Fix/stateless models response stream (#2037)

## Description

- **Summary of changes**: Describe the key changes in this PR and their
purpose.
- **Related issues**: Mention if this PR fixes or is connected to any
issues.
- **Motivation and context**: Explain the reason for the changes and the
problem they solve.
- **Environment or dependencies**: Specify any changes in dependencies
or environment configurations required for this update.
- **Impact on metrics**: (If applicable) Describe changes in any metrics
or performance benchmarks.

Fixes # (issue)

---

## Type of change

Please check the options that are relevant:

- [ ] Bug fix (non-breaking change which fixes an issue)
- [ ] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to not work as expected)
- [ ] Model update (Addition or modification of models)
- [ ] Other (please describe):

---

## Checklist

- [ ] Adherence to standards: Code complies with Agno’s style guidelines
and best practices.
- [ ] Formatting and validation: You have run `./scripts/format.sh` and
`./scripts/validate.sh` to ensure code is formatted and linted.
- [ ] Self-review completed: A thorough review has been performed by the
contributor(s).
- [ ] Documentation: Docstrings and comments have been added or updated
for any complex logic.
- [ ] Examples and guides: Relevant cookbook examples have been included
or updated (if applicable).
- [ ] Tested in a clean environment: Changes have been tested in a clean
environment to confirm expected behavior.
- [ ] Tests (optional): Tests have been added or updated to cover any
new or changed functionality.

---

## Additional Notes

Include any deployment notes, performance implications, security
considerations, or other relevant information (e.g., screenshots or logs
if applicable).

---------

Co-authored-by: Dirk Brand <[email protected]>

cookbook/agent_concepts/async/basic.py

@@ -10,4 +10,4 @@
     markdown=True,
 )
 # -*- Print a response to the cli
-asyncio.run(agent.aprint_response("Share a breakfast recipe.", stream=True))
+asyncio.run(agent.aprint_response("Share a breakfast recipe."))

cookbook/agent_concepts/async/basic_stream.py

@@ -0,0 +1,13 @@
+import asyncio
+
+from agno.agent import Agent
+from agno.models.openai import OpenAIChat
+
+agent = Agent(
+    model=OpenAIChat(id="gpt-4o"),
+    description="You help people with their health and fitness goals.",
+    instructions=["Recipes should be under 5 ingredients"],
+    markdown=True,
+)
+# -*- Print a response to the cli
+asyncio.run(agent.aprint_response("Share a breakfast recipe.", stream=True))

cookbook/agent_concepts/async/data_analyst.py

@@ -25,6 +25,4 @@
     - movies: contains information about movies from IMDB.
     """),
 )
-asyncio.run(
-    agent.aprint_response("What is the average rating of movies?", stream=False)
-)
+asyncio.run(agent.aprint_response("What is the average rating of movies?"))

libs/agno/agno/models/aws/claude.py

@@ -1,3 +1,4 @@
+
 from dataclasses import dataclass
 from os import getenv
 from typing import Any, Dict, Optional
@@ -114,3 +115,4 @@ def request_kwargs(self) -> Dict[str, Any]:
         if self.request_params:
             _request_params.update(self.request_params)
         return _request_params
+

libs/agno/agno/models/base.py

@@ -1086,4 +1086,4 @@ def __deepcopy__(self, memo):
 
         # Clear the new model to remove any references to the old model
         new_model.clear()
-        return new_model
+        return new_model

libs/agno/agno/models/cohere/chat.py

@@ -297,6 +297,7 @@ def _process_stream_response(
             assistant_message.tool_calls.append(tool_use)
             tool_use = {}
 
+
         elif (
             response.type == "message-end"
             and response.delta is not None

libs/agno/agno/models/groq/groq.py

@@ -283,6 +283,7 @@ async def ainvoke_stream(self, messages: List[Message]) -> Any:
         Returns:
             Any: An asynchronous iterator of chat completion chunks.
         """
+
         try:
             stream = await self.get_async_client().chat.completions.create(
                 model=self.id,
@@ -337,6 +338,7 @@ def parse_tool_calls(tool_calls_data: List[ChoiceDeltaToolCall]) -> List[Dict[st
                     tool_call_entry["type"] = _tool_call_type
         return tool_calls
 
+
     def parse_provider_response(self, response: ChatCompletion) -> ModelResponse:
         """
         Parse the Groq response into a ModelResponse.

libs/agno/agno/models/openai/chat.py

@@ -452,7 +452,7 @@ def parse_provider_response(self, response: Union[ChatCompletion, ParsedChatComp
         Parse the OpenAI response into a ModelResponse.
 
         Args:
-            response: Raw response from OpenAI
+            response: Response from invoke() method
 
         Returns:
             ModelResponse: Parsed response data
@@ -490,7 +490,7 @@ def parse_provider_response(self, response: Union[ChatCompletion, ParsedChatComp
             except Exception as e:
                 logger.warning(f"Error processing tool calls: {e}")
 
-        # -*- Add audio transcript to content if available
+        # Add audio transcript to content if available
         response_audio: Optional[ChatCompletionAudio] = response_message.audio
         if response_audio and response_audio.transcript and not model_response.content:
             model_response.content = response_audio.transcript
@@ -517,7 +517,7 @@ def parse_provider_response(self, response: Union[ChatCompletion, ParsedChatComp
 
     def parse_provider_response_delta(self, response_delta: ChatCompletionChunk) -> ModelResponse:
         """
-        Parse the OpenAI streaming response into ModelProviderResponse objects.
+        Parse the OpenAI streaming response into a ModelResponse.
 
         Args:
             response_delta: Raw response chunk from OpenAI

libs/agno/agno/models/response.py

@@ -7,7 +7,7 @@
 
 
 class ModelResponseEvent(str, Enum):
-    """Events that can be sent by the Model.response() method"""
+    """Events that can be sent by the model provider"""
 
     tool_call_started = "ToolCallStarted"
     tool_call_completed = "ToolCallCompleted"
@@ -16,7 +16,7 @@ class ModelResponseEvent(str, Enum):
 
 @dataclass
 class ModelResponse:
-    """Response returned by Model.response()"""
+    """Response from the model provider"""
 
     role: Optional[str] = None
 
@@ -35,6 +35,7 @@ class ModelResponse:
     extra: Dict[str, Any] = field(default_factory=dict)
 
 
+
 class FileType(str, Enum):
     MP4 = "mp4"
     GIF = "gif"