functions, or async functions.
            on_shutdown: A list of callables to run on application shutdown. Shutdown handler callables do
                not take any arguments, and may be either standard functions, or async functions.
            lifespan: A lifespan context function, which can be used to perform startup and shutdown tasks.
                This is a newer style that replaces the `on_startup` and `on_shutdown` handlers. Use one or
                the other, not both.

        Returns:
            An ASGI application for running Pydantic AI agents with AG-UI protocol support.
        """
        from pydantic_ai.ui.ag_ui.app import AGUIApp

        return AGUIApp(
            agent=self,
            # Agent.iter parameters
            output_type=output_type,
            message_history=message_history,
            deferred_tool_results=deferred_tool_results,
            model=model,
            deps=deps,
            model_settings=model_settings,
            usage_limits=usage_limits,
            usage=usage,
            infer_name=infer_name,
            toolsets=toolsets,
            # Starlette
            debug=debug,
            routes=routes,
            middleware=middleware,
            exception_handlers=exception_handlers,
            on_startup=on_startup,
            on_shutdown=on_shutdown,
            lifespan=lifespan,
        )

    def to_a2a(
        self,
        *,
        storage: Storage | None = None,
        broker: Broker | None = None,
        # Agent card
        name: str | None = None,
        url: str = 'http://localhost:8000',
        version: str = '1.0.0',
        description: str | None = None,
        provider: AgentProvider | None = None,
        skills: list[Skill] | None = None,
        # Starlette
        debug: bool = False,
        routes: Sequence[Route] | None = None,
        middleware: Sequence[Middleware] | None = None,
        exception_handlers: dict[Any, ExceptionHandler] | None = None,
        lifespan: Lifespan[FastA2A] | None = None,
    ) -> FastA2A:
        """Convert the agent to a FastA2A application.

        Example:
        ```python
        from pydantic_ai import Agent

        agent = Agent('openai:gpt-5.2')
        app = agent.to_a2a()
        ```

        The `app` is an ASGI application that can be used with any ASGI server.

        To run the application, you can use the following command:

        ```bash
        uvicorn app:app --host 0.0.0.0 --port 8000
        ```
        """
        from .._a2a import agent_to_a2a

        return agent_to_a2a(
            self,
            storage=storage,
            broker=broker,
            name=name,
            url=url,
            version=version,
            description=description,
            provider=provider,
            skills=skills,
            debug=debug,
            routes=routes,
            middleware=middleware,
            exception_handlers=exception_handlers,
            lifespan=lifespan,
        )

    async def to_cli(
        self: Self,
        deps: AgentDepsT = None,
        prog_name: str = 'pydantic-ai',
        message_history: Sequence[_messages.ModelMessage] | None = None,
        model_settings: ModelSettings | None = None,
        usage_limits: _usage.UsageLimits | None = None,
    ) -> None:
        """Run the agent in a CLI chat interface.

        Args:
            deps: The dependencies to pass to the agent.
            prog_name: The name of the program to use for the CLI. Defaults to 'pydantic-ai'.
            message_history: History of the conversation so far.
            model_settings: Optional settings to use for this model's request.
            usage_limits: Optional limits on model request count or token usage.

        Example:
        ```python {title="agent_to_cli.py" test="skip"}
        from pydantic_ai import Agent

        agent = Agent('openai:gpt-5.2', instructions='You always respond in Italian.')

        async def main():
            await agent.to_cli()
        ```
        """
        from rich.console import Console

        from pydantic_ai._cli import run_chat

        await run_chat(
            stream=True,
            agent=self,
            deps=deps,
            console=Console(),
            code_theme='monokai',
            prog_name=prog_name,
            message_history=message_history,
            model_settings=model_settings,
            usage_limits=usage_limits,
        )

    def to_cli_sync(
        self: Self,
        deps: AgentDepsT = None,
        prog_name: str = 'pydantic-ai',
        message_history: Sequence[_messages.ModelMessage] | None = None,
        model_settings: ModelSettings | None = None,
        usage_limits: _usage.UsageLimits | None = None,
    ) -> None:
        """Run the agent in a CLI chat interface with the non-async interface.

        Args:
            deps: The dependencies to pass to the agent.
            prog_name: The name of the program to use for the CLI. Defaults to 'pydantic-ai'.
            message_history: History of the conversation so far.
            model_settings: Optional settings to use for this model's request.
            usage_limits: Optional limits on model request count or token usage.

        ```python {title="agent_to_cli_sync.py" test="skip"}
        from pydantic_ai import Agent

        agent = Agent('openai:gpt-5.2', instructions='You always respond in Italian.')
        agent.to_cli_sync()
        agent.to_cli_sync(prog_name='assistant')
        ```
        """
        return _utils.get_event_loop().run_until_complete(
            self.to_cli(
                deps=deps,
                prog_name=prog_name,
                message_history=message_history,
                model_settings=model_settings,
                usage_limits=usage_limits,
            )
        )

model abstractmethod property

model: Model | KnownModelName | str | None

The default model configured for this agent.

name abstractmethod property writable

name: str | None

The name of the agent, used for logging.

If None, we try to infer the agent name from the call frame when the agent is first run.

description abstractmethod property writable

description: str | None

A human-readable description of the agent.

deps_type abstractmethod property

deps_type: type

The type of dependencies used by the agent.

output_type abstractmethod property

output_type: OutputSpec[OutputDataT]

The type of data output by agent runs, used to validate the data returned by the model, defaults to str.

event_stream_handler abstractmethod property

event_stream_handler: EventStreamHandler[AgentDepsT] | None

Optional handler for events from the model's streaming response and the agent's execution of tools.

toolsets abstractmethod property

toolsets: Sequence[AbstractToolset[AgentDepsT]]

All toolsets registered on the agent.

Output tools are not included.

output_json_schema

output_json_schema(
    output_type: (
        OutputSpec[OutputDataT | RunOutputDataT] | None
    ) = None,
) -> JsonSchema

The output return JSON schema.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

def output_json_schema(self, output_type: OutputSpec[OutputDataT | RunOutputDataT] | None = None) -> JsonSchema:
    """The output return JSON schema."""
    if output_type is None:
        output_type = self.output_type

    return_types = types_from_output_spec(output_spec=output_type)

    json_schemas: list[JsonSchema] = []
    for return_type in return_types:
        json_schema = TypeAdapter(return_type).json_schema(mode='serialization')
        if json_schema not in json_schemas:
            json_schemas.append(json_schema)

    if len(json_schemas) == 1:
        return json_schemas[0]
    else:
        json_schemas, all_defs = _utils.merge_json_schema_defs(json_schemas)
        json_schema: JsonSchema = {'anyOf': json_schemas}
        if all_defs:
            json_schema['$defs'] = all_defs
        return json_schema

run async

run(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AgentRunResult[OutputDataT]

run(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT],
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AgentRunResult[RunOutputDataT]

run(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AgentRunResult[Any]

Run the agent with a user prompt in async mode.

This method builds an internal agent graph (using system prompts, tools and output schemas) and then runs the graph to completion. The result of the run is returned.

Example:

from pydantic_ai import Agent

agent = Agent('openai:gpt-5.2')

async def main():
    agent_run = await agent.run('What is the capital of France?')
    print(agent_run.output)
    #> The capital of France is Paris.

Parameters:

Name	Type	Description	Default
user_prompt	str | Sequence[UserContent] | None	User input to start/continue the conversation.	None
output_type	OutputSpec[RunOutputDataT] | None	Custom output type to use for this run, output_type may only be used if the agent has no output validators since output validators would expect an argument that matches the agent's output type.	None
message_history	Sequence[ModelMessage] | None	History of the conversation so far.	None
deferred_tool_results	DeferredToolResults | None	Optional results for deferred tool calls in the message history.	None
model	Model | KnownModelName | str | None	Optional model to use for this run, required if model was not set when creating the agent.	None
instructions	AgentInstructions[AgentDepsT]	Optional additional instructions to use for this run.	None
deps	AgentDepsT	Optional dependencies to use for this run.	None
model_settings	AgentModelSettings[AgentDepsT] | None	Optional settings to use for this model's request, or a callable that receives RunContext and returns settings. Callables are called before each model request, allowing dynamic per-step settings.	None
usage_limits	UsageLimits | None	Optional limits on model request count or token usage.	None
usage	RunUsage | None	Optional usage to start with, useful for resuming a conversation or agents used in tools.	None
metadata	AgentMetadata[AgentDepsT] | None	Optional metadata to attach to this run. Accepts a dictionary or a callable taking RunContext; merged with the agent's configured metadata.	None
infer_name	bool	Whether to try to infer the agent name from the call frame if it's not set.	True
toolsets	Sequence[AbstractToolset[AgentDepsT]] | None	Optional additional toolsets for this run.	None
event_stream_handler	EventStreamHandler[AgentDepsT] | None	Optional handler for events from the model's streaming response and the agent's execution of tools to use for this run.	None
builtin_tools	Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None	Optional additional builtin tools for this run.	None
spec	dict[str, Any] | AgentSpec | None	Optional agent spec to apply for this run. At run time, spec values are additive.	None

Returns:

Type	Description
AgentRunResult[Any]	The result of the run.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

async def run(
    self,
    user_prompt: str | Sequence[_messages.UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[_messages.ModelMessage] | None = None,
    deferred_tool_results: DeferredToolResults | None = None,
    model: models.Model | models.KnownModelName | str | None = None,
    instructions: _instructions.AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: AgentModelSettings[AgentDepsT] | None = None,
    usage_limits: _usage.UsageLimits | None = None,
    usage: _usage.RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
    builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
    event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
    spec: dict[str, Any] | AgentSpec | None = None,
) -> AgentRunResult[Any]:
    """Run the agent with a user prompt in async mode.

    This method builds an internal agent graph (using system prompts, tools and output schemas) and then
    runs the graph to completion. The result of the run is returned.

    Example:
    ```python
    from pydantic_ai import Agent

    agent = Agent('openai:gpt-5.2')

    async def main():
        agent_run = await agent.run('What is the capital of France?')
        print(agent_run.output)
        #> The capital of France is Paris.
    ```

    Args:
        user_prompt: User input to start/continue the conversation.
        output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
            output validators since output validators would expect an argument that matches the agent's output type.
        message_history: History of the conversation so far.
        deferred_tool_results: Optional results for deferred tool calls in the message history.
        model: Optional model to use for this run, required if `model` was not set when creating the agent.
        instructions: Optional additional instructions to use for this run.
        deps: Optional dependencies to use for this run.
        model_settings: Optional settings to use for this model's request, or a callable
            that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
            Callables are called before each model request, allowing dynamic per-step settings.
        usage_limits: Optional limits on model request count or token usage.
        usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
        metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
            [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
        infer_name: Whether to try to infer the agent name from the call frame if it's not set.
        toolsets: Optional additional toolsets for this run.
        event_stream_handler: Optional handler for events from the model's streaming response and the agent's execution of tools to use for this run.
        builtin_tools: Optional additional builtin tools for this run.
        spec: Optional agent spec to apply for this run. At run time, spec values are additive.

    Returns:
        The result of the run.
    """
    if infer_name and self.name is None:
        self._infer_name(inspect.currentframe())

    event_stream_handler = event_stream_handler or self.event_stream_handler

    async with self.iter(
        user_prompt=user_prompt,
        output_type=output_type,
        message_history=message_history,
        deferred_tool_results=deferred_tool_results,
        model=model,
        instructions=instructions,
        deps=deps,
        model_settings=model_settings,
        usage_limits=usage_limits,
        usage=usage,
        metadata=metadata,
        toolsets=toolsets,
        builtin_tools=builtin_tools,
        spec=spec,
    ) as agent_run:
        async for node in agent_run:
            if event_stream_handler is not None and (
                self.is_model_request_node(node) or self.is_call_tools_node(node)
            ):
                async with node.stream(agent_run.ctx) as stream:
                    run_ctx = _agent_graph.build_run_context(agent_run.ctx)
                    wrapped = await agent_run.ctx.deps.root_capability.wrap_run_event_stream(run_ctx, stream=stream)
                    await event_stream_handler(run_ctx, wrapped)

    assert agent_run.result is not None, 'The graph run did not finish properly'
    return agent_run.result

run_sync

run_sync(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AgentRunResult[OutputDataT]

run_sync(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT],
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AgentRunResult[RunOutputDataT]

run_sync(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AgentRunResult[Any]

Synchronously run the agent with a user prompt.

This is a convenience method that wraps self.run with loop.run_until_complete(...). You therefore can't use this method inside async code or if there's an active event loop.

Example:

from pydantic_ai import Agent

agent = Agent('openai:gpt-5.2')

result_sync = agent.run_sync('What is the capital of Italy?')
print(result_sync.output)
#> The capital of Italy is Rome.

Parameters:

Name	Type	Description	Default
user_prompt	str | Sequence[UserContent] | None	User input to start/continue the conversation.	None
output_type	OutputSpec[RunOutputDataT] | None	Custom output type to use for this run, output_type may only be used if the agent has no output validators since output validators would expect an argument that matches the agent's output type.	None
message_history	Sequence[ModelMessage] | None	History of the conversation so far.	None
deferred_tool_results	DeferredToolResults | None	Optional results for deferred tool calls in the message history.	None
model	Model | KnownModelName | str | None	Optional model to use for this run, required if model was not set when creating the agent.	None
instructions	AgentInstructions[AgentDepsT]	Optional additional instructions to use for this run.	None
deps	AgentDepsT	Optional dependencies to use for this run.	None
model_settings	AgentModelSettings[AgentDepsT] | None	Optional settings to use for this model's request, or a callable that receives RunContext and returns settings. Callables are called before each model request, allowing dynamic per-step settings.	None
usage_limits	UsageLimits | None	Optional limits on model request count or token usage.	None
usage	RunUsage | None	Optional usage to start with, useful for resuming a conversation or agents used in tools.	None
metadata	AgentMetadata[AgentDepsT] | None	Optional metadata to attach to this run. Accepts a dictionary or a callable taking RunContext; merged with the agent's configured metadata.	None
infer_name	bool	Whether to try to infer the agent name from the call frame if it's not set.	True
toolsets	Sequence[AbstractToolset[AgentDepsT]] | None	Optional additional toolsets for this run.	None
event_stream_handler	EventStreamHandler[AgentDepsT] | None	Optional handler for events from the model's streaming response and the agent's execution of tools to use for this run.	None
builtin_tools	Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None	Optional additional builtin tools for this run.	None
spec	dict[str, Any] | AgentSpec | None	Optional agent spec to apply for this run. At run time, spec values are additive.	None

Returns:

Type	Description
AgentRunResult[Any]	The result of the run.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

def run_sync(
    self,
    user_prompt: str | Sequence[_messages.UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[_messages.ModelMessage] | None = None,
    deferred_tool_results: DeferredToolResults | None = None,
    model: models.Model | models.KnownModelName | str | None = None,
    instructions: _instructions.AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: AgentModelSettings[AgentDepsT] | None = None,
    usage_limits: _usage.UsageLimits | None = None,
    usage: _usage.RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
    builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
    event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
    spec: dict[str, Any] | AgentSpec | None = None,
) -> AgentRunResult[Any]:
    """Synchronously run the agent with a user prompt.

    This is a convenience method that wraps [`self.run`][pydantic_ai.agent.AbstractAgent.run] with `loop.run_until_complete(...)`.
    You therefore can't use this method inside async code or if there's an active event loop.

    Example:
    ```python
    from pydantic_ai import Agent

    agent = Agent('openai:gpt-5.2')

    result_sync = agent.run_sync('What is the capital of Italy?')
    print(result_sync.output)
    #> The capital of Italy is Rome.
    ```

    Args:
        user_prompt: User input to start/continue the conversation.
        output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
            output validators since output validators would expect an argument that matches the agent's output type.
        message_history: History of the conversation so far.
        deferred_tool_results: Optional results for deferred tool calls in the message history.
        model: Optional model to use for this run, required if `model` was not set when creating the agent.
        instructions: Optional additional instructions to use for this run.
        deps: Optional dependencies to use for this run.
        model_settings: Optional settings to use for this model's request, or a callable
            that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
            Callables are called before each model request, allowing dynamic per-step settings.
        usage_limits: Optional limits on model request count or token usage.
        usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
        metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
            [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
        infer_name: Whether to try to infer the agent name from the call frame if it's not set.
        toolsets: Optional additional toolsets for this run.
        event_stream_handler: Optional handler for events from the model's streaming response and the agent's execution of tools to use for this run.
        builtin_tools: Optional additional builtin tools for this run.
        spec: Optional agent spec to apply for this run. At run time, spec values are additive.

    Returns:
        The result of the run.
    """
    if infer_name and self.name is None:
        self._infer_name(inspect.currentframe())

    return _utils.get_event_loop().run_until_complete(
        self.run(
            user_prompt,
            output_type=output_type,
            message_history=message_history,
            deferred_tool_results=deferred_tool_results,
            model=model,
            instructions=instructions,
            deps=deps,
            model_settings=model_settings,
            usage_limits=usage_limits,
            usage=usage,
            metadata=metadata,
            infer_name=False,
            toolsets=toolsets,
            builtin_tools=builtin_tools,
            event_stream_handler=event_stream_handler,
            spec=spec,
        )
    )

run_stream async

run_stream(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AbstractAsyncContextManager[
    StreamedRunResult[AgentDepsT, OutputDataT]
]

run_stream(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT],
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AbstractAsyncContextManager[
    StreamedRunResult[AgentDepsT, RunOutputDataT]
]

run_stream(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AsyncIterator[StreamedRunResult[AgentDepsT, Any]]

Run the agent with a user prompt in async streaming mode.

This method builds an internal agent graph (using system prompts, tools and output schemas) and then runs the graph until the model produces output matching the output_type, for example text or structured data. At this point, a streaming run result object is yielded from which you can stream the output as it comes in, and -- once this output has completed streaming -- get the complete output, message history, and usage.

As this method will consider the first output matching the output_type to be the final output, it will stop running the agent graph and will not execute any tool calls made by the model after this "final" output. If you want to always run the agent graph to completion and stream events and output at the same time, use agent.run() with an event_stream_handler or agent.iter() instead.

Example:

from pydantic_ai import Agent

agent = Agent('openai:gpt-5.2')

async def main():
    async with agent.run_stream('What is the capital of the UK?') as response:
        print(await response.get_output())
        #> The capital of the UK is London.

Parameters:

Name	Type	Description	Default
user_prompt	str | Sequence[UserContent] | None	User input to start/continue the conversation.	None
output_type	OutputSpec[RunOutputDataT] | None	Custom output type to use for this run, output_type may only be used if the agent has no output validators since output validators would expect an argument that matches the agent's output type.	None
message_history	Sequence[ModelMessage] | None	History of the conversation so far.	None
deferred_tool_results	DeferredToolResults | None	Optional results for deferred tool calls in the message history.	None
model	Model | KnownModelName | str | None	Optional model to use for this run, required if model was not set when creating the agent.	None
instructions	AgentInstructions[AgentDepsT]	Optional additional instructions to use for this run.	None
deps	AgentDepsT	Optional dependencies to use for this run.	None
model_settings	AgentModelSettings[AgentDepsT] | None	Optional settings to use for this model's request, or a callable that receives RunContext and returns settings. Callables are called before each model request, allowing dynamic per-step settings.	None
usage_limits	UsageLimits | None	Optional limits on model request count or token usage.	None
usage	RunUsage | None	Optional usage to start with, useful for resuming a conversation or agents used in tools.	None
metadata	AgentMetadata[AgentDepsT] | None	Optional metadata to attach to this run. Accepts a dictionary or a callable taking RunContext; merged with the agent's configured metadata.	None
infer_name	bool	Whether to try to infer the agent name from the call frame if it's not set.	True
toolsets	Sequence[AbstractToolset[AgentDepsT]] | None	Optional additional toolsets for this run.	None
builtin_tools	Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None	Optional additional builtin tools for this run.	None
event_stream_handler	EventStreamHandler[AgentDepsT] | None	Optional handler for events from the model's streaming response and the agent's execution of tools to use for this run. It will receive all the events up until the final result is found, which you can then read or stream from inside the context manager. Note that it does not receive any events after the final result is found.	None
spec	dict[str, Any] | AgentSpec | None	Optional agent spec to apply for this run. At run time, spec values are additive.	None

Returns:

Type	Description
AsyncIterator[StreamedRunResult[AgentDepsT, Any]]	The result of the run.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

@asynccontextmanager
async def run_stream(  # noqa: C901
    self,
    user_prompt: str | Sequence[_messages.UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[_messages.ModelMessage] | None = None,
    deferred_tool_results: DeferredToolResults | None = None,
    model: models.Model | models.KnownModelName | str | None = None,
    instructions: _instructions.AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: AgentModelSettings[AgentDepsT] | None = None,
    usage_limits: _usage.UsageLimits | None = None,
    usage: _usage.RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
    builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
    event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
    spec: dict[str, Any] | AgentSpec | None = None,
) -> AsyncIterator[result.StreamedRunResult[AgentDepsT, Any]]:
    """Run the agent with a user prompt in async streaming mode.

    This method builds an internal agent graph (using system prompts, tools and output schemas) and then
    runs the graph until the model produces output matching the `output_type`, for example text or structured data.
    At this point, a streaming run result object is yielded from which you can stream the output as it comes in,
    and -- once this output has completed streaming -- get the complete output, message history, and usage.

    As this method will consider the first output matching the `output_type` to be the final output,
    it will stop running the agent graph and will not execute any tool calls made by the model after this "final" output.
    If you want to always run the agent graph to completion and stream events and output at the same time,
    use [`agent.run()`][pydantic_ai.agent.AbstractAgent.run] with an `event_stream_handler` or [`agent.iter()`][pydantic_ai.agent.AbstractAgent.iter] instead.

    Example:
    ```python
    from pydantic_ai import Agent

    agent = Agent('openai:gpt-5.2')

    async def main():
        async with agent.run_stream('What is the capital of the UK?') as response:
            print(await response.get_output())
            #> The capital of the UK is London.
    ```

    Args:
        user_prompt: User input to start/continue the conversation.
        output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
            output validators since output validators would expect an argument that matches the agent's output type.
        message_history: History of the conversation so far.
        deferred_tool_results: Optional results for deferred tool calls in the message history.
        model: Optional model to use for this run, required if `model` was not set when creating the agent.
        instructions: Optional additional instructions to use for this run.
        deps: Optional dependencies to use for this run.
        model_settings: Optional settings to use for this model's request, or a callable
            that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
            Callables are called before each model request, allowing dynamic per-step settings.
        usage_limits: Optional limits on model request count or token usage.
        usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
        metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
            [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
        infer_name: Whether to try to infer the agent name from the call frame if it's not set.
        toolsets: Optional additional toolsets for this run.
        builtin_tools: Optional additional builtin tools for this run.
        event_stream_handler: Optional handler for events from the model's streaming response and the agent's execution of tools to use for this run.
            It will receive all the events up until the final result is found, which you can then read or stream from inside the context manager.
            Note that it does _not_ receive any events after the final result is found.
        spec: Optional agent spec to apply for this run. At run time, spec values are additive.

    Returns:
        The result of the run.
    """
    if infer_name and self.name is None:
        # f_back because `asynccontextmanager` adds one frame
        if frame := inspect.currentframe():  # pragma: no branch
            self._infer_name(frame.f_back)

    event_stream_handler = event_stream_handler or self.event_stream_handler

    yielded = False
    async with self.iter(
        user_prompt,
        output_type=output_type,
        message_history=message_history,
        deferred_tool_results=deferred_tool_results,
        model=model,
        deps=deps,
        instructions=instructions,
        model_settings=model_settings,
        usage_limits=usage_limits,
        usage=usage,
        metadata=metadata,
        infer_name=False,
        toolsets=toolsets,
        builtin_tools=builtin_tools,
        spec=spec,
    ) as agent_run:
        # Handle wrap_run short-circuit: result is already available
        if agent_run.result is not None:
            graph_ctx = agent_run.ctx
            yield StreamedRunResult(
                graph_ctx.state.message_history,
                graph_ctx.deps.new_message_index,
                run_result=agent_run.result,
            )
            yielded = True

        first_node = agent_run.next_node  # start with the first node
        assert isinstance(first_node, _agent_graph.UserPromptNode)  # the first node should be a user prompt node
        node: _agent_graph.AgentNode[Any, Any] = first_node
        while not yielded:
            graph_ctx = agent_run.ctx
            if self.is_model_request_node(node):
                async with node.stream(graph_ctx) as stream:
                    final_result_event = None

                    async def stream_to_final(
                        stream: AgentStream,
                    ) -> AsyncIterator[_messages.ModelResponseStreamEvent]:
                        nonlocal final_result_event
                        async for event in stream:
                            yield event
                            if isinstance(event, _messages.FinalResultEvent):
                                final_result_event = event
                                break

                    run_ctx = _agent_graph.build_run_context(graph_ctx)
                    wrapped = await graph_ctx.deps.root_capability.wrap_run_event_stream(
                        run_ctx, stream=stream_to_final(stream)
                    )
                    if event_stream_handler is not None:
                        await event_stream_handler(run_ctx, wrapped)
                    else:
                        async for _ in wrapped:
                            pass

                    if final_result_event is not None:
                        final_result = FinalResult(
                            None, final_result_event.tool_name, final_result_event.tool_call_id
                        )
                        if yielded:
                            raise exceptions.AgentRunError('Agent run produced final results')  # pragma: no cover
                        yielded = True

                        messages = graph_ctx.state.message_history.copy()

                        async def on_complete() -> None:
                            """Called when the stream has completed.

                            The model response will have been added to messages by now
                            by `StreamedRunResult._marked_completed`.
                            """
                            nonlocal final_result
                            final_result = FinalResult(
                                await stream.get_output(), final_result.tool_name, final_result.tool_call_id
                            )

                            # When we get here, the `ModelRequestNode` has completed streaming after the final result was found.
                            # When running an agent with `agent.run`, we'd then move to `CallToolsNode` to execute the tool calls and
                            # find the final result.
                            # We also want to execute tool calls (in case `agent.end_strategy == 'exhaustive'`) here, but
                            # we don't want to use run the `CallToolsNode` logic to determine the final output, as it would be
                            # wasteful and could produce a different result (e.g. when text output is followed by tool calls).
                            # So we call `process_tool_calls` directly and then end the run with the found final result.

                            parts: list[_messages.ModelRequestPart] = []
                            async for _event in _agent_graph.process_tool_calls(
                                tool_manager=graph_ctx.deps.tool_manager,
                                tool_calls=stream.response.tool_calls,
                                tool_call_results=None,
                                tool_call_metadata=None,
                                final_result=final_result,
                                ctx=graph_ctx,
                                output_parts=parts,
                            ):
                                pass

                            # To allow this message history to be used in a future run without dangling tool calls,
                            # append a new ModelRequest using the tool returns and retries
                            if parts:
                                messages.append(
                                    _messages.ModelRequest(
                                        parts, run_id=graph_ctx.state.run_id, timestamp=_utils.now_utc()
                                    )
                                )

                            await agent_run.next(_agent_graph.SetFinalResult(final_result))

                        yield StreamedRunResult(
                            messages,
                            graph_ctx.deps.new_message_index,
                            stream,
                            on_complete,
                        )
                        break
            elif self.is_call_tools_node(node) and event_stream_handler is not None:
                async with node.stream(agent_run.ctx) as stream:
                    run_ctx = _agent_graph.build_run_context(agent_run.ctx)
                    wrapped = await agent_run.ctx.deps.root_capability.wrap_run_event_stream(run_ctx, stream=stream)
                    await event_stream_handler(run_ctx, wrapped)

            next_node = await agent_run.next(node)
            if isinstance(next_node, End) and agent_run.result is not None:
                # A final output could have been produced by the CallToolsNode rather than the ModelRequestNode,
                # if a tool function raised CallDeferred or ApprovalRequired.
                # In this case there's no response to stream, but we still let the user access the output etc as normal.
                yield StreamedRunResult(
                    graph_ctx.state.message_history,
                    graph_ctx.deps.new_message_index,
                    run_result=agent_run.result,
                )
                yielded = True
                break
            if not isinstance(next_node, _agent_graph.AgentNode):
                raise exceptions.AgentRunError(  # pragma: no cover
                    'Should have produced a StreamedRunResult before getting here'
                )
            node = cast(_agent_graph.AgentNode[Any, Any], next_node)

    if not yielded:
        raise exceptions.AgentRunError('Agent run finished without producing a final result')  # pragma: no cover

run_stream_sync

run_stream_sync(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> StreamedRunResultSync[AgentDepsT, OutputDataT]

run_stream_sync(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT],
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[AbstractBuiltinTool] | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> StreamedRunResultSync[AgentDepsT, RunOutputDataT]

run_stream_sync(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    event_stream_handler: (
        EventStreamHandler[AgentDepsT] | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> StreamedRunResultSync[AgentDepsT, Any]

Run the agent with a user prompt in sync streaming mode.

This is a convenience method that wraps run_stream() with loop.run_until_complete(...). You therefore can't use this method inside async code or if there's an active event loop.

This method builds an internal agent graph (using system prompts, tools and output schemas) and then runs the graph until the model produces output matching the output_type, for example text or structured data. At this point, a streaming run result object is yielded from which you can stream the output as it comes in, and -- once this output has completed streaming -- get the complete output, message history, and usage.

As this method will consider the first output matching the output_type to be the final output, it will stop running the agent graph and will not execute any tool calls made by the model after this "final" output. If you want to always run the agent graph to completion and stream events and output at the same time, use agent.run() with an event_stream_handler or agent.iter() instead.

Example:

from pydantic_ai import Agent

agent = Agent('openai:gpt-5.2')

def main():
    response = agent.run_stream_sync('What is the capital of the UK?')
    print(response.get_output())
    #> The capital of the UK is London.

Parameters:

Name	Type	Description	Default
user_prompt	str | Sequence[UserContent] | None	User input to start/continue the conversation.	None
output_type	OutputSpec[RunOutputDataT] | None	Custom output type to use for this run, output_type may only be used if the agent has no output validators since output validators would expect an argument that matches the agent's output type.	None
message_history	Sequence[ModelMessage] | None	History of the conversation so far.	None
deferred_tool_results	DeferredToolResults | None	Optional results for deferred tool calls in the message history.	None
model	Model | KnownModelName | str | None	Optional model to use for this run, required if model was not set when creating the agent.	None
deps	AgentDepsT	Optional dependencies to use for this run.	None
model_settings	AgentModelSettings[AgentDepsT] | None	Optional settings to use for this model's request, or a callable that receives RunContext and returns settings. Callables are called before each model request, allowing dynamic per-step settings.	None
usage_limits	UsageLimits | None	Optional limits on model request count or token usage.	None
usage	RunUsage | None	Optional usage to start with, useful for resuming a conversation or agents used in tools.	None
metadata	AgentMetadata[AgentDepsT] | None	Optional metadata to attach to this run. Accepts a dictionary or a callable taking RunContext; merged with the agent's configured metadata.	None
infer_name	bool	Whether to try to infer the agent name from the call frame if it's not set.	True
toolsets	Sequence[AbstractToolset[AgentDepsT]] | None	Optional additional toolsets for this run.	None
builtin_tools	Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None	Optional additional builtin tools for this run.	None
event_stream_handler	EventStreamHandler[AgentDepsT] | None	Optional handler for events from the model's streaming response and the agent's execution of tools to use for this run. It will receive all the events up until the final result is found, which you can then read or stream from inside the context manager. Note that it does not receive any events after the final result is found.	None
spec	dict[str, Any] | AgentSpec | None	Optional agent spec to apply for this run. At run time, spec values are additive.	None

Returns:

Type	Description
StreamedRunResultSync[AgentDepsT, Any]	The result of the run.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

def run_stream_sync(
    self,
    user_prompt: str | Sequence[_messages.UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[_messages.ModelMessage] | None = None,
    deferred_tool_results: DeferredToolResults | None = None,
    model: models.Model | models.KnownModelName | str | None = None,
    deps: AgentDepsT = None,
    model_settings: AgentModelSettings[AgentDepsT] | None = None,
    usage_limits: _usage.UsageLimits | None = None,
    usage: _usage.RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
    builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
    event_stream_handler: EventStreamHandler[AgentDepsT] | None = None,
    spec: dict[str, Any] | AgentSpec | None = None,
) -> result.StreamedRunResultSync[AgentDepsT, Any]:
    """Run the agent with a user prompt in sync streaming mode.

    This is a convenience method that wraps [`run_stream()`][pydantic_ai.agent.AbstractAgent.run_stream] with `loop.run_until_complete(...)`.
    You therefore can't use this method inside async code or if there's an active event loop.

    This method builds an internal agent graph (using system prompts, tools and output schemas) and then
    runs the graph until the model produces output matching the `output_type`, for example text or structured data.
    At this point, a streaming run result object is yielded from which you can stream the output as it comes in,
    and -- once this output has completed streaming -- get the complete output, message history, and usage.

    As this method will consider the first output matching the `output_type` to be the final output,
    it will stop running the agent graph and will not execute any tool calls made by the model after this "final" output.
    If you want to always run the agent graph to completion and stream events and output at the same time,
    use [`agent.run()`][pydantic_ai.agent.AbstractAgent.run] with an `event_stream_handler` or [`agent.iter()`][pydantic_ai.agent.AbstractAgent.iter] instead.

    Example:
    ```python
    from pydantic_ai import Agent

    agent = Agent('openai:gpt-5.2')

    def main():
        response = agent.run_stream_sync('What is the capital of the UK?')
        print(response.get_output())
        #> The capital of the UK is London.
    ```

    Args:
        user_prompt: User input to start/continue the conversation.
        output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
            output validators since output validators would expect an argument that matches the agent's output type.
        message_history: History of the conversation so far.
        deferred_tool_results: Optional results for deferred tool calls in the message history.
        model: Optional model to use for this run, required if `model` was not set when creating the agent.
        deps: Optional dependencies to use for this run.
        model_settings: Optional settings to use for this model's request, or a callable
            that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
            Callables are called before each model request, allowing dynamic per-step settings.
        usage_limits: Optional limits on model request count or token usage.
        usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
        metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
            [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
        infer_name: Whether to try to infer the agent name from the call frame if it's not set.
        toolsets: Optional additional toolsets for this run.
        builtin_tools: Optional additional builtin tools for this run.
        event_stream_handler: Optional handler for events from the model's streaming response and the agent's execution of tools to use for this run.
            It will receive all the events up until the final result is found, which you can then read or stream from inside the context manager.
            Note that it does _not_ receive any events after the final result is found.
        spec: Optional agent spec to apply for this run. At run time, spec values are additive.

    Returns:
        The result of the run.
    """
    if infer_name and self.name is None:
        self._infer_name(inspect.currentframe())

    async def _consume_stream():
        async with self.run_stream(
            user_prompt,
            output_type=output_type,
            message_history=message_history,
            deferred_tool_results=deferred_tool_results,
            model=model,
            deps=deps,
            model_settings=model_settings,
            usage_limits=usage_limits,
            usage=usage,
            metadata=metadata,
            infer_name=infer_name,
            toolsets=toolsets,
            builtin_tools=builtin_tools,
            event_stream_handler=event_stream_handler,
            spec=spec,
        ) as stream_result:
            yield stream_result

    async_result = _utils.get_event_loop().run_until_complete(anext(_consume_stream()))
    return result.StreamedRunResultSync(async_result)

run_stream_events

run_stream_events(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AsyncIterator[
    AgentStreamEvent | AgentRunResultEvent[OutputDataT]
]

run_stream_events(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT],
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AsyncIterator[
    AgentStreamEvent | AgentRunResultEvent[RunOutputDataT]
]

run_stream_events(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AsyncIterator[
    AgentStreamEvent | AgentRunResultEvent[Any]
]

Run the agent with a user prompt in async mode and stream events from the run.

This is a convenience method that wraps self.run and uses the event_stream_handler kwarg to get a stream of events from the run.

Example:

from pydantic_ai import Agent, AgentRunResultEvent, AgentStreamEvent

agent = Agent('openai:gpt-5.2')

async def main():
    events: list[AgentStreamEvent | AgentRunResultEvent] = []
    async for event in agent.run_stream_events('What is the capital of France?'):
        events.append(event)
    print(events)
    '''
    [
        PartStartEvent(index=0, part=TextPart(content='The capital of ')),
        FinalResultEvent(tool_name=None, tool_call_id=None),
        PartDeltaEvent(index=0, delta=TextPartDelta(content_delta='France is Paris. ')),
        PartEndEvent(
            index=0, part=TextPart(content='The capital of France is Paris. ')
        ),
        AgentRunResultEvent(
            result=AgentRunResult(output='The capital of France is Paris. ')
        ),
    ]
    '''

Arguments are the same as for self.run, except that event_stream_handler is now allowed.

Parameters:

Name	Type	Description	Default
user_prompt	str | Sequence[UserContent] | None	User input to start/continue the conversation.	None
output_type	OutputSpec[RunOutputDataT] | None	Custom output type to use for this run, output_type may only be used if the agent has no output validators since output validators would expect an argument that matches the agent's output type.	None
message_history	Sequence[ModelMessage] | None	History of the conversation so far.	None
deferred_tool_results	DeferredToolResults | None	Optional results for deferred tool calls in the message history.	None
model	Model | KnownModelName | str | None	Optional model to use for this run, required if model was not set when creating the agent.	None
instructions	AgentInstructions[AgentDepsT]	Optional additional instructions to use for this run.	None
deps	AgentDepsT	Optional dependencies to use for this run.	None
model_settings	AgentModelSettings[AgentDepsT] | None	Optional settings to use for this model's request, or a callable that receives RunContext and returns settings. Callables are called before each model request, allowing dynamic per-step settings.	None
usage_limits	UsageLimits | None	Optional limits on model request count or token usage.	None
usage	RunUsage | None	Optional usage to start with, useful for resuming a conversation or agents used in tools.	None
metadata	AgentMetadata[AgentDepsT] | None	Optional metadata to attach to this run. Accepts a dictionary or a callable taking RunContext; merged with the agent's configured metadata.	None
infer_name	bool	Whether to try to infer the agent name from the call frame if it's not set.	True
toolsets	Sequence[AbstractToolset[AgentDepsT]] | None	Optional additional toolsets for this run.	None
builtin_tools	Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None	Optional additional builtin tools for this run.	None
spec	dict[str, Any] | AgentSpec | None	Optional agent spec to apply for this run. At run time, spec values are additive.	None

Returns:

Type	Description
AsyncIterator[AgentStreamEvent | AgentRunResultEvent[Any]]	An async iterable of stream events AgentStreamEvent and finally a AgentRunResultEvent with the final
AsyncIterator[AgentStreamEvent | AgentRunResultEvent[Any]]	run result.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

def run_stream_events(
    self,
    user_prompt: str | Sequence[_messages.UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[_messages.ModelMessage] | None = None,
    deferred_tool_results: DeferredToolResults | None = None,
    model: models.Model | models.KnownModelName | str | None = None,
    instructions: _instructions.AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: AgentModelSettings[AgentDepsT] | None = None,
    usage_limits: _usage.UsageLimits | None = None,
    usage: _usage.RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
    builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
    spec: dict[str, Any] | AgentSpec | None = None,
) -> AsyncIterator[_messages.AgentStreamEvent | AgentRunResultEvent[Any]]:
    """Run the agent with a user prompt in async mode and stream events from the run.

    This is a convenience method that wraps [`self.run`][pydantic_ai.agent.AbstractAgent.run] and
    uses the `event_stream_handler` kwarg to get a stream of events from the run.

    Example:
    ```python
    from pydantic_ai import Agent, AgentRunResultEvent, AgentStreamEvent

    agent = Agent('openai:gpt-5.2')

    async def main():
        events: list[AgentStreamEvent | AgentRunResultEvent] = []
        async for event in agent.run_stream_events('What is the capital of France?'):
            events.append(event)
        print(events)
        '''
        [
            PartStartEvent(index=0, part=TextPart(content='The capital of ')),
            FinalResultEvent(tool_name=None, tool_call_id=None),
            PartDeltaEvent(index=0, delta=TextPartDelta(content_delta='France is Paris. ')),
            PartEndEvent(
                index=0, part=TextPart(content='The capital of France is Paris. ')
            ),
            AgentRunResultEvent(
                result=AgentRunResult(output='The capital of France is Paris. ')
            ),
        ]
        '''
    ```

    Arguments are the same as for [`self.run`][pydantic_ai.agent.AbstractAgent.run],
    except that `event_stream_handler` is now allowed.

    Args:
        user_prompt: User input to start/continue the conversation.
        output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
            output validators since output validators would expect an argument that matches the agent's output type.
        message_history: History of the conversation so far.
        deferred_tool_results: Optional results for deferred tool calls in the message history.
        model: Optional model to use for this run, required if `model` was not set when creating the agent.
        instructions: Optional additional instructions to use for this run.
        deps: Optional dependencies to use for this run.
        model_settings: Optional settings to use for this model's request, or a callable
            that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
            Callables are called before each model request, allowing dynamic per-step settings.
        usage_limits: Optional limits on model request count or token usage.
        usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
        metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
            [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
        infer_name: Whether to try to infer the agent name from the call frame if it's not set.
        toolsets: Optional additional toolsets for this run.
        builtin_tools: Optional additional builtin tools for this run.
        spec: Optional agent spec to apply for this run. At run time, spec values are additive.

    Returns:
        An async iterable of stream events `AgentStreamEvent` and finally a `AgentRunResultEvent` with the final
        run result.
    """
    if infer_name and self.name is None:
        self._infer_name(inspect.currentframe())

    # unfortunately this hack of returning a generator rather than defining it right here is
    # required to allow overloads of this method to work in python's typing system, or at least with pyright
    # or at least I couldn't make it work without
    return self._run_stream_events(
        user_prompt,
        output_type=output_type,
        message_history=message_history,
        deferred_tool_results=deferred_tool_results,
        model=model,
        instructions=instructions,
        deps=deps,
        model_settings=model_settings,
        usage_limits=usage_limits,
        usage=usage,
        metadata=metadata,
        toolsets=toolsets,
        builtin_tools=builtin_tools,
        spec=spec,
    )

iter abstractmethod async

iter(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AbstractAsyncContextManager[
    AgentRun[AgentDepsT, OutputDataT]
]

iter(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT],
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AbstractAsyncContextManager[
    AgentRun[AgentDepsT, RunOutputDataT]
]

iter(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AsyncIterator[AgentRun[AgentDepsT, Any]]

A contextmanager which can be used to iterate over the agent graph's nodes as they are executed.

This method builds an internal agent graph (using system prompts, tools and output schemas) and then returns an AgentRun object. The AgentRun can be used to async-iterate over the nodes of the graph as they are executed. This is the API to use if you want to consume the outputs coming from each LLM model response, or the stream of events coming from the execution of tools.

The AgentRun also provides methods to access the full message history, new messages, and usage statistics, and the final result of the run once it has completed.

For more details, see the documentation of AgentRun.

Example:

from pydantic_ai import Agent

agent = Agent('openai:gpt-5.2')

async def main():
    nodes = []
    async with agent.iter('What is the capital of France?') as agent_run:
        async for node in agent_run:
            nodes.append(node)
    print(nodes)
    '''
    [
        ModelRequestNode(
            request=ModelRequest(
                parts=[
                    UserPromptPart(
                        content='What is the capital of France?',
                        timestamp=datetime.datetime(...),
                    )
                ],
                timestamp=datetime.datetime(...),
                run_id='...',
            )
        ),
        CallToolsNode(
            model_response=ModelResponse(
                parts=[TextPart(content='The capital of France is Paris.')],
                usage=RequestUsage(input_tokens=56, output_tokens=7),
                model_name='gpt-5.2',
                timestamp=datetime.datetime(...),
                run_id='...',
            )
        ),
        End(data=FinalResult(output='The capital of France is Paris.')),
    ]
    '''
    print(agent_run.result.output)
    #> The capital of France is Paris.

Parameters:

Name	Type	Description	Default
user_prompt	str | Sequence[UserContent] | None	User input to start/continue the conversation.	None
output_type	OutputSpec[RunOutputDataT] | None	Custom output type to use for this run, output_type may only be used if the agent has no output validators since output validators would expect an argument that matches the agent's output type.	None
message_history	Sequence[ModelMessage] | None	History of the conversation so far.	None
deferred_tool_results	DeferredToolResults | None	Optional results for deferred tool calls in the message history.	None
model	Model | KnownModelName | str | None	Optional model to use for this run, required if model was not set when creating the agent.	None
instructions	AgentInstructions[AgentDepsT]	Optional additional instructions to use for this run.	None
deps	AgentDepsT	Optional dependencies to use for this run.	None
model_settings	AgentModelSettings[AgentDepsT] | None	Optional settings to use for this model's request, or a callable that receives RunContext and returns settings. Callables are called before each model request, allowing dynamic per-step settings.	None
usage_limits	UsageLimits | None	Optional limits on model request count or token usage.	None
usage	RunUsage | None	Optional usage to start with, useful for resuming a conversation or agents used in tools.	None
metadata	AgentMetadata[AgentDepsT] | None	Optional metadata to attach to this run. Accepts a dictionary or a callable taking RunContext; merged with the agent's configured metadata.	None
infer_name	bool	Whether to try to infer the agent name from the call frame if it's not set.	True
toolsets	Sequence[AbstractToolset[AgentDepsT]] | None	Optional additional toolsets for this run.	None
builtin_tools	Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None	Optional additional builtin tools for this run.	None
spec	dict[str, Any] | AgentSpec | None	Optional agent spec to apply for this run. At run time, spec values are additive.	None

Returns:

Type	Description
AsyncIterator[AgentRun[AgentDepsT, Any]]	The result of the run.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

@asynccontextmanager
@abstractmethod
async def iter(
    self,
    user_prompt: str | Sequence[_messages.UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[_messages.ModelMessage] | None = None,
    deferred_tool_results: DeferredToolResults | None = None,
    model: models.Model | models.KnownModelName | str | None = None,
    instructions: _instructions.AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: AgentModelSettings[AgentDepsT] | None = None,
    usage_limits: _usage.UsageLimits | None = None,
    usage: _usage.RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
    builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
    spec: dict[str, Any] | AgentSpec | None = None,
) -> AsyncIterator[AgentRun[AgentDepsT, Any]]:
    """A contextmanager which can be used to iterate over the agent graph's nodes as they are executed.

    This method builds an internal agent graph (using system prompts, tools and output schemas) and then returns an
    `AgentRun` object. The `AgentRun` can be used to async-iterate over the nodes of the graph as they are
    executed. This is the API to use if you want to consume the outputs coming from each LLM model response, or the
    stream of events coming from the execution of tools.

    The `AgentRun` also provides methods to access the full message history, new messages, and usage statistics,
    and the final result of the run once it has completed.

    For more details, see the documentation of `AgentRun`.

    Example:
    ```python
    from pydantic_ai import Agent

    agent = Agent('openai:gpt-5.2')

    async def main():
        nodes = []
        async with agent.iter('What is the capital of France?') as agent_run:
            async for node in agent_run:
                nodes.append(node)
        print(nodes)
        '''
        [
            ModelRequestNode(
                request=ModelRequest(
                    parts=[
                        UserPromptPart(
                            content='What is the capital of France?',
                            timestamp=datetime.datetime(...),
                        )
                    ],
                    timestamp=datetime.datetime(...),
                    run_id='...',
                )
            ),
            CallToolsNode(
                model_response=ModelResponse(
                    parts=[TextPart(content='The capital of France is Paris.')],
                    usage=RequestUsage(input_tokens=56, output_tokens=7),
                    model_name='gpt-5.2',
                    timestamp=datetime.datetime(...),
                    run_id='...',
                )
            ),
            End(data=FinalResult(output='The capital of France is Paris.')),
        ]
        '''
        print(agent_run.result.output)
        #> The capital of France is Paris.
    ```

    Args:
        user_prompt: User input to start/continue the conversation.
        output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
            output validators since output validators would expect an argument that matches the agent's output type.
        message_history: History of the conversation so far.
        deferred_tool_results: Optional results for deferred tool calls in the message history.
        model: Optional model to use for this run, required if `model` was not set when creating the agent.
        instructions: Optional additional instructions to use for this run.
        deps: Optional dependencies to use for this run.
        model_settings: Optional settings to use for this model's request, or a callable
            that receives [`RunContext`][pydantic_ai.tools.RunContext] and returns settings.
            Callables are called before each model request, allowing dynamic per-step settings.
        usage_limits: Optional limits on model request count or token usage.
        usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
        metadata: Optional metadata to attach to this run. Accepts a dictionary or a callable taking
            [`RunContext`][pydantic_ai.tools.RunContext]; merged with the agent's configured metadata.
        infer_name: Whether to try to infer the agent name from the call frame if it's not set.
        toolsets: Optional additional toolsets for this run.
        builtin_tools: Optional additional builtin tools for this run.
        spec: Optional agent spec to apply for this run. At run time, spec values are additive.

    Returns:
        The result of the run.
    """
    raise NotImplementedError
    yield

override abstractmethod

override(
    *,
    name: str | Unset = UNSET,
    deps: AgentDepsT | Unset = UNSET,
    model: Model | KnownModelName | str | Unset = UNSET,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | Unset
    ) = UNSET,
    tools: (
        Sequence[
            Tool[AgentDepsT]
            | ToolFuncEither[AgentDepsT, ...]
        ]
        | Unset
    ) = UNSET,
    instructions: (
        AgentInstructions[AgentDepsT] | Unset
    ) = UNSET,
    model_settings: (
        AgentModelSettings[AgentDepsT] | Unset
    ) = UNSET,
    spec: dict[str, Any] | AgentSpec | None = None
) -> Iterator[None]

Context manager to temporarily override agent name, dependencies, model, toolsets, tools, or instructions.

This is particularly useful when testing. You can find an example of this here.

Parameters:

Name	Type	Description	Default
name	str | Unset	The name to use instead of the name passed to the agent constructor and agent run.	UNSET
deps	AgentDepsT | Unset	The dependencies to use instead of the dependencies passed to the agent run.	UNSET
model	Model | KnownModelName | str | Unset	The model to use instead of the model passed to the agent run.	UNSET
toolsets	Sequence[AbstractToolset[AgentDepsT]] | Unset	The toolsets to use instead of the toolsets passed to the agent constructor and agent run.	UNSET
tools	Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] | Unset	The tools to use instead of the tools registered with the agent.	UNSET
instructions	AgentInstructions[AgentDepsT] | Unset	The instructions to use instead of the instructions registered with the agent.	UNSET
model_settings	AgentModelSettings[AgentDepsT] | Unset	The model settings to use instead of the model settings passed to the agent constructor. When set, any per-run model_settings argument is ignored.	UNSET
spec	dict[str, Any] | AgentSpec | None	Optional agent spec providing defaults for override.	None

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

@contextmanager
@abstractmethod
def override(
    self,
    *,
    name: str | _utils.Unset = _utils.UNSET,
    deps: AgentDepsT | _utils.Unset = _utils.UNSET,
    model: models.Model | models.KnownModelName | str | _utils.Unset = _utils.UNSET,
    toolsets: Sequence[AbstractToolset[AgentDepsT]] | _utils.Unset = _utils.UNSET,
    tools: Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] | _utils.Unset = _utils.UNSET,
    instructions: _instructions.AgentInstructions[AgentDepsT] | _utils.Unset = _utils.UNSET,
    model_settings: AgentModelSettings[AgentDepsT] | _utils.Unset = _utils.UNSET,
    spec: dict[str, Any] | AgentSpec | None = None,
) -> Iterator[None]:
    """Context manager to temporarily override agent name, dependencies, model, toolsets, tools, or instructions.

    This is particularly useful when testing.
    You can find an example of this [here](../testing.md#overriding-model-via-pytest-fixtures).

    Args:
        name: The name to use instead of the name passed to the agent constructor and agent run.
        deps: The dependencies to use instead of the dependencies passed to the agent run.
        model: The model to use instead of the model passed to the agent run.
        toolsets: The toolsets to use instead of the toolsets passed to the agent constructor and agent run.
        tools: The tools to use instead of the tools registered with the agent.
        instructions: The instructions to use instead of the instructions registered with the agent.
        model_settings: The model settings to use instead of the model settings passed to the agent constructor.
            When set, any per-run `model_settings` argument is ignored.
        spec: Optional agent spec providing defaults for override.
    """
    raise NotImplementedError
    yield

parallel_tool_call_execution_mode staticmethod

parallel_tool_call_execution_mode(
    mode: ParallelExecutionMode = "parallel",
) -> Iterator[None]

Set the parallel execution mode during the context.

Parameters:

Name	Type	Description	Default
mode	ParallelExecutionMode	The execution mode for tool calls: - 'parallel': Run tool calls in parallel, yielding events as they complete (default). - 'sequential': Run tool calls one at a time in order. - 'parallel_ordered_events': Run tool calls in parallel, but events are emitted in order, after all calls complete.	'parallel'

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

@staticmethod
@contextmanager
def parallel_tool_call_execution_mode(mode: _tool_manager.ParallelExecutionMode = 'parallel') -> Iterator[None]:
    """Set the parallel execution mode during the context.

    Args:
        mode: The execution mode for tool calls:
            - 'parallel': Run tool calls in parallel, yielding events as they complete (default).
            - 'sequential': Run tool calls one at a time in order.
            - 'parallel_ordered_events': Run tool calls in parallel, but events are emitted in order, after all calls complete.
    """
    with ToolManager.parallel_execution_mode(mode):
        yield

sequential_tool_calls deprecated staticmethod

sequential_tool_calls() -> Iterator[None]

Deprecated

Use parallel_execution_mode("sequential") instead.

Run tool calls sequentially during the context.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

@staticmethod
@contextmanager
@deprecated('Use `parallel_execution_mode("sequential")` instead.')
def sequential_tool_calls() -> Iterator[None]:
    """Run tool calls sequentially during the context."""
    with ToolManager.parallel_execution_mode('sequential'):
        yield

is_model_request_node staticmethod

is_model_request_node(
    node: AgentNode[T, S] | End[FinalResult[S]],
) -> TypeIs[ModelRequestNode[T, S]]

Check if the node is a ModelRequestNode, narrowing the type if it is.

This method preserves the generic parameters while narrowing the type, unlike a direct call to isinstance.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

@staticmethod
def is_model_request_node(
    node: _agent_graph.AgentNode[T, S] | End[result.FinalResult[S]],
) -> TypeIs[_agent_graph.ModelRequestNode[T, S]]:
    """Check if the node is a `ModelRequestNode`, narrowing the type if it is.

    This method preserves the generic parameters while narrowing the type, unlike a direct call to `isinstance`.
    """
    return isinstance(node, _agent_graph.ModelRequestNode)

is_call_tools_node staticmethod

is_call_tools_node(
    node: AgentNode[T, S] | End[FinalResult[S]],
) -> TypeIs[CallToolsNode[T, S]]

Check if the node is a CallToolsNode, narrowing the type if it is.

This method preserves the generic parameters while narrowing the type, unlike a direct call to isinstance.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

@staticmethod
def is_call_tools_node(
    node: _agent_graph.AgentNode[T, S] | End[result.FinalResult[S]],
) -> TypeIs[_agent_graph.CallToolsNode[T, S]]:
    """Check if the node is a `CallToolsNode`, narrowing the type if it is.

    This method preserves the generic parameters while narrowing the type, unlike a direct call to `isinstance`.
    """
    return isinstance(node, _agent_graph.CallToolsNode)

is_user_prompt_node staticmethod

is_user_prompt_node(
    node: AgentNode[T, S] | End[FinalResult[S]],
) -> TypeIs[UserPromptNode[T, S]]

Check if the node is a UserPromptNode, narrowing the type if it is.

This method preserves the generic parameters while narrowing the type, unlike a direct call to isinstance.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

@staticmethod
def is_user_prompt_node(
    node: _agent_graph.AgentNode[T, S] | End[result.FinalResult[S]],
) -> TypeIs[_agent_graph.UserPromptNode[T, S]]:
    """Check if the node is a `UserPromptNode`, narrowing the type if it is.

    This method preserves the generic parameters while narrowing the type, unlike a direct call to `isinstance`.
    """
    return isinstance(node, _agent_graph.UserPromptNode)

is_end_node staticmethod

is_end_node(
    node: AgentNode[T, S] | End[FinalResult[S]],
) -> TypeIs[End[FinalResult[S]]]

Check if the node is a End, narrowing the type if it is.

This method preserves the generic parameters while narrowing the type, unlike a direct call to isinstance.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

@staticmethod
def is_end_node(
    node: _agent_graph.AgentNode[T, S] | End[result.FinalResult[S]],
) -> TypeIs[End[result.FinalResult[S]]]:
    """Check if the node is a `End`, narrowing the type if it is.

    This method preserves the generic parameters while narrowing the type, unlike a direct call to `isinstance`.
    """
    return isinstance(node, End)

to_ag_ui

to_ag_ui(
    *,
    output_type: OutputSpec[OutputDataT] | None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    deps: AgentDepsT = None,
    model_settings: ModelSettings | None = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    debug: bool = False,
    routes: Sequence[BaseRoute] | None = None,
    middleware: Sequence[Middleware] | None = None,
    exception_handlers: (
        Mapping[Any, ExceptionHandler] | None
    ) = None,
    on_startup: Sequence[Callable[[], Any]] | None = None,
    on_shutdown: Sequence[Callable[[], Any]] | None = None,
    lifespan: (
        Lifespan[AGUIApp[AgentDepsT, OutputDataT]] | None
    ) = None
) -> AGUIApp[AgentDepsT, OutputDataT]

Returns an ASGI application that handles every AG-UI request by running the agent.

Note that the deps will be the same for each request, with the exception of the AG-UI state that's injected into the state field of a deps object that implements the StateHandler protocol. To provide different deps for each request (e.g. based on the authenticated user), use pydantic_ai.ag_ui.run_ag_ui or pydantic_ai.ag_ui.handle_ag_ui_request instead.

Example:

from pydantic_ai import Agent

agent = Agent('openai:gpt-5.2')
app = agent.to_ag_ui()

The app is an ASGI application that can be used with any ASGI server.

To run the application, you can use the following command:

uvicorn app:app --host 0.0.0.0 --port 8000

See AG-UI docs for more information.

Parameters:

Name	Type	Description	Default
output_type	OutputSpec[OutputDataT] | None	Custom output type to use for this run, output_type may only be used if the agent has no output validators since output validators would expect an argument that matches the agent's output type.	None
message_history	Sequence[ModelMessage] | None	History of the conversation so far.	None
deferred_tool_results	DeferredToolResults | None	Optional results for deferred tool calls in the message history.	None
model	Model | KnownModelName | str | None	Optional model to use for this run, required if model was not set when creating the agent.	None
deps	AgentDepsT	Optional dependencies to use for this run.	None
model_settings	ModelSettings | None	Optional settings to use for this model's request.	None
usage_limits	UsageLimits | None	Optional limits on model request count or token usage.	None
usage	RunUsage | None	Optional usage to start with, useful for resuming a conversation or agents used in tools.	None
infer_name	bool	Whether to try to infer the agent name from the call frame if it's not set.	True
toolsets	Sequence[AbstractToolset[AgentDepsT]] | None	Optional additional toolsets for this run.	None
debug	bool	Boolean indicating if debug tracebacks should be returned on errors.	False
routes	Sequence[BaseRoute] | None	A list of routes to serve incoming HTTP and WebSocket requests.	None
middleware	Sequence[Middleware] | None	A list of middleware to run for every request. A starlette application will always automatically include two middleware classes. ServerErrorMiddleware is added as the very outermost middleware, to handle any uncaught errors occurring anywhere in the entire stack. ExceptionMiddleware is added as the very innermost middleware, to deal with handled exception cases occurring in the routing or endpoints.	None
exception_handlers	Mapping[Any, ExceptionHandler] | None	A mapping of either integer status codes, or exception class types onto callables which handle the exceptions. Exception handler callables should be of the form handler(request, exc) -> response and may be either standard functions, or async functions.	None
on_startup	Sequence[Callable[[], Any]] | None	A list of callables to run on application startup. Startup handler callables do not take any arguments, and may be either standard functions, or async functions.	None
on_shutdown	Sequence[Callable[[], Any]] | None	A list of callables to run on application shutdown. Shutdown handler callables do not take any arguments, and may be either standard functions, or async functions.	None
lifespan	Lifespan[AGUIApp[AgentDepsT, OutputDataT]] | None	A lifespan context function, which can be used to perform startup and shutdown tasks. This is a newer style that replaces the on_startup and on_shutdown handlers. Use one or the other, not both.	None

Returns:

Type	Description
AGUIApp[AgentDepsT, OutputDataT]	An ASGI application for running Pydantic AI agents with AG-UI protocol support.

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

def to_ag_ui(
    self,
    *,
    # Agent.iter parameters
    output_type: OutputSpec[OutputDataT] | None = None,
    message_history: Sequence[_messages.ModelMessage] | None = None,
    deferred_tool_results: DeferredToolResults | None = None,
    model: models.Model | models.KnownModelName | str | None = None,
    deps: AgentDepsT = None,
    model_settings: ModelSettings | None = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    infer_name: bool = True,
    toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
    # Starlette
    debug: bool = False,
    routes: Sequence[BaseRoute] | None = None,
    middleware: Sequence[Middleware] | None = None,
    exception_handlers: Mapping[Any, ExceptionHandler] | None = None,
    on_startup: Sequence[Callable[[], Any]] | None = None,
    on_shutdown: Sequence[Callable[[], Any]] | None = None,
    lifespan: Lifespan[AGUIApp[AgentDepsT, OutputDataT]] | None = None,
) -> AGUIApp[AgentDepsT, OutputDataT]:
    """Returns an ASGI application that handles every AG-UI request by running the agent.

    Note that the `deps` will be the same for each request, with the exception of the AG-UI state that's
    injected into the `state` field of a `deps` object that implements the [`StateHandler`][pydantic_ai.ag_ui.StateHandler] protocol.
    To provide different `deps` for each request (e.g. based on the authenticated user),
    use [`pydantic_ai.ag_ui.run_ag_ui`][pydantic_ai.ag_ui.run_ag_ui] or
    [`pydantic_ai.ag_ui.handle_ag_ui_request`][pydantic_ai.ag_ui.handle_ag_ui_request] instead.

    Example:
    ```python
    from pydantic_ai import Agent

    agent = Agent('openai:gpt-5.2')
    app = agent.to_ag_ui()
    ```

    The `app` is an ASGI application that can be used with any ASGI server.

    To run the application, you can use the following command:

    ```bash
    uvicorn app:app --host 0.0.0.0 --port 8000
    ```

    See [AG-UI docs](../ui/ag-ui.md) for more information.

    Args:
        output_type: Custom output type to use for this run, `output_type` may only be used if the agent has
            no output validators since output validators would expect an argument that matches the agent's
            output type.
        message_history: History of the conversation so far.
        deferred_tool_results: Optional results for deferred tool calls in the message history.
        model: Optional model to use for this run, required if `model` was not set when creating the agent.
        deps: Optional dependencies to use for this run.
        model_settings: Optional settings to use for this model's request.
        usage_limits: Optional limits on model request count or token usage.
        usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
        infer_name: Whether to try to infer the agent name from the call frame if it's not set.
        toolsets: Optional additional toolsets for this run.

        debug: Boolean indicating if debug tracebacks should be returned on errors.
        routes: A list of routes to serve incoming HTTP and WebSocket requests.
        middleware: A list of middleware to run for every request. A starlette application will always
            automatically include two middleware classes. `ServerErrorMiddleware` is added as the very
            outermost middleware, to handle any uncaught errors occurring anywhere in the entire stack.
            `ExceptionMiddleware` is added as the very innermost middleware, to deal with handled
            exception cases occurring in the routing or endpoints.
        exception_handlers: A mapping of either integer status codes, or exception class types onto
            callables which handle the exceptions. Exception handler callables should be of the form
            `handler(request, exc) -> response` and may be either standard functions, or async functions.
        on_startup: A list of callables to run on application startup. Startup handler callables do not
            take any arguments, and may be either standard functions, or async functions.
        on_shutdown: A list of callables to run on application shutdown. Shutdown handler callables do
            not take any arguments, and may be either standard functions, or async functions.
        lifespan: A lifespan context function, which can be used to perform startup and shutdown tasks.
            This is a newer style that replaces the `on_startup` and `on_shutdown` handlers. Use one or
            the other, not both.

    Returns:
        An ASGI application for running Pydantic AI agents with AG-UI protocol support.
    """
    from pydantic_ai.ui.ag_ui.app import AGUIApp

    return AGUIApp(
        agent=self,
        # Agent.iter parameters
        output_type=output_type,
        message_history=message_history,
        deferred_tool_results=deferred_tool_results,
        model=model,
        deps=deps,
        model_settings=model_settings,
        usage_limits=usage_limits,
        usage=usage,
        infer_name=infer_name,
        toolsets=toolsets,
        # Starlette
        debug=debug,
        routes=routes,
        middleware=middleware,
        exception_handlers=exception_handlers,
        on_startup=on_startup,
        on_shutdown=on_shutdown,
        lifespan=lifespan,
    )

to_a2a

to_a2a(
    *,
    storage: Storage | None = None,
    broker: Broker | None = None,
    name: str | None = None,
    url: str = "http://localhost:8000",
    version: str = "1.0.0",
    description: str | None = None,
    provider: AgentProvider | None = None,
    skills: list[Skill] | None = None,
    debug: bool = False,
    routes: Sequence[Route] | None = None,
    middleware: Sequence[Middleware] | None = None,
    exception_handlers: (
        dict[Any, ExceptionHandler] | None
    ) = None,
    lifespan: Lifespan[FastA2A] | None = None
) -> FastA2A

Convert the agent to a FastA2A application.

Example:

from pydantic_ai import Agent

agent = Agent('openai:gpt-5.2')
app = agent.to_a2a()

The app is an ASGI application that can be used with any ASGI server.

To run the application, you can use the following command:

uvicorn app:app --host 0.0.0.0 --port 8000

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

def to_a2a(
    self,
    *,
    storage: Storage | None = None,
    broker: Broker | None = None,
    # Agent card
    name: str | None = None,
    url: str = 'http://localhost:8000',
    version: str = '1.0.0',
    description: str | None = None,
    provider: AgentProvider | None = None,
    skills: list[Skill] | None = None,
    # Starlette
    debug: bool = False,
    routes: Sequence[Route] | None = None,
    middleware: Sequence[Middleware] | None = None,
    exception_handlers: dict[Any, ExceptionHandler] | None = None,
    lifespan: Lifespan[FastA2A] | None = None,
) -> FastA2A:
    """Convert the agent to a FastA2A application.

    Example:
    ```python
    from pydantic_ai import Agent

    agent = Agent('openai:gpt-5.2')
    app = agent.to_a2a()
    ```

    The `app` is an ASGI application that can be used with any ASGI server.

    To run the application, you can use the following command:

    ```bash
    uvicorn app:app --host 0.0.0.0 --port 8000
    ```
    """
    from .._a2a import agent_to_a2a

    return agent_to_a2a(
        self,
        storage=storage,
        broker=broker,
        name=name,
        url=url,
        version=version,
        description=description,
        provider=provider,
        skills=skills,
        debug=debug,
        routes=routes,
        middleware=middleware,
        exception_handlers=exception_handlers,
        lifespan=lifespan,
    )

to_cli async

to_cli(
    deps: AgentDepsT = None,
    prog_name: str = "pydantic-ai",
    message_history: Sequence[ModelMessage] | None = None,
    model_settings: ModelSettings | None = None,
    usage_limits: UsageLimits | None = None,
) -> None

Run the agent in a CLI chat interface.

Parameters:

Name	Type	Description	Default
deps	AgentDepsT	The dependencies to pass to the agent.	None
prog_name	str	The name of the program to use for the CLI. Defaults to 'pydantic-ai'.	'pydantic-ai'
message_history	Sequence[ModelMessage] | None	History of the conversation so far.	None
model_settings	ModelSettings | None	Optional settings to use for this model's request.	None
usage_limits	UsageLimits | None	Optional limits on model request count or token usage.	None

Example:

agent_to_cli.py

from pydantic_ai import Agent

agent = Agent('openai:gpt-5.2', instructions='You always respond in Italian.')

async def main():
    await agent.to_cli()

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

async def to_cli(
    self: Self,
    deps: AgentDepsT = None,
    prog_name: str = 'pydantic-ai',
    message_history: Sequence[_messages.ModelMessage] | None = None,
    model_settings: ModelSettings | None = None,
    usage_limits: _usage.UsageLimits | None = None,
) -> None:
    """Run the agent in a CLI chat interface.

    Args:
        deps: The dependencies to pass to the agent.
        prog_name: The name of the program to use for the CLI. Defaults to 'pydantic-ai'.
        message_history: History of the conversation so far.
        model_settings: Optional settings to use for this model's request.
        usage_limits: Optional limits on model request count or token usage.

    Example:
    ```python {title="agent_to_cli.py" test="skip"}
    from pydantic_ai import Agent

    agent = Agent('openai:gpt-5.2', instructions='You always respond in Italian.')

    async def main():
        await agent.to_cli()
    ```
    """
    from rich.console import Console

    from pydantic_ai._cli import run_chat

    await run_chat(
        stream=True,
        agent=self,
        deps=deps,
        console=Console(),
        code_theme='monokai',
        prog_name=prog_name,
        message_history=message_history,
        model_settings=model_settings,
        usage_limits=usage_limits,
    )

to_cli_sync

to_cli_sync(
    deps: AgentDepsT = None,
    prog_name: str = "pydantic-ai",
    message_history: Sequence[ModelMessage] | None = None,
    model_settings: ModelSettings | None = None,
    usage_limits: UsageLimits | None = None,
) -> None

Run the agent in a CLI chat interface with the non-async interface.

Parameters:

Name	Type	Description	Default
deps	AgentDepsT	The dependencies to pass to the agent.	None
prog_name	str	The name of the program to use for the CLI. Defaults to 'pydantic-ai'.	'pydantic-ai'
message_history	Sequence[ModelMessage] | None	History of the conversation so far.	None
model_settings	ModelSettings | None	Optional settings to use for this model's request.	None
usage_limits	UsageLimits | None	Optional limits on model request count or token usage.	None

agent_to_cli_sync.py

from pydantic_ai import Agent

agent = Agent('openai:gpt-5.2', instructions='You always respond in Italian.')
agent.to_cli_sync()
agent.to_cli_sync(prog_name='assistant')

Source code in pydantic_ai_slim/pydantic_ai/agent/abstract.py

def to_cli_sync(
    self: Self,
    deps: AgentDepsT = None,
    prog_name: str = 'pydantic-ai',
    message_history: Sequence[_messages.ModelMessage] | None = None,
    model_settings: ModelSettings | None = None,
    usage_limits: _usage.UsageLimits | None = None,
) -> None:
    """Run the agent in a CLI chat interface with the non-async interface.

    Args:
        deps: The dependencies to pass to the agent.
        prog_name: The name of the program to use for the CLI. Defaults to 'pydantic-ai'.
        message_history: History of the conversation so far.
        model_settings: Optional settings to use for this model's request.
        usage_limits: Optional limits on model request count or token usage.

    ```python {title="agent_to_cli_sync.py" test="skip"}
    from pydantic_ai import Agent

    agent = Agent('openai:gpt-5.2', instructions='You always respond in Italian.')
    agent.to_cli_sync()
    agent.to_cli_sync(prog_name='assistant')
    ```
    """
    return _utils.get_event_loop().run_until_complete(
        self.to_cli(
            deps=deps,
            prog_name=prog_name,
            message_history=message_history,
            model_settings=model_settings,
            usage_limits=usage_limits,
        )
    )

WrapperAgent

Bases: AbstractAgent[AgentDepsT, OutputDataT]

Agent which wraps another agent.

Does nothing on its own, used as a base class.

Source code in pydantic_ai_slim/pydantic_ai/agent/wrapper.py

class WrapperAgent(AbstractAgent[AgentDepsT, OutputDataT]):
    """Agent which wraps another agent.

    Does nothing on its own, used as a base class.
    """

    def __init__(self, wrapped: AbstractAgent[AgentDepsT, OutputDataT]):
        self.wrapped = wrapped

    @property
    def model(self) -> models.Model | models.KnownModelName | str | None:
        return self.wrapped.model

    @property
    def name(self) -> str | None:
        return self.wrapped.name

    @name.setter
    def name(self, value: str | None) -> None:
        self.wrapped.name = value

    @property
    def description(self) -> str | None:
        return self.wrapped.description

    @description.setter
    def description(self, value: TemplateStr[AgentDepsT] | str | None) -> None:
        self.wrapped.description = value

    @property
    def deps_type(self) -> type:
        return self.wrapped.deps_type

    @property
    def output_type(self) -> OutputSpec[OutputDataT]:
        return self.wrapped.output_type

    @property
    def event_stream_handler(self) -> EventStreamHandler[AgentDepsT] | None:
        return self.wrapped.event_stream_handler

    @property
    def toolsets(self) -> Sequence[AbstractToolset[AgentDepsT]]:
        return self.wrapped.toolsets

    async def __aenter__(self) -> AbstractAgent[AgentDepsT, OutputDataT]:
        return await self.wrapped.__aenter__()

    async def __aexit__(self, *args: Any) -> bool | None:
        return await self.wrapped.__aexit__(*args)

    def output_json_schema(self, output_type: OutputSpec[OutputDataT | RunOutputDataT] | None = None) -> JsonSchema:
        return self.wrapped.output_json_schema(output_type=output_type)

    @overload
    def iter(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AbstractAsyncContextManager[AgentRun[AgentDepsT, OutputDataT]]: ...

    @overload
    def iter(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT],
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AbstractAsyncContextManager[AgentRun[AgentDepsT, RunOutputDataT]]: ...

    @asynccontextmanager
    async def iter(
        self,
        user_prompt: str | Sequence[_messages.UserContent] | None = None,
        *,
        output_type: OutputSpec[RunOutputDataT] | None = None,
        message_history: Sequence[_messages.ModelMessage] | None = None,
        deferred_tool_results: DeferredToolResults | None = None,
        model: models.Model | models.KnownModelName | str | None = None,
        instructions: _instructions.AgentInstructions[AgentDepsT] = None,
        deps: AgentDepsT = None,
        model_settings: AgentModelSettings[AgentDepsT] | None = None,
        usage_limits: _usage.UsageLimits | None = None,
        usage: _usage.RunUsage | None = None,
        metadata: AgentMetadata[AgentDepsT] | None = None,
        infer_name: bool = True,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
        builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> AsyncIterator[AgentRun[AgentDepsT, Any]]:
        """A contextmanager which can be used to iterate over the agent graph's nodes as they are executed.

        This method builds an internal agent graph (using system prompts, tools and output schemas) and then returns an
        `AgentRun` object. The `AgentRun` can be used to async-iterate over the nodes of the graph as they are
        executed. This is the API to use if you want to consume the outputs coming from each LLM model response, or the
        stream of events coming from the execution of tools.

        The `AgentRun` also provides methods to access the full message history, new messages, and usage statistics,
        and the final result of the run once it has completed.

        For more details, see the documentation of `AgentRun`.

        Example:
        ```python
        from pydantic_ai import Agent

        agent = Agent('openai:gpt-5.2')

        async def main():
            nodes = []
            async with agent.iter('What is the capital of France?') as agent_run:
                async for node in agent_run:
                    nodes.append(node)
            print(nodes)
            '''
            [
                ModelRequestNode(
                    request=ModelRequest(
                        parts=[
                            UserPromptPart(
                                content='What is the capital of France?',
                                timestamp=datetime.datetime(...),
                            )
                        ],
                        timestamp=datetime.datetime(...),
                        run_id='...',
                    )
                ),
                CallToolsNode(
                    model_response=ModelResponse(
                        parts=[TextPart(content='The capital of France is Paris.')],
                        usage=RequestUsage(input_tokens=56, output_tokens=7),
                        model_name='gpt-5.2',
                        timestamp=datetime.datetime(...),
                        run_id='...',
                    )
                ),
                End(data=FinalResult(output='The capital of France is Paris.')),
            ]
            '''
            print(agent_run.result.output)
            #> The capital of France is Paris.
        ```

        Args:
            user_prompt: User input to start/continue the conversation.
            output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
                output validators since output validators would expect an argument that matches the agent's output type.
            message_history: History of the conversation so far.
            deferred_tool_results: Optional results for deferred tool calls in the message history.
            model: Optional model to use for this run, required if `model` was not set when creating the agent.
            instructions: Optional additional instructions to use for this run.
            deps: Optional dependencies to use for this run.
            model_settings: Optional settings to use for this model's request.
            usage_limits: Optional limits on model request count or token usage.
            usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
            metadata: Optional metadata to attach to this run.
            infer_name: Whether to try to infer the agent name from the call frame if it's not set.
            toolsets: Optional additional toolsets for this run.
            builtin_tools: Optional additional builtin tools for this run.
            spec: Optional agent spec to apply for this run.

        Returns:
            The result of the run.
        """
        async with self.wrapped.iter(
            user_prompt=user_prompt,
            output_type=output_type,
            message_history=message_history,
            deferred_tool_results=deferred_tool_results,
            model=model,
            instructions=instructions,
            deps=deps,
            model_settings=model_settings,
            usage_limits=usage_limits,
            usage=usage,
            metadata=metadata,
            infer_name=infer_name,
            toolsets=toolsets,
            builtin_tools=builtin_tools,
            spec=spec,
        ) as run:
            yield run

    @contextmanager
    def override(
        self,
        *,
        name: str | _utils.Unset = _utils.UNSET,
        deps: AgentDepsT | _utils.Unset = _utils.UNSET,
        model: models.Model | models.KnownModelName | str | _utils.Unset = _utils.UNSET,
        toolsets: Sequence[AbstractToolset[AgentDepsT]] | _utils.Unset = _utils.UNSET,
        tools: Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] | _utils.Unset = _utils.UNSET,
        instructions: _instructions.AgentInstructions[AgentDepsT] | _utils.Unset = _utils.UNSET,
        model_settings: AgentModelSettings[AgentDepsT] | _utils.Unset = _utils.UNSET,
        spec: dict[str, Any] | AgentSpec | None = None,
    ) -> Iterator[None]:
        """Context manager to temporarily override agent name, dependencies, model, toolsets, tools, or instructions.

        This is particularly useful when testing.
        You can find an example of this [here](../testing.md#overriding-model-via-pytest-fixtures).

        Args:
            name: The name to use instead of the name passed to the agent constructor and agent run.
            deps: The dependencies to use instead of the dependencies passed to the agent run.
            model: The model to use instead of the model passed to the agent run.
            toolsets: The toolsets to use instead of the toolsets passed to the agent constructor and agent run.
            tools: The tools to use instead of the tools registered with the agent.
            instructions: The instructions to use instead of the instructions registered with the agent.
            model_settings: The model settings to use instead of the model settings passed to the agent constructor.
                When set, any per-run `model_settings` argument is ignored.
            spec: Optional agent spec to apply as overrides.
        """
        with self.wrapped.override(
            name=name,
            deps=deps,
            model=model,
            toolsets=toolsets,
            tools=tools,
            instructions=instructions,
            model_settings=model_settings,
            spec=spec,
        ):
            yield

iter async

iter(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AbstractAsyncContextManager[
    AgentRun[AgentDepsT, OutputDataT]
]

iter(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT],
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AbstractAsyncContextManager[
    AgentRun[AgentDepsT, RunOutputDataT]
]

iter(
    user_prompt: str | Sequence[UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[ModelMessage] | None = None,
    deferred_tool_results: (
        DeferredToolResults | None
    ) = None,
    model: Model | KnownModelName | str | None = None,
    instructions: AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: (
        AgentModelSettings[AgentDepsT] | None
    ) = None,
    usage_limits: UsageLimits | None = None,
    usage: RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | None
    ) = None,
    builtin_tools: (
        Sequence[
            AbstractBuiltinTool
            | BuiltinToolFunc[AgentDepsT]
        ]
        | None
    ) = None,
    spec: dict[str, Any] | AgentSpec | None = None
) -> AsyncIterator[AgentRun[AgentDepsT, Any]]

A contextmanager which can be used to iterate over the agent graph's nodes as they are executed.

This method builds an internal agent graph (using system prompts, tools and output schemas) and then returns an AgentRun object. The AgentRun can be used to async-iterate over the nodes of the graph as they are executed. This is the API to use if you want to consume the outputs coming from each LLM model response, or the stream of events coming from the execution of tools.

The AgentRun also provides methods to access the full message history, new messages, and usage statistics, and the final result of the run once it has completed.

For more details, see the documentation of AgentRun.

Example:

from pydantic_ai import Agent

agent = Agent('openai:gpt-5.2')

async def main():
    nodes = []
    async with agent.iter('What is the capital of France?') as agent_run:
        async for node in agent_run:
            nodes.append(node)
    print(nodes)
    '''
    [
        ModelRequestNode(
            request=ModelRequest(
                parts=[
                    UserPromptPart(
                        content='What is the capital of France?',
                        timestamp=datetime.datetime(...),
                    )
                ],
                timestamp=datetime.datetime(...),
                run_id='...',
            )
        ),
        CallToolsNode(
            model_response=ModelResponse(
                parts=[TextPart(content='The capital of France is Paris.')],
                usage=RequestUsage(input_tokens=56, output_tokens=7),
                model_name='gpt-5.2',
                timestamp=datetime.datetime(...),
                run_id='...',
            )
        ),
        End(data=FinalResult(output='The capital of France is Paris.')),
    ]
    '''
    print(agent_run.result.output)
    #> The capital of France is Paris.

Parameters:

Name	Type	Description	Default
user_prompt	str | Sequence[UserContent] | None	User input to start/continue the conversation.	None
output_type	OutputSpec[RunOutputDataT] | None	Custom output type to use for this run, output_type may only be used if the agent has no output validators since output validators would expect an argument that matches the agent's output type.	None
message_history	Sequence[ModelMessage] | None	History of the conversation so far.	None
deferred_tool_results	DeferredToolResults | None	Optional results for deferred tool calls in the message history.	None
model	Model | KnownModelName | str | None	Optional model to use for this run, required if model was not set when creating the agent.	None
instructions	AgentInstructions[AgentDepsT]	Optional additional instructions to use for this run.	None
deps	AgentDepsT	Optional dependencies to use for this run.	None
model_settings	AgentModelSettings[AgentDepsT] | None	Optional settings to use for this model's request.	None
usage_limits	UsageLimits | None	Optional limits on model request count or token usage.	None
usage	RunUsage | None	Optional usage to start with, useful for resuming a conversation or agents used in tools.	None
metadata	AgentMetadata[AgentDepsT] | None	Optional metadata to attach to this run.	None
infer_name	bool	Whether to try to infer the agent name from the call frame if it's not set.	True
toolsets	Sequence[AbstractToolset[AgentDepsT]] | None	Optional additional toolsets for this run.	None
builtin_tools	Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None	Optional additional builtin tools for this run.	None
spec	dict[str, Any] | AgentSpec | None	Optional agent spec to apply for this run.	None

Returns:

Type	Description
AsyncIterator[AgentRun[AgentDepsT, Any]]	The result of the run.

Source code in pydantic_ai_slim/pydantic_ai/agent/wrapper.py

@asynccontextmanager
async def iter(
    self,
    user_prompt: str | Sequence[_messages.UserContent] | None = None,
    *,
    output_type: OutputSpec[RunOutputDataT] | None = None,
    message_history: Sequence[_messages.ModelMessage] | None = None,
    deferred_tool_results: DeferredToolResults | None = None,
    model: models.Model | models.KnownModelName | str | None = None,
    instructions: _instructions.AgentInstructions[AgentDepsT] = None,
    deps: AgentDepsT = None,
    model_settings: AgentModelSettings[AgentDepsT] | None = None,
    usage_limits: _usage.UsageLimits | None = None,
    usage: _usage.RunUsage | None = None,
    metadata: AgentMetadata[AgentDepsT] | None = None,
    infer_name: bool = True,
    toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
    builtin_tools: Sequence[AbstractBuiltinTool | BuiltinToolFunc[AgentDepsT]] | None = None,
    spec: dict[str, Any] | AgentSpec | None = None,
) -> AsyncIterator[AgentRun[AgentDepsT, Any]]:
    """A contextmanager which can be used to iterate over the agent graph's nodes as they are executed.

    This method builds an internal agent graph (using system prompts, tools and output schemas) and then returns an
    `AgentRun` object. The `AgentRun` can be used to async-iterate over the nodes of the graph as they are
    executed. This is the API to use if you want to consume the outputs coming from each LLM model response, or the
    stream of events coming from the execution of tools.

    The `AgentRun` also provides methods to access the full message history, new messages, and usage statistics,
    and the final result of the run once it has completed.

    For more details, see the documentation of `AgentRun`.

    Example:
    ```python
    from pydantic_ai import Agent

    agent = Agent('openai:gpt-5.2')

    async def main():
        nodes = []
        async with agent.iter('What is the capital of France?') as agent_run:
            async for node in agent_run:
                nodes.append(node)
        print(nodes)
        '''
        [
            ModelRequestNode(
                request=ModelRequest(
                    parts=[
                        UserPromptPart(
                            content='What is the capital of France?',
                            timestamp=datetime.datetime(...),
                        )
                    ],
                    timestamp=datetime.datetime(...),
                    run_id='...',
                )
            ),
            CallToolsNode(
                model_response=ModelResponse(
                    parts=[TextPart(content='The capital of France is Paris.')],
                    usage=RequestUsage(input_tokens=56, output_tokens=7),
                    model_name='gpt-5.2',
                    timestamp=datetime.datetime(...),
                    run_id='...',
                )
            ),
            End(data=FinalResult(output='The capital of France is Paris.')),
        ]
        '''
        print(agent_run.result.output)
        #> The capital of France is Paris.
    ```

    Args:
        user_prompt: User input to start/continue the conversation.
        output_type: Custom output type to use for this run, `output_type` may only be used if the agent has no
            output validators since output validators would expect an argument that matches the agent's output type.
        message_history: History of the conversation so far.
        deferred_tool_results: Optional results for deferred tool calls in the message history.
        model: Optional model to use for this run, required if `model` was not set when creating the agent.
        instructions: Optional additional instructions to use for this run.
        deps: Optional dependencies to use for this run.
        model_settings: Optional settings to use for this model's request.
        usage_limits: Optional limits on model request count or token usage.
        usage: Optional usage to start with, useful for resuming a conversation or agents used in tools.
        metadata: Optional metadata to attach to this run.
        infer_name: Whether to try to infer the agent name from the call frame if it's not set.
        toolsets: Optional additional toolsets for this run.
        builtin_tools: Optional additional builtin tools for this run.
        spec: Optional agent spec to apply for this run.

    Returns:
        The result of the run.
    """
    async with self.wrapped.iter(
        user_prompt=user_prompt,
        output_type=output_type,
        message_history=message_history,
        deferred_tool_results=deferred_tool_results,
        model=model,
        instructions=instructions,
        deps=deps,
        model_settings=model_settings,
        usage_limits=usage_limits,
        usage=usage,
        metadata=metadata,
        infer_name=infer_name,
        toolsets=toolsets,
        builtin_tools=builtin_tools,
        spec=spec,
    ) as run:
        yield run

override

override(
    *,
    name: str | Unset = UNSET,
    deps: AgentDepsT | Unset = UNSET,
    model: Model | KnownModelName | str | Unset = UNSET,
    toolsets: (
        Sequence[AbstractToolset[AgentDepsT]] | Unset
    ) = UNSET,
    tools: (
        Sequence[
            Tool[AgentDepsT]
            | ToolFuncEither[AgentDepsT, ...]
        ]
        | Unset
    ) = UNSET,
    instructions: (
        AgentInstructions[AgentDepsT] | Unset
    ) = UNSET,
    model_settings: (
        AgentModelSettings[AgentDepsT] | Unset
    ) = UNSET,
    spec: dict[str, Any] | AgentSpec | None = None
) -> Iterator[None]

Context manager to temporarily override agent name, dependencies, model, toolsets, tools, or instructions.

This is particularly useful when testing. You can find an example of this here.

Parameters:

Name	Type	Description	Default
name	str | Unset	The name to use instead of the name passed to the agent constructor and agent run.	UNSET
deps	AgentDepsT | Unset	The dependencies to use instead of the dependencies passed to the agent run.	UNSET
model	Model | KnownModelName | str | Unset	The model to use instead of the model passed to the agent run.	UNSET
toolsets	Sequence[AbstractToolset[AgentDepsT]] | Unset	The toolsets to use instead of the toolsets passed to the agent constructor and agent run.	UNSET
tools	Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] | Unset	The tools to use instead of the tools registered with the agent.	UNSET
instructions	AgentInstructions[AgentDepsT] | Unset	The instructions to use instead of the instructions registered with the agent.	UNSET
model_settings	AgentModelSettings[AgentDepsT] | Unset	The model settings to use instead of the model settings passed to the agent constructor. When set, any per-run model_settings argument is ignored.	UNSET
spec	dict[str, Any] | AgentSpec | None	Optional agent spec to apply as overrides.	None

Source code in pydantic_ai_slim/pydantic_ai/agent/wrapper.py

@contextmanager
def override(
    self,
    *,
    name: str | _utils.Unset = _utils.UNSET,
    deps: AgentDepsT | _utils.Unset = _utils.UNSET,
    model: models.Model | models.KnownModelName | str | _utils.Unset = _utils.UNSET,
    toolsets: Sequence[AbstractToolset[AgentDepsT]] | _utils.Unset = _utils.UNSET,
    tools: Sequence[Tool[AgentDepsT] | ToolFuncEither[AgentDepsT, ...]] | _utils.Unset = _utils.UNSET,
    instructions: _instructions.AgentInstructions[AgentDepsT] | _utils.Unset = _utils.UNSET,
    model_settings: AgentModelSettings[AgentDepsT] | _utils.Unset = _utils.UNSET,
    spec: dict[str, Any] | AgentSpec | None = None,
) -> Iterator[None]:
    """Context manager to temporarily override agent name, dependencies, model, toolsets, tools, or instructions.

    This is particularly useful when testing.
    You can find an example of this [here](../testing.md#overriding-model-via-pytest-fixtures).

    Args:
        name: The name to use instead of the name passed to the agent constructor and agent run.
        deps: The dependencies to use instead of the dependencies passed to the agent run.
        model: The model to use instead of the model passed to the agent run.
        toolsets: The toolsets to use instead of the toolsets passed to the agent constructor and agent run.
        tools: The tools to use instead of the tools registered with the agent.
        instructions: The instructions to use instead of the instructions registered with the agent.
        model_settings: The model settings to use instead of the model settings passed to the agent constructor.
            When set, any per-run `model_settings` argument is ignored.
        spec: Optional agent spec to apply as overrides.
    """
    with self.wrapped.override(
        name=name,
        deps=deps,
        model=model,
        toolsets=toolsets,
        tools=tools,
        instructions=instructions,
        model_settings=model_settings,
        spec=spec,
    ):
        yield

AgentRun dataclass

Bases: Generic[AgentDepsT, OutputDataT]

A stateful, async-iterable run of an Agent.

You generally obtain an AgentRun instance by calling async with my_agent.iter(...) as agent_run:.

Once you have an instance, you can use it to iterate through the run's nodes as they execute. When an End is reached, the run finishes and result becomes available.

Example:

from pydantic_ai import Agent

agent = Agent('openai:gpt-5.2')

async def main():
    nodes = []
    # Iterate through the run, recording each node along the way:
    async with agent.iter('What is the capital of France?') as agent_run:
        async for node in agent_run:
            nodes.append(node)
    print(nodes)
    '''
    [
        ModelRequestNode(
            request=ModelRequest(
                parts=[
                    UserPromptPart(
                        content='What is the capital of France?',
                        timestamp=datetime.datetime(...),
                    )
                ],
                timestamp=datetime.datetime(...),
                run_id='...',
            )
        ),
        CallToolsNode(
            model_response=ModelResponse(
                parts=[TextPart(content='The capital of France is Paris.')],
                usage=RequestUsage(input_tokens=56, output_tokens=7),
                model_name='gpt-5.2',
                timestamp=datetime.datetime(...),
                run_id='...',
            )
        ),
        End(data=FinalResult(output='The capital of France is Paris.')),
    ]
    '''
    print(agent_run.result.output)
    #> The capital of France is Paris.

You can also manually drive the iteration using the next method for more granular control.

Source code in pydantic_ai_slim/pydantic_ai/run.py

@dataclasses.dataclass(repr=False)
class AgentRun(Generic[AgentDepsT, OutputDataT]):
    """A stateful, async-iterable run of an [`Agent`][pydantic_ai.agent.Agent].

    You generally obtain an `AgentRun` instance by calling `async with my_agent.iter(...) as agent_run:`.

    Once you have an instance, you can use it to iterate through the run's nodes as they execute. When an
    [`End`][pydantic_graph.nodes.End] is reached, the run finishes and [`result`][pydantic_ai.agent.AgentRun.result]
    becomes available.

    Example:
    ```python
    from pydantic_ai import Agent

    agent = Agent('openai:gpt-5.2')

    async def main():
        nodes = []
        # Iterate through the run, recording each node along the way:
        async with agent.iter('What is the capital of France?') as agent_run:
            async for node in agent_run:
                nodes.append(node)
        print(nodes)
        '''
        [
            ModelRequestNode(
                request=ModelRequest(
                    parts=[
                        UserPromptPart(
                            content='What is the capital of France?',
                            timestamp=datetime.datetime(...),
                        )
                    ],
                    timestamp=datetime.datetime(...),
                    run_id='...',
                )
            ),
            CallToolsNode(
                model_response=ModelResponse(
                    parts=[TextPart(content='The capital of France is Paris.')],
                    usage=RequestUsage(input_tokens=56, output_tokens=7),
                    model_name='gpt-5.2',
                    timestamp=datetime.datetime(...),
                    run_id='...',
                )
            ),
            End(data=FinalResult(output='The capital of France is Paris.')),
        ]
        '''
        print(agent_run.result.output)
        #> The capital of France is Paris.
    ```

    You can also manually drive the iteration using the [`next`][pydantic_ai.agent.AgentRun.next] method for
    more granular control.
    """

    _graph_run: GraphRun[
        _agent_graph.GraphAgentState, _agent_graph.GraphAgentDeps[AgentDepsT, Any], FinalResult[OutputDataT]
    ]
    _result_override: AgentRunResult[OutputDataT] | None = dataclasses.field(default=None, repr=False, init=False)
    _node_error: BaseException | None = dataclasses.field(default=None, repr=False, init=False)
    """Stores the original exception from node execution, before context manager __aexit__ may transform it."""

    @overload
    def _traceparent(self, *, required: Literal[False]) -> str | None: ...
    @overload
    def _traceparent(self) -> str: ...
    def _traceparent(self, *, required: bool = True) -> str | None:
        traceparent = self._graph_run._traceparent(required=False)  # type: ignore[reportPrivateUsage]
        if traceparent is None and required:  # pragma: no cover
            raise AttributeError('No span was created for this agent run')
        return traceparent

    @property
    def ctx(self) -> GraphRunContext[_agent_graph.GraphAgentState, _agent_graph.GraphAgentDeps[AgentDepsT, Any]]:
        """The current context of the agent run."""
        return GraphRunContext[_agent_graph.GraphAgentState, _agent_graph.GraphAgentDeps[AgentDepsT, Any]](
            state=self._graph_run.state, deps=self._graph_run.deps
        )

    @property
    def next_node(
        self,
    ) -> _agent_graph.AgentNode[AgentDepsT, OutputDataT] | End[FinalResult[OutputDataT]]:
        """The next node that will be run in the agent graph.

        This is the next node that will be used during async iteration, or if a node is not passed to `self.next(...)`.
        """
        task = self._graph_run.next_task
        return self._task_to_node(task)

    @property
    def result(self) -> AgentRunResult[OutputDataT] | None:
        """The final result of the run if it has ended, otherwise `None`.

        Once the run returns an [`End`][pydantic_graph.nodes.End] node, `result` is populated
        with an [`AgentRunResult`][pydantic_ai.agent.AgentRunResult].
        """
        if self._result_override is not None:
            return self._result_override
        graph_run_output = self._graph_run.output
        if graph_run_output is None:
            return None
        return AgentRunResult(
            graph_run_output.output,
            graph_run_output.tool_name,
            self._graph_run.state,
            self._graph_run.deps.new_message_index,
            self._traceparent(required=False),
        )

    def all_messages(self) -> list[_messages.ModelMessage]:
        """Return all messages for the run so far.

        Messages from older runs are included.
        """
        return self.ctx.state.message_history

    def all_messages_json(self, *, output_tool_return_content: str | None = None) -> bytes:
        """Return all messages from [`all_messages`][pydantic_ai.agent.AgentRun.all_messages] as JSON bytes.

        Returns:
            JSON bytes representing the messages.
        """
        return _messages.ModelMessagesTypeAdapter.dump_json(self.all_messages())

    def new_messages(self) -> list[_messages.ModelMessage]:
        """Return new messages for the run so far.

        Messages from older runs are excluded.
        """
        return self.all_messages()[self.ctx.deps.new_message_index :]

    def new_messages_json(self) -> bytes:
        """Return new messages from [`new_messages`][pydantic_ai.agent.AgentRun.new_messages] as JSON bytes.

        Returns:
            JSON bytes representing the new messages.
        """
        return _messages.ModelMessagesTypeAdapter.dump_json(self.new_messages())

    def __aiter__(
        self,
    ) -> AsyncIterator[_agent_graph.AgentNode[AgentDepsT, OutputDataT] | End[FinalResult[OutputDataT]]]:
        """Provide async-iteration over the nodes in the agent run."""
        return self

    async def __anext__(
        self,
    ) -> _agent_graph.AgentNode[AgentDepsT, OutputDataT] | End[FinalResult[OutputDataT]]:
        """Advance to the next node automatically based on the last returned node."""
        if self._result_override is not None:
            raise StopAsyncIteration
        next_node = self.next_node
        if isinstance(next_node, End):
            raise StopAsyncIteration
        try:
            return await self.next(next_node)
        except BaseException as exc:
            # Store the original exception before it passes through context manager
            # __aexit__ chains (e.g. GraphRun) that may transform it.
            self._node_error = exc
            raise

    def _task_to_node(
        self, task: EndMarker[FinalResult[OutputDataT]] | JoinItem | Sequence[GraphTaskRequest]
    ) -> _agent_graph.AgentNode[AgentDepsT, OutputDataT] | End[FinalResult[OutputDataT]]:
        if isinstance(task, Sequence) and len(task) == 1:
            first_task = task[0]
            if isinstance(first_task.inputs, BaseNode):  # pragma: no branch
                base_node: BaseNode[  # pyright: ignore[reportUnknownVariableType]
                    _agent_graph.GraphAgentState,
                    _agent_graph.GraphAgentDeps[AgentDepsT, OutputDataT],
                    FinalResult[OutputDataT],
                ] = first_task.inputs  # pyright: ignore[reportUnknownMemberType]
                if _agent_graph.is_agent_node(node=base_node):  # pragma: no branch
                    return base_node
        if isinstance(task, EndMarker):
            return End(task.value)
        raise exceptions.AgentRunError(f'Unexpected node: {task}')  # pragma: no cover

    def _node_to_task(self, node: _agent_graph.AgentNode[AgentDepsT, OutputDataT]) -> GraphTaskRequest:
        return GraphTaskRequest(NodeStep(type(node)).id, inputs=node, fork_stack=())

    async def next(
        self,
        node: _agent_graph.AgentNode[AgentDepsT, OutputDataT],
    ) -> _agent_graph.AgentNode[AgentDepsT, OutputDataT] | End[FinalResult[OutputDataT]]:
        """Manually drive the agent run by passing in the node you want to run next.

        This lets you inspect or mutate the node before continuing execution, or skip certain nodes
        under dynamic conditions. The agent run should be stopped when you return an [`End`][pydantic_graph.nodes.End]
        node.

        Example:
        ```python
        from pydantic_ai import Agent
        from pydantic_graph import End

        agent = Agent('openai:gpt-5.2')

        async def main():
            async with agent.iter('What is the capital of France?') as agent_run:
                next_node = agent_run.next_node  # start with the first node
                nodes = [next_node]
                while not isinstance(next_node, End):
                    next_node = await agent_run.next(next_node)
                    nodes.append(next_node)
                # Once `next_node` is an End, we've finished:
                print(nodes)
                '''
                [
                    UserPromptNode(
                        user_prompt='What is the capital of France?',
                        instructions_functions=[],
                        system_prompts=(),
                        system_prompt_functions=[],
                        system_prompt_dynamic_functions={},
                    ),
                    ModelRequestNode(
                        request=ModelRequest(
                            parts=[
                                UserPromptPart(
                                    content='What is the capital of France?',
                                    timestamp=datetime.datetime(...),
                                )
                            ],
                            timestamp=datetime.datetime(...),
                            run_id='...',
                        )
                    ),
                    CallToolsNode(
                        model_response=ModelResponse(
                            parts=[TextPart(content='The capital of France is Paris.')],
                            usage=RequestUsage(input_tokens=56, output_tokens=7),
                            model_name='gpt-5.2',
                            timestamp=datetime.datetime(...),
                            run_id='...',
                        )
                    ),
                    End(data=FinalResult(output='The capital of France is Paris.')),
                ]
                '''
                print('Final result:', agent_run.result.output)
                #> Final result: The capital of France is Paris.
        ```

        Args:
            node: The node to run next in the graph.

        Returns:
            The next node returned by the graph logic, or an [`End`][pydantic_graph.nodes.End] node if
            the run has completed.
        """
        # Note: It might be nice to expose a synchronous interface for iteration, but we shouldn't do it
        # on this class, or else IDEs won't warn you if you accidentally use `for` instead of `async for` to iterate.
        run_context = _agent_graph.build_run_context(self.ctx)

        async def _step_handler(
            n: _agent_graph.AgentNode[AgentDepsT, OutputDataT],
        ) -> _agent_graph.AgentNode[AgentDepsT, OutputDataT] | End[FinalResult[OutputDataT]]:
            task = [self._node_to_task(n)]
            try:
                task = await self._graph_run.next(task)
            except StopAsyncIteration:
                pass
            return self._task_to_node(task)

        return await self.ctx.deps.root_capability.wrap_node_run(run_context, node=node, handler=_step_handler)

    # TODO (v2): Make this a property
    def usage(self) -> _usage.RunUsage:
        """Get usage statistics for the run so far, including token usage, model requests, and so on."""
        return self._graph_run.state.usage

    @property
    def metadata(self) -> dict[str, Any] | None:
        """Metadata associated with this agent run, if configured."""
        return self._graph_run.state.metadata

    @property
    def run_id(self) -> str:
        """The unique identifier for the agent run."""
        return self._graph_run.state.run_id

    def __repr__(self) -> str:  # pragma: no cover
        result = self._graph_run.output
        result_repr = '<run not finished>' if result is None else repr(result.output)
        return f'<{type(self).__name__} result={result_repr} usage={self.usage()}>'

ctx property

ctx: GraphRunContext[
    GraphAgentState, GraphAgentDeps[AgentDepsT, Any]
]

The current context of the agent run.

next_node property

next_node: (
    AgentNode[AgentDepsT, OutputDataT]
    | End[FinalResult[OutputDataT]]
)

The next node that will be run in the agent graph.

This is the next node that will be used during async iteration, or if a node is not passed to self.next(...).

result property

result: AgentRunResult[OutputDataT] | None

The final result of the run if it has ended, otherwise None.

Once the run returns an End node, result is populated with an AgentRunResult.

all_messages

all_messages() -> list[ModelMessage]

Return all messages for the run so far.

Messages from older runs are included.

Source code in pydantic_ai_slim/pydantic_ai/run.py

def all_messages(self) -> list[_messages.ModelMessage]:
    """Return all messages for the run so far.

    Messages from older runs are included.
    """
    return self.ctx.state.message_history

all_messages_json

all_messages_json(
    *, output_tool_return_content: str | None = None
) -> bytes

Return all messages from all_messages as JSON bytes.

Returns:

Type	Description
bytes	JSON bytes representing the messages.

Source code in pydantic_ai_slim/pydantic_ai/run.py

def all_messages_json(self, *, output_tool_return_content: str | None = None) -> bytes:
    """Return all messages from [`all_messages`][pydantic_ai.agent.AgentRun.all_messages] as JSON bytes.

    Returns:
        JSON bytes representing the messages.
    """
    return _messages.ModelMessagesTypeAdapter.dump_json(self.all_messages())

new_messages

new_messages() -> list[ModelMessage]

Return new messages for the run so far.

Messages from older runs are excluded.

Source code in pydantic_ai_slim/pydantic_ai/run.py

def new_messages(self) -> list[_messages.ModelMessage]:
    """Return new messages for the run so far.

    Messages from older runs are excluded.
    """
    return self.all_messages()[self.ctx.deps.new_message_index :]

new_messages_json

new_messages_json() -> bytes

Return new messages from new_messages as JSON bytes.

Returns:

Type	Description
bytes	JSON bytes representing the new messages.

Source code in pydantic_ai_slim/pydantic_ai/run.py

def new_messages_json(self) -> bytes:
    """Return new messages from [`new_messages`][pydantic_ai.agent.AgentRun.new_messages] as JSON bytes.

    Returns:
        JSON bytes representing the new messages.
    """
    return _messages.ModelMessagesTypeAdapter.dump_json(self.new_messages())

__aiter__

__aiter__() -> (
    AsyncIterator[
        AgentNode[AgentDepsT, OutputDataT]
        | End[FinalResult[OutputDataT]]
    ]
)

Provide async-iteration over the nodes in the agent run.

Source code in pydantic_ai_slim/pydantic_ai/run.py

def __aiter__(
    self,
) -> AsyncIterator[_agent_graph.AgentNode[AgentDepsT, OutputDataT] | End[FinalResult[OutputDataT]]]:
    """Provide async-iteration over the nodes in the agent run."""
    return self

__anext__ async

__anext__() -> (
    AgentNode[AgentDepsT, OutputDataT]
    | End[FinalResult[OutputDataT]]
)

Advance to the next node automatically based on the last returned node.

Source code in pydantic_ai_slim/pydantic_ai/run.py

async def __anext__(
    self,
) -> _agent_graph.AgentNode[AgentDepsT, OutputDataT] | End[FinalResult[OutputDataT]]:
    """Advance to the next node automatically based on the last returned node."""
    if self._result_override is not None:
        raise StopAsyncIteration
    next_node = self.next_node
    if isinstance(next_node, End):
        raise StopAsyncIteration
    try:
        return await self.next(next_node)
    except BaseException as exc:
        # Store the original exception before it passes through context manager
        # __aexit__ chains (e.g. GraphRun) that may transform it.
        self._node_error = exc
        raise

next async

next(
    node: AgentNode[AgentDepsT, OutputDataT],
) -> (
    AgentNode[AgentDepsT, OutputDataT]
    | End[FinalResult[OutputDataT]]
)

Manually drive the agent run by passing in the node you want to run next.

This lets you inspect or mutate the node before continuing execution, or skip certain nodes under dynamic conditions. The agent run should be stopped when you return an End node.

Example:

from pydantic_ai import Agent
from pydantic_graph import End

agent = Agent('openai:gpt-5.2')

async def main():
    async with agent.iter('What is the capital of France?') as agent_run:
        next_node = agent_run.next_node  # start with the first node
        nodes = [next_node]
        while not isinstance(next_node, End):
            next_node = await agent_run.next(next_node)
            nodes.append(next_node)
        # Once `next_node` is an End, we've finished:
        print(nodes)
        '''
        [
            UserPromptNode(
                user_prompt='What is the capital of France?',
                instructions_functions=[],
                system_prompts=(),
                system_prompt_functions=[],
                system_prompt_dynamic_functions={},
            ),
            ModelRequestNode(
                request=ModelRequest(
                    parts=[
                        UserPromptPart(
                            content='What is the capital of France?',
                            timestamp=datetime.datetime(...),
                        )
                    ],
                    timestamp=datetime.datetime(...),
                    run_id='...',
                )
            ),
            CallToolsNode(
                model_response=ModelResponse(
                    parts=[TextPart(content='The capital of France is Paris.')],
                    usage=RequestUsage(input_tokens=56, output_tokens=7),
                    model_name='gpt-5.2',
                    timestamp=datetime.datetime(...),
                    run_id='...',
                )
            ),
            End(data=FinalResult(output='The capital of France is Paris.')),
        ]
        '''
        print('Final result:', agent_run.result.output)
        #> Final result: The capital of France is Paris.

Parameters:

Name	Type	Description	Default
node	AgentNode[AgentDepsT, OutputDataT]	The node to run next in the graph.	required

Returns:

Type	Description
AgentNode[AgentDepsT, OutputDataT] | End[FinalResult[OutputDataT]]	The next node returned by the graph logic, or an End node if
AgentNode[AgentDepsT, OutputDataT] | End[FinalResult[OutputDataT]]	the run has completed.

Source code in pydantic_ai_slim/pydantic_ai/run.py

async def next(
    self,
    node: _agent_graph.AgentNode[AgentDepsT, OutputDataT],
) -> _agent_graph.AgentNode[AgentDepsT, OutputDataT] | End[FinalResult[OutputDataT]]:
    """Manually drive the agent run by passing in the node you want to run next.

    This lets you inspect or mutate the node before continuing execution, or skip certain nodes
    under dynamic conditions. The agent run should be stopped when you return an [`End`][pydantic_graph.nodes.End]
    node.

    Example:
    ```python
    from pydantic_ai import Agent
    from pydantic_graph import End

    agent = Agent('openai:gpt-5.2')

    async def main():
        async with agent.iter('What is the capital of France?') as agent_run:
            next_node = agent_run.next_node  # start with the first node
            nodes = [next_node]
            while not isinstance(next_node, End):
                next_node = await agent_run.next(next_node)
                nodes.append(next_node)
            # Once `next_node` is an End, we've finished:
            print(nodes)
            '''
            [
                UserPromptNode(
                    user_prompt='What is the capital of France?',
                    instructions_functions=[],
                    system_prompts=(),
                    system_prompt_functions=[],
                    system_prompt_dynamic_functions={},
                ),
                ModelRequestNode(
                    request=ModelRequest(
                        parts=[
                            UserPromptPart(
                                content='What is the capital of France?',
                                timestamp=datetime.datetime(...),
                            )
                        ],
                        timestamp=datetime.datetime(...),
                        run_id='...',
                    )
                ),
                CallToolsNode(
                    model_response=ModelResponse(
                        parts=[TextPart(content='The capital of France is Paris.')],
                        usage=RequestUsage(input_tokens=56, output_tokens=7),
                        model_name='gpt-5.2',
                        timestamp=datetime.datetime(...),
                        run_id='...',
                    )
                ),
                End(data=FinalResult(output='The capital of France is Paris.')),
            ]
            '''
            print('Final result:', agent_run.result.output)
            #> Final result: The capital of France is Paris.
    ```

    Args:
        node: The node to run next in the graph.

    Returns:
        The next node returned by the graph logic, or an [`End`][pydantic_graph.nodes.End] node if
        the run has completed.
    """
    # Note: It might be nice to expose a synchronous interface for iteration, but we shouldn't do it
    # on this class, or else IDEs won't warn you if you accidentally use `for` instead of `async for` to iterate.
    run_context = _agent_graph.build_run_context(self.ctx)

    async def _step_handler(
        n: _agent_graph.AgentNode[AgentDepsT, OutputDataT],
    ) -> _agent_graph.AgentNode[AgentDepsT, OutputDataT] | End[FinalResult[OutputDataT]]:
        task = [self._node_to_task(n)]
        try:
            task = await self._graph_run.next(task)
        except StopAsyncIteration:
            pass
        return self._task_to_node(task)

    return await self.ctx.deps.root_capability.wrap_node_run(run_context, node=node, handler=_step_handler)

usage

usage() -> RunUsage

Get usage statistics for the run so far, including token usage, model requests, and so on.

Source code in pydantic_ai_slim/pydantic_ai/run.py

def usage(self) -> _usage.RunUsage:
    """Get usage statistics for the run so far, including token usage, model requests, and so on."""
    return self._graph_run.state.usage

metadata property

metadata: dict[str, Any] | None

Metadata associated with this agent run, if configured.

run_id property

run_id: str

The unique identifier for the agent run.

AgentRunResult dataclass

Bases: Generic[OutputDataT]

The final result of an agent run.

Source code in pydantic_ai_slim/pydantic_ai/run.py

@dataclasses.dataclass
class AgentRunResult(Generic[OutputDataT]):
    """The final result of an agent run."""

    output: OutputDataT
    """The output data from the agent run."""

    _output_tool_name: str | None = dataclasses.field(repr=False, compare=False, default=None)
    _state: _agent_graph.GraphAgentState = dataclasses.field(
        repr=False, compare=False, default_factory=_agent_graph.GraphAgentState
    )
    _new_message_index: int = dataclasses.field(repr=False, compare=False, default=0)
    _traceparent_value: str | None = dataclasses.field(repr=False, compare=False, default=None)

    @overload
    def _traceparent(self, *, required: Literal[False]) -> str | None: ...
    @overload
    def _traceparent(self) -> str: ...
    def _traceparent(self, *, required: bool = True) -> str | None:
        if self._traceparent_value is None and required:  # pragma: no cover
            raise AttributeError('No span was created for this agent run')
        return self._traceparent_value

    def _set_output_tool_return(self, return_content: str) -> list[_messages.ModelMessage]:
        """Set return content for the output tool.

        Useful if you want to continue the conversation and want to set the response to the output tool call.
        """
        if not self._output_tool_name:
            raise ValueError('Cannot set output tool return content when the return type is `str`.')

        messages = self._state.message_history
        last_message = messages[-1]
        for idx, part in enumerate(last_message.parts):
            if isinstance(part, _messages.ToolReturnPart) and part.tool_name == self._output_tool_name:
                # Only do deepcopy when we have to modify
                copied_messages = list(messages)
                copied_last = deepcopy(last_message)
                copied_last.parts[idx].content = return_content  # type: ignore[misc]
                copied_messages[-1] = copied_last
                return copied_messages

        raise LookupError(f'No tool call found with tool name {self._output_tool_name!r}.')

    def all_messages(self, *, output_tool_return_content: str | None = None) -> list[_messages.ModelMessage]:
        """Return the history of _messages.

        Args:
            output_tool_return_content: The return content of the tool call to set in the last message.
                This provides a convenient way to modify the content of the output tool call if you want to continue
                the conversation and want to set the response to the output tool call. If `None`, the last message will
                not be modified.

        Returns:
            List of messages.
        """
        if output_tool_return_content is not None:
            return self._set_output_tool_return(output_tool_return_content)
        else:
            return self._state.message_history

    def all_messages_json(self, *, output_tool_return_content: str | None = None) -> bytes:
        """Return all messages from [`all_messages`][pydantic_ai.agent.AgentRunResult.all_messages] as JSON bytes.

        Args:
            output_tool_return_content: The return content of the tool call to set in the last message.
                This provides a convenient way to modify the content of the output tool call if you want to continue
                the conversation and want to set the response to the output tool call. If `None`, the last message will
                not be modified.

        Returns:
            JSON bytes representing the messages.
        """
        return _messages.ModelMessagesTypeAdapter.dump_json(
            self.all_messages(output_tool_return_content=output_tool_return_content)
        )

    def new_messages(self, *, output_tool_return_content: str | None = None) -> list[_messages.ModelMessage]:
        """Return new messages associated with this run.

        Messages from older runs are excluded.

        Args:
            output_tool_return_content: The return content of the tool call to set in the last message.
                This provides a convenient way to modify the content of the output tool call if you want to continue
                the conversation and want to set the response to the output tool call. If `None`, the last message will
                not be modified.

        Returns:
            List of new messages.
        """
        return self.all_messages(output_tool_return_content=output_tool_return_content)[self._new_message_index :]

    def new_messages_json(self, *, output_tool_return_content: str | None = None) -> bytes:
        """Return new messages from [`new_messages`][pydantic_ai.agent.AgentRunResult.new_messages] as JSON bytes.

        Args:
            output_tool_return_content: The return content of the tool call to set in the last message.
                This provides a convenient way to modify the content of the output tool call if you want to continue
                the conversation and want to set the response to the output tool call. If `None`, the last message will
                not be modified.

        Returns:
            JSON bytes representing the new messages.
        """
        return _messages.ModelMessagesTypeAdapter.dump_json(
            self.new_messages(output_tool_return_content=output_tool_return_content)
        )

    @property
    def response(self) -> _messages.ModelResponse:
        """Return the last response from the message history."""
        # The response may not be the very last item if it contained an output tool call. See `CallToolsNode._handle_final_result`.
        for message in reversed(self.all_messages()):
            if isinstance(message, _messages.ModelResponse):
                return message
        raise ValueError('No response found in the message history')  # pragma: no cover

    # TODO (v2): Make this a property
    def usage(self) -> _usage.RunUsage:
        """Return the usage of the whole run."""
        return self._state.usage

    # TODO (v2): Make this a property
    def timestamp(self) -> datetime:
        """Return the timestamp of last response."""
        return self.response.timestamp

    @property
    def metadata(self) -> dict[str, Any] | None:
        """Metadata associated with this agent run, if configured."""
        return self._state.metadata

    @property
    def run_id(self) -> str:
        """The unique identifier for the agent run."""
        return self._state.run_id

output instance-attribute

output: OutputDataT

The output data from the agent run.

all_messages

all_messages(
    *, output_tool_return_content: str | None = None
) -> list[ModelMessage]

Return the history of _messages.

Parameters:

Name	Type	Description	Default
output_tool_return_content	str | None	The return content of the tool call to set in the last message. This provides a convenient way to modify the content of the output tool call if you want to continue the conversation and want to set the response to the output tool call. If None, the last message will not be modified.	None

Returns:

Type	Description
list[ModelMessage]	List of messages.

Source code in pydantic_ai_slim/pydantic_ai/run.py

def all_messages(self, *, output_tool_return_content: str | None = None) -> list[_messages.ModelMessage]:
    """Return the history of _messages.

    Args:
        output_tool_return_content: The return content of the tool call to set in the last message.
            This provides a convenient way to modify the content of the output tool call if you want to continue
            the conversation and want to set the response to the output tool call. If `None`, the last message will
            not be modified.

    Returns:
        List of messages.
    """
    if output_tool_return_content is not None:
        return self._set_output_tool_return(output_tool_return_content)
    else:
        return self._state.message_history

all_messages_json

all_messages_json(
    *, output_tool_return_content: str | None = None
) -> bytes

Return all messages from all_messages as JSON bytes.

Parameters:

Name	Type	Description	Default
output_tool_return_content	str | None	The return content of the tool call to set in the last message. This provides a convenient way to modify the content of the output tool call if you want to continue the conversation and want to set the response to the output tool call. If None, the last message will not be modified.	None

Returns:

Type	Description
bytes	JSON bytes representing the messages.

Source code in pydantic_ai_slim/pydantic_ai/run.py

def all_messages_json(self, *, output_tool_return_content: str | None = None) -> bytes:
    """Return all messages from [`all_messages`][pydantic_ai.agent.AgentRunResult.all_messages] as JSON bytes.

    Args:
        output_tool_return_content: The return content of the tool call to set in the last message.
            This provides a convenient way to modify the content of the output tool call if you want to continue
            the conversation and want to set the response to the output tool call. If `None`, the last message will
            not be modified.

    Returns:
        JSON bytes representing the messages.
    """
    return _messages.ModelMessagesTypeAdapter.dump_json(
        self.all_messages(output_tool_return_content=output_tool_return_content)
    )

new_messages

new_messages(
    *, output_tool_return_content: str | None = None
) -> list[ModelMessage]

Return new messages associated with this run.

Messages from older runs are excluded.

Parameters:

Name	Type	Description	Default
output_tool_return_content	str | None	The return content of the tool call to set in the last message. This provides a convenient way to modify the content of the output tool call if you want to continue the conversation and want to set the response to the output tool call. If None, the last message will not be modified.	None

Returns:

Type	Description
list[ModelMessage]	List of new messages.

Source code in pydantic_ai_slim/pydantic_ai/run.py

def new_messages(self, *, output_tool_return_content: str | None = None) -> list[_messages.ModelMessage]:
    """Return new messages associated with this run.

    Messages from older runs are excluded.

    Args:
        output_tool_return_content: The return content of the tool call to set in the last message.
            This provides a convenient way to modify the content of the output tool call if you want to continue
            the conversation and want to set the response to the output tool call. If `None`, the last message will
            not be modified.

    Returns:
        List of new messages.
    """
    return self.all_messages(output_tool_return_content=output_tool_return_content)[self._new_message_index :]

new_messages_json

new_messages_json(
    *, output_tool_return_content: str | None = None
) -> bytes

Return new messages from new_messages as JSON bytes.

Parameters:

Name	Type	Description	Default
output_tool_return_content	str | None	The return content of the tool call to set in the last message. This provides a convenient way to modify the content of the output tool call if you want to continue the conversation and want to set the response to the output tool call. If None, the last message will not be modified.	None

Returns:

Type	Description
bytes	JSON bytes representing the new messages.

Source code in pydantic_ai_slim/pydantic_ai/run.py

def new_messages_json(self, *, output_tool_return_content: str | None = None) -> bytes:
    """Return new messages from [`new_messages`][pydantic_ai.agent.AgentRunResult.new_messages] as JSON bytes.

    Args:
        output_tool_return_content: The return content of the tool call to set in the last message.
            This provides a convenient way to modify the content of the output tool call if you want to continue
            the conversation and want to set the response to the output tool call. If `None`, the last message will
            not be modified.

    Returns:
        JSON bytes representing the new messages.
    """
    return _messages.ModelMessagesTypeAdapter.dump_json(
        self.new_messages(output_tool_return_content=output_tool_return_content)
    )

response property

response: ModelResponse

Return the last response from the message history.

usage

usage() -> RunUsage

Return the usage of the whole run.

Source code in pydantic_ai_slim/pydantic_ai/run.py

def usage(self) -> _usage.RunUsage:
    """Return the usage of the whole run."""
    return self._state.usage

timestamp

timestamp() -> datetime

Return the timestamp of last response.

Source code in pydantic_ai_slim/pydantic_ai/run.py

def timestamp(self) -> datetime:
    """Return the timestamp of last response."""
    return self.response.timestamp

metadata property

metadata: dict[str, Any] | None

Metadata associated with this agent run, if configured.

run_id property

run_id: str

The unique identifier for the agent run.

EndStrategy module-attribute

EndStrategy = Literal['early', 'exhaustive']

RunOutputDataT module-attribute

RunOutputDataT = TypeVar('RunOutputDataT')

Type variable for the result data of a run where output_type was customized on the run call.

capture_run_messages

capture_run_messages() -> Iterator[list[ModelMessage]]

Context manager to access the messages used in a run, run_sync, or run_stream call.

Useful when a run may raise an exception, see model errors for more information.

Examples:

from pydantic_ai import Agent, capture_run_messages

agent = Agent('test')

with capture_run_messages() as messages:
    try:
        result = agent.run_sync('foobar')
    except Exception:
        print(messages)
        raise

Note

If you call run, run_sync, or run_stream more than once within a single capture_run_messages context, messages will represent the messages exchanged during the first call only.

Source code in pydantic_ai_slim/pydantic_ai/_agent_graph.py

@contextmanager
def capture_run_messages() -> Iterator[list[_messages.ModelMessage]]:
    """Context manager to access the messages used in a [`run`][pydantic_ai.agent.AbstractAgent.run], [`run_sync`][pydantic_ai.agent.AbstractAgent.run_sync], or [`run_stream`][pydantic_ai.agent.AbstractAgent.run_stream] call.

    Useful when a run may raise an exception, see [model errors](../agent.md#model-errors) for more information.

    Examples:
    ```python
    from pydantic_ai import Agent, capture_run_messages

    agent = Agent('test')

    with capture_run_messages() as messages:
        try:
            result = agent.run_sync('foobar')
        except Exception:
            print(messages)
            raise
    ```

    !!! note
        If you call `run`, `run_sync`, or `run_stream` more than once within a single `capture_run_messages` context,
        `messages` will represent the messages exchanged during the first call only.
    """
    token = None
    messages: list[_messages.ModelMessage] = []

    # Try to reuse existing message context if available
    try:
        messages = _messages_ctx_var.get().messages
    except LookupError:
        # No existing context, create a new one
        token = _messages_ctx_var.set(_RunMessages(messages))

    try:
        yield messages
    finally:
        # Clean up context if we created it
        if token is not None:
            _messages_ctx_var.reset(token)

InstrumentationSettings dataclass

Options for instrumenting models and agents with OpenTelemetry.

Used in:

• Agent(instrument=...)
• Agent.instrument_all()
• InstrumentedModel

See the Debugging and Monitoring guide for more info.

Source code in pydantic_ai_slim/pydantic_ai/models/instrumented.py

@dataclass(init=False)
class InstrumentationSettings:
    """Options for instrumenting models and agents with OpenTelemetry.

    Used in:

    - `Agent(instrument=...)`
    - [`Agent.instrument_all()`][pydantic_ai.agent.Agent.instrument_all]
    - [`InstrumentedModel`][pydantic_ai.models.instrumented.InstrumentedModel]

    See the [Debugging and Monitoring guide](https://ai.pydantic.dev/logfire/) for more info.
    """

    tracer: Tracer = field(repr=False)
    logger: Logger = field(repr=False)
    event_mode: Literal['attributes', 'logs'] = 'attributes'
    include_binary_content: bool = True
    include_content: bool = True
    version: Literal[1, 2, 3, 4] = DEFAULT_INSTRUMENTATION_VERSION
    use_aggregated_usage_attribute_names: bool = False

    def __init__(
        self,
        *,
        tracer_provider: TracerProvider | None = None,
        meter_provider: MeterProvider | None = None,
        include_binary_content: bool = True,
        include_content: bool = True,
        version: Literal[1, 2, 3, 4] = DEFAULT_INSTRUMENTATION_VERSION,
        event_mode: Literal['attributes', 'logs'] = 'attributes',
        logger_provider: LoggerProvider | None = None,
        use_aggregated_usage_attribute_names: bool = False,
    ):
        """Create instrumentation options.

        Args:
            tracer_provider: The OpenTelemetry tracer provider to use.
                If not provided, the global tracer provider is used.
                Calling `logfire.configure()` sets the global tracer provider, so most users don't need this.
            meter_provider: The OpenTelemetry meter provider to use.
                If not provided, the global meter provider is used.
                Calling `logfire.configure()` sets the global meter provider, so most users don't need this.
            include_binary_content: Whether to include binary content in the instrumentation events.
            include_content: Whether to include prompts, completions, and tool call arguments and responses
                in the instrumentation events.
            version: Version of the data format. This is unrelated to the Pydantic AI package version.
                Version 1 is based on the legacy event-based OpenTelemetry GenAI spec
                    and will be removed in a future release.
                    The parameters `event_mode` and `logger_provider` are only relevant for version 1.
                Version 2 uses the newer OpenTelemetry GenAI spec and stores messages in the following attributes:
                    - `gen_ai.system_instructions` for instructions passed to the agent.
                    - `gen_ai.input.messages` and `gen_ai.output.messages` on model request spans.
                    - `pydantic_ai.all_messages` on agent run spans.
                Version 3 is the same as version 2, with additional support for thinking tokens.
                Version 4 is the same as version 3, with GenAI semantic conventions for multimodal content:
                    URL-based media uses type='uri' with uri and mime_type fields (and modality for image/audio/video).
                    Inline binary content uses type='blob' with mime_type and content fields (and modality for image/audio/video).
                    https://opentelemetry.io/docs/specs/semconv/gen-ai/non-normative/examples-llm-calls/#multimodal-inputs-example
            event_mode: The mode for emitting events in version 1.
                If `'attributes'`, events are attached to the span as attributes.
                If `'logs'`, events are emitted as OpenTelemetry log-based events.
            logger_provider: The OpenTelemetry logger provider to use.
                If not provided, the global logger provider is used.
                Calling `logfire.configure()` sets the global logger provider, so most users don't need this.
                This is only used if `event_mode='logs'` and `version=1`.
            use_aggregated_usage_attribute_names: Whether to use `gen_ai.aggregated_usage.*` attribute names
                for token usage on agent run spans instead of the standard `gen_ai.usage.*` names.
                Enable this to prevent double-counting in observability backends that aggregate span
                attributes across parent and child spans. Defaults to False.
                Note: `gen_ai.aggregated_usage.*` is a custom namespace, not part of the OpenTelemetry
                Semantic Conventions. It may be updated if OTel introduces an official convention.
        """
        from pydantic_ai import __version__

        tracer_provider = tracer_provider or get_tracer_provider()
        meter_provider = meter_provider or get_meter_provider()
        logger_provider = logger_provider or get_logger_provider()
        scope_name = 'pydantic-ai'
        self.tracer = tracer_provider.get_tracer(scope_name, __version__)
        self.meter = meter_provider.get_meter(scope_name, __version__)
        self.logger = logger_provider.get_logger(scope_name, __version__)
        self.event_mode = event_mode
        self.include_binary_content = include_binary_content
        self.include_content = include_content

        if event_mode == 'logs' and version != 1:
            warnings.warn(
                'event_mode is only relevant for version=1 which is deprecated and will be removed in a future release.',
                stacklevel=2,
            )
            version = 1

        self.version = version
        self.use_aggregated_usage_attribute_names = use_aggregated_usage_attribute_names

        # As specified in the OpenTelemetry GenAI metrics spec:
        # https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-metrics/#metric-gen_aiclienttokenusage
        tokens_histogram_kwargs = dict(
            name='gen_ai.client.token.usage',
            unit='{token}',
            description='Measures number of input and output tokens used',
        )
        try:
            self.tokens_histogram = self.meter.create_histogram(
                **tokens_histogram_kwargs,
                explicit_bucket_boundaries_advisory=TOKEN_HISTOGRAM_BOUNDARIES,
            )
        except TypeError:  # pragma: lax no cover
            # Older OTel/logfire versions don't support explicit_bucket_boundaries_advisory
            self.tokens_histogram = self.meter.create_histogram(
                **tokens_histogram_kwargs,  # pyright: ignore
            )
        self.cost_histogram = self.meter.create_histogram(
            'operation.cost',
            unit='{USD}',
            description='Monetary cost',
        )

    def messages_to_otel_events(
        self, messages: list[ModelMessage], parameters: ModelRequestParameters | None = None
    ) -> list[LogRecord]:
        """Convert a list of model messages to OpenTelemetry events.

        Args:
            messages: The messages to convert.
            parameters: The model request parameters.

        Returns:
            A list of OpenTelemetry events.
        """
        events: list[LogRecord] = []
        instructions = InstrumentedModel._get_instructions(messages, parameters)  # pyright: ignore [reportPrivateUsage]
        if instructions is not None:
            events.append(
                LogRecord(
                    attributes={'event.name': 'gen_ai.system.message'},
                    body={**({'content': instructions} if self.include_content else {}), 'role': 'system'},
                )
            )

        for message_index, message in enumerate(messages):
            message_events: list[LogRecord] = []
            if isinstance(message, ModelRequest):
                for part in message.parts:
                    if hasattr(part, 'otel_event'):
                        message_events.append(part.otel_event(self))
            elif isinstance(message, ModelResponse):  # pragma: no branch
                message_events = message.otel_events(self)
            for event in message_events:
                event.attributes = {
                    'gen_ai.message.index': message_index,
                    **(event.attributes or {}),
                }
            events.extend(message_events)

        for event in events:
            event.body = InstrumentedModel.serialize_any(event.body)
        return events

    def messages_to_otel_messages(self, messages: list[ModelMessage]) -> list[_otel_messages.ChatMessage]:
        result: list[_otel_messages.ChatMessage] = []
        for message in messages:
            if isinstance(message, ModelRequest):
                for is_system, group in itertools.groupby(message.parts, key=lambda p: isinstance(p, SystemPromptPart)):
                    message_parts: list[_otel_messages.MessagePart] = []
                    for part in group:
                        if hasattr(part, 'otel_message_parts'):
                            message_parts.extend(part.otel_message_parts(self))

                    result.append(
                        _otel_messages.ChatMessage(role='system' if is_system else 'user', parts=message_parts)
                    )
            elif isinstance(message, ModelResponse):  # pragma: no branch
                otel_message = _otel_messages.OutputMessage(role='assistant', parts=message.otel_message_parts(self))
                if message.finish_reason is not None:
                    otel_message['finish_reason'] = message.finish_reason
                result.append(otel_message)
        return result

    def handle_messages(
        self,
        input_messages: list[ModelMessage],
        response: ModelResponse,
        system: str,
        span: Span,
        parameters: ModelRequestParameters | None = None,
    ):
        if self.version == 1:
            events = self.messages_to_otel_events(input_messages, parameters)
            for event in self.messages_to_otel_events([response], parameters):
                events.append(
                    LogRecord(
                        attributes={'event.name': 'gen_ai.choice'},
                        body={
                            'index': 0,
                            'message': event.body,
                        },
                    )
                )
            for event in events:
                event.attributes = {
                    GEN_AI_SYSTEM_ATTRIBUTE: system,
                    **(event.attributes or {}),
                }
            self._emit_events(span, events)
        else:
            output_messages = self.messages_to_otel_messages([response])
            assert len(output_messages) == 1
            output_message = output_messages[0]

            instructions = InstrumentedModel._get_instructions(input_messages, parameters)  # pyright: ignore [reportPrivateUsage]
            system_instructions_attributes = self.system_instructions_attributes(instructions)

            attributes: dict[str, AttributeValue] = {
                'gen_ai.input.messages': json.dumps(self.messages_to_otel_messages(input_messages)),
                'gen_ai.output.messages': json.dumps([output_message]),
                **system_instructions_attributes,
                'logfire.json_schema': json.dumps(
                    {
                        'type': 'object',
                        'properties': {
                            'gen_ai.input.messages': {'type': 'array'},
                            'gen_ai.output.messages': {'type': 'array'},
                            **(
                                {'gen_ai.system_instructions': {'type': 'array'}}
                                if system_instructions_attributes
                                else {}
                            ),
                            'model_request_parameters': {'type': 'object'},
                        },
                    }
                ),
            }
            span.set_attributes(attributes)

    def system_instructions_attributes(self, instructions: str | None) -> dict[str, str]:
        if instructions and self.include_content:
            return {
                'gen_ai.system_instructions': json.dumps([_otel_messages.TextPart(type='text', content=instructions)]),
            }
        return {}

    def _emit_events(self, span: Span, events: list[LogRecord]) -> None:
        if self.event_mode == 'logs':
            for event in events:
                self.logger.emit(event)
        else:
            attr_name = 'events'
            span.set_attributes(
                {
                    attr_name: json.dumps([InstrumentedModel.event_to_dict(event) for event in events]),
                    'logfire.json_schema': json.dumps(
                        {
                            'type': 'object',
                            'properties': {
                                attr_name: {'type': 'array'},
                                'model_request_parameters': {'type': 'object'},
                            },
                        }
                    ),
                }
            )

    def record_metrics(
        self,
        response: ModelResponse,
        price_calculation: PriceCalculation | None,
        attributes: dict[str, AttributeValue],
    ):
        for typ in ['input', 'output']:
            if not (tokens := getattr(response.usage, f'{typ}_tokens', 0)):  # pragma: no cover
                continue
            token_attributes = {**attributes, 'gen_ai.token.type': typ}
            self.tokens_histogram.record(tokens, token_attributes)
            if price_calculation:
                cost = float(getattr(price_calculation, f'{typ}_price'))
                self.cost_histogram.record(cost, token_attributes)

__init__

__init__(
    *,
    tracer_provider: TracerProvider | None = None,
    meter_provider: MeterProvider | None = None,
    include_binary_content: bool = True,
    include_content: bool = True,
    version: Literal[
        1, 2, 3, 4
    ] = DEFAULT_INSTRUMENTATION_VERSION,
    event_mode: Literal[
        "attributes", "logs"
    ] = "attributes",
    logger_provider: LoggerProvider | None = None,
    use_aggregated_usage_attribute_names: bool = False
)

Create instrumentation options.

Parameters:

Name	Type	Description	Default
tracer_provider	TracerProvider | None	The OpenTelemetry tracer provider to use. If not provided, the global tracer provider is used. Calling logfire.configure() sets the global tracer provider, so most users don't need this.	None
meter_provider	MeterProvider | None	The OpenTelemetry meter provider to use. If not provided, the global meter provider is used. Calling logfire.configure() sets the global meter provider, so most users don't need this.	None
include_binary_content	bool	Whether to include binary content in the instrumentation events.	True
include_content	bool	Whether to include prompts, completions, and tool call arguments and responses in the instrumentation events.	True
version	Literal[1, 2, 3, 4]	Version of the data format. This is unrelated to the Pydantic AI package version. Version 1 is based on the legacy event-based OpenTelemetry GenAI spec and will be removed in a future release. The parameters event_mode and logger_provider are only relevant for version 1. Version 2 uses the newer OpenTelemetry GenAI spec and stores messages in the following attributes: - gen_ai.system_instructions for instructions passed to the agent. - gen_ai.input.messages and gen_ai.output.messages on model request spans. - pydantic_ai.all_messages on agent run spans. Version 3 is the same as version 2, with additional support for thinking tokens. Version 4 is the same as version 3, with GenAI semantic conventions for multimodal content: URL-based media uses type='uri' with uri and mime_type fields (and modality for image/audio/video). Inline binary content uses type='blob' with mime_type and content fields (and modality for image/audio/video). https://opentelemetry.io/docs/specs/semconv/gen-ai/non-normative/examples-llm-calls/#multimodal-inputs-example	DEFAULT_INSTRUMENTATION_VERSION
event_mode	Literal['attributes', 'logs']	The mode for emitting events in version 1. If 'attributes', events are attached to the span as attributes. If 'logs', events are emitted as OpenTelemetry log-based events.	'attributes'
logger_provider	LoggerProvider | None	The OpenTelemetry logger provider to use. If not provided, the global logger provider is used. Calling logfire.configure() sets the global logger provider, so most users don't need this. This is only used if event_mode='logs' and version=1.	None
use_aggregated_usage_attribute_names	bool	Whether to use gen_ai.aggregated_usage.* attribute names for token usage on agent run spans instead of the standard gen_ai.usage.* names. Enable this to prevent double-counting in observability backends that aggregate span attributes across parent and child spans. Defaults to False. Note: gen_ai.aggregated_usage.* is a custom namespace, not part of the OpenTelemetry Semantic Conventions. It may be updated if OTel introduces an official convention.	False

Source code in pydantic_ai_slim/pydantic_ai/models/instrumented.py

def __init__(
    self,
    *,
    tracer_provider: TracerProvider | None = None,
    meter_provider: MeterProvider | None = None,
    include_binary_content: bool = True,
    include_content: bool = True,
    version: Literal[1, 2, 3, 4] = DEFAULT_INSTRUMENTATION_VERSION,
    event_mode: Literal['attributes', 'logs'] = 'attributes',
    logger_provider: LoggerProvider | None = None,
    use_aggregated_usage_attribute_names: bool = False,
):
    """Create instrumentation options.

    Args:
        tracer_provider: The OpenTelemetry tracer provider to use.
            If not provided, the global tracer provider is used.
            Calling `logfire.configure()` sets the global tracer provider, so most users don't need this.
        meter_provider: The OpenTelemetry meter provider to use.
            If not provided, the global meter provider is used.
            Calling `logfire.configure()` sets the global meter provider, so most users don't need this.
        include_binary_content: Whether to include binary content in the instrumentation events.
        include_content: Whether to include prompts, completions, and tool call arguments and responses
            in the instrumentation events.
        version: Version of the data format. This is unrelated to the Pydantic AI package version.
            Version 1 is based on the legacy event-based OpenTelemetry GenAI spec
                and will be removed in a future release.
                The parameters `event_mode` and `logger_provider` are only relevant for version 1.
            Version 2 uses the newer OpenTelemetry GenAI spec and stores messages in the following attributes:
                - `gen_ai.system_instructions` for instructions passed to the agent.
                - `gen_ai.input.messages` and `gen_ai.output.messages` on model request spans.
                - `pydantic_ai.all_messages` on agent run spans.
            Version 3 is the same as version 2, with additional support for thinking tokens.
            Version 4 is the same as version 3, with GenAI semantic conventions for multimodal content:
                URL-based media uses type='uri' with uri and mime_type fields (and modality for image/audio/video).
                Inline binary content uses type='blob' with mime_type and content fields (and modality for image/audio/video).
                https://opentelemetry.io/docs/specs/semconv/gen-ai/non-normative/examples-llm-calls/#multimodal-inputs-example
        event_mode: The mode for emitting events in version 1.
            If `'attributes'`, events are attached to the span as attributes.
            If `'logs'`, events are emitted as OpenTelemetry log-based events.
        logger_provider: The OpenTelemetry logger provider to use.
            If not provided, the global logger provider is used.
            Calling `logfire.configure()` sets the global logger provider, so most users don't need this.
            This is only used if `event_mode='logs'` and `version=1`.
        use_aggregated_usage_attribute_names: Whether to use `gen_ai.aggregated_usage.*` attribute names
            for token usage on agent run spans instead of the standard `gen_ai.usage.*` names.
            Enable this to prevent double-counting in observability backends that aggregate span
            attributes across parent and child spans. Defaults to False.
            Note: `gen_ai.aggregated_usage.*` is a custom namespace, not part of the OpenTelemetry
            Semantic Conventions. It may be updated if OTel introduces an official convention.
    """
    from pydantic_ai import __version__

    tracer_provider = tracer_provider or get_tracer_provider()
    meter_provider = meter_provider or get_meter_provider()
    logger_provider = logger_provider or get_logger_provider()
    scope_name = 'pydantic-ai'
    self.tracer = tracer_provider.get_tracer(scope_name, __version__)
    self.meter = meter_provider.get_meter(scope_name, __version__)
    self.logger = logger_provider.get_logger(scope_name, __version__)
    self.event_mode = event_mode
    self.include_binary_content = include_binary_content
    self.include_content = include_content

    if event_mode == 'logs' and version != 1:
        warnings.warn(
            'event_mode is only relevant for version=1 which is deprecated and will be removed in a future release.',
            stacklevel=2,
        )
        version = 1

    self.version = version
    self.use_aggregated_usage_attribute_names = use_aggregated_usage_attribute_names

    # As specified in the OpenTelemetry GenAI metrics spec:
    # https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-metrics/#metric-gen_aiclienttokenusage
    tokens_histogram_kwargs = dict(
        name='gen_ai.client.token.usage',
        unit='{token}',
        description='Measures number of input and output tokens used',
    )
    try:
        self.tokens_histogram = self.meter.create_histogram(
            **tokens_histogram_kwargs,
            explicit_bucket_boundaries_advisory=TOKEN_HISTOGRAM_BOUNDARIES,
        )
    except TypeError:  # pragma: lax no cover
        # Older OTel/logfire versions don't support explicit_bucket_boundaries_advisory
        self.tokens_histogram = self.meter.create_histogram(
            **tokens_histogram_kwargs,  # pyright: ignore
        )
    self.cost_histogram = self.meter.create_histogram(
        'operation.cost',
        unit='{USD}',
        description='Monetary cost',
    )

messages_to_otel_events

messages_to_otel_events(
    messages: list[ModelMessage],
    parameters: ModelRequestParameters | None = None,
) -> list[LogRecord]

Convert a list of model messages to OpenTelemetry events.

Parameters:

Name	Type	Description	Default
messages	list[ModelMessage]	The messages to convert.	required
parameters	ModelRequestParameters | None	The model request parameters.	None

Returns:

Type	Description
list[LogRecord]	A list of OpenTelemetry events.

Source code in pydantic_ai_slim/pydantic_ai/models/instrumented.py

def messages_to_otel_events(
    self, messages: list[ModelMessage], parameters: ModelRequestParameters | None = None
) -> list[LogRecord]:
    """Convert a list of model messages to OpenTelemetry events.

    Args:
        messages: The messages to convert.
        parameters: The model request parameters.

    Returns:
        A list of OpenTelemetry events.
    """
    events: list[LogRecord] = []
    instructions = InstrumentedModel._get_instructions(messages, parameters)  # pyright: ignore [reportPrivateUsage]
    if instructions is not None:
        events.append(
            LogRecord(
                attributes={'event.name': 'gen_ai.system.message'},
                body={**({'content': instructions} if self.include_content else {}), 'role': 'system'},
            )
        )

    for message_index, message in enumerate(messages):
        message_events: list[LogRecord] = []
        if isinstance(message, ModelRequest):
            for part in message.parts:
                if hasattr(part, 'otel_event'):
                    message_events.append(part.otel_event(self))
        elif isinstance(message, ModelResponse):  # pragma: no branch
            message_events = message.otel_events(self)
        for event in message_events:
            event.attributes = {
                'gen_ai.message.index': message_index,
                **(event.attributes or {}),
            }
        events.extend(message_events)

    for event in events:
        event.body = InstrumentedModel.serialize_any(event.body)
    return events

EventStreamHandler module-attribute

EventStreamHandler: TypeAlias = Callable[
    [
        RunContext[AgentDepsT],
        AsyncIterable[AgentStreamEvent],
    ],
    Awaitable[None],
]

A function that receives agent RunContext and an async iterable of events from the model's streaming response and the agent's execution of tools.