Merge branch 'main' of https://github.com/pydantic/pydantic-ai into adding_run_id_to_modelmessage

Author: adtyavrdhn

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.
 

pydantic_ai_slim/pydantic_ai/models/google.py

@@ -677,7 +677,7 @@ async def _get_event_iterator(self) -> AsyncIterator[ModelResponseStreamEvent]:
                         provider_name=self.provider_name,
                     )
 
-                if part.text is not None:
+                if part.text:
                     if part.thought:
                         yield self._parts_manager.handle_thinking_delta(vendor_part_id='thinking', content=part.text)
                     else:
@@ -822,7 +822,7 @@ def _process_response_from_parts(
         elif part.code_execution_result is not None:
             assert code_execution_tool_call_id is not None
             item = _map_code_execution_result(part.code_execution_result, provider_name, code_execution_tool_call_id)
-        elif part.text is not None:
+        elif part.text:
             if part.thought:
                 item = ThinkingPart(content=part.text)
             else:

pydantic_ai_slim/pydantic_ai/run.py

@@ -135,6 +135,36 @@ def result(self) -> AgentRunResult[OutputDataT] | None:
             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]]]:

tests/test_agent.py

@@ -6078,3 +6078,48 @@ def delete_file() -> None:
     assert result.output == snapshot(
         DeferredToolRequests(approvals=[ToolCallPart(tool_name='delete_file', tool_call_id=IsStr())])
     )
+
+
+async def test_message_history():
+    def llm(messages: list[ModelMessage], _info: AgentInfo) -> ModelResponse:
+        return ModelResponse(parts=[TextPart('ok here is text')])
+
+    agent = Agent(FunctionModel(llm))
+
+    async with agent.iter(
+        message_history=[
+            ModelRequest(parts=[UserPromptPart(content='Hello')]),
+        ],
+    ) as run:
+        async for _ in run:
+            pass
+        assert run.new_messages() == snapshot(
+            [
+                ModelResponse(
+                    parts=[TextPart(content='ok here is text')],
+                    usage=RequestUsage(input_tokens=51, output_tokens=4),
+                    model_name='function:llm:',
+                    timestamp=IsDatetime(),
+                ),
+            ]
+        )
+        assert run.new_messages_json().startswith(b'[{"parts":[{"content":"ok here is text",')
+        assert run.all_messages() == snapshot(
+            [
+                ModelRequest(
+                    parts=[
+                        UserPromptPart(
+                            content='Hello',
+                            timestamp=IsDatetime(),
+                        )
+                    ]
+                ),
+                ModelResponse(
+                    parts=[TextPart(content='ok here is text')],
+                    usage=RequestUsage(input_tokens=51, output_tokens=4),
+                    model_name='function:llm:',
+                    timestamp=IsDatetime(),
+                ),
+            ]
+        )
+        assert run.all_messages_json().startswith(b'[{"parts":[{"content":"Hello",')