pydantic-ai-slim 1.7.0__tar.gz → 1.9.0__tar.gz

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/.gitignore

@@ -10,7 +10,7 @@ env*/
 /TODO.md
 /postgres-data/
 .DS_Store
-examples/pydantic_ai_examples/.chat_app_messages.sqlite
+.chat_app_messages.sqlite
 .cache/
 .vscode/
 /question_graph_history.json

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pydantic-ai-slim
-Version: 1.7.0
+Version: 1.9.0
 Summary: Agent Framework / shim to use Pydantic with LLMs, slim package
 Project-URL: Homepage, https://github.com/pydantic/pydantic-ai/tree/main/pydantic_ai_slim
 Project-URL: Source, https://github.com/pydantic/pydantic-ai/tree/main/pydantic_ai_slim
@@ -33,7 +33,7 @@ Requires-Dist: genai-prices>=0.0.35
 Requires-Dist: griffe>=1.3.2
 Requires-Dist: httpx>=0.27
 Requires-Dist: opentelemetry-api>=1.28.0
-Requires-Dist: pydantic-graph==1.7.0
+Requires-Dist: pydantic-graph==1.9.0
 Requires-Dist: pydantic>=2.10
 Requires-Dist: typing-inspection>=0.4.0
 Provides-Extra: a2a
@@ -57,7 +57,7 @@ Requires-Dist: dbos>=1.14.0; extra == 'dbos'
 Provides-Extra: duckduckgo
 Requires-Dist: ddgs>=9.0.0; extra == 'duckduckgo'
 Provides-Extra: evals
-Requires-Dist: pydantic-evals==1.7.0; extra == 'evals'
+Requires-Dist: pydantic-evals==1.9.0; extra == 'evals'
 Provides-Extra: fastmcp
 Requires-Dist: fastmcp>=2.12.0; extra == 'fastmcp'
 Provides-Extra: google
@@ -96,6 +96,8 @@ Provides-Extra: tavily
 Requires-Dist: tavily-python>=0.5.0; extra == 'tavily'
 Provides-Extra: temporal
 Requires-Dist: temporalio==1.18.0; extra == 'temporal'
+Provides-Extra: ui
+Requires-Dist: starlette>=0.45.3; extra == 'ui'
 Provides-Extra: vertexai
 Requires-Dist: google-auth>=2.36.0; extra == 'vertexai'
 Requires-Dist: requests>=2.32.2; extra == 'vertexai'

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/pydantic_ai/__init__.py

@@ -65,6 +65,7 @@ from .messages import (
     ModelResponseStreamEvent,
     MultiModalContent,
     PartDeltaEvent,
+    PartEndEvent,
     PartStartEvent,
     RetryPromptPart,
     SystemPromptPart,
@@ -164,6 +165,7 @@ __all__ = (
     'ModelResponseStreamEvent',
     'MultiModalContent',
     'PartDeltaEvent',
+    'PartEndEvent',
     'PartStartEvent',
     'RetryPromptPart',
     'SystemPromptPart',

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/pydantic_ai/_agent_graph.py

@@ -267,6 +267,9 @@ class UserPromptNode(AgentNode[DepsT, NodeRunEndT]):
 
         next_message.instructions = await ctx.deps.get_instructions(run_context)
 
+        if not messages and not next_message.parts and not next_message.instructions:
+            raise exceptions.UserError('No message history, user prompt, or instructions provided')
+
         return ModelRequestNode[DepsT, NodeRunEndT](request=next_message)
 
     async def _handle_deferred_tool_results(  # noqa: C901

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/pydantic_ai/_cli.py

@@ -103,7 +103,7 @@ def cli_exit(prog_name: str = 'pai'):  # pragma: no cover
 
 
 def cli(  # noqa: C901
-    args_list: Sequence[str] | None = None, *, prog_name: str = 'pai', default_model: str = 'openai:gpt-4.1'
+    args_list: Sequence[str] | None = None, *, prog_name: str = 'pai', default_model: str = 'openai:gpt-5'
 ) -> int:
     """Run the CLI and return the exit code for the process."""
     parser = argparse.ArgumentParser(
@@ -124,7 +124,7 @@ Special prompts:
         '-m',
         '--model',
         nargs='?',
-        help=f'Model to use, in format "<provider>:<model>" e.g. "openai:gpt-4.1" or "anthropic:claude-sonnet-4-0". Defaults to "{default_model}".',
+        help=f'Model to use, in format "<provider>:<model>" e.g. "openai:gpt-5" or "anthropic:claude-sonnet-4-5". Defaults to "{default_model}".',
     )
     # we don't want to autocomplete or list models that don't include the provider,
     # e.g. we want to show `openai:gpt-4o` but not `gpt-4o`

pydantic_ai_slim-1.9.0/pydantic_ai/ag_ui.py

@@ -0,0 +1,163 @@
+"""Provides an AG-UI protocol adapter for the Pydantic AI agent.
+
+This package provides seamless integration between pydantic-ai agents and ag-ui
+for building interactive AI applications with streaming event-based communication.
+"""
+
+# TODO (v2): Remove this module in favor of `pydantic_ai.ui.ag_ui`
+
+from __future__ import annotations
+
+from collections.abc import AsyncIterator, Sequence
+from typing import Any
+
+from . import DeferredToolResults
+from .agent import AbstractAgent
+from .messages import ModelMessage
+from .models import KnownModelName, Model
+from .output import OutputSpec
+from .settings import ModelSettings
+from .tools import AgentDepsT
+from .toolsets import AbstractToolset
+from .usage import RunUsage, UsageLimits
+
+try:
+    from ag_ui.core import BaseEvent
+    from ag_ui.core.types import RunAgentInput
+    from starlette.requests import Request
+    from starlette.responses import Response
+
+    from .ui import SSE_CONTENT_TYPE, OnCompleteFunc, StateDeps, StateHandler
+    from .ui.ag_ui import AGUIAdapter
+    from .ui.ag_ui.app import AGUIApp
+except ImportError as e:  # pragma: no cover
+    raise ImportError(
+        'Please install the `ag-ui-protocol` and `starlette` packages to use `AGUIAdapter`, '
+        'you can use the `ag-ui` optional group — `pip install "pydantic-ai-slim[ag-ui]"`'
+    ) from e
+
+
+__all__ = [
+    'SSE_CONTENT_TYPE',
+    'StateDeps',
+    'StateHandler',
+    'AGUIApp',
+    'OnCompleteFunc',
+    'handle_ag_ui_request',
+    'run_ag_ui',
+]
+
+
+async def handle_ag_ui_request(
+    agent: AbstractAgent[AgentDepsT, Any],
+    request: Request,
+    *,
+    output_type: OutputSpec[Any] | 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,
+    on_complete: OnCompleteFunc[BaseEvent] | None = None,
+) -> Response:
+    """Handle an AG-UI request by running the agent and returning a streaming response.
+
+    Args:
+        agent: The agent to run.
+        request: The Starlette request (e.g. from FastAPI) containing the AG-UI run input.
+
+        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.
+        on_complete: Optional callback function called when the agent run completes successfully.
+            The callback receives the completed [`AgentRunResult`][pydantic_ai.agent.AgentRunResult] and can access `all_messages()` and other result data.
+
+    Returns:
+        A streaming Starlette response with AG-UI protocol events.
+    """
+    return await AGUIAdapter[AgentDepsT].dispatch_request(
+        request,
+        agent=agent,
+        deps=deps,
+        output_type=output_type,
+        message_history=message_history,
+        deferred_tool_results=deferred_tool_results,
+        model=model,
+        model_settings=model_settings,
+        usage_limits=usage_limits,
+        usage=usage,
+        infer_name=infer_name,
+        toolsets=toolsets,
+        on_complete=on_complete,
+    )
+
+
+def run_ag_ui(
+    agent: AbstractAgent[AgentDepsT, Any],
+    run_input: RunAgentInput,
+    accept: str = SSE_CONTENT_TYPE,
+    *,
+    output_type: OutputSpec[Any] | 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,
+    on_complete: OnCompleteFunc[BaseEvent] | None = None,
+) -> AsyncIterator[str]:
+    """Run the agent with the AG-UI run input and stream AG-UI protocol events.
+
+    Args:
+        agent: The agent to run.
+        run_input: The AG-UI run input containing thread_id, run_id, messages, etc.
+        accept: The accept header value for the run.
+
+        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.
+        on_complete: Optional callback function called when the agent run completes successfully.
+            The callback receives the completed [`AgentRunResult`][pydantic_ai.agent.AgentRunResult] and can access `all_messages()` and other result data.
+
+    Yields:
+        Streaming event chunks encoded as strings according to the accept header value.
+    """
+    adapter = AGUIAdapter(agent=agent, run_input=run_input, accept=accept)
+    return adapter.encode_stream(
+        adapter.run_stream(
+            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,
+            on_complete=on_complete,
+        ),
+    )

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/pydantic_ai/agent/abstract.py

@@ -49,7 +49,7 @@ if TYPE_CHECKING:
     from starlette.routing import BaseRoute, Route
     from starlette.types import ExceptionHandler, Lifespan
 
-    from ..ag_ui import AGUIApp
+    from pydantic_ai.ui.ag_ui.app import AGUIApp
 
 
 T = TypeVar('T')
@@ -654,6 +654,9 @@ class AbstractAgent(Generic[AgentDepsT, OutputDataT], ABC):
                 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. ')
                 ),
@@ -683,6 +686,9 @@ class AbstractAgent(Generic[AgentDepsT, OutputDataT], ABC):
             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
@@ -696,7 +702,6 @@ class AbstractAgent(Generic[AgentDepsT, OutputDataT], ABC):
             model_settings=model_settings,
             usage_limits=usage_limits,
             usage=usage,
-            infer_name=infer_name,
             toolsets=toolsets,
             builtin_tools=builtin_tools,
         )
@@ -713,7 +718,6 @@ class AbstractAgent(Generic[AgentDepsT, OutputDataT], ABC):
         model_settings: ModelSettings | None = None,
         usage_limits: _usage.UsageLimits | None = None,
         usage: _usage.RunUsage | None = None,
-        infer_name: bool = True,
         toolsets: Sequence[AbstractToolset[AgentDepsT]] | None = None,
         builtin_tools: Sequence[AbstractBuiltinTool] | None = None,
     ) -> AsyncIterator[_messages.AgentStreamEvent | AgentRunResultEvent[Any]]:
@@ -739,7 +743,7 @@ class AbstractAgent(Generic[AgentDepsT, OutputDataT], ABC):
                     model_settings=model_settings,
                     usage_limits=usage_limits,
                     usage=usage,
-                    infer_name=infer_name,
+                    infer_name=False,
                     toolsets=toolsets,
                     builtin_tools=builtin_tools,
                     event_stream_handler=event_stream_handler,
@@ -989,11 +993,14 @@ class AbstractAgent(Generic[AgentDepsT, OutputDataT], ABC):
     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,
@@ -1034,12 +1041,14 @@ class AbstractAgent(Generic[AgentDepsT, OutputDataT], ABC):
         uvicorn app:app --host 0.0.0.0 --port 8000
         ```
 
-        See [AG-UI docs](../ag-ui.md) for more information.
+        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.
@@ -1069,12 +1078,14 @@ class AbstractAgent(Generic[AgentDepsT, OutputDataT], ABC):
         Returns:
             An ASGI application for running Pydantic AI agents with AG-UI protocol support.
         """
-        from ..ag_ui import AGUIApp
+        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,

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/pydantic_ai/direct.py

@@ -50,7 +50,7 @@ async def model_request(
 
     async def main():
         model_response = await model_request(
-            'anthropic:claude-3-5-haiku-latest',
+            'anthropic:claude-haiku-4-5',
             [ModelRequest.user_text_prompt('What is the capital of France?')]  # (1)!
         )
         print(model_response)
@@ -58,7 +58,7 @@ async def model_request(
         ModelResponse(
             parts=[TextPart(content='The capital of France is Paris.')],
             usage=RequestUsage(input_tokens=56, output_tokens=7),
-            model_name='claude-3-5-haiku-latest',
+            model_name='claude-haiku-4-5',
             timestamp=datetime.datetime(...),
         )
         '''
@@ -103,7 +103,7 @@ def model_request_sync(
     from pydantic_ai.direct import model_request_sync
 
     model_response = model_request_sync(
-        'anthropic:claude-3-5-haiku-latest',
+        'anthropic:claude-haiku-4-5',
         [ModelRequest.user_text_prompt('What is the capital of France?')]  # (1)!
     )
     print(model_response)
@@ -111,7 +111,7 @@ def model_request_sync(
     ModelResponse(
         parts=[TextPart(content='The capital of France is Paris.')],
         usage=RequestUsage(input_tokens=56, output_tokens=7),
-        model_name='claude-3-5-haiku-latest',
+        model_name='claude-haiku-4-5',
         timestamp=datetime.datetime(...),
     )
     '''
@@ -172,6 +172,12 @@ def model_request_stream(
                     index=0, delta=TextPartDelta(content_delta='a German-born theoretical ')
                 ),
                 PartDeltaEvent(index=0, delta=TextPartDelta(content_delta='physicist.')),
+                PartEndEvent(
+                    index=0,
+                    part=TextPart(
+                        content='Albert Einstein was a German-born theoretical physicist.'
+                    ),
+                ),
             ]
             '''
     ```
@@ -229,6 +235,12 @@ def model_request_stream_sync(
                 index=0, delta=TextPartDelta(content_delta='a German-born theoretical ')
             ),
             PartDeltaEvent(index=0, delta=TextPartDelta(content_delta='physicist.')),
+            PartEndEvent(
+                index=0,
+                part=TextPart(
+                    content='Albert Einstein was a German-born theoretical physicist.'
+                ),
+            ),
         ]
         '''
     ```

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/pydantic_ai/durable_exec/dbos/_agent.py

@@ -640,6 +640,9 @@ class DBOSAgent(WrapperAgent[AgentDepsT, OutputDataT], DBOSConfiguredInstance):
                 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. ')
                 ),

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/pydantic_ai/durable_exec/prefect/_agent.py

@@ -598,6 +598,9 @@ class PrefectAgent(WrapperAgent[AgentDepsT, OutputDataT]):
                 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. ')
                 ),

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/pydantic_ai/durable_exec/temporal/_agent.py

@@ -669,6 +669,9 @@ class TemporalAgent(WrapperAgent[AgentDepsT, OutputDataT]):
                 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. ')
                 ),

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/pydantic_ai/messages.py

@@ -13,7 +13,7 @@ import pydantic
 import pydantic_core
 from genai_prices import calc_price, types as genai_types
 from opentelemetry._events import Event  # pyright: ignore[reportPrivateImportUsage]
-from typing_extensions import Self, deprecated
+from typing_extensions import deprecated
 
 from . import _otel_messages, _utils
 from ._utils import generate_tool_call_id as _generate_tool_call_id, now_utc as _now_utc
@@ -514,16 +514,16 @@ class BinaryContent:
                 vendor_metadata=bc.vendor_metadata,
             )
         else:
-            return bc  # pragma: no cover
+            return bc
 
     @classmethod
-    def from_data_uri(cls, data_uri: str) -> Self:
+    def from_data_uri(cls, data_uri: str) -> BinaryContent:
         """Create a `BinaryContent` from a data URI."""
         prefix = 'data:'
         if not data_uri.startswith(prefix):
-            raise ValueError('Data URI must start with "data:"')  # pragma: no cover
+            raise ValueError('Data URI must start with "data:"')
         media_type, data = data_uri[len(prefix) :].split(';base64,', 1)
-        return cls(data=base64.b64decode(data), media_type=media_type)
+        return cls.narrow_type(cls(data=base64.b64decode(data), media_type=media_type))
 
     @pydantic.computed_field
     @property
@@ -1612,6 +1612,14 @@ class PartStartEvent:
     part: ModelResponsePart
     """The newly started `ModelResponsePart`."""
 
+    previous_part_kind: (
+        Literal['text', 'thinking', 'tool-call', 'builtin-tool-call', 'builtin-tool-return', 'file'] | None
+    ) = None
+    """The kind of the previous part, if any.
+
+    This is useful for UI event streams to know whether to group parts of the same kind together when emitting events.
+    """
+
     event_kind: Literal['part_start'] = 'part_start'
     """Event type identifier, used as a discriminator."""
 
@@ -1634,6 +1642,30 @@ class PartDeltaEvent:
     __repr__ = _utils.dataclasses_no_defaults_repr
 
 
+@dataclass(repr=False, kw_only=True)
+class PartEndEvent:
+    """An event indicating that a part is complete."""
+
+    index: int
+    """The index of the part within the overall response parts list."""
+
+    part: ModelResponsePart
+    """The complete `ModelResponsePart`."""
+
+    next_part_kind: (
+        Literal['text', 'thinking', 'tool-call', 'builtin-tool-call', 'builtin-tool-return', 'file'] | None
+    ) = None
+    """The kind of the next part, if any.
+
+    This is useful for UI event streams to know whether to group parts of the same kind together when emitting events.
+    """
+
+    event_kind: Literal['part_end'] = 'part_end'
+    """Event type identifier, used as a discriminator."""
+
+    __repr__ = _utils.dataclasses_no_defaults_repr
+
+
 @dataclass(repr=False, kw_only=True)
 class FinalResultEvent:
     """An event indicating the response to the current model request matches the output schema and will produce a result."""
@@ -1649,9 +1681,9 @@ class FinalResultEvent:
 
 
 ModelResponseStreamEvent = Annotated[
-    PartStartEvent | PartDeltaEvent | FinalResultEvent, pydantic.Discriminator('event_kind')
+    PartStartEvent | PartDeltaEvent | PartEndEvent | FinalResultEvent, pydantic.Discriminator('event_kind')
 ]
-"""An event in the model response stream, starting a new part, applying a delta to an existing one, or indicating the final result."""
+"""An event in the model response stream, starting a new part, applying a delta to an existing one, indicating a part is complete, or indicating the final result."""
 
 
 @dataclass(repr=False)

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/pydantic_ai/models/__init__.py

@@ -27,6 +27,7 @@ from .._run_context import RunContext
 from ..builtin_tools import AbstractBuiltinTool
 from ..exceptions import UserError
 from ..messages import (
+    BaseToolCallPart,
     BinaryImage,
     FilePart,
     FileUrl,
@@ -35,9 +36,12 @@ from ..messages import (
     ModelMessage,
     ModelRequest,
     ModelResponse,
+    ModelResponsePart,
     ModelResponseStreamEvent,
+    PartEndEvent,
     PartStartEvent,
     TextPart,
+    ThinkingPart,
     ToolCallPart,
     VideoUrl,
 )
@@ -543,7 +547,44 @@ class StreamedResponse(ABC):
                 async for event in iterator:
                     yield event
 
-            self._event_iterator = iterator_with_final_event(self._get_event_iterator())
+            async def iterator_with_part_end(
+                iterator: AsyncIterator[ModelResponseStreamEvent],
+            ) -> AsyncIterator[ModelResponseStreamEvent]:
+                last_start_event: PartStartEvent | None = None
+
+                def part_end_event(next_part: ModelResponsePart | None = None) -> PartEndEvent | None:
+                    if not last_start_event:
+                        return None
+
+                    index = last_start_event.index
+                    part = self._parts_manager.get_parts()[index]
+                    if not isinstance(part, TextPart | ThinkingPart | BaseToolCallPart):
+                        # Parts other than these 3 don't have deltas, so don't need an end part.
+                        return None
+
+                    return PartEndEvent(
+                        index=index,
+                        part=part,
+                        next_part_kind=next_part.part_kind if next_part else None,
+                    )
+
+                async for event in iterator:
+                    if isinstance(event, PartStartEvent):
+                        if last_start_event:
+                            end_event = part_end_event(event.part)
+                            if end_event:
+                                yield end_event
+
+                            event.previous_part_kind = last_start_event.part.part_kind
+                        last_start_event = event
+
+                    yield event
+
+                end_event = part_end_event()
+                if end_event:
+                    yield end_event
+
+            self._event_iterator = iterator_with_part_end(iterator_with_final_event(self._get_event_iterator()))
         return self._event_iterator
 
     @abstractmethod

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/pydantic_ai/models/groq.py

@@ -524,6 +524,8 @@ class GroqStreamedResponse(StreamedResponse):
     async def _get_event_iterator(self) -> AsyncIterator[ModelResponseStreamEvent]:  # noqa: C901
         try:
             executed_tool_call_id: str | None = None
+            reasoning_index = 0
+            reasoning = False
             async for chunk in self._response:
                 self._usage += _map_usage(chunk)
 
@@ -540,10 +542,16 @@ class GroqStreamedResponse(StreamedResponse):
                     self.finish_reason = _FINISH_REASON_MAP.get(raw_finish_reason)
 
                 if choice.delta.reasoning is not None:
+                    if not reasoning:
+                        reasoning_index += 1
+                        reasoning = True
+
                     # NOTE: The `reasoning` field is only present if `groq_reasoning_format` is set to `parsed`.
                     yield self._parts_manager.handle_thinking_delta(
-                        vendor_part_id='reasoning', content=choice.delta.reasoning
+                        vendor_part_id=f'reasoning-{reasoning_index}', content=choice.delta.reasoning
                     )
+                else:
+                    reasoning = False
 
                 if choice.delta.executed_tools:
                     for tool in choice.delta.executed_tools:

{pydantic_ai_slim-1.7.0 → pydantic_ai_slim-1.9.0}/pydantic_ai/models/openai.py

@@ -1148,10 +1148,10 @@ class OpenAIResponsesModel(Model):
             + list(model_settings.get('openai_builtin_tools', []))
             + self._get_tools(model_request_parameters)
         )
-
+        profile = OpenAIModelProfile.from_profile(self.profile)
         if not tools:
             tool_choice: Literal['none', 'required', 'auto'] | None = None
-        elif not model_request_parameters.allow_text_output:
+        elif not model_request_parameters.allow_text_output and profile.openai_supports_tool_choice_required:
             tool_choice = 'required'
         else:
             tool_choice = 'auto'
@@ -1184,7 +1184,6 @@ class OpenAIResponsesModel(Model):
             text = text or {}
             text['verbosity'] = verbosity
 
-        profile = OpenAIModelProfile.from_profile(self.profile)
         unsupported_model_settings = profile.openai_unsupported_model_settings
         for setting in unsupported_model_settings:
             model_settings.pop(setting, None)