…s#755)

Move away from "callback" nested properties in the dict and explicitly passing invocation_state migrating to behaviors on the TypedEvent:

 - TypedEvent.is_callback_event for determining if an event should be yielded and or invoked in the callback
 - TypedEvent.prepare for taking in invocation_state

Customers still only get dictionaries, as we decided that this will remain an implementation detail for the time being, but this makes the events typed all the way up until *just* before we yield events back to the caller

---------

Co-authored-by: Mackenzie Zastrow <[email protected]>

Our current implementation of AgentTool.stream() has a problem that we don't differentiate between intermediate streaming events and the final ToolResult events.  Our only contract is that the last event *must be* be the tool result that is passed to the LLM.  Our switch to Typed Events (strands-agents#755) pushes us in the right direction but for backwards compatibility we can't update the signature of `AgentTool.stream()` (nor have we exposed externally TypedEvents yet). That means that if we implemented tool-streaming today, then callers would see non-generator functions yielding both a `ToolStreamEvent` and `ToolResultEvent` even though they're not actually streaming responses.

To avoid the odd behavior noted above, we'll special-case SDK-defined functions by allowing them to emit `ToolStreamEvent` and `ToolResultEvent` types directly (bypassing our normal wrapping), since they have the knowledge of when tools are actually generators or not.

There's no observable difference in behavior to callers (this is all internal behavior), but this means that when we switch the flip for Tool Streaming, non-generator tools will **not** emit ToolStreamEvents - at least for AgentTool implementations that are in the SDK.

…s#755)

Move away from "callback" nested properties in the dict and explicitly passing invocation_state migrating to behaviors on the TypedEvent:

 - TypedEvent.is_callback_event for determining if an event should be yielded and or invoked in the callback
 - TypedEvent.prepare for taking in invocation_state

Customers still only get dictionaries, as we decided that this will remain an implementation detail for the time being, but this makes the events typed all the way up until *just* before we yield events back to the caller

---------

Co-authored-by: Mackenzie Zastrow <[email protected]>

Our current implementation of AgentTool.stream() has a problem that we don't differentiate between intermediate streaming events and the final ToolResult events.  Our only contract is that the last event *must be* be the tool result that is passed to the LLM.  Our switch to Typed Events (#755) pushes us in the right direction but for backwards compatibility we can't update the signature of `AgentTool.stream()` (nor have we exposed externally TypedEvents yet). That means that if we implemented tool-streaming today, then callers would see non-generator functions yielding both a `ToolStreamEvent` and `ToolResultEvent` even though they're not actually streaming responses.

To avoid the odd behavior noted above, we'll special-case SDK-defined functions by allowing them to emit `ToolStreamEvent` and `ToolResultEvent` types directly (bypassing our normal wrapping), since they have the knowledge of when tools are actually generators or not.

There's no observable difference in behavior to callers (this is all internal behavior), but this means that when we switch the flip for Tool Streaming, non-generator tools will **not** emit ToolStreamEvents - at least for AgentTool implementations that are in the SDK.

Co-authored-by: Mackenzie Zastrow <[email protected]>