Merge branch 'main' into 3225

Author: g-eoj

docs/durable_execution/temporal.md

@@ -172,7 +172,7 @@ As workflows and activities run in separate processes, any values passed between
 
 To account for these limitations, tool functions and the [event stream handler](#streaming) running inside activities receive a limited version of the agent's [`RunContext`][pydantic_ai.tools.RunContext], and it's your responsibility to make sure that the [dependencies](../dependencies.md) object provided to [`TemporalAgent.run()`][pydantic_ai.durable_exec.temporal.TemporalAgent.run] can be serialized using Pydantic.
 
-Specifically, only the `deps`, `run_id`, `retries`, `tool_call_id`, `tool_name`, `tool_call_approved`, `retry`, `max_retries`, `run_step` and `partial_output` fields are available by default, and trying to access `model`, `usage`, `prompt`, `messages`, or `tracer` will raise an error.
+Specifically, only the `deps`, `run_id`, `retries`, `tool_call_id`, `tool_name`, `tool_call_approved`, `retry`, `max_retries`, `run_step`, `usage`, and `partial_output` fields are available by default, and trying to access `model`, `prompt`, `messages`, or `tracer` will raise an error.
 If you need one or more of these attributes to be available inside activities, you can create a [`TemporalRunContext`][pydantic_ai.durable_exec.temporal.TemporalRunContext] subclass with custom `serialize_run_context` and `deserialize_run_context` class methods and pass it to [`TemporalAgent`][pydantic_ai.durable_exec.temporal.TemporalAgent] as `run_context_type`.
 
 ### Streaming

docs/models/anthropic.md

@@ -83,8 +83,8 @@ agent = Agent(model)
 Anthropic supports [prompt caching](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching) to reduce costs by caching parts of your prompts. Pydantic AI provides three ways to use prompt caching:
 
 1. **Cache User Messages with [`CachePoint`][pydantic_ai.messages.CachePoint]**: Insert a `CachePoint` marker in your user messages to cache everything before it
-2. **Cache System Instructions**: Enable the [`AnthropicModelSettings.anthropic_cache_instructions`][pydantic_ai.models.anthropic.AnthropicModelSettings.anthropic_cache_instructions] [model setting](../agents.md#model-run-settings) to cache your system prompt
-3. **Cache Tool Definitions**: Enable the [`AnthropicModelSettings.anthropic_cache_tool_definitions`][pydantic_ai.models.anthropic.AnthropicModelSettings.anthropic_cache_tool_definitions] [model setting](../agents.md#model-run-settings) to cache your tool definitions
+2. **Cache System Instructions**: Set [`AnthropicModelSettings.anthropic_cache_instructions`][pydantic_ai.models.anthropic.AnthropicModelSettings.anthropic_cache_instructions] to `True` (uses 5m TTL by default) or specify `'5m'` / `'1h'` directly
+3. **Cache Tool Definitions**: Set [`AnthropicModelSettings.anthropic_cache_tool_definitions`][pydantic_ai.models.anthropic.AnthropicModelSettings.anthropic_cache_tool_definitions] to `True` (uses 5m TTL by default) or specify `'5m'` / `'1h'` directly
 
 You can combine all three strategies for maximum savings:
 
@@ -96,8 +96,9 @@ agent = Agent(
     'anthropic:claude-sonnet-4-5',
     system_prompt='Detailed instructions...',
     model_settings=AnthropicModelSettings(
+        # Use True for default 5m TTL, or specify '5m' / '1h' directly
         anthropic_cache_instructions=True,
-        anthropic_cache_tool_definitions=True,
+        anthropic_cache_tool_definitions='1h',  # Longer cache for tool definitions
     ),
 )
 
@@ -134,7 +135,7 @@ agent = Agent(
     'anthropic:claude-sonnet-4-5',
     system_prompt='Instructions...',
     model_settings=AnthropicModelSettings(
-        anthropic_cache_instructions=True
+        anthropic_cache_instructions=True  # Default 5m TTL
     ),
 )
 

docs/models/google.md

@@ -214,22 +214,22 @@ from pydantic_ai.models.google import GoogleModel, GoogleModelSettings
 settings = GoogleModelSettings(
     temperature=0.2,
     max_tokens=1024,
-    google_thinking_config={'thinking_budget': 2048},
+    google_thinking_config={'thinking_level': 'low'},
     google_safety_settings=[
         {
             'category': HarmCategory.HARM_CATEGORY_HATE_SPEECH,
             'threshold': HarmBlockThreshold.BLOCK_LOW_AND_ABOVE,
         }
     ]
 )
-model = GoogleModel('gemini-2.5-flash')
+model = GoogleModel('gemini-2.5-pro')
 agent = Agent(model, model_settings=settings)
 ...
 ```
 
 ### Disable thinking
 
-You can disable thinking by setting the `thinking_budget` to `0` on the `google_thinking_config`:
+On models older than Gemini 2.5 Pro, you can disable thinking by setting the `thinking_budget` to `0` on the `google_thinking_config`:
 
 ```python
 from pydantic_ai import Agent

pydantic_ai_slim/pydantic_ai/_agent_graph.py

@@ -216,6 +216,12 @@ async def run(  # noqa: C901
         ctx.state.message_history = messages
         ctx.deps.new_message_index = len(messages)
 
+        # Validate that message history starts with a user message
+        if messages and isinstance(messages[0], _messages.ModelResponse):
+            raise exceptions.UserError(
+                'Message history cannot start with a `ModelResponse`. Conversations must begin with a user message.'
+            )
+
         if self.deferred_tool_results is not None:
             return await self._handle_deferred_tool_results(self.deferred_tool_results, messages, ctx)
 

pydantic_ai_slim/pydantic_ai/_json_schema.py

@@ -25,7 +25,7 @@ def __init__(
         *,
         strict: bool | None = None,
         prefer_inlined_defs: bool = False,
-        simplify_nullable_unions: bool = False,
+        simplify_nullable_unions: bool = False,  # TODO (v2): Remove this, no longer used
     ):
         self.schema = schema
 
@@ -146,10 +146,9 @@ def _handle_union(self, schema: JsonSchema, union_kind: Literal['anyOf', 'oneOf'
 
         handled = [self._handle(member) for member in members]
 
-        # convert nullable unions to nullable types
+        # TODO (v2): Remove this feature, no longer used
         if self.simplify_nullable_unions:
             handled = self._simplify_nullable_union(handled)
-
         if len(handled) == 1:
             # In this case, no need to retain the union
             return handled[0] | schema
@@ -161,7 +160,7 @@ def _handle_union(self, schema: JsonSchema, union_kind: Literal['anyOf', 'oneOf'
 
     @staticmethod
     def _simplify_nullable_union(cases: list[JsonSchema]) -> list[JsonSchema]:
-        # TODO: Should we move this to relevant subclasses? Or is it worth keeping here to make reuse easier?
+        # TODO (v2): Remove this method, no longer used
         if len(cases) == 2 and {'type': 'null'} in cases:
             # Find the non-null schema
             non_null_schema = next(

pydantic_ai_slim/pydantic_ai/durable_exec/temporal/_run_context.py

@@ -14,7 +14,7 @@
 class TemporalRunContext(RunContext[AgentDepsT]):
     """The [`RunContext`][pydantic_ai.tools.RunContext] subclass to use to serialize and deserialize the run context for use inside a Temporal activity.
 
-    By default, only the `deps`, `run_id`, `retries`, `tool_call_id`, `tool_name`, `tool_call_approved`, `retry`, `max_retries`, `run_step` and `partial_output` attributes will be available.
+    By default, only the `deps`, `run_id`, `retries`, `tool_call_id`, `tool_name`, `tool_call_approved`, `retry`, `max_retries`, `run_step`, `usage`, and `partial_output` attributes will be available.
     To make another attribute available, create a `TemporalRunContext` subclass with a custom `serialize_run_context` class method that returns a dictionary that includes the attribute and pass it to [`TemporalAgent`][pydantic_ai.durable_exec.temporal.TemporalAgent].
     """
 
@@ -51,6 +51,7 @@ def serialize_run_context(cls, ctx: RunContext[Any]) -> dict[str, Any]:
             'max_retries': ctx.max_retries,
             'run_step': ctx.run_step,
             'partial_output': ctx.partial_output,
+            'usage': ctx.usage,
         }
 
     @classmethod

pydantic_ai_slim/pydantic_ai/messages.py

@@ -627,6 +627,13 @@ class CachePoint:
     kind: Literal['cache-point'] = 'cache-point'
     """Type identifier, this is available on all parts as a discriminator."""
 
+    ttl: Literal['5m', '1h'] = '5m'
+    """The cache time-to-live, either "5m" (5 minutes) or "1h" (1 hour).
+
+    Supported by:
+
+    * Anthropic. See https://docs.claude.com/en/docs/build-with-claude/prompt-caching#1-hour-cache-duration for more information."""
+
 
 MultiModalContent = ImageUrl | AudioUrl | DocumentUrl | VideoUrl | BinaryContent
 UserContent: TypeAlias = str | MultiModalContent | CachePoint
@@ -970,6 +977,9 @@ class ModelRequest:
     run_id: str | None = None
     """The unique identifier of the agent run in which this message originated."""
 
+    metadata: dict[str, Any] | None = None
+    """Additional data that can be accessed programmatically by the application but is not sent to the LLM."""
+
     @classmethod
     def user_text_prompt(cls, user_prompt: str, *, instructions: str | None = None) -> ModelRequest:
         """Create a `ModelRequest` with a single user prompt as text."""
@@ -1060,7 +1070,7 @@ class FilePart:
 
     def has_content(self) -> bool:
         """Return `True` if the file content is non-empty."""
-        return bool(self.content)  # pragma: no cover
+        return bool(self.content.data)
 
     __repr__ = _utils.dataclasses_no_defaults_repr
 
@@ -1214,6 +1224,9 @@ class ModelResponse:
     run_id: str | None = None
     """The unique identifier of the agent run in which this message originated."""
 
+    metadata: dict[str, Any] | None = None
+    """Additional data that can be accessed programmatically by the application but is not sent to the LLM."""
+
     @property
     def text(self) -> str | None:
         """Get the text in the response."""

pydantic_ai_slim/pydantic_ai/models/__init__.py

@@ -145,24 +145,28 @@
         'cohere:command-r7b-12-2024',
         'deepseek:deepseek-chat',
         'deepseek:deepseek-reasoner',
+        'google-gla:gemini-flash-latest',
+        'google-gla:gemini-flash-lite-latest',
         'google-gla:gemini-2.0-flash',
         'google-gla:gemini-2.0-flash-lite',
         'google-gla:gemini-2.5-flash',
+        'google-gla:gemini-2.5-flash-preview-09-2025',
+        'google-gla:gemini-2.5-flash-image',
         'google-gla:gemini-2.5-flash-lite',
         'google-gla:gemini-2.5-flash-lite-preview-09-2025',
-        'google-gla:gemini-2.5-flash-preview-09-2025',
         'google-gla:gemini-2.5-pro',
-        'google-gla:gemini-flash-latest',
-        'google-gla:gemini-flash-lite-latest',
+        'google-gla:gemini-3-pro-preview',
+        'google-vertex:gemini-flash-latest',
+        'google-vertex:gemini-flash-lite-latest',
         'google-vertex:gemini-2.0-flash',
         'google-vertex:gemini-2.0-flash-lite',
         'google-vertex:gemini-2.5-flash',
+        'google-vertex:gemini-2.5-flash-preview-09-2025',
+        'google-vertex:gemini-2.5-flash-image',
         'google-vertex:gemini-2.5-flash-lite',
         'google-vertex:gemini-2.5-flash-lite-preview-09-2025',
-        'google-vertex:gemini-2.5-flash-preview-09-2025',
         'google-vertex:gemini-2.5-pro',
-        'google-vertex:gemini-flash-latest',
-        'google-vertex:gemini-flash-lite-latest',
+        'google-vertex:gemini-3-pro-preview',
         'grok:grok-2-image-1212',
         'grok:grok-2-vision-1212',
         'grok:grok-3',