Merge branch 'main' into bedrock_error

Author: cjermain

docs/api/models/function.md

@@ -36,7 +36,14 @@ async def model_function(
     print(info)
     """
     AgentInfo(
-        function_tools=[], allow_text_output=True, output_tools=[], model_settings=None
+        function_tools=[],
+        allow_text_output=True,
+        output_tools=[],
+        model_settings=None,
+        model_request_parameters=ModelRequestParameters(
+            function_tools=[], builtin_tools=[], output_tools=[]
+        ),
+        instructions=None,
     )
     """
     return ModelResponse(parts=[TextPart('hello world')])

docs/builtin-tools.md

@@ -31,7 +31,7 @@ making it ideal for queries that require up-to-date data.
 |----------|-----------|-------|
 | OpenAI Responses | ✅ | Full feature support. To include search results on the [`BuiltinToolReturnPart`][pydantic_ai.messages.BuiltinToolReturnPart] that's available via [`ModelResponse.builtin_tool_calls`][pydantic_ai.messages.ModelResponse.builtin_tool_calls], enable the [`OpenAIResponsesModelSettings.openai_include_web_search_sources`][pydantic_ai.models.openai.OpenAIResponsesModelSettings.openai_include_web_search_sources] [model setting](agents.md#model-run-settings). |
 | Anthropic | ✅ | Full feature support |
-| Google | ✅ | No parameter support. No [`BuiltinToolCallPart`][pydantic_ai.messages.BuiltinToolCallPart] or [`BuiltinToolReturnPart`][pydantic_ai.messages.BuiltinToolReturnPart] is generated when streaming. Using built-in tools and user tools (including [output tools](output.md#tool-output)) at the same time is not supported; to use structured output, use [`PromptedOutput`](output.md#prompted-output) instead. |
+| Google | ✅ | No parameter support. No [`BuiltinToolCallPart`][pydantic_ai.messages.BuiltinToolCallPart] or [`BuiltinToolReturnPart`][pydantic_ai.messages.BuiltinToolReturnPart] is generated when streaming. Using built-in tools and function tools (including [output tools](output.md#tool-output)) at the same time is not supported; to use structured output, use [`PromptedOutput`](output.md#prompted-output) instead. |
 | Groq | ✅ | Limited parameter support. To use web search capabilities with Groq, you need to use the [compound models](https://console.groq.com/docs/compound). |
 | OpenAI Chat Completions | ❌ | Not supported |
 | Bedrock | ❌ | Not supported |
@@ -123,7 +123,7 @@ in a secure environment, making it perfect for computational tasks, data analysi
 | Provider | Supported | Notes |
 |----------|-----------|-------|
 | OpenAI | ✅ | To include code execution output on the [`BuiltinToolReturnPart`][pydantic_ai.messages.BuiltinToolReturnPart] that's available via [`ModelResponse.builtin_tool_calls`][pydantic_ai.messages.ModelResponse.builtin_tool_calls], enable the [`OpenAIResponsesModelSettings.openai_include_code_execution_outputs`][pydantic_ai.models.openai.OpenAIResponsesModelSettings.openai_include_code_execution_outputs] [model setting](agents.md#model-run-settings). If the code execution generated images, like charts, they will be available on [`ModelResponse.images`][pydantic_ai.messages.ModelResponse.images] as [`BinaryImage`][pydantic_ai.messages.BinaryImage] objects. The generated image can also be used as [image output](output.md#image-output) for the agent run. |
-| Google | ✅ | Using built-in tools and user tools (including [output tools](output.md#tool-output)) at the same time is not supported; to use structured output, use [`PromptedOutput`](output.md#prompted-output) instead. |
+| Google | ✅ | Using built-in tools and function tools (including [output tools](output.md#tool-output)) at the same time is not supported; to use structured output, use [`PromptedOutput`](output.md#prompted-output) instead. |
 | Anthropic | ✅ | |
 | Groq | ❌ | |
 | Bedrock | ❌ | |
@@ -315,7 +315,7 @@ allowing it to pull up-to-date information from the web.
 
 | Provider | Supported | Notes |
 |----------|-----------|-------|
-| Google | ✅ | No [`BuiltinToolCallPart`][pydantic_ai.messages.BuiltinToolCallPart] or [`BuiltinToolReturnPart`][pydantic_ai.messages.BuiltinToolReturnPart] is currently generated; please submit an issue if you need this. Using built-in tools and user tools (including [output tools](output.md#tool-output)) at the same time is not supported; to use structured output, use [`PromptedOutput`](output.md#prompted-output) instead. |
+| Google | ✅ | No [`BuiltinToolCallPart`][pydantic_ai.messages.BuiltinToolCallPart] or [`BuiltinToolReturnPart`][pydantic_ai.messages.BuiltinToolReturnPart] is currently generated; please submit an issue if you need this. Using built-in tools and function tools (including [output tools](output.md#tool-output)) at the same time is not supported; to use structured output, use [`PromptedOutput`](output.md#prompted-output) instead. |
 | OpenAI | ❌ | |
 | Anthropic | ❌ | |
 | Groq | ❌ | |

docs/deferred-tools.md

@@ -142,18 +142,18 @@ print(result.all_messages())
     ),
     ModelRequest(
         parts=[
-            ToolReturnPart(
-                tool_name='delete_file',
-                content='Deleting files is not allowed',
-                tool_call_id='delete_file',
-                timestamp=datetime.datetime(...),
-            ),
             ToolReturnPart(
                 tool_name='update_file',
                 content="File '.env' updated: ''",
                 tool_call_id='update_file_dotenv',
                 timestamp=datetime.datetime(...),
             ),
+            ToolReturnPart(
+                tool_name='delete_file',
+                content='Deleting files is not allowed',
+                tool_call_id='delete_file',
+                timestamp=datetime.datetime(...),
+            ),
         ]
     ),
     ModelResponse(

docs/logfire.md

@@ -263,6 +263,7 @@ The following providers have dedicated documentation on Pydantic AI:
 - [Agenta](https://docs.agenta.ai/observability/integrations/pydanticai)
 - [Confident AI](https://documentation.confident-ai.com/docs/llm-tracing/integrations/pydanticai)
 - [LangWatch](https://docs.langwatch.ai/integration/python/integrations/pydantic-ai)
+- [Braintrust](https://www.braintrust.dev/docs/integrations/sdk-integrations/pydantic-ai)
 
 ## Advanced usage
 

docs/models/overview.md

@@ -86,6 +86,12 @@ You can use [`FallbackModel`][pydantic_ai.models.fallback.FallbackModel] to atte
 in sequence until one successfully returns a result. Under the hood, Pydantic AI automatically switches
 from one model to the next if the current model returns a 4xx or 5xx status code.
 
+!!! note
+
+   The provider SDKs on which Models are based (like OpenAI, Anthropic, etc.) often have built-in retry logic that can delay the `FallbackModel` from activating.
+
+    When using `FallbackModel`, it's recommended to disable provider SDK retries to ensure immediate fallback, for example by setting `max_retries=0` on a [custom OpenAI client](openai.md#custom-openai-client).
+
 In the following example, the agent first makes a request to the OpenAI model (which fails due to an invalid API key),
 and then falls back to the Anthropic model.
 

examples/pydantic_ai_examples/rag.py

@@ -115,7 +115,7 @@ async def build_search_db():
     async with httpx.AsyncClient() as client:
         response = await client.get(DOCS_JSON)
         response.raise_for_status()
-    sections = sessions_ta.validate_json(response.content)
+    sections = sections_ta.validate_json(response.content)
 
     openai = AsyncOpenAI()
     logfire.instrument_openai(openai)
@@ -183,7 +183,7 @@ def embedding_content(self) -> str:
         return '\n\n'.join((f'path: {self.path}', f'title: {self.title}', self.content))
 
 
-sessions_ta = TypeAdapter(list[DocsSection])
+sections_ta = TypeAdapter(list[DocsSection])
 
 
 # pyright: reportUnknownMemberType=false

pydantic_ai_slim/pydantic_ai/_agent_graph.py

@@ -374,9 +374,10 @@ async def _prepare_request_parameters(
 ) -> models.ModelRequestParameters:
     """Build tools and create an agent model."""
     output_schema = ctx.deps.output_schema
-    output_object = None
-    if isinstance(output_schema, _output.NativeOutputSchema):
-        output_object = output_schema.object_def
+
+    prompted_output_template = (
+        output_schema.template if isinstance(output_schema, _output.PromptedOutputSchema) else None
+    )
 
     function_tools: list[ToolDefinition] = []
     output_tools: list[ToolDefinition] = []
@@ -391,7 +392,8 @@ async def _prepare_request_parameters(
         builtin_tools=ctx.deps.builtin_tools,
         output_mode=output_schema.mode,
         output_tools=output_tools,
-        output_object=output_object,
+        output_object=output_schema.object_def,
+        prompted_output_template=prompted_output_template,
         allow_text_output=output_schema.allows_text,
         allow_image_output=output_schema.allows_image,
     )
@@ -489,7 +491,6 @@ async def _prepare_request(
         message_history = _clean_message_history(message_history)
 
         model_request_parameters = await _prepare_request_parameters(ctx)
-        model_request_parameters = ctx.deps.model.customize_request_parameters(model_request_parameters)
 
         model_settings = ctx.deps.model_settings
         usage = ctx.state.usage
@@ -570,7 +571,7 @@ async def _run_stream() -> AsyncIterator[_messages.HandleResponseEvent]:  # noqa
                     # we got an empty response.
                     # this sometimes happens with anthropic (and perhaps other models)
                     # when the model has already returned text along side tool calls
-                    if text_processor := output_schema.text_processor:
+                    if text_processor := output_schema.text_processor:  # pragma: no branch
                         # in this scenario, if text responses are allowed, we return text from the most recent model
                         # response, if any
                         for message in reversed(ctx.state.message_history):
@@ -584,8 +585,12 @@ async def _run_stream() -> AsyncIterator[_messages.HandleResponseEvent]:  # noqa
                                         # not part of the final result output, so we reset the accumulated text
                                         text = ''  # pragma: no cover
                                 if text:
-                                    self._next_node = await self._handle_text_response(ctx, text, text_processor)
-                                    return
+                                    try:
+                                        self._next_node = await self._handle_text_response(ctx, text, text_processor)
+                                        return
+                                    except ToolRetryError:
+                                        # If the text from the preview response was invalid, ignore it.
+                                        pass
 
                     # Go back to the model request node with an empty request, which means we'll essentially
                     # resubmit the most recent request that resulted in an empty response,
@@ -622,11 +627,11 @@ async def _run_stream() -> AsyncIterator[_messages.HandleResponseEvent]:  # noqa
                     else:
                         assert_never(part)
 
-                # At the moment, we prioritize at least executing tool calls if they are present.
-                # In the future, we'd consider making this configurable at the agent or run level.
-                # This accounts for cases like anthropic returns that might contain a text response
-                # and a tool call response, where the text response just indicates the tool call will happen.
                 try:
+                    # At the moment, we prioritize at least executing tool calls if they are present.
+                    # In the future, we'd consider making this configurable at the agent or run level.
+                    # This accounts for cases like anthropic returns that might contain a text response
+                    # and a tool call response, where the text response just indicates the tool call will happen.
                     alternatives: list[str] = []
                     if tool_calls:
                         async for event in self._handle_tool_calls(ctx, tool_calls):
@@ -770,7 +775,6 @@ def build_run_context(ctx: GraphRunContext[GraphAgentState, GraphAgentDeps[DepsT
         if ctx.deps.instrumentation_settings
         else DEFAULT_INSTRUMENTATION_VERSION,
         run_step=ctx.state.run_step,
-        tool_call_approved=ctx.state.run_step == 0,
     )
 
 
@@ -1034,7 +1038,7 @@ async def _call_tool(
         elif isinstance(tool_call_result, ToolApproved):
             if tool_call_result.override_args is not None:
                 tool_call = dataclasses.replace(tool_call, args=tool_call_result.override_args)
-            tool_result = await tool_manager.handle_call(tool_call)
+            tool_result = await tool_manager.handle_call(tool_call, approved=True)
         elif isinstance(tool_call_result, ToolDenied):
             return _messages.ToolReturnPart(
                 tool_name=tool_call.tool_name,